Digital transformation

Artificial Intelligence

## In this blog, we answer the following questions:

- What is Artificial Intelligence (AI)?
- What is the difference between AI and machine Learning (ML)?
- How can AI be used in organizations?
- What does it take to build a machine learning application?
- What are some examples of machine learning applications?
- What is VIKTOR?

**Note:** You can use the navigation bar bellow to get directly to the topic of your choice!



large_MicrosoftTeams-image (25).png

medium_MicrosoftTeams-image (25).png

small_MicrosoftTeams-image (25).png

thumbnail_MicrosoftTeams-image (25).png

Blog_AI_and_Machine_learning_engineering_construction_17

Unlock the real potential of artificial intelligence for engineering and construction by turning data into knowledge | VIKTOR.ai.

AI and ML for engineering & construction | VIKTOR.ai


### Definition of Aritifical Intelligence

As the world keeps on innovating, **Artificial Intelligence** (AI) gets heard and talked about more and more often. Even though AI has become a fairly mainstream topic these days, a lot of people still struggle to provide a clear definition of it. This is not strange, because there are many distinctive types of AI that all have their own specifics. For example, regarding their level of sophistication. If we divide them based on that, we end up the with these four groups:

- **Reactive AI:** This is the most basic type of AI. It provides a predictable output based on the input it receives and always reacts to identical situations in the same way. Examples of Reactive AI are [email spam filters](https://bdtechtalks.com/2020/11/30/machine-learning-spam-detection/) and the [Netflix recommendation section](https://towardsdatascience.com/deep-dive-into-netflixs-recommender-system-341806ae3b48). 

- **Limited Memory AI:** Limited Memory AI learns from the data it has been fed, It consists of machine learning models that store the data and use it to ‘learn’ and make more accurate predictions and recommendations in the future. An example of this are [self-driving cars](https://www.electronicdesign.com/markets/automotive/article/21147200/nxp-semiconductors-the-role-of-machine-learning-in-autonomous-vehicles). These use data that was collected in the recent past to make decisions. For example, they use sensors to identify people that cross the street or spot traffic signals and other factors that need to be considered and anticipated whilst driving.

- **Theory of Mind AI:** This type of AI goes a little further than the previous ones. It refers to the ability of machines to make actual decisions that can be compared to decisions made by humans. Such machines can for example [detect, understand, and remember emotions](https://bluewhaleapps.com/blog/implementing-machine-learning-for-emotion-detection) and can adjust their way of interacting with others based on that. For example, if you say you are hungry, the AI may offer you an apple to fix it!

- **Self-Aware AI:** This type of AI is the most evolved one and is also the only one we have yet to develop, It refers to the ability of machines to become self-aware and have an actual consciousness. Whether this will ever happen, is a question that is [yet to be answered](https://www.scientificamerican.com/article/will-machines-ever-become-conscious/).

![AIML 0 (1).svg](https://cms.viktor.ai/uploads/AIML_0_1_28df55b8ee.svg)

The most basic types of AI (Reactive and Limited Memory) are also the most commonly occurring ones. From these two, Limited Memory AI is currently the most popular and widely used type of AI. Read more about the [four types of AI](https://www.bmc.com/blogs/artificial-intelligence-types/).

### Impact of Artificial Intelligence

As of today, the Engineering and Construction industry is still one of the least digitized industries. That is why there is still so much room for improvement and implementation of new developments to facilitate all kinds of processes. From product manufacturing, to services, design generation, and workflow automation and optimization, AI can be used to optimize all kinds of processes in all kinds of industries. The decision to start implementing AI can be a difficult one because it leads to both a lot of opportunities as well as challenges. It is our own choice to decide whether we are going to use it to our advantage or not.

AI explained

When people decide to start implementing AI into their organization, most choose to use machine learning. ML is not only an abundant but also a cheap technique to create more value for your company. For example, ML can help you [improve customer loyalty and retention](https://hbr.org/2017/05/8-ways-machine-learning-is-improving-companies-work-processes) and [hire the right people for the right position](https://hbr.org/2017/05/8-ways-machine-learning-is-improving-companies-work-processes). That is why, in this blog, we mostly focus on the implementation of ML to improve organizational processes.

### Differences between AI and ML

The differences between machine learning and artificial intelligence may be hard to explain sometimes. First off, because AI is hard to define on its own. Second, because [ML is actually a type of AI](https://www.northeastern.edu/graduate/blog/artificial-intelligence-vs-machine-learning-whats-the-difference/).

AI, simply said, refers to the capability of a **machine** to perform a certain ‘smart behaviour’. ML is **not a machine** but **an algorithm** that learns patterns from datasets to predict future outcomes, recognize patterns, or suggest different classes to the data. Something that humans simply would not be able to do. This means that with ML, you can for example teach a system to perform a specific task without providing it the specific instructions  by feeding it with ‘training data’ that enables it to learn and detect patterns.

### Types of Machine Learning

Even though all ML algorithms rely on data to learn their skills, there are also a lot of differences between how the algorithms use this data to learn. Just as AI has four distinctive types, there are three commonly occurring types of ML:


![MicrosoftTeams-image (21).png](https://cms.viktor.ai/uploads/Microsoft_Teams_image_21_e934cb5f3d.png)

-	**Supervised Learning:** This is a type of ML in which both the input and output of a (training) dataset are already known to the machine. This means that when an algorithm is fed a certain input, it is also fed with the corresponding output. Besides this, the algorithm also generates its own output. In case of errors between the algorithm’s generated output and the predefined dataset output, the algorithm adapts itself to produce the desired output. It therefore ‘learns’ from the dataset which input values should reproduce what output values. For future input data, the algorithm can now predict an output. This type of ML is often used for [classification problems](https://www.enjoyalgorithms.com/blogs/classification-and-regression-in-machine-learning), such as regression problems, such as logistic regressions or decision trees, and [regression problems](https://www.enjoyalgorithms.com/blogs/classification-and-regression-in-machine-learning), such as linear regressions and regression trees.
-	**Unsupervised Learning:** As you may expect, with Unsupervised Learning the algorithm gets no help from the user. This means it has no way of comparing its own output to an already predefined and correctly labelled output. Instead, it gets fed a certain input and detects patterns by itself, with the goal to identify some structure in the data. This type of ML is often used to segments groups (data, people, maps) based on similar attributes (for example the Netflix recommendations). We call this [clustering](https://www.enjoyalgorithms.com/blogs/classification-and-regression-in-machine-learning).
-	**Reinforcement Learning:** With this type of ML, the algorithm discovers by itself which actions yield the greatest rewards through trial and error. The algorithm wants to make the right decisions, as its objective is to take the actions that lead to the biggest reward in the quickest way possible. In other words: Learning the most efficient policy, such as with Pacman in this YouTube video.

<iframe width="560" height="315" src="https://www.youtube.com/embed/QilHGSYbjDQ" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>


### Supervised versus Unsupervised 

The two [most commonly used ML techniques](https://www.simplilearn.com/10-algorithms-machine-learning-engineers-need-to-know-article) are Supervised and Unsupervised Learning, as these are the fastest and cheapest to implement. The main difference between the two comes down to the labelled/unlabelled data that is fed to the algorithm by the model. When you have to choose between the two types, it important to carefully evaluate your input data (labelled or unlabelled?), define your goals (recurring problem to solve or new problem to predict?), and review your algorithm options (can it support your data volume and structure?). Answering all these questions will let you know whether you are looking to do a classification, regression, or clustering and with that you also know if you need Supervised or Unsupervised Learning.

**Note:** When you apply Unsupervised Learning, the results will be less transparent, because you cannot see how the model got there. The output may therefore be inaccurate. Unsupervised Learning simply puts persons, datapoints, and events into categories without providing information on how those categorisations came to be. A movie recommendation system can for example recommend Harry Potter because you like Star Wars because of a random reason like 'all people with your birthday also they like these movies'. In reality, it is very unrealistic to assume that a birthday influences what movies a person likes. An unsupervised learning algorithm does not know that and might retrieve non-causal correlations like this from a dataset. 

![AIML 2.svg](https://cms.viktor.ai/uploads/AIML_2_7e10fc77e7.svg)



Where Unsupervised Learning is often used for [clustering](https://cloudvane.net/data-science/machine-learning-101-clustering-regression-and-classification/) of data, Supervised Learning is used for [classification and regression](https://cloudvane.net/data-science/machine-learning-101-clustering-regression-and-classification/) analyses. People often want to use ML to cluster data for things such as customer segmentation, targeted marketing, and recommender systems. Using ML to classify data is often done for things as image classification, identity fraud detection, diagnostics, and customer retention. Regression analyses on data are for example performed to detect population growth and advertising popularity, estimate life expectancy, and forecast markets and weather.

