基于SVM模型的公交故障预测——以北京市为例  

Bus Fault Prediction Based on SVM Model——A Case Study of Beijing

作　　者：邵强 倪丹 陈兴付 易乐 米磊 陈艳艳 SHAO Qiang;NI Dan;CHEN Xingfu;YI Le;MI Lei;CHEN Yanyan(Beijing Public Transportation Group,Beijing 100161,China;Beijing University of Technology College of Metropolitan Transportation,Beijing 100124,China)

机构地区：[1]北京公共交通控股(集团)有限公司,北京100161 [2]北京工业大学城市交通学院,北京100124

出　　处：《交通工程》2025年第3期16-20,共5页Journal of Transportation Engineering

摘　　要：随着公交车辆运营强度的不断增加,近年来公交车辆发生故障的频率也随之增加。如何提前对公交车辆故障进行预测对于优化公交维修策略以及提升车辆保养维修质量十分重要。因此,利用北京公交车辆的维修数据,本文基于支持向量机(Support Vector Machine,SVM)模型,将影响车辆的主要特征参数作为输入指标,实现对公交车辆故障的预测。通过与北京公交集团的真实维修数据对比,发现本文建立的公交车辆故障预测模型预测准确率达到83.98%,具有较好的准确率。With the intensifying operations of public transportation,there has been a noticeable increase in the occurrence of vehicle failures in recent years.The ability to predict bus vehicle failures in advance is of paramount importance for optimizing maintenance strategies and enhancing the quality of vehicle maintenance and repair.Consequently,this study utilizes maintenance data from public transport vehicles in Beijing to develop a predictive model for identifying public transport vehicle failures using the Support Vector Machine(SVM)algorithm.The model considers the key characteristic parameters that impact vehicle performance as input indicators.Through comparison with real maintenance data from the Beijing Public Transportation Group,it is determined that the proposed prediction model achieves an accuracy rate of 83.98%,which demonstrates a commendable level of precision.

关 键 词：公共交通 支持向量机 故障预测 

分 类 号：U495[交通运输工程—交通运输规划与管理]