基于多目标优化的列车车轮镟修策略研究
Research on Train Wheel Re-Profiling Strategy Based on Multi-Objective Optimization
DOI: 10.12677/hjdm.2024.143012, PDF,    科研立项经费支持
作者: 牛泓博, 张 旭, 陈秉智, 曾 毅：大连交通大学机车车辆工程学院，辽宁 大连；大连交通大学高速列车服役安全关键技术铁路行业重点实验室，辽宁 大连
关键词: 车轮镟修；多目标优化；NSGA-II算法；数据拟合；Wheel Re-Profiling； Multi-Objective Optimization； NSGA-II Algorithm； Data Fitting
摘要: 在列车的日常运行过程中，车轮的维护保养十分重要。随着列车运行，轮缘厚度会逐渐因磨损而减小，因此需要对车轮进行镟修以恢复轮缘厚度，镟修能够有效减缓车轮半径的磨损速度，还能达到提高车轮寿命和保证行车安全的目的。本文以车轮寿命和平均每月成本作为目标函数建立多目标优化模型。并NSGA-II算法对模型进行求解，得到了最佳方案为镟修6次车轮。相对于传统固定修方案，车轮寿命提升33.5%，运营成本减少25.1%。最后将NSGA-II算法求解的结果与蒙特卡洛循环法以及GDE算法的求解结果进行对比分析，结果表明NSGA-II算法求解结果更为优秀。
Abstract: In the daily operation of trains, maintenance of the train wheels is crucial. As trains operate, the thickness of the wheel flange gradually decreases due to wear and tear, necessitating wheel re-profiling to restore the flange thickness. Re-profiling effectively slows down the rate of wheel radius wear and tear, thus increasing the wheel lifespan and ensuring operational safety. This paper establishes a multi-objective optimization model with the objectives of maximizing the wheel lifespan and minimizing the average monthly cost. The NSGA-II algorithm is employed to solve the model, yielding the optimal solution of re-profiling the wheels 6 times. Compared to the traditional fixed maintenance schedule, the wheel lifespan is increased by 33.5% while the operational cost is reduced by 25.1%. Finally, the results obtained by the NSGA-II algorithm are compared and analyzed against those obtained by the Monte Carlo simulation method and the GDE algorithm, demonstrating the superior performance of the NSGA-II algorithm.
文章引用：牛泓博, 张旭, 陈秉智, 曾毅. 基于多目标优化的列车车轮镟修策略研究[J]. 数据挖掘, 2024, 14(3): 135-142. https://doi.org/10.12677/hjdm.2024.143012

参考文献

[1] De Arizon, J., Verlinden, O. and Dehombreux, P. (2007) Prediction of Wheel Wear in Urban Railway Transport: Comparison of Existing Models. Vehicle System Dynamics, 45, 849-866. [Google Scholar] [CrossRef] 
[2] Cui, D., Li, L., Wang, H., Wen, Z. and Xiong, J. (2015) High-Speed EMU Wheel Re-Profiling Threshold for Complex Wear Forms from Dynamics Viewpoint. Wear, 338-339, 307-315. [Google Scholar] [CrossRef] 
[3] Wang, L., Xu, H., Yuan, H., Zhao, W. and Chen, X. (2015) Optimizing the Re-Profiling Strategy of Metro Wheels Based on a Data-Driven Wear Model. European Journal of Operational Research, 242, 975-986. [Google Scholar] [CrossRef] 
[4] Zhu, W., Yang, D., Guo, Z., Huang, J. and Huang, Y. (2015) Data-Driven Wheel Wear Modeling and Reprofiling Strategy Optimization for Metro Systems. Transportation Research Record: Journal of the Transportation Research Board, 2476, 67-76. [Google Scholar] [CrossRef] 
[5] Zeng, Y., Song, D., Zhang, W., Zhou, B., Xie, M. and Tang, X. (2022) An Optimal Life Cycle Reprofiling Strategy of Train Wheels Based on Markov Decision Process of Wheel Degradation. IEEE Transactions on Intelligent Transportation Systems, 23, 10354-10364. [Google Scholar] [CrossRef] 
[6] Lin, Z., Lu, Z., Yong, X., Wei, J. and Wang, X. (2022) Optimization of Metro Wheel Reprofiling Based on Cluster Analysis. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 236, 997-1007. [Google Scholar] [CrossRef] 
[7] Song, C.-Y. and Choi, H.-Y. (2022) Multi-Objective Profile Design Optimization to Minimize Wear Damage and Surface Fatigue of City Train Wheel. Applied Sciences, 12, Article 3940. [Google Scholar] [CrossRef] 
[8] Yuan, H., Xiao, S. and Wang, Y. (2006) Feasible Analysis of Wheelset Class-Lathing on the Statistics of: Wheelset Wearing. Urban Mass Transit, 9, 43-45.
[9] Tian, Y., Cheng, R., Zhang, X. and Jin, Y. (2017) PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimization [Educational Forum]. IEEE Computational Intelligence Magazine, 12, 73-87. [Google Scholar] [CrossRef] 
[10] Deb, K., Pratap, A., Agarwal, S. and Meyarivan, T. (2002) A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6, 182-197. [Google Scholar] [CrossRef] 

为你推荐