![AIML 8.svg](https://cms.viktor.ai/uploads/AIML_8_ea18307784.svg)

Because classification of data is a popular way to use ML, this is also used to for example recognize digits based on pixels. This works by linking the composition of certain pixels to a specific category and is roughly the same principle as a camera with [facial recognition](https://www.pxl-vision.com/en/blog/machine-learning-and-how-it-applies-to-facial-recognition-technology#:~:text=Facial%20recognition%20is%20a%20technology,in%20a%20pre%2Dexisting%20database.). What happens when the camera ‘sees’ your face, is it actually recognizes the pixels that depict your face on film. These pixels are classified as ‘a person’s head’ and are therefore recognized as one. With digit recognition, the same goes for the pixels that make up the number, except for each number the pixels are classified into a category anywhere from 0 to 9 instead of ‘a person’s head’ or ‘not a person’s head’.

[![Facial recognition machine learning AI](https://cms.viktor.ai/uploads/blog_AI_long_read_facial_recognition_f3e3509094.jpg)](https://www.dailymail.co.uk/sciencetech/article-2958597/Facial-recognition-breakthrough-Deep-Dense-software-spots-faces-images-partially-hidden-UPSIDE-DOWN.html)


AI versus ML

ML is a popular type of AI for many businesses to create the most value from their work and efforts because it is both a 1) abundant and 2) cheap technique. 

1. [Abundant](https://machinelearningmastery.com/machine-learning-is-popular/), because there is an ever-growing amount of (varieties of) data. It is important for companies to find a way to quickly and automatically run analyses and generate accurate results, as this has simply become impossible to manage for humans. In this, ML can be used to analyse, categorise, and store lots of data. 
2. And cheap, because computational processing has become a lot cheaper and more powerful, and data storage is more affordable than ever. Because of that, a lot of companies started using ML to build precise models to identify profitable opportunities, enhance decision-making and security, provide accurate results, lower change of errors, and avoid risks, and even more.

> “You can have data without information, but you cannot have information without data.” – Daniel Keys Moran. 

![AIML 3.svg](https://cms.viktor.ai/uploads/AIML_3_d80dfba9d0.svg)


### Deep Learning

But wait, these are not the only reasons for why companies have increasingly started using ML. Over the past few years, technologies that facilitate the application of ML have become considerably more accessible. This has led engineers with a limited amount of training to be able to apply ML to their work. A versatile ML technique that is now often used by engineers is the [Deep Learning](https://machinelearningmastery.com/what-is-deep-learning/) algorithm, which is a type of Supervised Learning that uses so-called [Artificial Neural Networks (ANN)](https://towardsdatascience.com/applied-deep-learning-part-1-artificial-neural-networks-d7834f67a4f6) to learn from datasets.

![AIML 4.svg](https://cms.viktor.ai/uploads/AIML_4_5ba8ae389f.svg)

### Artificial Neural Networks

ANN’s were initially inspired by the brain, as they narrowly resemble the brain’s structure that consists of neurons that are wired together. A fully connected ANN consists of subsequent layers with each their own number of units that process the input per layer. Because input is processed per layer, the input that is processed by a certain unit in a certain layer each time depends on the output from the units from the previous layer. Therefore, ultimately the final output depends on the processing that is done by all the units in the last layer of the network. 

As ANN’s are a type of Supervised Learning, these networks also need to go through a learning phase before they can actually be used to recognize patterns and produce the desired output. Because the ANN is trained in the same way as with Supervised Learning, it can be used to automatically learn complex patterns in datasets. Due to that ability, they have become the foundation for the development of many life-changing applications in all kinds of industries, from AI platforms built on ANNs that process input (text) to [translate web pages themselves](https://towardsdatascience.com/language-translation-with-rnns-d84d43b40571) (thing Google Translate!), to ANNs that are able to [detect spam mail](https://medium.com/emergent-future/spam-detection-using-neural-networks-in-python-9b2b2a062272), and to Deep Learning algorithms that use ANNs to predict the likelihood of certain future events. 

![AIML 5.svg](https://cms.viktor.ai/uploads/AIML_5_99b15070ef.svg)

To give another example of what can be done with ANN’s, we will refer back to our first ML example with the number classification. For this, a certain type of ANN is often used for processing that performs particularly well in image recognition, called the more complex Convolutional Neural Network (CNN) algorithm. 

### AI and ML in today’s industry

Even though ML may sound very high-tech, all these automated technologies have been around for quite a while already (think about online advertising, cloud documents, automatic updating, etc.). It can still be difficult to understand how we have gotten here in the first place. Some people may think that the automation of certain tasks is here to replace human labour, while instead the purpose is  to make people’s lives easier!

That is why companies in all kinds of industries (not just tech!) have started using the benefits of AI, ML, and its many applications to increase productivity and expand possibilities. A few examples of well-known companies that use these techniques are: 

- **Google**, of course for [a lot of things](https://bernardmarr.com/how-does-google-use-artificial-intelligence/#:~:text=Google%20uses%20AI%20to%20analyze,and%20Washington%20in%20the%20U.S.). Google build a prototype software that has the ability to mimic the human mind and even has short-term memory. Additionally, Google owns ‘Nest’, which is voice assistant that can be used to control a series of home products (‘Smart Home’) that leverage AI technology.

- **IBM** build an AI machine called [Watson](https://www.ibm.com/nl-en/watson) that can detect patterns, ask questions in human voice, and answer (correctly) as well. Watson has the ability to search through loads of information within seconds. This allowed him to win the popular US TV show Jeopardy and conducted research that may help eradicate cancer.

- **BMW** uses AI to [analyse component images](https://www.bmwgroup.com/en/innovation/technologies-and-mobility/artificial-intelligence.html) from their production line and scan for deviations to detect possible errors in their manufacturing. 

- **Boeing** uses Augmented Reality to [scan images of their airplanes](https://upskill.io/landing/upskill-and-boeing/) that are sent to a processing platform to detect abnormalities in the design.

- [Facebook](https://research.fb.com/category/facebook-ai-research-/), [Microsoft](https://www.microsoft.com/en-us/ai?activetab=pivot1%3aprimaryr6), [Yelp](https://www.eater.com/2016/7/19/12222742/yelp-artificial-intelligence-image-detection), [Pinterest](https://www.wired.com/brandlab/2018/11/pinterest-uses-ai-capture-imaginations/), [Twitter](https://www.verdict.co.uk/twitter-ai-automation/#:~:text=Twitter%20AI%20is%20being%20used,speech%20or%20promoting%20terrorist%20activities.), [HubSpot](https://www.hubspot.com/artificial-intelligence), and many more…

![AI auto.jpg](https://cms.viktor.ai/uploads/AI_auto_2e7e43412f.jpg)

### AI and ML in your organization

A lot of companies are already reaping the benefits of AI, sometimes even without people really noticing that AI is at the cause. 

As ML allows organizations to turn (large) datasets into knowledge and enable them to act on it, it is clear that it could do no harm to incorporate ML applications into your organization as well. However, this is of course easier said than done. Before you successfully do this, there are a few organizational aspects that have to be considered first.

### Organizational challenges

Of course, the idea of applying new technologies, such as ML techniques, to boost the performance of your organization sounds great. But don’t forget that simply applying some new digital tool is not an immediate and overnight solution to your problems. Right now, many of these developments don’t get much further than the prove of concept. How come? The answer lies with the fact that the people that are in charge often only think about implementing the solution and forget about two other important factors, which are the processes that will be automated and the people that are going to work with it.  

Therefore, for your digital solution to work, there are three important factors that need to be paid enough attention to in this order:

-	First **people:** Before you can use your digital solution, the people that are going to use it should be willing to adapt to this change. They may not (yet) be convinced that it will work out well or that they are able to operate it. Additionally, your digital solution may affect the way that they do their jobs. It is very well possible that they are not afraid that this will not be in a positive way or that they are simply not ready for this change. Thus, getting your people on board should be the first step to applying new digital solutions, like ML.
-	After you have convinced your people, the **process** follows: Changing entire processes is not as simple as it seems. That is why you should consider very carefully which process are possible and also profitable to digitize before you start applying a digital solution that may ultimately not work. Ask yourself questions. For example, “Is it possible to automate this process using ML?”
-	Last but not least, you implement the **technology**: Only after you have looked at the people and process components, you can start thinking about actually implementing a digital solution that suits both your people and processes.
The focus of your digital transformation should be 80% people and 20% technology.

