机械基础工程

基于整群抽样和支持向量回归模型的高功率半导体激光器剩余使用寿命预测

展开
  • 1.合肥工业大学管理学院,合肥,230009
    2.合肥工业大学航空结构件成形制造与装备安徽省重点实验室,合肥,230009
    3.浙江大学机械工程学院,杭州,310058 4.安徽皖维集团有限责任公司,合肥,238002
严建文,男,1967年生,博士、教授、博士研究生导师。研究方向为智能制造工程管理、可靠性理论。发表论文20余篇。E-mail:yanjianwen@hfpress.com。

收稿日期: 2019-08-21

  修回日期: 2021-05-12

  网络出版日期: 2021-07-15

基金资助

中央高校基本科研业务费专项资金(PA2019GDP K0048);安徽省博士后研究人员科研活动资助经费(2018B257)

RUL Prediction of High-power Semiconductor Lasers Based on Cluster Sampling and SVR Model#br#

Expand
  • 1. School of Management,Hefei University of Technology,Hefei,230009
    2. Anhui Province Key Lab of Aerospace Structural Parts Forming Technology and Equipment,Hefei University of Technology,Hefei,230009
    3. School of Mechanical Engineering,Zhejiang University,Hangzhou,310058
    4. Anhui Wanwei Group Co.,Ltd.,Hefei,238002

Received date: 2019-08-21

  Revised date: 2021-05-12

  Online published: 2021-07-15

摘要

剩余使用寿命(RUL)预测是高功率半导体激光器在各种环境应力作用下可靠性评估的核心问题。在实际应用中,现有支持向量回归(SVR)方法均侧重于保证所训练模型的回归曲线的整体误差最小,以追求方法的泛化性,这往往造成关键预警阶段特别是临近故障失效前的预测结果不理想,不能可靠地支持维护决策。提出了一种基于整群抽样的SVR模型训练方法,对测试样本后期观测数据进行多次整群抽样后用于SVR模型测试,SVR模型中的参数使得SVR模型对训练样本的后期数据拟合得更好。实例分析验证了该方法的有效性和稳健性,研究结果表明,所提方法的预测性能和实用价值优于现有几种代表性的小样本分析方法。

本文引用格式

严建文, 钟小虎, 范煜, 郭三敏, . 基于整群抽样和支持向量回归模型的高功率半导体激光器剩余使用寿命预测[J]. 中国机械工程, 2021 , 32(13) : 1523 -1529 . DOI: 10.3969/j.issn.1004-132X.2021.13.002

Abstract

RUL prediction was the core problem of reliability evaluation of high-power semiconductor lasers under various environmental stresses. In practical applications, the existing SVR methods all focused on minimizing the overall errors of the regression curve of the trained model, so as to pursue the generalization, which often resulted in unsatisfactory prediction results at the critical early warning stage, especially before the near-failure, and failed to ensure its reliability. Therefore, the SVR model training method was proposed based on cluster sampling. The observation data in the later period of the test samples were sampled for multiple cluster and then used for the SVR model test. The parameters in the SVR model made the SVR model fit the data in the later period of the training samples better. The effectiveness and robustness of the proposed method were verified by a case study, the results show that the performance and practical value of the proposed method are better than those of several representative small sample analysis methods.

