Reliability model for key components of urban rail transit train based on improved hunter-prey optimization

IF 1.7 4区工程技术 Q3 ENGINEERING, INDUSTRIAL

Proceedings of the Institution of Mechanical Engineers Part O-Journal of Risk and Reliability Pub Date : 2024-03-01 DOI:10.1177/1748006x241231067

Jiecheng Zhong, Deqiang He, Zhenzhen Jin, Haimeng Sun, Sheng Shan

{"title":"Reliability model for key components of urban rail transit train based on improved hunter-prey optimization","authors":"Jiecheng Zhong, Deqiang He, Zhenzhen Jin, Haimeng Sun, Sheng Shan","doi":"10.1177/1748006x241231067","DOIUrl":null,"url":null,"abstract":"The reliability of key components of urban rail transit (URT) plays an important role in the maintenance plans of URT. It is necessary to establish the reliability model of URT trains. In the current research, the reliability model has a limited scope of application and fails to accurately depict the reliability of key components in URT trains. To solve the above problem, a multi-peak type mixture Weibull distribution model is established using several three-parameter Weibull distributions based on fault modes of components sourced from historical lifetime data. Due to the complexity of this model, parameter estimation is challenging. For this purpose, an improved hunter-prey optimization (IHPO) was proposed to improve parameter estimation accuracy. Firstly, an improved Hénon chaos map was introduced to improve the distribution of the initial population. Secondly, the Lévy flight was introduced to increase the probability of the individual spreading to the whole range at the late stage. Lastly, a nonlinear balance factor was proposed to enhance the algorithm’s global search capability. The simulation experiment was carried out with examples of the balanced pressing wheel and the wheelset. The IHPO algorithm-based parameter estimation method shows the highest R-square with values of 0.996 and 0.999, respectively, and the lowest root mean square error with values of 0.019 and 0.008, respectively. The simulation results demonstrate that the stability and optimization of the HPO are improved, and the multi-peak mixture Weibull distribution model based on the IHPO can accurately depict URT trains’ reliability.","PeriodicalId":51266,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers Part O-Journal of Risk and Reliability","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Institution of Mechanical Engineers Part O-Journal of Risk and Reliability","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1177/1748006x241231067","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, INDUSTRIAL","Score":null,"Total":0}

引用次数: 0

Abstract

The reliability of key components of urban rail transit (URT) plays an important role in the maintenance plans of URT. It is necessary to establish the reliability model of URT trains. In the current research, the reliability model has a limited scope of application and fails to accurately depict the reliability of key components in URT trains. To solve the above problem, a multi-peak type mixture Weibull distribution model is established using several three-parameter Weibull distributions based on fault modes of components sourced from historical lifetime data. Due to the complexity of this model, parameter estimation is challenging. For this purpose, an improved hunter-prey optimization (IHPO) was proposed to improve parameter estimation accuracy. Firstly, an improved Hénon chaos map was introduced to improve the distribution of the initial population. Secondly, the Lévy flight was introduced to increase the probability of the individual spreading to the whole range at the late stage. Lastly, a nonlinear balance factor was proposed to enhance the algorithm’s global search capability. The simulation experiment was carried out with examples of the balanced pressing wheel and the wheelset. The IHPO algorithm-based parameter estimation method shows the highest R-square with values of 0.996 and 0.999, respectively, and the lowest root mean square error with values of 0.019 and 0.008, respectively. The simulation results demonstrate that the stability and optimization of the HPO are improved, and the multi-peak mixture Weibull distribution model based on the IHPO can accurately depict URT trains’ reliability.

查看原文本刊更多论文

基于改进的猎人-猎物优化的城市轨道交通列车关键部件可靠性模型

城市轨道交通（URT）关键部件的可靠性在URT维护计划中发挥着重要作用。建立城市轨道交通列车的可靠性模型十分必要。在目前的研究中，可靠性模型的应用范围有限，不能准确描述城市轨道交通列车关键部件的可靠性。为解决上述问题，本文根据历史寿命数据中部件的故障模式，利用多个三参数 Weibull 分布建立了多峰型混合 Weibull 分布模型。由于该模型的复杂性，参数估计具有挑战性。为此，我们提出了一种改进的猎人-猎物优化（IHPO）方法，以提高参数估计的准确性。首先，引入了改进的 Hénon 混沌图，以改善初始种群的分布。其次，引入莱维飞行以增加个体在后期扩散到整个范围的概率。最后，提出了一个非线性平衡因子，以增强算法的全局搜索能力。仿真实验以平衡压轮和轮组为例进行。基于 IHPO 算法的参数估计方法显示出最高的 R 方，分别为 0.996 和 0.999；最小的均方根误差，分别为 0.019 和 0.008。仿真结果表明，HPO 的稳定性和优化性得到了提高，基于 IHPO 的多峰混合 Weibull 分布模型能够准确地描述 URT 列车的可靠性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Proceedings of the Institution of Mechanical Engineers Part O-Journal of Risk and Reliability ENGINEERING, MULTIDISCIPLINARY-ENGINEERING, INDUSTRIAL

CiteScore

4.50

自引率

19.00%

发文量

审稿时长

6-12 weeks

期刊介绍： The Journal of Risk and Reliability is for researchers and practitioners who are involved in the field of risk analysis and reliability engineering. The remit of the Journal covers concepts, theories, principles, approaches, methods and models for the proper understanding, assessment, characterisation and management of the risk and reliability of engineering systems. The journal welcomes papers which are based on mathematical and probabilistic analysis, simulation and/or optimisation, as well as works highlighting conceptual and managerial issues. Papers that provide perspectives on current practices and methods, and how to improve these, are also welcome