BT/MT: »Bayesian optimization for optimal experimental design in production processes«

The Fraunhofer-Gesellschaft (www.fraunhofer.com) currently operates 76 institutes and research institutions throughout Germany and is the world’s leading applied research organization. Around 30 800 employees work with an annual research budget of 3.0 billion euros.

At the Fraunhofer IPT in Aachen, we work with more than 530 employees every day to make the production of the future more digital, more flexible and more sustainable. In the department for production quality, we focus on the digitalization of production systems to increase quality, resilience, and sustainability of production.

The optimization of production processes is becoming increasingly important, but also more complex, due to rising demands on the sustainability of processes. Bayesian optimization (BO) - a particular machine learning method - represents a promising alternative to traditional process optimization methods due to its adaptive decision making and data efficiency. A key challenge is the configuration of the BO-method (i.e., surrogate model and acquisition function) depending on the characteristics of the optimization problem. To establish Bayesian optimization in production engineering practice, this thesis aims to analyze which BO-methods are well suited for different optimization problems with respect to an accurate and efficient optimization.

What you will do

Literature research on Bayesian optimization and optimal experimental design in production processes
Analysis of different BO-algorithms and their dependencies on process optimization properties
Derivation of a set of properties for characterization of production processes
Development of a methodology for optimal configuration of the BO-algorithm regarding the defined properties of the production process
Verification and validation of the methodology for a freely selectable use case from optics production, laser processing or biotechnology
Documentation of the results and writing of the scientific work

What you bring to the table

You study mechanical engineering, computer science, mathematics or a comparable subject
You are interested in the field of production engineering and the transfer of theoretical concepts into real-world applications
You are familiar with the theory and the approaches of machine learning and would like to specialize in this subject area
Your strength is analytical thinking, and you have good abstraction skills
A high degree of motivation, willingness to learn, and independence
Good language skills in German and/or English

What you can expect

Application-oriented research in the integration of machine learning into industrial production processes
Ideal framework for practical experience alongside studies in a renowned research institute
Collaboration in a multi-member team within an exciting research project in cooperation with several Fraunhofer institutes
Excellent equipment of machines and devices

We value and promote the diversity of our employees' skills and therefore welcome all applications - regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Severely disabled persons are given preference in the event of equal suitability.

With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future.

Interested? Apply online now. We look forward to getting to know you!

Questions according to this position will be answered by:
Lars Leyendecker M.Sc.
Research Assistant Production Quality
Phone: +49 241 8904-314

Fraunhofer Institute for Production Technology IPT

www.ipt.fraunhofer.de

Requisition Number: 68141 Application Deadline:

Job Segment: Research Assistant, Mechanical Engineer, Computer Science, Biotech, Research, Engineering, Technology, Science

Apply now »