Global Sliding Mode Control for Brushless DC Motors by Neural Networks

A global sliding mode control scheme by neural networks is proposed for high performance drive systems of brushless DC motors with uncertain external disturbances and unknown loads. A global sliding mode manifold is designed in this approach, which guarantees that the system states can be on the sliding mode manifold at initial time and the system robustness is increased. A radial basis function neural network (RBFNN) is applied to learn the maximum of unknown loads and external disturbances. Based on the neural networks, the switching control parameters of sliding mode control can be adaptively adjusted with uncertain external disturbances and unknown loads. Therefore, the chattering of the sliding mode controller is eliminated without sacrificing its robustness. Simulation results proved the validity of the control scheme.