The Application Of Neural Network Intelligent Control In DC Driver System

Neural network control is an important mode of intelligent control,and it is widely used in branches of control science,,First,the architecture and the learning rule (error back propagation algorithm) of multiplayered neural network which is widely used in control system are presentedo Especially,the paper refers to the architecture ofdiagonal recurrent neural network and its learning algorithm-----recurrentprediction error algorithm because of its faster convergence with low computing costoNext,before introducing the neural network control to the double close loop DC driver system,the controllers of current and velocity loop are designed using engineering design approach after analysis of the system,,Simulation models of the system are created.Then,as the substitute of the traditional PI controller,neuron adaptive PSD controller is used to alternate the velocity loop of DC driver system,,Simulation results show that the super-shoot in new system is small and the performance in the way of anti-disturbance and anti-time-varying parameters are higher than the traditional PI controller and robustness of the DC driver system improved greatly,,In addition,through analysis of the character of the neuron adaptive PSD controller ,the paper presents a neural network self-tuning control method for DC driver system in which the diagonal recurrent neural network is used to identify the plant to calculate the plant's sensitivity for PSD controllers Simulation results indicate that excellent static dynamic target was got with this control method and the performance of the system is improved greatly,...