![people tech.png](https://cms.viktor.ai/uploads/people_tech_db1e190a83.png)

*There is a lot that goes into implementing new technologies and doing so is certainly not done within one day. It is important to strategically take on this process of digitally transforming your organization. Read more on how to do this in our white paper “People first, tech second: The way to boost digital transformation in the Engineering and Construction industry.”*

[![create successful applications](https://cms.viktor.ai/uploads/CTA_mastering_app_creation_2_d432d3bf35.png)](https://www.viktor.ai/white-papers/how-to-build-successful-apps)


Thus, it is important to look carefully at the people and processes in your organization that are connected to your digital solution before actually implementing it. Once you have done that, the next step is to narrow down the requirements for this solution.



AI and ML in organizations

Now that we have discussed the organizational aspects of applying new digital solutions such as ML techniques to your business, you are going to take a deeper look at the mechanisms behind building such an application. 

These steps you need to take to build your application are as follows:

- Define your problem
- Gather your data
- Choose your measure of success
- Set your evaluation protocol
- Prepare your data
- Develop your model
- Draw your conclusion

### Step 1: Define your problem

The first step to building a ML application actually has to do with the process part of digitally transforming your organization (so: After people, before technology). 

Here, you have to define the problem: What process do you want to replace using ML? 

**Note:** Because ML is able to recognize patterns in datasets and the algorithm has to be trained to recognize them with training data first, you can only use ML if:

- The outputs can be predicted given the inputs
- Your available data is sufficient enough for the algorithm to learn the relationship between the inputs and the outputs

### Step 2: Gather your data

If you want your prediction to be more accurate, you have to collect large amounts of input data with good quality to train your algorithm. More and accurate data equals more accurate predictions. We are telling you this because the importance of the preparation of data is often underestimated. The algorithm can only be as good as the quality of the data. Data preprocessing: filtering out faulty data, data normalization, cherry-picking important features, etc., is what makes or breaks a successful ML application.

> “The machine learning result can only be as good as the data it receives” – Lars Janssen, MSc Student Applied Physics at Delft University of Technology and R&D Intern at VIKTOR

### Step 3: Choose your measure of success

This factor is really important because in order to prove your success, you have to make it measurable somehow. Therefore, you should define the goal you want to reach using ML somehow and determine how you are going to measure this. This goal should both be in line with both your business’ broader objective and the type of problem that you want to solve (using ML0, such as *'I want to deliver good service to our customers. This can be done by using ML algorithms to predict and optimize the time it takes us to deliver a project'.*

### Step 4: Set your evaluation protocol

In the third step you have decided on what your goal is. Now, you also have to decide on how you are going to measure it. This often depends on the type of class of the problem you want to solve (clustering, classification, regression). 

Whenever you measure performance, you will mostly end up with a score to indicate how well your model has predicted the outcome. For example, for classification you get a score for classification accuracy (in %), which is the total correct correction of the ML model divided by the total predictions made by the model x 100.

So, what you have to do is pick a dataset that you will use to train the model with. You do not use all data for training but hold a smaller part of it aside, this smaller subset is called the validation dataset. After each training step, you provide the model with the validation dataset, and use this to test the accuracy of the model's performance on this validation dataset.  As the number of training steps increase, the model’s performance with respect to the training set improves. It is however crucial to monitor whether the model’s performance with respect to the validation set improves as well. If this is not the case, it shows that the model is ‘overfitted’ on the training set. With overfitted we mean that the trained model is improving its performance at predicting ‘unseen’ datapoints. The goal of machine learning is to apply the model for the prediction of future (unseen) datapoints. The observation of a model performance improvement on the validation dataset is therefore crucial.

![AIML 6.svg](https://cms.viktor.ai/uploads/AIML_6_c6676e1e9f.svg)

### Step 5: Prepare your data

Now that you know what your problem is, what data you are going to use to solve it, how you are going to measure whether you solved it successfully or not, and how you are going to do perform these measurements, you still need to prepare your data before it can be ‘fed’ to the ML model. For this you have to:

- Check for missing data. If there is any data missing, these fields can either be deleted or you can insert the missing values yourself manually.
- Make sure the algorithm can interpret the values correctly. Is your data categorical? Then the features of this data can either be nominal (e.g. type of pile) or ordinal (e.g. size of pile). For the ML model to correctly interpret these values, you have to assign numeral values to these features (e.g. pile type 1 = 1, pile type 2 = 2). 
- Scale the features. In cases where you have multiple features on different scales, you have to rescale them so that the scales align and they can be compared to each other. This can either be done by normalization (scaling on a range from 0 to 1) or standardization (centering at 0 with a range of 1).
- Select the features that are meaningful. For your ML model to be the most accurate, you must make sure that there is as little redundant data as possible. Otherwise, the model will get too complex compared to the training data and will not be able to predict accurately. 
- Split your data into subsets. To get the best predictions, you have to split your data into three subsets: The training set, the validation set and the test set. With the training set, the model is trained. The validation set is used during training to evaluate whether you are not overfitting the model too specifically to the training set. The test set is not used during the training process, the model has therefore never seen this dataset. The evaluation of this test set therefore gives a realistic approximation for the model’s performance for future predictions.

![AIML 9.svg](https://cms.viktor.ai/uploads/AIML_9_5cc3966b0a.svg)

### Step 6: Develop your model

Before you can develop your actual model, you first have to come up with the baseline: A benchmark model to measure the performance and accuracy of your ML algorithm. This benchmark model is used to determine what your actual model has to look like to come up with the best score. So, for example, depending on the number of groups you have to split your data in or what the best scoring method is for your data (classification, regression).

### Step 7: Draw your conclusions

After you have chosen the most accurate model and used it to predict data, you are going to interpret this data and draw conclusions from it. What do the predictions say about the future? 



How to build a ML app

## The Pile Foundation application

[Voorbij Funderingstechniek](https://www.voorbijfunderingstechniek.nl/) is specialized in executing all kinds of foundation work. With that, they are leaders when it comes to delivering carrying capacity for infrastructure, hydraulic engineering, utility construction, and industrial construction. They offer their partners creative and innovative solutions to their problems and together carry the success of realizing beautiful projects. Voorbij used the VIKTOR platform as application development platform to build [several modules](https://www.voorbijfunderingstechniek.nl/actueel/base-ft-blog) that support them in optimizing various of the processes that occur during these projects, for example for [the (re)design of pile foundations](https://www.viktor.ai/customer-cases/34/automation-parametric-design-python-digitization) and, in this case, the estimation of pile driving time.

Foundations of buildings in the Netherlands often require a deep foundation that makes it possible to transfer building loads to a subsurface layer further down, because a solid layer that can facilitate large foundation loads can often lie deep beneath the surface. Therefore, the foundations of large constructions (e.g. distribution centers or traffic overpasses) can require thousands of piles to be driven into these depths for stabilization. For both cost estimation and scheduling it is important to know the correct amount of time it will take to drive these piles. 

Currently, pile drive time is estimated by exploiting knowledge about the soil through CPTs (Cone Penetration Tests) that are taken from the location and used to classify soil composition (e.g. sand or clay). Because recently the registration of pile drive data has significantly increased, it has become possible to improve the predictions of pile drive time in future projects by applying Machine Learning techniques, also using customer pile drive measurements and CPT data. As a ML algorithm, an Artificial Neural Network is used to predict penetration speed values based on CPT data by training it on measured pile drive measurements and the corresponding CPT data. 

The ML model is implemented within an application development platform so that engineers are enabled to train and apply the ML model to the engineering process themselves.

*Learn more about Voorbij’s projects on the VIKTOR platform.*
- [Pile foundation application 1.0](https://www.viktor.ai/customer-cases/7/digital-transformation-python-pile-foundations)
- [Pile foundation application 3.0](https://www.viktor.ai/customer-cases/34/automation-parametric-design-python-digitization)
- [Voorbij's smart AI application](https://www.viktor.ai/blog/41/application-development-python-automation-artificial-intelligence)

Next, it is described stepwise how Voorbij build their ML application.

First, Voorbij defined the problem. They wanted to predict pile drive time. For this, there was sufficient input data (recently significantly increased even), since pile driving speeds and soil measurements (CPTs) are registered in large quantities. Because pile driving speed mainly depends on soil properties, this information can be used by a ML approach to estimate drive speed. Thus, the problem was that they were unable to predict pile drive time and needed data for their application to do so. 

Second, they found a way to gather their data, as they needed data from pile driving, customer pile drive measurements, and CPTs to be able to predict pile drive time. For them, to be able to predict penetration speed, CPTs measurements had to be evaluated at a certain depth so that these evaluations could be used as input features for the ML model to predict a certain speed at this depth. This data was extracted from their database from previous projects.

