Master Thesis AI-based Sensorless Edrive Control

Analyze state-of-the-art machine learning and neural network approaches applied to sensorless control of electric drives. Develop novel AI-based control architectures, exploring both modular and end-to-end neural network designs. Implement, test, and validate control algorithms using high-fidelity electric drive simulation models. Document methodology, analyze results, and present findings to the development team. This six-month hybrid thesis requires enrollment at a university with a Master's degree in Cybernetics, Engineering, Mathematics, Computer Science, or comparable fields, alongside profound knowledge of control engineering and machine learning, Python, or MATLAB.