GAE在列车牵引系统早期故障检测中的应用  

Application of GAE in incipient fault detection of speed train traction system

作　　者：程超[1] 鞠云飞 刘明[1] 陈宏田 韩玲[3] 文韬 CHENG Chao;JU Yunfei;LIU Ming;CHEN Hongtian;HAN Ling;WEN Tao(College of Computer Science and Engineering,Changchun University of Technology,Changchun Jilin 130012,China;Department of Chemical and Material Engineering,University of Alberta,Alberta Edmonton AB T6G 2V4,Canada;College of Electromechanical Engineering,Changchun University of Technology,Changchun Jilin 130012,China;School of Electronic Information Engineering,Beijing Jiaotong University,Beijing 100044,China)

机构地区：[1]长春工业大学计算机科学与工程学院,吉林长春130012 [2]阿尔伯塔大学化学与材料工程系,加拿大阿尔伯塔埃德蒙顿AB T6G 2V4 [3]长春工业大学机电工程学院,吉林长春130012 [4]北京交通大学电子信息工程学院,北京100044

出　　处：《中国安全科学学报》2022年第6期73-78,共6页China Safety Science Journal

基　　金：国家自然科学基金资助(61903047,62120106011,52172323);中央高校基本科研业务费专项资金资助(2021RC271)。

摘　　要：为解决高速列车牵引系统的早期故障检测问题,首先,利用广义自编码器(GAE)处理系统采集的数据;然后,借助携带故障信息的残差生成器来检验统计量,有效增强早期故障检测能力;最后,在高速列车牵引控制仿真平台上,分别针对气隙偏心、转子断条、链路和轴承4种故障进行试验研究,验证其在线应用的有效性。结果表明:GAE的残差生成器具有较强的适用性和灵敏度,能够适应牵引系统的非线性特征,故障检测无误报,漏报概率低于6%。In order to address problems in incipient fault detection of traction system for high-speed trains,firstly,data collected from the system was processed by GAE.Then,statistics were tested on residual generator carrying fault information,which could effectively enhance fault detection ability.Finally,effectiveness and feasibility of the proposed method were validated on a traction system platform of high-speed trains,where four kinds of faults were studied,including air gap eccentricity,bar breaking,end link and bearing.The results show that the residual generator of GAE has strong applicability and sensitivity,and can adapt to the nonlinear characteristics of traction system.There is no false alarm phenomenon in fault detection,and the missing alarm ratio is less than 6%.

关 键 词：广义自编码器(GAE) 高速列车 牵引系统 早期故障检测 神经网络 

分 类 号：X924.3[环境科学与工程—安全科学]