Master Thesis Robust Identification of Compositional Electrical Drive Models — Identifiability, Sensitivity & Excitation Analysis
Core
Develop robust diagnostics for physics-based electric drive models by analyzing parameter identifiability, sensitivity, and excitation content to improve identification quality.
Role type
Master's thesis researcher (system identification & electrical drives)
Builds
Robustness diagnostics for an existing identification pipeline
Domain
Electrical engineering, system identification, control theory
Deliverable
production ML models | research
Required skills
Python programming, dynamic systems modeling, differential equations, physics of electrical machines
Preferred skills
MATLAB/Simulink, machine learning, automatic differentiation (JAX/PyTorch)
Technologies
Python, JAX, PyTorch, MATLAB/Simulink
Responsibilities
Review literature on robust system identification and design of experiments; develop and implement robustness diagnostics; analyze excitation content of datasets; evaluate the approach using a practical benchmark use case; document and present research findings; extend the approach to handle partially observable states like temperature.