Third, they chose how they were going to measure the success of their ML application. Voorbij’s problem was that they were unable to tell the time it would take to drive piles for projects quickly and precisely. Therefore, their goal was to be able to measure this time accurately and quickly using ML, thus the measurement of success was going to be the accuracy of these prediction measurements. This aligns with the company’s broader objective to deliver good service to their customers, spend their time efficiently, and accurately predict the course of a project.

Fourth and fifth, to be able to predict penetration speed, they chose for a Supervised Learning ML model that leverages the data from CPTs to predict the pile drive speed. The ANN adapts itself during training, such that for given CPT values, the correct pile drive speed is predicted. 
Voorbij used their training data for two distinctive relevant possible scenarios as to how their ML application can be applied in practice:

- Scenario 1: The client can use a few pile measurements at the start of an individual project as the training dataset. Based on this dataset, the ANN can predict the penetration speed for the piles that are driven in the remainder of the project. These penetration speed values can thereafter be used to improve the estimation of the total project time. 
- Scenario 2: Another possible scenario would be to train the machine learning model on one or multiple projects to predict the penetration speed values at completely different locations. These predictions can then be used to estimate the total project time before the start of the project.

Sixth, a model was built with an ANN. To determine the optimal model, a little experimenting was done regarding the number of units per layer within the ANN.  The value of each output layer of the model was the predicted penetration speed. To optimize predictions, a small part of the datasets was used as validation set, the performance of the model on this validation set was monitored during the training of the ANN. To prevent overfitting to the training set, training was stopped automatically after all data was ran through the model several times, while at the same time the validation set performance did not increase. To set a limited amount of training time, the maximum allowed number of training rounds (also called epochs) during training was set to a maximum.

And seventh, they drew their conclusions from the results of the model. The two different scenarios described in step 4 yielded different results when it came down to prediction accuracy:

- Individual projects: For these projects, the results of the test set are presented for the case where 10% of the total number of penetration speed measurements are used as training set to predict the remaining 90%. The output of the ANN penetration speed values is fitted to the training set measurements. After training, the ANN is able to predict the pile penetration speed at certain locations as a function of the depth at the test set locations. For one construction project, the ANN model was able to predict the pile penetration speed at the test set locations with a relative error of 10%. 
- Multiple projects: In this scenario, a full set of penetration speed measurements from an entire area site is defined as the training set and the full set of measurements from another entire area site is defined as the test set. The output of the ANN penetration speed values is fitted to the training set measurements. In this scenario, the performance of the ANN decreases significantly (the relative error rises to 31%), compared to the individual project-scenario. 

With these predicted penetration speed values, the total drive time can be predicted. The predicted total drive time can then be compared with the actual registered total drive time. The results from these total drive time estimations are displayed here for two separate projects with differing soil compositions.

![AIML 10.svg](https://cms.viktor.ai/uploads/AIML_10_de922172d2.svg)


Lack of accuracy on the right project can be explained by the fact that if the penetration speed at a certain moment is so low that it is close to zero, the machine cannot register this and rounds it to 0 m/s. This is also confirmed by these scatter plots displaying the registered drive time against the computing drive times. The blue dots denote that during these drives, the speed was always larger than 0 m/s and the red dots denote a speed of 0 m/s. On the right graph, the speed measurements from the lesser accurately predicted project are presented and explained. This exemplifies the importance of correct input data for the ML model. 

![AIML 11.svg](https://cms.viktor.ai/uploads/AIML_11_ba985d7abf.svg)


The model is trained with relatively rudimentary training data within the VIKTOR app and is able to predict penetration speed values for a given CPT. The performance of the penetration speed prediction is maximized if a small sample of the pile field is used to train the model. This predicted penetration speed can then be used to predict the estimated total driving time.

## Digit recognition

In the beginning we explained how ML could be used to classify for example numbers, faces, and more. Below is such an example of an application that can classify numbers. For this application, and SVC were used. Here, it can be seen in action.

<div style="padding:54.58% 0 0 0;position:relative;"><iframe src="https://player.vimeo.com/video/599377922?badge=0&amp;autopause=0&amp;player_id=0&amp;app_id=58479&amp;h=12ffa279fd" frameborder="0" allow="autoplay; fullscreen; picture-in-picture" allowfullscreen style="position:absolute;top:0;left:0;width:100%;height:100%;" title="Viktor - Mozilla Firefox 2021-08-12 10-20-20"></iframe></div><script src="https://player.vimeo.com/api/player.js"></script>

What happens within the application is as follows: An image recognition task is performed on 64-pixel hand-written images of digits in the web application. The goal of the algorithm is to recognize for a given 64-pixel image, which digit is hand-written in the image. Here, an SVC model is trained on a dataset consisting of 1797 images with corresponding labels. The SVC is trained to recognize an image as a digit between 0 to 9. With this SVC model it is possible to achieve a classification accuracy of ~99% on new images, which the model has not ‘seen’ during training. In the application it is possible to train the model with hyperparameters that can be set in the app and this trained model can be directly deployed to recognize new images.








Examples of ML apps

Developments regarding AI en ML are touching and will continue to touch all kinds of aspects in organizations. From what we have told you and what can be concluded from the example of Voorbij’s case, you can see that the possibilities of using ML techniques to automate all kinds of processes are extensive and beneficial. Therefore, the importance of finding a good way to gather, store, access and use data before you can unlock the powers of it and put it to work is undeniable. 

That is where the VIKTOR platform comes in.

## VIKTOR explained

VIKTOR is an application development platform that enables people to rapidly build their own online applications with a Python Software Development Kit (SDK). The VIKTOR platform is a place where people can centralize and distribute data, models, and analyses to others such that it acts as a single point of truth. Additionally, you can use the platform to integrate with data sources and all relevant software packages. In combination with the ability to automate and use algorithms, such as Machine Learning, you are able to find the best solution fast. With a VIKTOR application, you can interpret data quick and easy by means of understandable insights provided on an interactive and customizable dashboard, which enables you to turn your knowledge into an asset!

## Want to know more?

VIKTOR is on a mission to unleash the world’s real engineering potential. That is why we are developing a platform where engineers can build their own web-based applications using Python. We work closely together with for example engineering, construction, and manufacturing companies and help them boost their digital transformation. We would love to hear your feedback on our ideas and invite you to try out the platform and help us create the perfect tools that enable you to **automate the boring, engineer the awesome!**


About VIKTOR

AI and Machine Learning in Engineering and Construction

1. What is parametric design, and how is it evolving
2. Collaborative parametric design: working together for better results
3. How to make tools available to others
4. Active collaboration on parametric design tools
5. Parametric design in a billion-euro project
6. What collaborative parametric design means for you



large_Viktor White Paper The future of parametric design is_ COLLABORATION.jpg

medium_Viktor White Paper The future of parametric design is_ COLLABORATION.jpg

small_Viktor White Paper The future of parametric design is_ COLLABORATION.jpg

thumbnail_Viktor White Paper The future of parametric design is_ COLLABORATION.jpg

WP_white

large_parametric_steel_structure.png

medium_parametric_steel_structure.png

small_parametric_steel_structure.png

thumbnail_parametric_steel_structure.png

WP_white_2

The adoption of parametric design grows exponentially thanks to friendly programming languages like Python or visual programming packages like Dynamo or Grasshopper.
 
Our perception is changing. We no longer see parametric design as a model to solve specific technical problems, but rather as a new way of working, in which stakeholders collaborate to find the best solution for a project.

Learn about the latest trends and the future of parametric design in this white paper

Collaborative parametric design models allow you to work together for better solutions

Download the white paper and get INSPIRED

Did you know parametric design models are no longer just used to solve specific technical problems, but rather as a new way of working? Read here how stakeholders use parametric design to collaborate and find the best solutions for their projects!

The Future of Parametric Design is COLLABORATION

Creating Apps & Python

## Data-driven decision-making with Revit 

Revit is a software package for BIM (Building Information Modelling) that can be used to build 3D design and construction models, much alike Tekla. Revit is an excellent tool for those in need of software for collaborative and multidisciplinary design processes. It provides access to intelligent and model-based processes to plan, design, construct, and manage buildings and infrastructure and is therefore a popular tool for companies in the Engineering and Construction industry. Especially for people from different disciplines, like Architecture, Engineering, and Construction, Revit is a great tool to facilitate working together in a collaborative design environment. 

