基于時序數(shù)據(jù)的列車牽引系統(tǒng)故障預(yù)測方法

摘" 要： 牽引系統(tǒng)作為列車動能轉(zhuǎn)換的關(guān)鍵模塊，如果發(fā)生故障會給整車正常運行帶來重大安全隱患，所以對其進(jìn)行故障預(yù)測具有重要意義。然而，傳統(tǒng)預(yù)測方法存在高度依賴人工經(jīng)驗判斷、不能包含大量故障特征、預(yù)測精度不足等問題。為此，文中提出一種基于時序數(shù)據(jù)的故障預(yù)測方法。利用XGBoost算法對列車牽引變流器系統(tǒng)的故障特征進(jìn)行計算和篩選，確定與變流器故障相關(guān)性較強(qiáng)的關(guān)鍵特征；采用貝葉斯優(yōu)化的LSTM模型自適應(yīng)地學(xué)習(xí)多源變量數(shù)據(jù)特征，利用時間窗對特征變量數(shù)據(jù)進(jìn)行截取，實現(xiàn)對不同類型故障的預(yù)測。實驗結(jié)果表明，所提方法在預(yù)測變流器場景下的6種故障時準(zhǔn)確率可達(dá)到91%以上。

關(guān)鍵詞： 牽引系統(tǒng)； 故障預(yù)測； 時序數(shù)據(jù)； XGBoost算法； LSTM； 時間窗

中圖分類號： TN911.23?34； TP183" " " " " " " "文獻(xiàn)標(biāo)識碼： A" " " " " " " " " " " "文章編號： 1004?373X（2025）04?0057?06

Method of train traction system fault prediction based on timeseries data

HE Xinlai， SUN Geng， WANG Minjie， ZHAI Yinan， CHEN Yanlin， YIN Xian， FENG Yanhong

（College of Information Engineering， Dalian Ocean University， Dalian 116023， China）

Abstract： As a key module for the conversion of train kinetic energy， traction system will bring great safety risks to the normal operation of the vehicle if it fails， so it is of great significance to predict its failure. However， traditional prediction methods have problems such as high dependence on manual experience judgment， inability to include a large number of fault features， and insufficient prediction accuracy. On this basis， a method of fault prediction based on timeseries data is proposed. The XGBoost algorithm is used to calculate and screen the fault features of the train traction converter system to determine the key features that are strongly correlated with the converter faults. The LSTM model optimized by Bayes is used to adaptively learn the multi?source variable data features， and the time window is used to intercept the feature variable data to realize the prediction of different types of faults. The experimental results show that The accuracy of the proposed method can reach more than 91% when predicting 6 kinds of faults in converter scenario.

Keywords： traction system; fault prediction; timeseries data; XGBoost algorithm; LSTM; time window

0" 引" 言

牽引系統(tǒng)作為列車的核心組成部分，其穩(wěn)定運行對于整個鐵路運輸?shù)陌踩陵P(guān)重要[1]。牽引系統(tǒng)故障會對列車的安全運營產(chǎn)生重要影響，甚至導(dǎo)致列車停止運行，帶來嚴(yán)重?fù)p失，所以對故障進(jìn)行預(yù)測具有重要意義。近年來，隨著故障預(yù)測相關(guān)理論的研究逐漸深入，故障預(yù)測的方法根據(jù)對象的不同可大致分為以下四種：基于物理模型的預(yù)測方法、基于數(shù)學(xué)模型的預(yù)測方法、基于機(jī)器學(xué)習(xí)的預(yù)測方法和基于長短期記憶網(wǎng)絡(luò)的預(yù)測方法。這些方法各有其特點和適用場景，需要根據(jù)實際情況進(jìn)行選擇和優(yōu)化。文獻(xiàn)[2]提出了一種城軌列車牽引系統(tǒng)故障預(yù)測和健康管理系統(tǒng)設(shè)計方案。……