参考文献

[1]李学敏,苏国强,翟光美,等. 高功率半导体激光器在金属材料加工中的应用[J]. 太原理工大学学报, 2016, 47(2):140-143.
LI Xuemin, SU Guoqiang, ZHAI Guangmei, et al. The Application of High-power Semiconductor Laser in Metallic Material processing[J]. Journal of Taiyuan University of Technology, 2016, 47(2):140-143.
[2]PECHT M. Prognostics and Health Management of Electronics[M]. Hoboken:Wiley, 2008.
[3]GEBRAEEL N, PAN J. Prognostic Degradation Models for Computing and Updating Residual Life Distributions in a Time-varying Environment[J]. IEEE Transactions on Reliability, 2008, 57(4):539-550.
[4]CURCURU G, GALANTE G, LOMBARDO A. A Predictive Maintenance Policy with Imperfect Monitoring[J]. Reliability Engineering & System Safety, 2010, 95(9):989-997.
[5]ZHAO Zhen,WANG Fuli, JIA Mingxing, et al. Predictive Maintenance Policy Based on Process Data[J]. Chemometrics and Intelligent Laboratory Systems, 2010, 103(2):137-143.
[6]SI Xiaosheng, WANG Wenbin, HU Changhua, et al. Remaining Useful Life Estimation: a Review on the Statistical Data Driven Approaches[J]. European Journal of Operational Research, 2011, 213(1):1-14.
[7]ZHANG Zhengxin, SI Xiaosheng, HU Changhua, et al. Degradation Data Analysis and Remaining Useful Life Estimation:a Review on Wiener-Process-based Methods[J]. European Journal of Operational Research, 2018, 271(3):775-796.
[8]WANG X L, BALAKRISHNAN N, GUO B, et al. Residual Life Estimation Based on Bivariate Non-stationary Gamma Degradation Process[J]. Journal of Statistical Computation and Simulation, 2015, 85(2):405-421.
[9]PAN Donghui, LIU Jiabao, CAO Jinde. Remaining Useful Life Estimation Using an Inverse Gaussian Degradation Model[J]. Neurocomputing, 2016, 185:64-72.
[10]LIN D M, MAKIS V. Recursive Filters for a Partially Observable System Subject to Random Failure[J]. Advances in Applied Probability, 2003, 35(1):207-227.
[11]DONG M, HE D. Hidden Semi-Markov Model-based Methodology for Multi-sensor Equipment Health Diagnosis and Prognosis[J]. European Journal of Operational Research, 2007, 178(3):858-878.
[12]YE Zhisheng, CHEN Nan. The Inverse Gaussian Process as a Degradation Model[J]. Technometrics, 2014, 56(3):302-311.
[13]PAN Donghui, LIU Jiabao, CAO Jinde. Remaining Useful Life Estimation Using an Inverse Gaussian Degradation Model[J]. Neurocomputing, 2016, 185:64-72.
[14]WANG Xiao, XU Dihua. An Inverse Gaussian Process Model for Degradation Data[J]. Technometrics, 2010, 52(2):188-197.
[15]裴洪,胡昌华,司小胜,等. 基于机器学习的设备剩余寿命预测方法综述[J].机械工程学报, 2019, 55(8):1-13.
PEI Hong, HU Changhua, SI Xiaosheng, et al. Review of Machine Learning Based Remaining Useful Life Prediction Methods for Equipment[J]. Journal of Mechanical Engineering, 2019, 55(8):1-13.
[16]CANNARILE F, BARALDI P, ZIO E. An Evidential Similarity-based Regression Method for the Prediction of Equipment Remaining Useful Life in Presence of Incomplete Degradation Trajectories[J]. Fuzzy Sets and Systems,2018, 367:36-50.
[17]TIAN Zhigang. An Artificial Neural Network Method for Remaining Useful Life Prediction of Equipment Subject to Condition Monitoring[J]. Journal of Intelligent Manufacturing, 2012, 23(2):227-237.
[18]ZIO E, MAIO F D. A Data-driven Fuzzy Approach for Predicting the Remaining Useful Life in Dynamic Failure Scenarios of a Nuclear System[J]. Reliability Engineering & System Safety, 2010, 95(1):49-57.
[19]BENKEDJOUH T, MEDJAHER K, ZERHOUNI N, et al. Remaining Useful Life Estimation Based on Nonlinear Feature Reduction and Support Vector Regression[J]. Engineering Applications of Artificial Intelligence, 2013, 26(7):1751-1760.
[20]BENKEDJOUH T, MEDJAHER K, ZERHOUNI N, et al. Health Assessment and Life Prediction of Cutting Tools Based on Support Vector Regression[J]. Journal of Intelligent Manufacturing, 2015, 26(2):213-223.
[21]LIU Yingchao, HU Xiaofeng, ZHANG Wenjuan. Remaining Useful Life Prediction Based on Health Index Similarity[J]. Reliability Engineering & System Safety, 2019, 18:502-510.
[22]LIU Zhen, WANG Qing, SONG Chenliang, et al. Similarity-based Difference Analysis Approach for Remaining Useful Life Prediction of GaAs-based Semiconductor Lasers[J]. IEEE Access, 2017, 5:21508-21523.
[23]LIU J, VITELLI V, ZIO E, et al. A Novel Dynamic-weighted Probabilistic Support Vector Regression-based Ensemble for Prognostics of Time Series Data[J]. IEEE Transactions on Reliability, 2015, 64(4):1203-1213.
[24]FUMEO E, ONETO L, ANGUITA D. Condition Based Maintenance in Railway Transportation Systems Based on Big Data Streaming Analysis[J]. Procedia Computer Science, 2015, 53:437-446.
[25]HUYNH K T, GRALL A, BERENGUER C. A Parametric Predictive Maintenance Decision-making Framework Considering Improved System Health Prognosis Precision[J]. IEEE Transactions on Reliability, 2018, 68(1):375-396.
[26]ZHAO Zhen, WANG Fuli, JIA Mingxing, et al. Predictive Maintenance Policy Based on Process Data[J]. Chemometrics and Intelligent Laboratory Systems, 2010, 103:137-143.
[27]李玲玲,顾训华,李凤强,等. 基于GaAs激光器性能退化的可靠性度量方法[J]. 工程设计学报, 2012, 19(3):166-169.
LI Lingling, GU Xunhua, LI Fengqiang, et al. Reliability Assessment Method based on GaAs Laser Performance Degradation[J]. Chinese Journal of Engineering Design, 2012, 19(3):166-169.
文章导航

/

〈 〉