Besides using Revit to generate and optimize design models, you may also want to use it for other purposes, such as getting better insights, enhancing decision making, and managing your projects. But how? Unfortunately, Revit’s database is hard to access, and therefore you will need other tools to acquire this information. The solution is building your own application with VIKTOR that you can use to automate and optimize design and provide simplified interactive insights from source applications such as BIM360, Relatics, Primavera, Excel, and Revit. This way you are not only able to use your source application’s software for automated and optimized designs, but also have access to a dashboard where you can view, analyse, compare, and check all project data. 

![appdashboarding.png](/uploads/appdashboarding_b78867e415.png)

*Dashboarding with interactive graphs, charts, and tabels in a VIKTOR application* 

## Great potential, little accessibility 

Especially compared to other software packages, Revit software is more data-intensive and can be used to build more sustainable designs. Where AutoCAD is most used for the creation of 2D drawings, Revit can also be used for modelling, cost schedule generation, collaboration, and change management.  

### Specialists required 

Although software programs like Revit are very handy design tools, they do have a learning curve: Often only a specialist knows how it works. This makes other disciplines depend on both time and resources of these specialized individuals. Additionally, when working with design software, models are normally built manually. For example, when you design a house, you draw the roof, the walls, etc. one-by-one by hand. This could really slow down a project if something needs to change or if mistakes are made, because in that case everything needs to be redesigned manually (by the specialist) as well. On top of that, Revit does not provide its’ users with an option to extract, view, and analyse data from its’ database, which causes a lot of valuable insights to become lost. 

### Black box 

Even though Revit is a very data-intensive software program, the contents of its’ database remain a mystery to users. It is clear that when it comes to design features, Revit is already a popular tool for many companies. However, many software programs like Revit are also black boxes and in order to access the information that is hidden inside, a tool is needed to extract, visualize, verify, compare, and analyse data from a source application. Only then, the full potential of a software program is unlocked, and data can be used to optimize not only the design process, but other processes as well. 

## Great potential, lots of accessibility! 

Luckily, there is a solution to both problems. By building a web-based application for any part of your workflow on the VIKTOR platform, you can integrate with every source application you want. Because VIKTOR is a platform made for engineers, it has a large variety of digital buildings blocks (like LEGO’s), such as integrations with structural design software like Revit and Civil 3D. VIKTOR web apps provide a central database, where data is provided with version control, and an intuitive user-friendly interface where other disciplines can easily use encapsulated expert knowledge. Additionally, the interface provides you with a customizable dashboard where you can visualize interactive results to clearly interpret, analyse, and compare data. You can also quickly and easily generate and optimize designs based on a few input [parameters]https://www.viktor.ai/blog/46/parametric-design-cloud-engineering-construction). This way, you can become the specialist yourself and also use data from your source application to create more value on projects!

![Iconsicions.png](/uploads/Iconsicions_577d386566.png)

*Turn your knowledge into asset!* 

### Become the specialist 

If you build an application on the VIKTOR platform that integrates with a software program, you can create a customized interface that you can use to control your source application. That means, if you integrate with Revit, you can work with Revit software without actually having to open Revit or have it installed on your device at all.  

Because applications on the VITKOR platform are based on [parametric design methods](https://www.viktor.ai/parametric-design-software), you don’t have to (hire a specialist) to calculate your designs manually any longer. Based on only a few input parameters and a set of additional requirements, you can use your application to generate the most optimal design for you within moments of time, that can easily be collaborated on or shared with others. 

<div style="padding:56.25% 0 0 0;position:relative;"><iframe src="https://player.vimeo.com/video/574320490?badge=0&amp;autopause=0&amp;player_id=0&amp;app_id=58479" frameborder="0" allow="autoplay; fullscreen; picture-in-picture" allowfullscreen style="position:absolute;top:0;left:0;width:100%;height:100%;" title="DV_Dynamo-VIKTOR_nodes_ViktorUBak_v3 (online-video-cuttercom)"></iframe></div><script src="https://player.vimeo.com/api/player.js"></script> 

*The creation of a design model through an integration with Revit, Civil3D, and Dynamo on the VIKTOR platform* 

### Unlock full potential 

If you integrate a source application with your custom application on the VIKTOR platform, you immediately gain access to the source application’s database. Using [Machine Learning](https://www.viktor.ai/blog/40/artificial-intelligence-machine-learning-engineering-construction) algorithms, your application analyses data from all previous projects you have been working on. Based on that experience, the application automatically builds analytical models on demand. Since the applications learns from previous input, the more data and iterations (from different disciplines) you feed the application, the more specific these outcome predictions will become.   

![appgrowth.png](/uploads/appgrowth_bd9a589fc0.png)

*Improve your learning-curve!* 

Using this information, data can be visualized and used to communicate things clearly and effectively. You can customize your dashboard and visualize the desired data in the form of interactive graphs, plots, and infographics. For example, to: 

- Test whether objects meet the required standards 
- Apply [Artificial intelligence and Machine Learning techniques](https://www.viktor.ai/blog/40/artificial-intelligence-machine-learning-engineering-construction) to analyse and transform data 
- Use knowledge you gained from one project and apply it to another project (optimize and predict processes) 
- Make complex data more accessible, usable, and understandable 
- Compare results 
- Get valuable insights 
- Enhance decision-making 
- Anticipate errors 

Additionally, you can integrate with multiple source applications, connecting tools and data from several projects. Especially once you start expanding your database this way, you can really start applying your knowledge and improve your learning-curve! 

![App previewintegration.png](/uploads/App_previewintegration_af3d49db4b.png)

*Integrate with as many software programs as you want to expand your database!* 

The first step to data visualization is the extraction of data. A powerful tool that is especially created as a plug-in on Revit, which allows for the extraction of data to different platforms (Excel, Access, Microsoft SQL, MySQL, and SQLite) and data serialization formats (Json, XML, HTML, etc.) using the standard nodes or packages, is Dynamo. Read more about how Revit’s structural design software can be used, specifically through this [Dynamo plug-in, on the VIKTOR platform](https://www.viktor.ai/blog/12/web-application-python-Dynamo-civil3d). 

See how you can [build your own parametric design application](https://www.viktor.ai/parametric-design-software) now!

 


small_appRevit - VIKTOR (1).png

thumbnail_appRevit - VIKTOR (1).png

Blog_data_driven_decision_making_revit_2

Data-driven decision-making with Revit

### Content: 

1. An introduction to developing successful applications
2. Designing and planning your application
3. How to start coding
4. Gathering and processing feedback
5. Increasing the adoption of your app



How to create successful application that ensure adoption

medium_White Papers & guides - Building succesful applications.jpg

small_White Papers & guides - Building succesful applications.jpg

thumbnail_White Papers & guides - Building succesful applications.jpg

WP_pink

How to create a succesful that people will adopt

large_White Papers & Guides - Building Succesful applications

medium_White Papers & Guides - Building Succesful applications

small_White Papers & Guides - Building Succesful applications

thumbnail_White Papers & Guides - Building Succesful applications

WP_pink_2

Do you want to build a successful application? This guide is here to help you make apps that provide real value to your work and that other people will definitely want to use too!

Over the past years, we, the application developers at VIKTOR, have built many apps for many different industries. We have learned a lot from that and now want to share our experiences with you. 

The principles and processes we explain in this guide are the same as we apply daily. They have helped us build anything from simple apps designed to save time to advanced engineering applications that are used to automatically calculate underground tunnels, dikes, and other large structures. 

This guide will provide actionable insights that are useful for anyone involved in creating custom software tools. For example:

- People developing the tools (developers, engineers, data scientists, etc..)
- End-users, who will use the tools when they are released
- Project managers who are interested in workflow automation/optimization
- Program managers, who oversee and stimulate digital transformation initiatives
- Domain experts, who provide their expertise to people creating software tools
- And anyone else interesting in the process of creating awesome software tools

Learn the process to build apps that provide real value to your work and that other people will definitely want to use as well.

Build successful applications

Learn how to build apps that provide real value to your work and that other people will definitely want to use as well.

Building Successful Applications

The DEC is an initiative of Heijmans, BAM Infra Nederland, and Ballast Nedam. As of recently, Boskalis Nederland, Dura Vermeer, Mobilis, van Oord, VIKTOR, and VolkerWessels have become a part of the community as well. That is why it is now time to share the DEC with the rest of the world as well!

On our new website (available in Dutch), www.digitalengineeringcommunity.nl, you can find all information on latest developments. Additonalloy, we show you how you can join in as well!

## First application developments

Now the first applications are being developed, it already shows that collaborating is the future. These kind of developments are happening in every company. It is a big task, but not a unique one. Therefore, when we are working together on every aspect, there is no need for everyone to reinvent the wheel each time. By collaborating as a sector we can digitize faster, more effective, and cheaper!

