Master Thesis - Degradation analysis of Solid Oxide Cell (SOC) stacks with Machine Learning methods

Your Job:

In the department "Electrochemical Process and System Technologies" of IEK-9, research and development activities in the field of solid oxide cells (SOCs) focus primarily on optimizing the performance and lifetime of stacks and systems for various applications. SOCs are electrochemical energy converters with a solid oxide ceramic electrolyte, which are typically operated at high temperatures and can achieve very high efficiencies. When operated as a fuel cell (Solid Oxide Fuel Cell: SOFC), electrolysis (Solid Oxide Electrolysis Cell: SOEC) or co-electrolysis, or even in reversible mode (reversible Solid Oxide Cell: rSOC), the SOC offers great potential for defossilization of a wide range of applications. In order to exploit this potential in the future, it is necessary to improve the competitiveness of SOCs by increasing performance, reducing degradation and minimizing manufacturing costs. The aim of this master thesis is to investigate the applicability of different Machine Learning (ML) methods for degradation analysis, quantification or classification. The focus is on long-term operating data of SOC stacks operated in both fuel cell and electrolysis modes. Your tasks will include the following:

• Familiarisation with the basic functioning and already known degradation mechanisms of SOC stacks, as well as conventional methods for identifying and quantifying degradation events
  
• Familiarisation with the long-term operational data of SOC stacks and statistical evaluations of the already consolidated data sets, with regard to material and operational data
  
• Development and extension of ML models for the quantitative and qualitative determination and prediction of the degradation of SOC stacks depending on the material and operating parameters

Your Profile:

• Ongoing master studies in engineering or natural sciences, mathematics, physics or similar
  
• Programming skills in Python required (especially Numpy, Pandas, Scikit-learn etc.)
  
• Theoretical and practical prior knowledge in Machine Learning, preferably in the area of time series analysis, is required
  
• Basic understanding of how electrochemical converters work, especially solid oxide cells, is desirable
  
• Interest in understanding the mode of operation and the interactions during ageing/degradation processes of electrochemical converters
  
• Independent and responsible way of working, willingness to work and a high degree of team spirit
  
• Good written and oral communication skills in German or English

Our Offer:

We work on the very latest issues that impact our society and are offering you the chance to actively help in shaping the change! We support you in your work with:

• An interesting and socially relevant topic for your thesis with future-oriented themes
  
• Ideal conditions for gaining practical experience alongside your studies
  
• An interdisciplinary collaboration on projects in an international, committed and collegial team
  
• Excellent technical equipment and the newest technology
  
• A large research campus with green spaces, offering the best possible means for networking with colleagues and pursuing sports alongside work
  
• Qualified support through your scientific colleagues
  
• The chance to independently prepare and work on your tasks
  
• Flexible working hours as well as a reasonable remuneration
  
• Flexible work (location) arrangements, e.g. remote work
  

The position is initially for a fixed term of 6-12 months.

We welcome applications from people with diverse backgrounds, e.g. in terms of age, gender, disability, sexual orientation / identity, and social, ethnic and religious origin. A diverse and inclusive working environment with equal opportunities in which everyone can realize their potential is important to us.