30hp-Leveraging generative ai for simulation models in production

Background:
Optimizing material flow in automotive production is key to improving efficiency and reducing energy use. Traditional material flow simulation models, often based on stochastic methods, help evaluate manufacturing processes both during design and after implementation. However, they struggle with scalability and managing complex systems, requiring time-consuming tasks like process mapping and data analysis. Generative AI offers an opportunity by automating scenario generation and using historical data to create faster, more adaptable simulations. This thesis will explore how generative AI can speed up and scale simulation model design.

Assignment:
The objective of this master thesis is to explore how generative AI can be effectively applied to create material flow simulation models in manufacturing. The student(s) investigate both theoretical and practical aspects of integrating GenAI techniques into existing simulation environments, with a focus on improving flexibility, speed, and accuracy of model predictions. Key areas of focus may include:

-    Explore GenAI-driven techniques at various stages of simulation model development.
-    Design and test a GenAI-assisted prototype in a realistic production environment.
-    Train and validate the GenAI-driven simulation models using real-world data from Scania's production lines.
-    Compare the performance of GenAI-driven models with traditional simulation methods.

Use cases include the creation of XML code files for material flow simulation including productivity and energy consumption parameters, and natural language-driven SQL query generation for streamlined data access and for extracting statistical distributions.

What We Offer:
-    Direct collaboration with a leading company in the automotive sector.
-    Access to real production environments and data for hands-on experimentation.
-    Mentorship from experienced professionals.
-    Opportunity to contribute to cutting-edge research with real-world industrial applications.

Education and time plan:
Education: Master’s program in Computer Science, Industrial or Automation Engineering, Data Science, Artificial Intelligence
Qualifications: Knowledge of machine learning and AI algorithms, programming skills

Number of students: 1-2
Start date: January 2025
Estimated time needed: 20 weeks

Contact persons and supervisors:

Thomas Schmitt, thomas.schmitt@scania.com

Application:

Your application must include a CV, personal letter and transcript of grades.

A background check might be conducted for this position. We are conducting interviews continuously and may close the recruitment earlier than the date specified.

See attached file