## Trust is at the core

On construction projects there is already a lot of collaborating going on. Also on this new theme people are starting to collaborate and trust each other. Every organization is free to choose whether they want to join in on a development or not and is also free to participate later on. There are several ways organizations can participate in a development, such as by supplying usable code, offering skilled programmers, or providing financial support. The expansion of the DEC with other organizations is the next logical step and we are looking forward to it!

Join the DEC and apply at [www.digitalengineeringcommunity.nl!](http://www.digitalengineeringcommunity.nl)



large_first collective automation application.jpg

medium_first collective automation application.jpg

small_first collective automation application.jpg

thumbnail_first collective automation application.jpg

Blog_digital_engineering_community_collaboration

Digital Engineering Community: Fast digitization with collaboration

## Get the white paper

**INDEX**

1. Construction companies and digital transformation
2. Technology trends for a different approach
3. Technology trends in the construction industry
4. A new technology trend for the construction industry
5. Low code for the construction industry
6. The VIKTOR platform
7. What does it cost?
8. How to start
9. What's next?

small_White Paper Digital Transformation Engineering and construction industry.jpg

thumbnail_White Paper Digital Transformation Engineering and construction industry.jpg

WP_dark_blue

large_gravity-based foundation application.jpg

medium_gravity-based foundation application.jpg

small_gravity-based foundation application.jpg

thumbnail_gravity-based foundation application.jpg

Customer_case_centralizing_data_faster_gravity_based_foundation_analysis_2

Autonomous cars, algorithms that are trading stocks, people having conversations with robots and digital services from the valley make our lives easier. It is already part of many different industries and drives extreme productivity. Considering these benefits of digitalization, there is huge potential in introducing this in the engineering and construction sector.

However, the engineering and construction industry spends way less on digital transformation than other sectors or automotive. So when the benefits are obvious, why have the engineering and construction industry not yet fully embraced new digital technologies? The reasons of lacking behind are understandable and have to do with the characteristics of the industry. But we have come to a time where there are increasing opportunities at hand for 
the sector to speed up digital transformation.

What are these trends in digital transformation and how will it effect the engineering and construction industry? You can read the answers to these questions and more in the white paper.



Learn about the trends on digital transformation and how to take the next step.

Download the White Paper and get INSPIRED

What are the trends in digital transformation and how will it effect the engineering and construction industry? You can read the answers to these questions and more in the white paper.

Digital Transformation Engineering and Construction Industry

Parametric design


## Embracing new technologies

All kinds of companies in all kinds of sectors are increasingly using new technologies to work more efficient on products and projects. It is important to highlight what these technologies are and how they can benefit business to keep inspiring people to use these findings and improve their industry. As part of this inspiration process, Robert-Jan was invited to talk about these new innovations. Sitting in front a background picture of Back to the Future, he takes us on a time travel to both the past and the future of technology in the Engineering and Construction industry.

## Software evolution in the E&C industry

“Back in the ’50s” Robert-Jan explains, “engineers used to work in big rooms, with big tables, drawing their designs on big pieces of paper, all by hand. Those people could probably not imagine that the tools they were using back then were all going to be replaced by technology at some point”. 

Around the 1950’s was also the time that the first Computer Aided Design (CAD) was released, which embarked the start of it all. At the time, it was not immediately successful. It was just a big machine that literally replaced real pen and paper with a digital pen and computer screen, not very user-friendly. It was not until the 1980’s that the Autodesk came with the first AutoCAD program. That is when computers finally took over the drawing process, which then led to the next innovation in design as well: 3D modelling. This took about 20 years to get successful, but once it was, that is when the implication of BIM (Building Information Modelling) came around, which allowed for more analysis and the addition of extra data to models. 

Robert-Jan remembers a situation from two years ago when he was involved in a project where they started arguing about whether they should use 3D models or not. “That exact situation provides a good example of how slow this process of embracing new technologies goes, especially in the Engineering and Construction industry. Not even by now, the use of 3D models is truly embraced.”

### Parametric design as part of the evolution

This gets us to another innovation that is a very hot topic nowadays, which is [parametric design](https://www.viktor.ai/blog/46/parametric-design-cloud-engineering-construction). According to Robert-Jan, a lot of people see this as a huge evolution in design methods and even call it the holy grail. Robert-Jan himself however does not see it that way. He rather sees parametric design as part of the visual programming evolution that already started back in the 1980's. 

### Another way of drawing

“[Parametric design](https://www.viktor.ai/blog/46/parametric-design-cloud-engineering-construction) is actually just another way of drawing: It is drawing with nodes. Of course, this gives you more freedom, but in the end, we are still creating the same end-product as before: Drawings. However, what I do think is very interesting about this development is that in comparison with a 3D model you get to put some knowledge within a [parametric model](https://www.viktor.ai/parametric-design-software). When you shift a wall in a 3D model else nothing happens. When you do this in a [parametric design model](https://www.viktor.ai/blog/46/parametric-design-cloud-engineering-construction), everything linked starts to shift as well.”, Robert-Jan explains. “Unfortunately, parametric design tools still lack accessibility and need democratization of knowledge. It is hard to communicate what they are and expose what they can do to the rest of the world. Most of the time, these models are stand-alone documents on someone’s machine, and the only end-user is also the one who created it.”

### Friendly visual programming

Starting with programming is still scary to a lot of people due to the weird syntax, bright colours, and other stuff that does not make any sense to them at all. It is a big step to start programming when you possess zero knowledge about or experience with coding. However, you don’t have to go from zero to hundred all at once. An interesting way to introduce programming principles to for example an engineer is by starting with visual programming instead. 

> “With visual programming, everything looks a lot more friendly and accessible. You have this little block that is a function, you have an input and an output, and you put those together and create something.” – Robert-Jan
 
### From visual programming to actual coding

> “Visual programming makes the threshold to learning how to code much lower. Visual programming contains the same principles found in conventional programming, but you can obtain a better understanding about what you are doing since everything is visualised now. To me, this is fundamental to increase people's confidence, which is needed to take the step to much more abstract conventional programming. Right now, I have been using C#, Python, and visual programming. The complexity of the computational process determines which one I choose. In some cases you come to face the limitations of visual programming. That is when conventional programming becomes a good alternative.” – Rayaan  Ajouz, Design Automation Specialist at Bouwen met Staal.  

### The rise of custom developed software tools

Companies and people themselves are increasingly using all kinds of programming tools to start developing their own their own custom software tools to help meet their unique requirements. But what kind of tools are currently the most popular? And for whom do people develop custom software tools? How much time do they spend doing this? These are the questions that Robert-Jan asks the audience to get an accurate image of the current situation regarding the software developer community. 

From a survey at the start of the webinar it was concluded that:
- A significant part of the audience was part of the structural engineering sector. 
- These people indicated to use platforms as Dynamo, Excel, and Python most often to develop their own software tools. 
- Most people developed custom software tools not for themselves, but for their colleagues.
- And they spend half a week up to a week per month doing so. 
      
![parametric design engineering construction automation application](https://cms.viktor.ai/uploads/Blog_the_future_of_engineering_survey_83a0f9fd46.png)



## A new generation in engineering software

### The bars are shifting
 
![03_01.png](/uploads/03_01_a20971d815.png)

This picture shows the levels of knowledge between technology companies (left) and engineering companies (right) in the 1950’s. Back then, technology companies did not have a lot of knowledge. That was until they adopted Computer Aided Design (CAD) and started using this to get some better understandings in the field of engineering. Although CAD helped technology companies gain knowledge, it made engineering companies lose some due to the fact that they started using computers, which now took over some of the work. Then, technology companies started implementing BIM and 3D models and gained even more knowledge. Slowly, the knowledge of engineering companies was getting replaced more and more by technological innovations, making the bars shift once again. 

![03_GIF.gif](/uploads/03_GIF_c31964d64a.gif)

“If you are a structural engineer right now, you might find this an ominous future perspective for engineering companies. However, this is not how I see the future.”, Robert-Jan explains. “I see a future where the bars are actually moving more towards each other. Engineering companies have a lot of people that only just now are getting introduced to the concept of visual programming and are beginning to see the potential of coding. They are doing it for all kinds of different reasons: To improve internal work processes, to be able to create a design quicker and more efficiently, or to explore the terrain of improving their business model, for example by offering micro services of applications to the world.”

### A better future starts with yourself

So, if you are an engineer and this scares you, Robert-Jan has some advice for you: “Don’t be like those engineers from the ‘50s that are stuck in their old design methods. Start improving your skills by using these new technologies that are now around, if you haven’t already. Set a deadline for yourself: In five years I will have written my first Python script and started replacing my technologies!”

