This study presents a hybrid data-mining framework based on feature selection algorithms and clustering methods to perform the pattern discovery of high-speed railway train rescheduling strategies(RSs).The proposed mo...This study presents a hybrid data-mining framework based on feature selection algorithms and clustering methods to perform the pattern discovery of high-speed railway train rescheduling strategies(RSs).The proposed model is composed of two states.In the first state,decision tree,random forest,gradient boosting decision tree(GBDT)and extreme gradient boosting(XGBoost)models are used to investigate the importance of features.The features that have a high influence on RSs are first selected.In the second state,a K-means clustering method is used to uncover the interdependences between RSs and the influencing features,based on the results in the first state.The proposed method can determine the quantitative relationships between RSs and influencing factors.The results clearly show the influences of the factors on RSs,the possibilities of different train operation RSs under different situations,as well as some key time periods and key trains that the controllers should pay more attention to.The research in this paper can help train traffic controllers better understand the train operation patterns and provides direction for optimizing rail traffic RSs.展开更多
变速箱是旋转机械传动系统的重要组成部分,在工程实践中对其进行快速有效的故障诊断和故障分类具有重要意义。以变速工况下齿轮的振动信号为分析对象,基于短时间傅里叶变换(Short Time Fourier Transform,STFT)时频表示方法构建一种新...变速箱是旋转机械传动系统的重要组成部分,在工程实践中对其进行快速有效的故障诊断和故障分类具有重要意义。以变速工况下齿轮的振动信号为分析对象,基于短时间傅里叶变换(Short Time Fourier Transform,STFT)时频表示方法构建一种新的故障特征,引入支持向量机(Support Vector Machine,SVM)进行故障分类。结果表明,该故障特征可有效表征齿轮故障。展开更多
基金This work was supported by the National Natural Science Foundation of China(Grant No.71871188)The authors also acknowledge the Open Fund of Hubei Key Laboratory of Power System Design and Test for Electrical Vehicle and the support of the State Key Laboratory of Rail Traffic Control(Grant No.RCS2019K007).Finally,the authors are grateful for the useful contributions made by their project partners.
文摘This study presents a hybrid data-mining framework based on feature selection algorithms and clustering methods to perform the pattern discovery of high-speed railway train rescheduling strategies(RSs).The proposed model is composed of two states.In the first state,decision tree,random forest,gradient boosting decision tree(GBDT)and extreme gradient boosting(XGBoost)models are used to investigate the importance of features.The features that have a high influence on RSs are first selected.In the second state,a K-means clustering method is used to uncover the interdependences between RSs and the influencing features,based on the results in the first state.The proposed method can determine the quantitative relationships between RSs and influencing factors.The results clearly show the influences of the factors on RSs,the possibilities of different train operation RSs under different situations,as well as some key time periods and key trains that the controllers should pay more attention to.The research in this paper can help train traffic controllers better understand the train operation patterns and provides direction for optimizing rail traffic RSs.
