High-speed train speed control method and system

Abstract

The invention discloses a high-speed train speed control method and system. The method comprises the following steps that S1, a unit-shift multi-mass-point train model being built for a high-speed train according to the train dynamics principle; S2, constructing a high-speed train speed tracking controller based on a CACMAC neural network and a PID controller; S3, unit traction force and braking force of the train being calculated according to a difference value between the expected speed and the actual speed of the train through the high-speed train speed tracking controller, and the acting force needing to be adjusted of the train being obtained based on compound control of a CACMAC controller and a PID controller with the unit-movement multi-mass-point model as a controlled object; and S4, obtaining a new actual speed of the train according to the adjusted acting force.

Description

technical field [0001] The present invention relates to the technical field of speed control of high-speed trains, in particular to a CACMAC (Credit Assigned Cerebellar Model Articulation Controller, Credit Assigned Cerebellar Model Articulation Controller) neural network and PID (Proportional-Integral-Derivative, proportional-integral-derivative) control A high-speed train speed control method and system based on a device combination. Background technique [0002] At present, under the impetus of artificial intelligence, the driving mode of high-speed trains has begun to develop in the direction of automatic driving. Position tracking control is the key control unit in ATO, the design and research of its control algorithm must become a development demand, and it is also the key to realize the intelligentization and automation of railway traffic. [0003] First of all, in the research of high-speed train dynamics model, some people combine Takagi-Sugen (T-S) model with fuzz...

AI Technical Summary

Problems solved by technology

[0008] 1. The establishment of the T-S model depends on the establishment of certain rules, which has the disadvantage of uncertainty;

[0009] 2. The single-particle train model ignores the interaction between train cars. Although it is the most widely used, with the continuous development of control theory, its calculation is too simple and convenient, and it has the disadvantage that it can no longer meet the requirements for train safety control;

[0010] 3. Although the multi-particle model considers the interaction force between carriages, it considers too many nonlinear systems, and has the disadvantage that the calculation process is

Images