> “The world is changing, and technology is starting to play a far more profound role within the engineering industry. It is up to us to determine how far the blue line will progress and the green line will decline. So, let’s get busy!” – Robert-Jan 

### Our way is already paved

Compared to other industries, the Engineering and Construction industry seems to be lagging on technological developments. The Aviation and Aerospace industry are for example very high-tech. They were front-runners from the beginning on. You can't compete with that.

“In the Construction industry, we are very slow and sceptical about the adoption of new technologies. In many projects there is a lot of pressure regarding time and cost, which means there isn’t much room for innovation left. Therefore, we are not the front-runners.”, says Robert-Jan. “However, we are not doing too bad either. Other industries aren’t doing worse, but we shouldn’t compare. It could actually be beneficial that we are not the first ones that are doing all this developing. The others have been blowing money and resources on stuff that did not work as well as they hoped it would and we are now getting the stuff that does work from them!”

## Democratization of knowledge through web applications

### Why web applications are gaining popularity

This timeline shows where we want to head with software development. In the 1950’s was when the digitising process started. The goal is to fully democratize all knowledge to the point where anyone can use it. Currently, most companies are in the optimising stage: They are doing optimizations, but having difficulties distributing their knowledge. The capturing of knowledge into assets and distributing it this way is a logical next step. 

For this, you must move to the internet by developing web applications that allow you to better capture and distribute knowledge. Web applications are very accessible, since you don't have to install any software or whatsoever on your device, you simply have to log in on the online platform, which can be done from anywhere you want if you have an internet connection. Additionally, a web application ensures that you are always working with the latest version and that all changes are tracked neatly as well. 

![01.png](/uploads/01_5e180785ea.png)

  
### App development is no Rocket Science

Creating a web application is easier said than done when you are part of an engineering company that doesn’t know anything about programming languages, setting up services, cyber security, version control, or back-end developing. Luckily, all of this is not necessary. There are a lot of software development platforms out there to help you along the way. In a lot of other industries, people (we call them 'citizen developers') are already using these platforms to develop their own digital tools and the benefit of that is really noticeable!

“A citizen developer is not a true software developer. They haven’t studied Computer Science or something alike but thanks to these online platforms they are enabled to share their knowledge with other people and easily create their own applications.”, Explains Robert-Jan. “Even in the construction industry, where a lot of people are not that 'tech-savvy' at all, a lot more citizen developers are popping op!”

## Build your own application with a development platform

### Stop reinventing the wheel

Lately, a lot of different application development platforms are emerging, that are here to help you build your own applications. Each one of them has its pros and cons, and there is always a good reason to choose one over the other. Luckily, there is still so much to do that there is more than enough room for all of them.  

VIKTOR is also one of these platforms. What are we specialized at? We help you reduce workload by automating repetitive tasks. Why try to reinvent the wheel when you can use a platform that helps you design all the tools you need? See how you in only three steps you can create awesome applications using just a few lines of Python code in this video:

<div style="padding:56.25% 0 0 0;position:relative;"><iframe src="https://player.vimeo.com/video/545019231?badge=0&amp;autopause=0&amp;player_id=0&amp;app_id=58479" frameborder="0" allow="autoplay; fullscreen; picture-in-picture" allowfullscreen style="position:absolute;top:0;left:0;width:100%;height:100%;" title="VIKTOR Explained under 2 minutes"></iframe></div><script src="https://player.vimeo.com/api/player.js"></script>

### Build company-wide asset

We provide a Python software development kit, which basically means that you can create web applications very easily by writing Python code, instead of HTML, JavaScript, back-end, and all of that. You can also easily integrate already existing models from other tools if you like to. Once your application is ready, you just have to deploy it in the cloud and work on it together with whomever you want. 

Building a company-wide asset from scratch will cost a lot of time and money. Using a software development platform like VIKTOR gives you a head start since you have access to standard components, version control, user management and whatnot. All you have to bring is your domain knowledge and get it out there by sharing with colleagues and clients!

### Easily integrate with Python

There are a lot of open-source packages that can be implemented into VIKTOR. Python is one of those, and it’s a great tool as well. What Robert-Jan really likes about Python is that there is a big community with a lot of support. “If you have a question about something, someone else probably already asked the same and the answer is somewhere out there.”

> “Programming with VIKTOR and Python is not scary at all. You are really going to enjoy it! Automate the boring and engineer the awesome, that is what it is all about. It allows you to create awesome tools that let you develop awesome things for the world.” – Robert-Jan

## So, what will the future look like?

> “There are so many of these application development platforms, maybe one day they will work together to integrate their features as well.” - Robert-Jan

Robert-Jan is on the application team and they can help you with developing your own application if you don’t know Python or your company doesn’t have people that understand how to develop their own tools. However, they don’t want to develop the tool for you. The development team wants you to develop your own tool and they can help you with that along the way. Because if everyone develops their own tools, the sharing of knowledge between companies can be boosted.

### New ways to share knowledge

The [Digital Engineering Community (DEC)](https://www.viktor.ai/blog/31/digital-transformation-python-construction) is a combination of a few of the biggest construction companies. They are jointly working together to build application on the VIKTOR platform. They are all co-owners of the code that has been created and share all knowledge within their community. What would be great is if this could be opened further and more people get involved! 

Want to watch the whole webinar? Go to the YouTube video here!

<https://www.youtube.com/watch?v=k6NPcSGPuHE&list=PL4Yo2I-oZ8-5gdW_0hwUbxW7-bMkiRidQ&index=7&ab_channel=BouwenmetStaal>



large_software developer.jpg

medium_software developer.jpg

small_software developer.jpg

thumbnail_software developer.jpg

Blog_will_we_all_become_software_developers_7

The future of Engineering: Will we all become software developers?

Combining the expertise of both companies allows for the creation of an integrated product. Through an API, CRUX Engineering Microservices (CEMS), a starting IT company that is powered by CRUX, will take care of the backend, which contains the heart of the geo-calculations. VIKTOR is responsible for the creation of an accessible and easy to use web application. 

“It is a nice collaboration between CRUX and VIKTOR because at CRUX they have a lot of professional experience in soil mechanics, foundations, and geotechnical engineering and they also create a lot of powerful API's. These things may be a bit hard to understand for people that are not necessarily educated in coding and Python so making this kind of knowledge from CRUX more accessible through use of the VIKTOR platform is really beneficial to engineers. We make this part accessible for them with an intuitive interface that everybody is able to use.” – Matthias Hauth, Python developer at VIKTOR. 

Before this, VIKTOR and CRUX had already been working together on [GeoTools](https://www.viktor.ai/blog/14/web-application-python-geotechnics): an application that automatically interprets CPTs on the VIKTOR platform based on [machine learning](https://www.viktor.ai/blog/40/artificial-intelligence-machine-learning-engineering-construction) via an [API developed by CEMS](https://www.viktor.ai/blog/15/digital-transformation-automation-Excel-python-geotechnics). PileCore and VibraCore are two other collaborative applications, developed to design pile foundations and predict vibrations caused by foundation activities. These applications are currently developed and will be launched this summer! 

In the picture are from left to right Jacco Haasnoot (Director/owner of CRUX), Johan Zwaan (partner at CEMS), Stijn Jansen (Head application development at VIKTOR), Matthias Hauth (Python developer at VIKTOR), Peter Madlener (Co-founder of VIKTOR), and Wouter Riedijk (Co-founder of VIKTOR).  

We are looking forward to our collaboration! 

large_MicrosoftTeams-image (4).png

medium_MicrosoftTeams-image (4).png

small_MicrosoftTeams-image (4).png

thumbnail_MicrosoftTeams-image (4).png

Blog_viktor_crux_partnership_geo_engineers

VIKTOR and CRUX announce partnership to develop automation products for Geo Engineers 

1. An introduction to Artificial Intelligence
2. Artificial Intelligence vs Machine Learning
3. AI and ML in organizations
4. Building a Machine Learning application
5. About VIKTOR

artificial intelligence AI machine learning ML engineering construction

medium_A4 - White Paper COVERwp ai cover.png

small_A4 - White Paper COVERwp ai cover.png

thumbnail_A4 - White Paper COVERwp ai cover.png

WP_green

artificial intelligence machine learning engineering construction

large_artificial intelligence machine learning engineering construction

medium_artificial intelligence machine learning engineering construction

small_artificial intelligence machine learning engineering construction

thumbnail_artificial intelligence machine learning engineering construction

Blog_AI_and_Machine_learning_engineering_construction_1

What exactly is artificial intelligence? 
What are the four types of AI? 
How does artificial intelligence differ from machine learning? 
And what are the different types of ML?

