作者：王清波, 宁静, 叶运广, 陈春俊

作者单位：西南交通大学机械工程学院, 四川 成都 610031

关键词：高速列车齿轮箱;裂纹识别;Kriging代理模型;随机粒子群优化算法

摘要：

为建立裂纹结构动力响应与裂纹参数之间的解析关系从而对齿轮箱裂纹进行有效识别，提出一种可替代原有高精度分析模型的计算量小且计算精度较高的基于代理模型的裂纹识别方法。利用初始样本通过有限元与插值算法建立裂纹结构参数与动力响应之间的Kriging代理模型对应关系，从而代替原有的物理参数模型与结构响应关系，有效减少有限元计算次数，并通过随机粒子群优化方法对建立的代理模型进行全局裂纹参数寻优。通过一个悬臂梁结构的数值算例，对所提方法进行有效验证，并将该方法应用到某高速列车齿轮箱的裂纹识别中，结果表明该方法能够有效地对结构裂纹进行识别。

Crack identification of high-speed train gearbox based on surrogate model

WANG Qingbo, NING Jing, YE Yunguang, CHEN Chunjun

School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China

Abstract: In order to establish an analytical relationship between the dynamic response of crack and the crack parameters for effective identification of gearbox crack, a crack identification method with minor calculation and high computational accuracy could represent original high precision analysis model that was proposed based on surrogate model. The initial samples were used to construct the Kriging surrogate model via the finite element and interpolation algorithm to represent the relationship between the structural parameters and the dynamic response instead of that between the original physics parameters and the dynamic response, reducing the finite element calculation effectively and the random particle swarm optimization(PSO) algorithm was used to optimize the global crack parameters for the established surrogate model. A numerical example of a cantilever structure was given to prove the effectiveness of the method, and it was used in crack identification of high-speed train gearbox. The results indicate that the method can effectively identify structural crack.

Keywords: high-speed train gearbox;crack identification;Kriging surrogate model;random PSO algorithm

2018, 44(3): 131-136  收稿日期: 2017-08-29;收到修改稿日期: 2017-10-18

基金项目: 国家自然科学基金项目（51475387）；中央高校基本业务费专项基金项目（2682014CX033）；四川省科技创新苗子工程项目（2015102）

作者简介: 王清波(1993-),男,甘肃张掖市人,硕士研究生,专业方向为智能化状态监测及故障诊断等。

参考文献

[1] 翟婉明. 车辆-轨道耦合动力学[M]. 4版. 北京:科学出版社,2014:121-150.
[2] 范军,宋瑞,谷安斯,等. 高速动车组齿轮箱体振动特性研究[J]. 铁道技术监督,2013,41(12):31-40.
[3] FAN W, QIAO P. Vibration-based damage identification methods:A review and comparative study[J]. Structural Health Monitoring,2010,9(3):83-111.
[4] 王光远. 论不确定性结构力学的发展[J]. 力学进展,2002,32(2):205-211.
[5] WANG G G, SHAN S. Review of meta-modeling tech-niques in support of engineering design optimization[J]. Trans of ASME Journal of Mechanical Design,2007,129(4):370-380.
[6] FORRESTER A I, KEANE A J. Recent advances in surrogate-based optimization[J]. Progress in Aerospace Sciences,2009(45):50-79.
[7] SIMPSON T W, PEPLINSKI J D. Meta-models for computer-based engineering design:survey and recom-mendation[J]. Engineering with Computers,2001(17):129-150.
[8] GORISSEN D. Grid-enabled adaptive surrogate modeling for computer aided engineering[D]. Belgium:Phd Thesis of Ghent University,2010.
[9] NOEL C. The origins of Kriging[J]. Math Geol,1990,22(3):239-252.
[10] KAYMAZ I. Application of Kriging method to structural reliability problems[J]. Structural Safety,2005(27):133-151.
[11] KLEIJNEN J P C. Kriging meta-modeling in simulation:A review[J]. European Journal of Operational Research,2009(192):707-716.
[12] NOBARI A, OUYANG H J. Uncertainty quantification of squeal instability via surrogate modeling[J]. Mechanical Systems and Signal Processing,2015(66/67):887-908.
[13] 刘东. 粒子群优化算法及其工程应用研究[D]. 成都:西南交通大学,2013.
[14] ZHANG B, TAN A C C, LIN J H. Gearbox fault diagnosis of high-speed railway train[J]. Engineering Failure Analysis,2016(66):407-420.