计算机集成制造系统 ›› 2016, Vol. 22 ›› Issue (第9期): 2187-2194.DOI: 10.13196/j.cims.2016.09.015

• 产品创新开发技术 • 上一篇    下一篇

基于自适应隐式半马尔可夫模型的设备健康诊断与寿命预测方法

刘勤明,李亚琴,吕文元,叶春明   

  1. 上海理工大学管理学院
  • 出版日期:2016-09-30 发布日期:2016-09-30
  • 基金资助:
    国家自然科学基金资助项目(71471116,71271138);上海市浦江人才计划资助项目(14PJC077);教育部人文社会科学研究青年基金资助项目(15YJCZH096);上海理工大学人文社科攀登计划资助项目(16HJPD-B04);上海理工大学国家级项目培育基金资助项目(16HJPYQN02);上海理工大学博士启动基金资助项目(BSQD201403)。

Equipment health diagnostics and prognostics method based on adaptive HSMM

  • Online:2016-09-30 Published:2016-09-30
  • Supported by:
    Project supported by the National Natural Science Foundation,China(No.71471116,71271138),the Shanghai Pujiang Program,China(No.14PJC077),the Humanity and Social Science Youth foundation of Ministry of Education,China(No.15YJCZH096),the Hujiang Foundation-Humanity and Social Science “Climbing” Program of University of Shanghai for Science and Technology,China(No.16HJPD-B04),the Programs of National Training Foundation of University of Shanghai for Science and Technology,China(No.16HJPYQN02),and the Doctoral Startup Foundation Project of University of Shanghai for Science and Technology,China(No.BSQD201403).

PDF

摘要： 针对设备健康诊断与寿命预测问题,提出一种基于自适应隐式半马尔可夫模型(AHSMM)结合多传感器信息的设备健康预测方法。提出了AHSMM的前向—后向算法、Viterbi算法和Baum-Welch算法,有效降低了模型的计算复杂性。利用最大似然线性回归训练对输出概率分布和驻留概率分布进行自适应训练,处理多传感器信息间的差异性,进行有效的多传感器信息融合,以更加准确地进行设备健康诊断与寿命预测。利用失效率理论建立了对设备剩余使用寿命进行预测的基本步骤。通过美国卡特彼勒公司液压泵的状态识别和健康预测实际案例对所提出的方法进行评价与验证,实验结果表明,基于AHSMM的设备健康诊断和性能衰退预测方法比传统的隐式半马尔可夫模型(HSMM)更有效。

关键词: 自适应隐式半马尔可夫模型, 健康诊断, 剩余有效寿命, 最大似然线性回归, 多传感器信息

Abstract: To improve the accuracy and validity of equipment health diagnosis and prognosis,a method of equipment management integrating multi-sensor information based on Adaptive Hidden Semi-Markov Model (AHSMM) was proposed.The basic algorithms of AHSMM were modified to decrease computation and space complexity,and the modified HSMM with multi-sensor information was applied,in which the hidden degradation process could be seen as the system state.The maximum likelihood linear regression transformations method was used to train the output and duration distributions to re-estimate all unknown parameters.The AHSMM could also be used to obtain the transition probabilities among health states and health state durations.The main results were verified by a case study,and the results showed that it had a better performance for health diagnosis and prognosis than HSMM.

Key words: adaptive hidden semi-Markov model, health diagnostics, residual useful lifetime, maximum likelihood linear regression, multi-sensor information

中图分类号: 

京ICP备12012770号-3
Copyright © 《计算机集成制造系统》编辑部
技术支持：北京玛格泰克科技发展有限公司
总访问量
今日访问
在线人数