30 credits – Realistic training data generation using generative adversarial neural networks Job at Scania in Södertälje
Being able to use vehicles according to plan and without the risk of unplanned breakdowns is fundamental to ensure an efficient transport system. If a vehicle’s health status can be accurately predicted or forecasted there is a potential to streamline maintenance, increase operational availability, and reduce the risks of costly repairs and destroyed cargo.
Accurate health status predictions are fundamental to ensure operational availability. However, because of the diversity in the way trucks and buses typically are configured and used, accurate prediction models are difficult to achieve. In addition, data-driven prognostics rely on large amounts of historical failure data to estimate prognostics model parameters and this type of data is typically limited in real-world industrial scenarios. Often, the amount of data that can be collected is large but the rare and often the most interesting examples are very few. This makes it difficult for data-driven models to extract degradation patterns and characterise system performance from historical data.
Lately with the advent of generative adversarial neural networks, successful attempts to generate truthful synthetic training data has been made. This synthetic data can be used as a surrogate when data for a particular class or type of observation is scarce.
The project will develop methods and knowledge for how to reduce the uncertainty and error of data-driven prognostic models by generation of truthful historical failure data, and thus allow for effective implementation of predictive maintenance.
Education and skills
Master’s student in computer science, mathematics, physics or similar, preferably with specialization in statistics, machine learning, artificial intelligence and data science. Documented experience and skills in Python in addition to machine learning and deep learning, is a merit.
A thesis project is a great way to learn more about Scania and our many interesting career opportunities.
Number of students: 1-2 (you can apply separately or together)
Start date: Autumn 2020
Estimated time needed: 20 weeks, Full-time
Language of work: Good knowledge in English is required
The work will be carried out at our offices in Södertälje and from home.
Enclose CV, personal letter, and grades. If you are applying in pairs, send in separate personal applications in which you state your preferred colleague. Selections will be made throughout the application period, but with a with a break during the vacation weeks (part of July/August).
Olof Steinert YSFS, supervisor, [email protected]
Company Location: Södertälje