Analysis and prediction of high‐speed train wheel wear based on SIMPACK and backpropagation neural networks. Issue 7 (27th May 2019)

• Record Type: Journal Article
• Authors: Wang, Shuwen; Yan, Hao; Liu, Caixia; Fan, Ning; Liu, Xiaoming; Wang, Chengguo
• Other Names: Stahl Frederic Theodor guestEditor.; Neagu Daniel guestEditor.; Campean Felician guestEditor.; Gheorghe Marian guestEditor.
• Is Part Of: Expert systems. Volume 38:Issue 7(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-05-27
• Subjects: BP neural networks -- high‐speed train -- SIMPACK -- wheel wear; Expert systems (Computer science); 006.33
• DOI: 10.1111/exsy.12417
• Languages: English
• ISSNs: 0266-4720

Abstract

Abstract: As train running speeds increase, the wheel–rail interactions of high‐speed trains are becoming more complicated, and predicting and monitoring wheel wear are becoming increasingly important for the safe operation of high‐speed trains. Therefore, identifying the critical factors that affect the wear of wheel–rail interactions and developing novel methods to predict wheel wear are of great importance. In this work, SIMPACK is used to establish a dynamic model of a high‐speed train and to investigate the normal and lateral contact forces of the wheel–rail interfaces and the wear of the wheels for a train passing through a specially designed route that consists of straight‐line, smooth‐curved, and circular tracks. The wheel wear is predicted by means of the Archard wear model based on the SIMPACK analysis, and the wear is validated by a backpropagation neural network (BPNN) classification based on daily measured data provided by the Beijing Railway Administration. The results from the SIMPACK dynamic simulation and the BPNN classification show that the position of a wheel in a bogie has a significant effect on the wheel wear, but the position of a carriage in a train does not have a significant effect on the wheel wear. The findings from this study are very useful for the maintenance and safe operation of high‐speed trains.