基于车-车通信的RBFNN量化滑模控制的ATO算法  

ATO Algorithm of RBFNN Quantization Sliding Mode Control Based on Train-to-Train Communication

作　　者：杨军霞[1] 张友鹏[1] YANG Jun-xia;ZHANG You-peng(School of Automation and Electrical Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China)

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：《兰州交通大学学报》2022年第1期68-73,共6页Journal of Lanzhou Jiaotong University

基　　金：甘肃省教育厅优秀研究生“创新之星”项目(2021CXZX-552)。

摘　　要：针对车-车通信过程中因信道容量约束产生的列车控制精度降低的问题,提出基于RBFNN(radical basis function neural network,RBFNN)的自适应量化滑模ATO(automatic train operation,ATO)控制方法.基于自适应量化滑模控制技术,利用RBFNN对列车模型受到的附加阻力及未知扰动进行自适应逼近补偿,并引入基本阻力参数自适应机制以实现列车高精度控制,保证列车运行安全.仿真结果表明:该算法能够保证列车高精度跟踪理想的运行曲线,实现列车在站间的平稳运行和精确停车.Aiming at the problem of the train control accuracy reduction caused by the channel capacity constraints in the train-to-train communication process,an self-adaptive quantitation sliding mode ATO(automatic train operation)control method based on RBFNN(radial basis function neural network)is proposed.Based on the adaptive quantization sliding mode control technology,RBFNN is used to adaptively approximate and compensate the additional resistance and unknown disturbance to the train model,and the adaptive mechanism of basic resistance parameters is introduced to realize the high-precision control and ensure the safety of the train operation.The simulation results show that the algorithm can ensure the train to track the desired operating curve with high precision,and realize the smooth operation and precise parking of the train between stations.

关 键 词：ATO 车-车通信 RBFNN 自适应控制 量化控制 

分 类 号：U284.4[交通运输工程—交通信息工程及控制]