Fault-Tolerant Control of a Six-Phase Motor Drive System Using a Takagi–Sugeno–Kang Type Fuzzy Neural Network With Asymmetric Membership Function

Abstract

A Takagi-Sugeno-Kang type fuzzy neural network with asymmetric membership function (TSKFNN-AMF) is proposed in this study for the fault-tolerant control of a six-phase permanent-magnet synchronous motor (PMSM) drive system. First, the dynamics of the six-phase PMSM drive system is described in detail. Then, the fault detection and operating decision method is briefly introduced. Moreover, to achieve the required control performance and to maintain the stability of a six-phase PMSM drive system under faulty condition, the TSKFNN-AMF control, which combines the advantages of a Takagi-Sugeno-Kang type fuzzy logic system and an asymmetric membership function, is developed. The network structure, online learning algorithm using a delta adaptation law, and convergence analysis of the TSKFNN-AMF are described in detail. Furthermore, to enhance the control performance of the proposed intelligent fault-tolerant control, a 32-bit floating-point digital signal processor TMS320F28335 is adopted for the implementation of the proposed fault-tolerant control system. Finally, some experimental results are illustrated to show the validity of the proposed TSKFNN-AMF fault-tolerant control for the six-phase PMSM drive system.