Neural Network Compensator-Based Control for Enhancing IPMSM Dynamics and Copper Loss Efficiency for Air Compressor

• Published in: IEEE access Vol. 12; p. 1
• Main Authors: Guo, Jiawei, Sun, Linfeng, Kawaguchi, Takahiro, Hashimoto, Seiji
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">dq axis synthesis current control; Air compressors; Air conditioning; Algorithms; Artificial neural networks; back propagation (BP); Back propagation networks; Backpropagation; Compensators; Computer simulation; Control methods; Control systems; Copper; Copper loss; dq axis synthesis current control; Dynamic control; Efficiency; Hardware; Heuristic algorithms; Interior permanent-magnet synchronous motor (IPMSM); Motors; neural network (NN); Neural networks; Optimization; Permanent magnet motors; Permanent magnets; Synchronous motors; Training; Transient response; Vectors; Velocity
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2024.3396170

Although significant efforts have been made to enhance industrial air conditioning systems, there are still efficiency and transient response issues in vehicle air conditioning systems using IPMSM compressors. This paper focuses on the neural network compensator-based control in an interior permanent-magnet synchronous motor (IPMSM) to address the occurrence of reduced power copper loss efficiency and degraded velocity response in the motor system when confronted with periodic dynamic disturbances of step signals. This paper encompasses two main objectives: the first objective is to introduce a neural network (NN) compensator to improve the power copper loss efficiency. The NN compensator is developed using the velocity loop and current loop control model equation of an IPMSM, and trained to implement optimal compensation control based on the back propagation algorithm. The second objective is to optimize the dynamic performance of velocity response compared to the traditional maximum torque per ampere (MTPA) current control method under step disturbance and dynamic control conditions by building an experimental system for validation, incorporating both hardware and simulation. Another significant advantage is the low computational load introduced by the neural network compensator, rendering it well-suited for implementation within low-order DSP systems. The results indicate that the neural network compensator surpasses conventional MTPA control method in both simulation and hardware-based implementations concerning power copper loss and velocity response in an IPMSM control system.