Robust control for permanent magnet in-wheel motor in electric vehicles using adaptive fuzzy neural network with inverse system decoupling

Abstract

To eliminate the chattering phenomenon and effectively enhance the robustness and dynamic response of the speed control system of a permanent magnet in-wheel motor (PMIWM), a novel decoupling approach is proposed. The speed control system of the PMIWM is analyzed and modeled. By introducing the inverse model into the original PMIWM system, a new decoupling pseudo-linear system is established. A control method based on adaptive fuzzy neural network (AFNN) is investigated to obtain an accurate speed trajectory. The inverse system control approach is introduced into the AFNN-based control system. The PMIWM speed is decoupled completely by the proposed adaptive fuzzy neural network inverse (AFNNI) method. Experiments are carried out on a hardware-in-the-loop (HIL) test bench. Compared with traditional PID control scheme, the proposed AFNNI control strategy can realize a better speed control performance and ensure the robust stability of the PMIWM, even though the motor may suffer from both sudden change in velocity and severe variation under different drive cycles.