Neural networks based speed-torque estimators for induction motors and performance metrics

Sagar Verma (1, 2) , Nicolas Henwood (1) , Marc Castella (3, 4, 5) , Al Kassem Jebai (1) , Jean-Christophe Pesquet (2)

1 Schneider Toshiba Inverter Europe [Pacy-sur-Eure]
2 OPIS - OPtimisation Imagerie et Santé
3 IP Paris - Institut Polytechnique de Paris
4 TSP - CITI - Communications, Images et Traitement de l'Information
5 TIPIC-SAMOVAR - Traitement de l'Information Pour Images et Communications

This paper focuses on the quantitative analysis of deep neural networks used in data-driven modeling of induction motor dynamics. With the availability of a large amount of data generated by industrial sensor networks, it is now possible to train deep neural networks. Recently researchers have started exploring the usage of such networks for physics modeling, online control, monitoring, and fault prediction in induction motor operations. We consider the problem of estimating speed and torque from currents and voltages of an induction motor. Neural networks provide quite good performance for this task when analysed from a machine learning perspective using standard metrics. We show, however, that there are some caveats in using machine learning metrics to analyze a neural network model when applied to induction motor problems. Given the mission-critical nature of induction motor operations, the performance of neural networks has to be validated from an electrical engineering point of view. To this end, we evaluate several traditional neural network architectures and recent state of the art architectures on dynamic and quasi-static benchmarks using electrical engineering metrics.

Mots clés: Induction motor; Neural networks; Deep learning; Time series; Training

Domaines: Energie électrique; Electromagnétisme; Systèmes dynamiques [math.DS]; Intelligence artificielle [cs.AI]; Réseau de neurones [cs.NE]

Sagar Verma, Nicolas Henwood, Marc Castella, Al Kassem Jebai, Jean-Christophe Pesquet. Neural networks based speed-torque estimators for induction motors and performance metrics. IECON 2020 - 46th Annual Conference of the IEEE Industrial Electronics Society, Oct 2020, Singapore, Singapore. pp.495-500, ⟨10.1109/IECON43393.2020.9255236⟩. ⟨hal-02907937⟩