Research on Prediction of Metro Wheel Wear Based on Integrated Data-Model-Driven Approach

Abstract

Existing research on wheel wear prediction uses either data-driven or model-based methods. However, due to the high reliability and limited sample characteristics of metro wheel wear, data-driven methods are not accurate enough and require relatively high data costs, and model-based methods mainly lack verification with measured data and generalization ability. To address the shortcomings of the two types of methods, a new approach combining model-based and data-driven methods is used to predict wheel wear in this paper. First, the least-squares algorithm is used to analyze and calculate the difference between the wear measurement for a specific running mileage and the corresponding simulated wear, with the minimum difference taken as an objective function. By means of optimization algorithms including Genetic Algorithm, Particle Swarm Optimization, Tabu Search and Simulated Annealing, the wear coefficient k in Jendel wear model is optimized, thereby obtaining an optimized Jendel wear model. Later, metro wheel wear for additional running mileage is simulated and predicted through combined application of the vehicle system dynamics, wheel-rail contact, and optimized Jendel wear models. Finally, the paper analyzes the wear prediction results obtained by the integrated data-model-driven approach and compares them with the results of traditional methods and measured data. The results suggest that the integrated data-model-driven approach effectively reduces the uncertainty in selecting the wear coefficient by experience, lowers the experimental data costs, and improves the wear prediction accuracy. Therefore, it is a promising approach to wheel wear prediction. INDEX TERMS Metro wheel, wear prediction, data-model driven, optimization algorithms, Jendel wear model.

Intelligent Diagnosis for Railway Wheel Flat Using Frequency-Domain Gramian Angular Field and Transfer Learning Network

“…Railway vehicles are efficient due to their large capacities and high speeds. However, these advantages result in many wheel surface defects, especially wheel flats with certain numbers and sizes [1][2][3]. Wheel flat can increase contact force instantaneously and make severe noise [4][5][6][7][8].…”

Simulation of wheel and rail profile wear: a review of numerical models

“…Although great attention must be paid to the computational efficiency of the simulation, a direct quantitative comparison of the numerical models described in the previous section cannot be provided. In fact, the numerical tools shown above were Budapest University [65], KTH [38,66,67,[69][70][71][72][73], PoliMi [75], USFD [78], PoliMi + USFD [34,77,79], SWJTU [83], UNiFI + SWJTU [86], Others [88][89][90][91][92] Rail wear models: KTH [74], SWJTU [84] Wheel and rail wear models: Budapest University [36,64] Wheel wear models: AWARE [43,44,[94][95][96], UniFi [98][99][100][101][102]107], SWJTU [109,112], IIT [113][114][115]125], Others [93,97,111,116] Wheel and rail wear models: Un...…”

“…A simple application of this approach was proposed by Zhu et al [93], who slightly modified the KTH strategy performing the dynamic simulations in Simpack and then computed the wheel wear with a dedicated Matlab routine, which also determined the wheel worn profile shape.…”

A new hybrid approach to predict worn wheel profile shapes

“…Profile shape evolution caused by wear is currently typically predicted in one of two ways: using a method based on contact mechanics (1) or one based on statistical methods (2). The first method uses multi-body-dynamics (MBD) simulations and local wheel-rail contact analysis to obtain wheel-rail contact parameters (e.g.…”

“…Currently, two methods are widely used to predict worn wheel profiles [1], [2]. One method is based on contact mechanics and is widely applicable to many scenarios.…”