Neural Network Based Fault Diagnosis and Fault Tolerant Control for BLDC Motor

A fault diagnostics and fault tolerant control system for controller of brushless direct current motor is designed. The neural network state observer is trained by real nonlinear control system. From the residual difference between outputs of actual system and neural network observer, the fault of control system is detected and determined. The simulation results and study on fault diagnostics are implemented for system controller, current and speed sensor faults. Fault tolerant control is realized by using compensation controller and can guarantee the stability and performance. The results of simulation show the effectiveness of the proposed method with scaling location of the fault and the time of occurrence, and eliminating the noise and offering high robustness.