关键词: 开关磁阻电机, 粒子群优化算法, 模糊 PI 控制, 柔性神经网络控制

Abstract: To solve the problems of switched reluctance motor, such as strong nonlinearity, large torque pulsation, speed regulation performance to be improved, a fuzzy PI control method based on particle swarm optimization ( PSO) and flexible neural network ( FNN) was adopted. The fuzzy control theory and PI control were combined and optimized by particle swarm optimization algorithm. Three kinds of simulation experiments were carried out: non-optimized fuzzy PI control for the outer speed loop, traditional PID control and particle swarm optimization fuzzy PI control. All the three simulation experiments used flexible neural network ( FNN) as the inner torque loop. Compared with the simulation results, it was found that the particle swarm optimization fuzzy PI control had the smallest torque ripple when the rated speed was 150 r / min, 800 r / min and 1 500 r / min, which improved the robustness of the system. The experimental results show that
the fuzzy PI control with particle swarm optimization as the speed outer loop and the FNN acting on the torque inner loop have good performance, which is suitable for the torque ripple suppression of switched reluctance motor.

Key words: switched reluctance motor( SRM), particle swarm optimization( PSO) algorithm, fuzzy PI control, flexible neural network( FNN) control