首页 | 本学科首页   官方微博 | 高级检索  
     

基于朴素贝叶斯分类器的公共自行车系统故障诊断方法
引用本文:时中朝,郝伟娜,董红召.基于朴素贝叶斯分类器的公共自行车系统故障诊断方法[J].中国机械工程,2019,30(8):983.
作者姓名:时中朝  郝伟娜  董红召
作者单位:浙江工业大学智能交通系统联合研究所,杭州,310006
基金项目:国家自然科学基金资助项目(61773347); 浙江省公益技术研究项目(LGF19F030001)
摘    要:针对公共自行车没有安装车载检测传感器、流动及停放区域较大、管理部门无法及时发现自行车故障等问题,提出了基于朴素贝叶斯分类器的自行车故障诊断方法。通过分析公共自行车系统(PBS)租用记录、维修记录和用户评价,选取15个状态分类特征作为自行车故障检测的特征向量;根据朴素贝叶斯分类器后验概率,获取每个状态分类特征对类的贡献率;以召回率作为评价指标来预测诊断故障自行车。采用杭州市PBS 2016年的相关数据对模型进行实践验证,通过预测模型输入特征值的优化,测试样本的召回率达85.79%,精度较为理想。

关 键 词:贝叶斯分类器  公共自行车系统  故障诊断  贡献率  

Public Bicycle System Fault Diagnosis Based on Naive Bayesian Classifier
SHI Zhongchao,HAO Weina,DONG Hongzhao.Public Bicycle System Fault Diagnosis Based on Naive Bayesian Classifier[J].China Mechanical Engineering,2019,30(8):983.
Authors:SHI Zhongchao  HAO Weina  DONG Hongzhao
Affiliation:ITS Joint Research Institute, Zhejiang University of Technology, Hangzhou, 310006
Abstract:In view of the facts that PBS was not equipped with on-board detection sensors, bicycle failure might not be found directly in time and make rider to suffer the safety risks. To solve such an issue, a bicycle fault diagnosis method was proposed based on naive Bayesian classifier. By analyzing the PBS historical data including rental records, maintenance records and user evaluation etc., 15 state classification features were extracted as feature vectors for bicycle fault detection. Based on the posterior probability of Naive Bayesian classifier, the contribution rate of each state classification feature to the class was obtained; the recall rate was used as an evaluation index to predict the diagnosis of failed bikes. Based on the running data of 2016 from Hangzhou PBS, the model was verified by experiments. Through the optimization of the input eigenvalue of the prediction model, the recall rate of the test samples reaches 85.79% with satisfactory accuracy.
Keywords:Bayesian classifier  public bicycle system(PBS)  fault diagnosis  contribution rate  
本文献已被 CNKI 等数据库收录!
点击此处可从《中国机械工程》浏览原始摘要信息
点击此处可从《中国机械工程》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号