Research On High-speed Train Operation Process Control Method Based On RBFNN

With the rapid development of society,high-speed trains are becoming more and more popular as a fast and efficient means of transportation.They have become an indispensable part of the modern transportation system.However,because high-speed trains run fast,the operating environment is complex and changeable,the working conditions change frequently,and the system is susceptible to various unknown internal and external interferences,presenting the characteristics of rapid time-varying and strong nonlinearity.Therefore,the design makes the high-speed trains.The automatic train driving(ATO)system that can not only operate safely and reliably but also track the target speed and displacement with high precision still have great practical significance.To design a safe and efficient ATO system,it is necessary to explore the two directions of the high-speed train modeling method and control strategy.The specific research content of this paper is as follows:1.Firstly,the action characteristics of train coupler force and the influence of complex line conditions on train operation are described,the different forces before and after the whole train are analyzed,and the longitudinal dynamics model of the train is established according to the characteristics of the power dispersion of the high-speed train.Because different types of high-speed trains have different car marshaling methods,this paper uses CRH380 B high-speed trains as the research object and uses each car as a mass point to analyze the force,and analyze the traction/braking force of the train and the impact during operation.The basic resistance,the resistance of complex lines,and the force of the coupler were described,A multi-particle longitudinal dynamic model which can describe the running characteristics of high-speed train more accurately and comprehensively is obtained.2.According to the established high-speed train longitudinal dynamics model,considering the passenger flow in the train compartment,a high-speed train minimum parameter adaptive RBFNN direct controller is designed.An ideal feedback control law is designed for the established train model without external interference.RBFNN is introduced to fit the ideal control output.Then,taking the influence of interference items into account,the adaptive law is designed to replace the neural network weights.Adjusted and proved the stability of Lyapunov.The simulation experiment verifies the effectiveness of the control method.3.Aiming at the established high-speed train longitudinal dynamics model,considering the partial failure of the train’s actuators,a high-speed train backstepping sliding mode faulttolerant controller based on RBFNN is designed.RBFNN is used to approximate the nonlinear function part of system,and adaptive compensation method is used to deal with actuator faults,and the combined backstepping sliding mode method is used to achieve the solution of interference suppression and operation tracking control problems,and a design based on RBFNN is designed The backstepping sliding mode fault-tolerant control algorithm is used to track the speed and displacement of high-speed trains,and can handle partial failures of actuators during train operation.Finally,simulation experiments are used to verify that the designed control method can improve the control accuracy of the control system,and can redistribute the control force of each power car when the train actuator fails partially,so as to ensure the safe operation of the train and the speed and displacement tracking effect,and has a certain degree The anti-interference ability.