Digital signal processor-based probabilistic fuzzy neural network control of in-wheel motor drive for light electric vehicle

A digital signal processor (DSP)-based probabilistic fuzzy neural network (PFNN) control is proposed in this study to control an in-wheel motor drive using a six-phase permanent magnet synchronous motor (PMSM) for light electric vehicle (LEV). First, the dynamics of LEV and in-wheel motor drive system with lumped uncertainty are described in detail. Then, a feedback linearisation control is designed to control the in-wheel motor drive system. Moreover, a non-linear disturbance observer (NDO) is applied to estimate the lumped uncertainty for the designed feedback linearisation control. However, the system response is degraded by the existed observer error. In order to achieve the required control performance of LEV, the PFNN control is developed for the control of the in-wheel motor drive system. The network structure and its on-line learning algorithm using delta adaptation law of the PFNN are derived. Moreover, a 32-bit fixed-point DSP, TMS320F2812, is adopted for the implementation of the proposed intelligent controlled drive system. Finally, some experimental results are illustrated to show the validity of the proposed PFNN control for in-wheel motor drive system.