Data-Driven Permanent Magnet Temperature Estimation in Synchronous Motors With Supervised Machine Learning: A Benchmark

• Published in: IEEE transactions on energy conversion Vol. 36; no. 3; pp. 2059 - 2067
• Main Authors: Kirchgassner, Wilhelm, Wallscheid, Oliver, Bocker, Joachim
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Biological system modeling; Computational modeling; Data collection; Data models; deep learning; Estimation; functional safety; Machine learning; Model accuracy; Neural networks; Overheating; Permanent magnet motors; permanent magnet synchronous motor; Permanent magnets; Regression models; Signal injection; Support vector machines; Synchronous motors; temperature estimation; Temperature measurement; Temperature profiles; Temperature sensors; Thermal analysis; thermal management
• ISSN: 0885-8969; 1558-0059
• DOI: 10.1109/TEC.2021.3052546

Monitoring the magnet temperature in permanent magnet synchronous motors (PMSMs) for automotive applications is a challenging task for several decades now, as signal injection or sensor-based methods still prove unfeasible in a commercial context. Overheating results in severe motor deterioration and is thus of high concern for the machine's control strategy and its design. Lack of precise temperature estimations leads to lesser device utilization and higher material cost. In this work, several machine learning (ML) models are empirically evaluated on their estimation accuracy for the task of predicting latent high-dynamic magnet temperature profiles, specifically, ordinary least squares, support vector regression, <inline-formula><tex-math notation="LaTeX">k</tex-math></inline-formula>-nearest neighbors, randomized trees, and neural networks. Having test bench data available, it is shown that ML approaches relying merely on collected data meet the estimation performance of classical thermal models built on thermodynamic theory. Through benchmarking, this work reveals the potential of simpler ML models in terms of regression accuracy, model size, and their data demand in comparison to parameter-heavy deep neural networks, which were investigated in the literature before. Especially linear regression and simple feed-forward neural networks with optimized hyperparameters mark strong predictive quality at low to moderate model sizes.