基于LDA-CLCBA组合模型的高速铁路道岔故障诊断

ZY(J)7电液道岔转换设备已在高速铁路大量投入使用，对其进行精确的故障诊断有助于高速铁路道岔的日常维护作业。以ZY(J)7道岔故障文本数据作为研究对象，提出一种基于LDA(latent dirichlet allocation)主题模型与关联规则分类技术相结合的高速铁路道岔故障诊断模型。该模型首先采用LDA主题模型实现ZY(J)7道岔故障文本数据的特征提取；其次，由于道岔各故障类别数据的不均衡性，将原有的关联规则分类算法引入类支持度相关概念进行不平衡数据的处理，最终实现ZY(J)7道岔的故障诊断。通过对某铁路局2017～2019年的ZY(J)7道岔故障文本数据进行实验分析，实验结果表明提出的故障诊断方法分类精确率和召回率分别达到95.08%和90.24%,既保证了整体分类的准确率又有较好的小类别分类性能。

Fault diagnosis for turnout of high-speed railway basedon LDA-CLCBA hybrid model

ZY(J)7 electrohydraulic turnout switch equipment has been widely used in high-speed railway, and accurate fault diagnosis ishelpful to the daily maintenance of high-speed railway turnout. Taking the fault text data of ZY( J) 7 turnout as the research object, afault diagnosis model for high-speed railway turnout was proposed, which combined LDA topic model with association rules classificationtechnology. Firstly, this model adopted LDA topic model to extract the feature of ZY(J)7 turnout fault text data. Secondly, due to theunbalanced data of each fault type of turnout, the original association rule classification algorithm was introduced into the concept of classsupport to deal with unbalanced data, and finally the fault diagnosis of ZY(J)7 switch was realized. Through the experimental analysis ofZY(J)7 turnout fault text data of a railway bureau from 2017 to 2019, the experimental results indicate that the classification precisionand recall rate of the proposed fault diagnosis method are 95. 08% and 90. 24% respectively, which not only guarantees the accuracy ofthe whole classification, but also gets better classification performance of minority class.