Speed control of BLDCM based on compensated fuzzy neural network

Aiming at the multivariable, nonlinearity, strong coupling, time-variable characteristics of speed control system of brushless DC motor (BLDCM), the CFNNC algorithm is proposed to obtain high precision speed controlling. This algorithm combines compensative fuzzy logic and neural network, adjust the input and output of fuzzy membership functions, and optimize the fuzzy inference dynamically according to the logic compensation algorithm. The fault tolerance, stability and working speed of the network are improved greatly due to the introduction of fuzzy neuron. The simulation and experiment results of DSP-based control system prove that this method have rapid response and robustness, and its dynamic characteristic is much better than that of traditional PID controller.