Research On Adaptive Sliding Mode Control Of Train Speed Based On Radial Basis Function Neural Network

With the continuous expansion of China’s high-speed railway network and the increasing speed of high-speed train operations,fast and intensive tracking of multiple trains has become the new normal for high-speed railway operation management and high-speed train operation control.Although the safety of high-speed trains is gradually improving,with the large-scale construction of high-speed railways,their operating environment has become more challenging and complex,and high-speed trains are more susceptible to external interference,making it difficult for existing train operation control methods to ensure the safe and stable operation of high-speed trains in the process of intelligent tracking.Therefore,how to design an anti-disturbance operation control strategy adapted to the characteristics of high-speed trains has become a hot research direction in the field of intelligent tracking operation control of high-speed trains at present.Through research in train dynamics and control systems,effective application of neural networks and intelligent algorithms can help us better understand high-speed train operation characteristics and operation control problems,and design more robust and anti-disturbance operation control strategies.(1)An efficient and reliable multi-mass point dynamics model is established to describe the dynamics of high-speed trains based on the CRH3 type rolling stock train as the research basis.(2)A new control strategy to improve the stability and anti-disturbance of trains,the radial basis neural network sliding mode adaptive control,is proposed.The radial basis neural network is invoked,the anti-disturbance adaptive law is proposed and demonstrated,and the control strategy is optimised to ensure the safe,efficient,energy-saving and comfortable tracking of high-speed trains during operation.Simulation examples demonstrate that the radial basis neural network sliding mode adaptive control method has good stability and anti-disturbance under the conditions of multiple operating conditions and unknown external disturbances.(3)The train operation control problem under control input constraint is presented,the radial-based neural network sliding mode adaptive control structure is improved,the adaptive should assist system is introduced,the adaptive law is proposed and demonstrated,and the stability and anti-disturbance under input constraint is verified by experimental comparison simulation.(4)A train operation control simulation system based on Matlab App Designer is designed,in which a simulation system with functions such as train part parameter adjustment,multiple control scheme selection and simulation curve configuration is realized,and the train operation status can be tracked in real time at the same time.