Research On High Precision AC Position Servo System Based On Self-built Neural Network

In modern warfare,the high precision and stability of firepower strike are increasingly emphasized,to achieve the best strike effect with the least cost.For ship-based rocket launcher system,there are many factors that affect the accuracy of shooting,such as weather conditions,ship swing,the accuracy of the gun,among which the precision of ship-mounted rocket launcher is one of the most important factors.In the context of the development of a ship-based rocket launcher,the 'modeling and control strategy of AC servo system are studied,to improve the control performance of AC servo system,and then improve the accuracy of the firing accuracy of ship-borne rocket launcher,and finally improve its shooting accuracy.This paper mainly studies the following aspects:(1)This paper introduces the basic structure of the AC servo system of a shipborne rocket launcher,analyzes PMSM used in the AC servo system,and deduces the PMSM model.Based on the PMSM model,the mathematic model of the AC servo system of the shipborne rocket launcher is deduced.According to the mathematical model,the AC servo system is a complex nonlinear system.(2)The identification of the system was studied.Firstly,RBF neural network is used to identify the system.Aiming at the deficiency of the traditional RBF neural network identification ability,the fixed network structure and the unchangeable number of nodes.in this paper,an improved self-constructed recursive neural network(SRNN)algorithm for system identification is proposed,which can increase and delete the number of neurons in the hidden layer on-line.The simulation results show that the system identification based on SRNN is more effective.(3)The control strategy of the system is studied.First,the internal model control is applied to the system control research.Aiming at the insufficiency of internal model control,an adaptive internal model control based on SRNN is designed for AC position servo system control.The system simulation model is built in MATLAB to verify the effectiveness of design scheme.(4)A hardware-in-the-loop simulation platform for the AC servo system of the shipborne rocket launcher is built.The hardware circuit and control interface of the host computer are designed to verify the control performance of the adaptive internal model control strategy based on SRNN.According to the test results,the control strategy can meet the requirements of high precision control of shipborne rocket launcher.