PhD Thesis - Reliable Multi-Scale Surrogate Models (f/m/div.)

Company Description

Do you want beneficial technologies being shaped by your ideas? Whether in the areas of mobility solutions, consumer goods, industrial technology or energy and building technology – with us, you will have the chance to improve quality of life all across the globe. Welcome to Bosch.

The Robert Bosch GmbH is looking forward to your application!

Job Description

Numerical simulation plays an important role within the design and development of new products. However, trying to capture “the real” predictive behavior of a product design in terms of performance and reliability is often challenging. Especially in the context of multi-scale problems, the mathematical models need to resolve many scales and consequently are very compute intensive in terms of computational runtime and memory demands. In general, surrogate modelling approaches have been proven to be a viable option to speed-up computational models. However, classical approaches often fail in multi-scale problems within industrial settings.  

In this PhD thesis we want to investigate, how to efficiently speed-up multi-scale problems using surrogate modelling on a specific Bosch use case. Especially in the setting that we want to combine simulation data with measurements to improve the predictive quality. Naturally, the problem setup poses many challenges, out of which are:

• Modelling the multi-scales with proper surrogates
• Combine data and simulation with uncertainty within the training phase of the surrogate models to add a notion of reliability
• Deal with large parameter spaces
• Approximate strong non-linear functional behavior

Qualifications

• Education: excellent university degree in applied mathematics
• Experience and Knowledge: strong knowledge in numerical simulation of ordinary and partial differential equations; good knowledge of machine learning methods (supervised and unsupervised learning), surrogate modelling or model order reduction; strong programming skills, ideally in Python; solid knowledge in probability theory / statistical methods
• Enthusiasm: interest in solving industrial applications
• Languages: fluent in English

Additional Information

www.bosch.com/research
https://www.bosch-ai.com

The final Phd topic is subject to your university. Start: February 2024

Please submit all relevant documents (incl. CV, certificates, transcript of records).

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity.

Need support during your application?
Kevin Heiner (Human Resources)
+49 711 811 12223

Need further information about the job?
Michael Schick (Functional Department)
+49 711 811 15877

#LI-DNI