Research On Control Strategy Of Hydraulic Thrust System Of Shield Based On Neural Network

With the advantages of high speed,high efficiency,high quality,environmental protection,safety and reliability,the shield tunneling technology has been gradually popularized and applied.In recent years,the success of Homemade Metro Shield Machine assembly line and the smooth acceptance of the overseas tunnel project shows that China has made a historic breakthrough in the field of independent research and development.However,the key technologies in the field of adaptive design,system integration and other fields are still mastered by developed countries,such as Europe and America,Japan and so on.The propulsion system is a key part of the shield adaptive design,the straight line,the attitude adjustment and the change of the direction of the shield depend on the coordination of the cylinder in the propulsion system,The quality of the propulsion system control is very important to the performance and quality of the shield tunneling machine.Therefore,the research on the control strategy of shield propulsion system is of great significance to promote the development of China's shield industry.Treating the propulsion system,the response characteristics of propulsion system and the performance of synchronous control of multiple propulsion cylinders under different load conditions are studied.Firstly,the mechanical structure,hydraulic system and the working principle of Shield propulsion system and the experiment platform are introduced;Then,the physical model of the hydraulic system was established by AMESim software,conventional PID control is used to analyze the characteristics of the propulsion velocity and pressure response,and the multi cylinder synchronization,the simulation results show that the thrust pressure has great influence on the speed,and the speed control effect is not satisfactory under the conventional PID controlideal.For that reason,to solve the mutualin terference problem of the pressure and the speed of the shield propulsion system under the condition of variable load and flow,the control strategy of BP neural network PID is proposed in this paper.Combined with the Simulink software,the simulation results show that the stability of the BP neural network PID is good,and the overshoot of the pressure and speed of the cylinder is greatly reduced when the flow and load change;In order to improve the performance of multi cylinder synchronous control of shield under unbalanced load,The single neuron PID control strategy is proposed,and the response characteristics of the propulsion system under different control strategies are compared and analyzed.It is concluded that the single neuron PID can greatly improve the synchronization of the propulsion cylinder when the load is biased.At last,two kinds of control strategies are tested on the shield experiment platform,and the experimental data are basically consistent with the simulation results,it is proved that the neural network combined with classical PID control can suppress the uncertainty and nonlinearity of propulsion system.The theoretical research and experimental analysis results of this paper provide a theoretical reference for the design and optimization of shield control system.