Graduation project AI (in collaboration with McDermott)
Together with our client McDermott, we offer a thesis where you research for McDermott about 'Robust symbol detection and recognition in piping and instrumentation diagrams'.
What will you do
40%
Research
40%
Development
20%
Implementation
This project is concerned with the recognition of symbols of piping and process equipment together with the instrumentation and control devices that appear on piping and instrumentation diagrams (P&ID). Each item on the P&ID is associated with a pipeline. Piping engineers often receive drawings from clients in PDF format rather than a digital format produced in engineering software packages. This is due to confidentiality reasons and can also be true when dealing with legacy drawings.
From P&IDs, piping engineers are required to generate material take off (MTOs) documents which will include the list of equipment, their quantities, sizes, etc. The MTO is used to create estimates of costs. To generate MTOs, piping engineers will manually go through every single drawing, identify the symbols, count them, and fill in an MTO spreadsheet. It can take around 36 hours of a highly skilled engineer’s time to generate an MTO for 10 drawings and every project has around 500-1000 drawings. Additionally, the process is prone to mistakes and may require additional checks. Mistakes in quantities, sizes or materials can have huge cost implications.
An AI based approach helps automate the generation of MTOs from P&IDs. It is expected that a human interaction level will still be required for instance in some cases engineers’ expertise may be required to decide on the quantities based on what is presented on drawings. Note that every project has its own legend sheets i.e. symbols differ between projects.
The desired model needs to be able to:
- Identify equipment and instruments on drawings with reasonable accuracy
- Process 100s of documents simultaneously
- Require reasonable training hours (as symbols are project specific)
- Enable extraction of line numbers as well as symbol recognition
- Associate line numbers with symbols
- Automatically populate an MTO spreadsheet
- Any scripts must be written in Python.
About McDermott
Please visit our website to find out more about McDermott and what we do as a company.
Your profile
You have experience with programming in Python
You have an interest and experience in machine learning and deep learning for object- and text recognition
You are proactive in trying and testing new ideas and working with engineers
You are able to apply research findings in a timely manner
What will you get?
You have the unique opportunity to graduate from 2 different companies at the same time, an established company like McDermott and a scale up VIKTOR
A nice team where you are well guided and where you are really part of the company
A research that does not disappear in a drawer, but with which you can really make an impact and make a contribution
Why does our team like this job
"During my internship at VIKTOR this summer, I explored the opportunities for machine learning in the construction industry. An application is developed that is able to predict pile drive times for different construction projects with an artificial neural network. This network is trained on prior pile drive measurements, which the user can upload in the app. "
Lars Janssen
Research and development intern (2021)
What can you expect from us?
Flexibility
It's about what you deliver. How, when and where? That's up to you. From our inspiring office or from your well-facilitated home office. First take the children to school in the morning or do some sports in the afternoon and then get back to work full of energy. Do what works best for you.
Healthy work-life balance
Of course you have a very nice job at VIKTOR ;). But other things are important too, such as family, friends and hobbies. Working overtime is avoided as much as possible. With 28 days off, we hope that you have enough time to do everything you love. If 28 days are not enough because you want to make a world trip, that is possible too!
Awesome team
Be part of an enthusiastic and driven team. We have a lot of fun and there is a plenty of room for ideas and initiatives. The most brilliant ideas often arise during a team outing, drinks or team building day. The weekly demos give you a good idea of what other colleagues are working on and how the platform is evolving. The flat structure ensures quick communication and decision-making.
Personal growth
Due to the monthly 1-on-1 conversations, there is constant attention on your personal growth and wellbeing. We are happy to help you develop yourself and realize your ambitions. You are part of a growing company where you contribute to innovative developments with a major impact. If you grow, we grow.
Our Five Stage Recruitment Process
1
Review
Thanks for your application! We will consider your application and contact you soon.
2
Phone Call
You have an interesting background! We are very curious and would like to learn more about you.
3
1st Job Interview
During a first interview we really get to know each other, and of course we tell you more about our vision and ambitions.
4
Assignment
We think you'll fit well with the team! Time to evaluate your (development) skills with some fun assignments.
5
2nd Job Interview
Nice skills! We are happy to have a second interview where we go deeper into the content of the position.
Job offer
We are both excited. You will receive a job offer and hopefully we can welcome you soon!
Apply for this position
Don't hesitate and apply right away! In case of questions, drop us a line at jobs@viktor.ai or contact HR directly via LinkedIn.
