Research On Evaluation Of Health Status Of High Spped Railwar Catenary

The rapid development of high-speed railway in China puts forward higher requirements for traction power supply system.As one of the most vulnerable links in the traction power supply system of high-speed railway,the safety and stability of the catenary system plays an important role in the operation safety of the whole high-speed railway system.This paper takes the high-speed railway catenary system as the research object,on the basis of the related research of the contact network fault prediction and health management(PHM),through selecting the reasonable index system and weight determination method,and comparing different forecasting methods to realize the bottom level index prediction,the comprehensive evaluation and prediction model of the contact network health condition is established,and the analysis is based on the actual data.This paper combines the field maintenance experience and the operation and maintenance rules of high-speed railway catenary to determine the selected indicators and establish the index system.After the establishment of the index system,the bottom level indicators are integrated to express the condition of the catenary.This paper divides the health of catenary into dynamic geometric parameters,contact line smoothness parameters,pantograph current receiving performance and other sub indicators.Considering the different subjective and objective factors of weight giving,the weight is combined weight based on AHP and entropy weight method,and the hierarchical structure model of comprehensive evaluation of the health condition of catenary is established.In this paper,the parameters evaluation set is determined,and the fuzzy processing method of the characteristic value of each sub layer of the high-speed railway contact network and the method of dividing the state range of the bottom index eigenvalue are studied.Based on the data,the threshold value of each index evaluation set is determined,and " M(,?)" is selected as the fuzzy operator in the fuzzy evaluation.In the prediction research,this paper makes data complement and data exception elimination for contact pressure,guide height,pull out value and hard point actual test data.The first mock exam is used to extract the feature of the time series.The variance is taken as the eigenvalue of the detection parameters.Based on the feature extraction,the prediction method is selected by the appropriate linear prediction and the nonlinear characteristics of the data characteristic time series.The ARIMA-SVM combination forecasting model is established.The combination model and the single model prediction result show that the combined model can be improved.High accuracy and stability of prediction.Finally,combined with the actual operation data,the paper verifies the health condition assessment and prediction model.The results show that the predicted evaluation results are basically consistent with the actual data evaluation results,which provides the basis for scientific formulation of the maintenance strategy of the catenary.