Master Thesis Machine Learning

General information:

Do you have a deep interest in applied machine learning and would like to join a multinational organization with lots of development opportunities? Our team is dedicated to creating a future where innovative digital technology brings cleaner energy to people around the world. We are now looking for thesis workers at our R&D department. You will be part of our R&D department at G&PQS, within the Power Grids division, Vaesteraas. Our focus is on software and hardware development; integration and testing - working in close collaboration. Get acquainted with parts of the FACTS power electronic converter control solution, learn about the Python/MATLAB interface and the MATLAB/Simulink model. Investigate and develop a prototype machine learning algorithm for the purpose of potentially improving the performance of the power electronic converter. This includes early on discussing various promising ideas with supervisors about benefits and drawbacks. Evaluate the performance and limitations for various operation scenarios including out-of-distribution scenarios and fault cases.Some parts of the work can be done at distance, you will be required to be at the office for most of the thesis work. You will live Hitachi Energy's core values of safety and integrity, which means taking responsibility for your own actions while caring for your colleagues, and the business. in an international environment where you will get great possibilities to develop further within Hitachi Energy.

Responsibilities:

Developing and evaluating a prototype machine learning algorithm for integration with the FACTS (Flexible AC Transmission Systems) power electronic converter control The end goal would be to potentially improve the performance of a FACTS power electronic converter Understanding the current state-of-the-art machine learning methods. Specifically, focusing on methods that are promising for application and integration into the control of a power electronic converter Understanding of sim2real challenges and mitigations to increase robustness. In addition, understanding of control hardware system implementation limitations considering both training and inference Understanding relevant parts of the FACTS power electronic converter control. Furthermore, understand where there is a potential benefit of integrating machine learning methods Managing the programming and development environment required for the thesis work This includes a Python environment, a Python/MATLAB interface, and a MATLAB/Simulink environment Note that a simulation model will be available in MATLAB/Simulink and any machine learning algorithms are expected to be developed in Python Living Hitachi energy's core values of safety and integrity, which means taking responsibility for your own actions while caring for your colleagues and the business

Your background:

Required Student of Master of Science, Engineering Physics, Electrical Engineering or Computer Science degree Good knowledge/experience in Python A good learner and with out of box thinking. Good knowledge in MATLAB, power systems and/or control is a plus Genuine interest in machine learning and programming