Thesis Work: Machine Learning-based Identification of Electric Motors Parameters for Control

ABB Inc.
United States, North Carolina, Cary
305 Gregson Drive (Show on map)
Oct 18, 2025
At ABB, we help industries outrun - leaner and cleaner. Here, progress is an expectation - for you, your team, and the world. As a global market leader, we'll give you what you need to make it happen. It won't always be easy, growing takes grit. But at ABB, you'll never run alone. Run what runs the world. This Position reports to: R&D Department Lead You will be part of Powertrain & Digitalization team at ABB Corporate Research in Vasteras, Sweden. At Corporate Research we lead the innovation within ABB and our task is to ensure ABB's technology competitiveness now and in the future. We work in close collaboration with other research centers, our business areas: Motion, Process Automation, Robotics & Discrete Automation and Electrification, as well academic and industrial partners. In our creative and highly skilled team we develop, design, build and test new concepts and prototypes of physical and digital powertrains consisting of electric energy source, electrical motor, electric drive, and a selected application. Details Period: January - July 2026 30 ECTS per student Number of students: 1 Location: On site ABB Corporate Research in Vasteras, Sweden or Hybrid Your responsibilities Conduct a stateoftheart review on machinelearning methods for electric motor parameter identification Develop, implement, and evaluate MLbased parameter identification models in MATLAB/Simulink for a selected motor type Design simulation studies and, where applicable, structured experiments to generate identification data under representative operating conditions Compare ML approaches with classical/systemidentification baselines and quantify accuracy, robustness, and computational footprint Analyze the effect of identified parameters on torquecontrol performance, including steadystate accuracy and dynamic response Explore generalization strategies across operating points and model mismatch, including noise robustness and domain shift Prepare clean, versioncontrolled code, reproducible experiments, and clear documentation to enable handover Summarize findings in a thesis report and presentation; contribution to a scientific publication is encouraged when results warrant it Your background Currently pursuing a Master's degree in Electrical Engineering or a closely related field Good working knowledge of MATLAB and Simulink Interest in control theory and power electronics; familiarity with electric machines is beneficial Familiarity with datadriven methods and fundamentals of machine learning or system identification is an advantage Theoretical grounding in signals and systems, statistics, and optimization will be beneficial for model design and evaluation Strong interest in research and clear technical communication in English More about us ABBis a global technology leader in electrification and automation. We see our purpose as being to enable a more sustainable and resource-efficient future. By connecting our engineering and digitalization expertise, we help industries run at high performance, while becoming more efficient, productive and sustainable so they outperform. We call this: 'Engineered to Outrun.' You are welcome to apply the latest by November 21. Please note that selection will be done on an ongoing basis and the position may be filled before last day of application. We look forward to receiving your application (preferably in English). Join us. Be part of the team where progress happens, industries transform, and your work shapes the world. Run What Runs the World. A Future Opportunity Please note that this position is part of our talent pipeline and not an active job opening at this time. By applying, you express your interest in future career opportunities with ABB. We value people from different backgrounds. Could this be your story? Apply today or visit www.abb.com to learn more about us and see the impact of our work across the globe.