Train Operation Control Based On Neural Network Adaptive Sliding Mode And COA Trajectory Optimization

As my country’s important infrastructure,the main support for national economic construction,and the main means of transportation for people’s daily life,high-speed railways play an important role in ensuring the efficient implementation of my country’s policies,promoting high-quality growth of local economies,and providing safe,comfortable,punctual and convenient transportation.Huge effect.Due to the substantial increase in the number of high-speed trains in China and the speed of operation,the high-speed,high-density,and high-energy-consumption operation of trains in the high-speed road network has become the new normal.The safe,stable,energy-saving and emission-reduction operation of high-speed trains is of great significance and practical value.This paper mainly studies the control and energy-saving optimization of high-speed train operation process,and studies from two aspects of realizing precise tracking control and optimizing tracking operation curve.The specific research contents are as follows:(1)Establish a kinematic model of a single-particle train,summarize the train operation strategy and conversion principles,analyze and model indicators such as parking accuracy,train punctuality,comfort,and traction energy consumption,and establish a model based on these indicators.The energy-saving optimization model of train speed curve provides the basis for train tracking control and tracking speed curve optimization.(2)Aiming at the uncertainty of train motion model and the problem of high-speed train tracking control with external disturbance,an adaptive Radial Basis Function(RBF)neural network sliding mode control method with disturbance observer is designed.Aiming at the uncertainty of the train model,an adaptive RBF neural network robust controller is designed for tracking control,and the neural network weight adaptive law is designed through the characteristics of the RBF neural network to estimate the unknown function of the train model.Aiming at the external disturbance of train operation,the exponential convergence disturbance observer is used for disturbance compensation,which improves the anti-disturbance ability of the train during operation.Lyapunov stability analysis ensures the stability of the control system.The simulation results verify that the designed control method not only solves the adaptive approximation of the unknown resistance part of the train model,but also introduces a disturbance observer to external the nonlinear disturbance is compensated,the controller has strong stability,and the high precision and fast tracking of the desired trajectory is realized.(3)Aiming at the energy consumption optimization problem during the operation of high-speed trains,a method for optimizing the tracking speed curve of high-speed trains based on the Coyote Optimization Algorithm(COA)is designed.The Coyote algorithm has excellent global optimization capabilities.In the single-train section operation scenario,the high-speed train operation control strategy is taken as the research object.The Coyote optimization algorithm is applied to solve the multi-objective optimization model of the train,and the train operation control strategy and the optimal tracking speed curve is combined with the designed controller for tracking control.The experimental results fully verify that the Coyote algorithm can effectively optimize the train tracking curve and achieve the purpose of energy-saving tracking operation of the train.