基于粒子群算法的隐式广义预测在ATO中的应用  

Application of Implicit Generalized Prediction Based on Particle Swarm Optimization algorithm in ATO

作　　者：马宝峰[1] 路小娟[1] 

机构地区：[1]兰州交通大学自动化与电气工程学院,兰州730070

出　　处：《铁道标准设计》2015年第6期143-147,共5页Railway Standard Design

基　　金：甘肃省自然科学基金(1208RJZA180)

摘　　要：由于列车运行速度的不断提高,对列车自动驾驶(Automatic Train Operation,ATO)系统提出更高的要求。针对隐式广义预测(Implicit Generalized Predictive Control,IGPC)控制器在ATO中难以获得最优预测控制输入的问题,运用一种基于粒子群优化(Particle Swarm Optimization,PSO)的IGPC算法对ATO系统进行控制。为更进一步提高PSO算法的寻优能力,对基本PSO算法进行改进,从而有效提高系统的寻优精度和速度。并对有约束情况下的CRH2型车进行仿真验证,仿真结果显示PSO-IGPC比单纯IGPC对ATO的控制效果更优。The continuous increase of train speed sets higher requirements for the Automatic Train Operation （ ATO） system. As it is difficult to obtain the optimal predictive control input for the implicit generalized predictive controller in the automatic train operation, this paper applies an IGPC algorithm based on Particle Swarm Optimization （ PSO） to control the ATO system. In order to further optimize PSO, the basic PSO algorithm is improved, thus effectively improving the accuracy and speed of searching optimization. The CHR2 trains are simulated and verified under constrained conditions. The simulation results show that PSO-IGPC has a better effect than simple IGPC control for ATO.

关 键 词：列车自动驾驶 隐式广义预测控制算法 粒子群优化算法 仿真 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]