In this White Paper, we will answer all of these questions and more about the topic.

Find out how you can use AI to improve and automate (engineering) processes within your organization and learn how to build a machine learning application yourself as we guide you through the following chapters:

1. An introduction to Artificial Intelligence
2. Artificial Intelligence and Machine Learning
3. AI and ML in organizations
4. Building a Machine Learning application
5. About VIKTOR

Find out how you can use Artificial Intelligence and Machine Learning to automate engineering processes!

Artificial Intelligence in Engineering and Construction

It is impossible to conceive any large project without hundreds of different models in CAD software such as Autodesk. The "manual" work of today consists of many mouse clicks behind a desk. Most skilled modelers have improved their workflow by automating parts of their work, reducing the number of clicks and saving time on large projects. 

## The advantages and disadvantages of Dynamo 

One of the most beloved tools by modelers to automate their work is Dynamo, a visual programming tool. By no longer requiring programming experience, it makes automation more accessible and allows modelers to quickly automate repetitive tasks. The engineers at Arcadis are clearly aware of the many advantages this provides, as many of them use Dynamo a lot in their work. 

However, Dynamo also has some disadvantages. Since it is very easy to start with Dynamo, it is also very easy to make complex models resemble big knots that can be very difficult for someone else to untie. 

Much like a very complex Excel sheet made by somebody else, these complicated models are very difficult to share among co-workers. So, everybody tends to make their own program, as this is usually faster than understanding how to use somebody else's.  

## Use it, without breaking it 

This is where VIKTOR comes in. VIKTOR is a web application development platform with a Python framework. Amongst others, it has an integration with Dynamo. VIKTOR enables easy sharing of Dynamo [parametric design models](https://www.viktor.ai/parametric-design-software) with your colleagues. It provides an easy-to-use user interface that asks for input and shows the results. This allows you to use a model you don’t know, without being afraid to break it. You don't need to learn another new tool, or program, and you can use models from your colleagues easily. Obviously, this can save enormous amounts of time. Furthermore, this can prevent mistakes from happening as you can polish one model rather than having ten different versions made by ten different colleagues floating around. Indeed, as soon as you finish it, the app is instantly available online. Additionally, providing access to colleagues is easy and fast. 

## Finished by lunchtime 

Arcadis has proven the development speed by converting some of their Dynamo models to VIKTOR-based interfaces. A day was setup where some of their engineers met with people from VIKTOR to move some of their most used projects to the VIKTOR platform. The expectation was that it would be a lot of work and they set aside an entire day for it, but in reality, they were finished by lunchtime. 

The main advantage for Arcadis is that the skills of their engineers are now easily transferable. There is no steep learning curve and no need for inhouse web-development. All they needed was their existing Dynamo knowledge and 10 to 20 lines of Python code that are mostly reusable. 


## From spaghetti to just three sliders 

In a single morning they managed to create two web apps from their Dynamo projects. Both are shown here. The first generates a design for a Highrise building based on three parameters. The second generates a model of a Dome with four parameters. 

 ![inspriational 1.jpg](/uploads/inspriational_1_356d1c6f86.jpg)

*A design of a Highrise building based on three parametesr*

![Slide1.PNG](/uploads/Slide1_8f4b1ecab4.PNG)

*A model of a dome based on four parameters*

As you can see, the Dynamo code is not very intuitive. In the presented ‘spaghetti’ it is not easy to understand what is happening and what you need to do. To someone that is not ‘in the know’, it will take time and explanations to be able to use it. Confusion and mistakes are likely. 

Below, we have the VIKTOR web-app. This is the same Dynamo code, just with a wrapper around it. In this case, it is very easy to understand what is happening. There are three parameters. Based on those, a design for a building is generated and visualized within the same screen. Almost no explanation is needed to be able use this, even someone that never used Dynamo could figure it out alone in a few minutes. This allows tools and knowledge to easily be shared within teams and within a company. No need for everyone to build their own version and to reinvent the wheel. One model is enough. 

<div style="padding:56.25% 0 0 0;position:relative;"><iframe src="https://player.vimeo.com/video/563612861?badge=0&amp;autopause=0&amp;player_id=0&amp;app_id=58479" frameborder="0" allow="autoplay; fullscreen; picture-in-picture" allowfullscreen style="position:absolute;top:0;left:0;width:100%;height:100%;" title="LinkedIn_Tower"></iframe></div><script src="https://player.vimeo.com/api/player.js"></script>

<iframe src="https://player.vimeo.com/video/513789510" width="640" height="564" frameborder="0" allow="autoplay; fullscreen" allowfullscreen></iframe>

**Automate the boring. Engineer the awesome!**



thumbnail_Dynamo and arcadis.jpg

Dynamo and arcadis.jpg

Find out how you can use Python to share Dynamo models with colleagues & facilitate collaboration on VIKTOR.ai.

How to share Dynamo models in the Cloud with Python

Dynamo and Python in the Cloud for easy sharing and accessibility


>“We are very enthusiastic about this collaboration! Together with our business ProductOwner and a ‘Coding Engineer’ we are exploring this collaboration in the development of the underwater concrete floors application. Quite exciting, with questions as ‘what is generic and suited for shared development?’ versus ‘where do we secure our own IP?’ It is clear that this kind of automation is necessary. The exploration surrounds the question: What can we do together? And with that faster and cheaper?” – Mark van den Brink, Digital Transformation Lead at WSP 

## From idea to proposal
 
In a few sessions with the participating parties, the four ideas have been worked out into the following proposals:

### Crane hardstand

The purpose of this development is enabling engineers to determine the stability of crawler- and outrigger cranes, including the design of possible needed ground improvement, fast and easy to decrease the changes of tripping over. Within the application, cranes can be inserted parametrically, from which the maximal ground pressure can be determined. CPT’s (.gef files) can easily be uploaded as well. These are directly interpreted to a schematized overview of the soil layout. From there on, the stability can be determined through an integration with D-Foundations (shallow foundations). 

### Floor on piles

Many infrastructural objects consist of a concrete foundation- and floor. With this development, an optimal design of the combination floor and piles can easily be generated, including the ideal reinforcement configuration. A constructor can use this application to easily link the force effect from a finite element model (e.g. SCIA) to a cut test (e.g. IDEA StatiCa). Additionally, the pile plan can be varied to find the optimal configuration between plate reinforcement and piles. 

### Sheet piles/Construction pits

To realize construction and (temporarily) turn ground, we use sheet piles and construction pits. The purpose of this development is to parametrically design sheet piles and integrate these with anchors, underwater concrete floors, outrigger frames, etc. Within this application, the sheet pile is tested through an integration with D-SheetPiling, which enables the fast calculation of different cuts and variants.

### Underwater concrete floors

Underwater concrete is, amongst others, used for underground parking garages, underpasses, and tunnels. This development fits nicely with sheet piles/construction pits. With the application, a design of a floor including anchorage is parametrically designed to automatically generate the optimal configuration. The underwater concrete floors are tested conform the CUR77. The carrying capacity of the anchors/piles is determined through an integration with D-Foundations. 

## How to participate? 

To turn the development ideas into concrete proposals, a few in-depth sessions were organized to come up with ‘user stories’ that form the basis of every application’s functionality. Based on the user stories, a development plan and associated estimation of the costs can be determined. In March, the first definitive proposals will be sent to the entire community. Every party that is interested in joining one or more of the development proposals can sign up.

>“It’s like the old saying “many hands make light work”. Especially with crane hardstands. We all have the same goal in mind, which is safety. This is something we should take on together, so that we can quickly develop a good tool that helps us check the stability of cranes.” – Arie-Jan Tol, Team Lead at engineering firm Hektec
 
## What is the DEC?

*Accelerated digitization through collaboration*

The DEC is thé digital meeting point for the construction and infra sector, where ideas for software development come together, are started up, and accelerated. 

We share our knowledge so that we can work together to invent the wheel, make it easier to finance the (engineering) process, and offer smart and high-quality solutions. 

The initiators are Ballast Nedam, BAM, Boskalis Nederland, Dura Vermeer, Heijmans, Mobilis, Van Oord, VIKTOR, VolkerWessels. Antea Group, CRUX, Hektec, RPS, Tauw, and WSP are now a part of the DEC as well.


medium_DEC foto.jpg

small_DEC foto.jpg

thumbnail_DEC foto.jpg

Blog_DEC_development_ideas_2022

The Digital Engineering Community is expanding and has 4 new development proposals for engineering automation apps early 2022. Join now!

VIKTOR Blog

Expansion DEC brings 4 development proposals early 2022