基于无偏灰色-马尔可夫模型的地铁牵引系统故障预测

Prediction for subway traction system failures based on unbiased grey-Markov model

故障准确预测能够有效提高地铁车辆的检修效率。针对地铁牵引系统的故障预测问题,利用故障统计数据,提出一种基于无偏灰色-马尔可夫模型的预测方法。以受电弓模块为例,首先利用无偏灰色模型预测未来该模块的故障情况,接着建立了无偏灰色-马尔可夫模型,通过马尔可夫状态转移概率矩阵判断该模块未来可能处于的故障状态,最后利用修正函数对模型预测值进行修正,从而完成故障的准确预测。结果表明,将无偏灰色理论与马尔可夫模型相结合来预测故障较之单独使用无偏灰色预测模型具有更高的精度等级,对制定地铁列车牵引系统主动维护策略具有重要的参考意义。

Accurate prediction of failures can effectively improve the efficiency of subway vehicle maintenance.Aiming at the problem of predicting the number of failures of the subway traction system,using failure statistical data,this paper proposes a prediction method based on unbiased grey-Markov model.Taking the pantograph module as an example,first use the unbiased grey model to predict the failure situation of the module in the future;then construct an unbiased grey-Markov model,and use the Markov state transition probability matrix to judge the possible failure state of the module in the future;finally,use the correction function to correct the predicted value of the model,so as to complete the accurate prediction of failures.The results show that the combination of unbiased grey theory and Markov model to predict failures has a higher accuracy level than the unbiased grey prediction model alone,which has important reference significance for the formulation of active maintenance strategies for subway train traction systems.