零寿命标签下退化设备剩余寿命预测方法

裴洪; 司小胜; 胡昌华; 郑建飞; 张建勋; 董青

doi:10.12263/DZXB.20221201

您当前的位置：

首页 >

文章列表页 >

零寿命标签下退化设备剩余寿命预测方法

学术论文 | 更新时间：2025-12-08

- 零寿命标签下退化设备剩余寿命预测方法
- Prognostic Method of Remaining Useful Life for Degraded Equipment Under Zero Life Label
- 电子学报 2023年51卷第7期页码：1939-1948
- 作者机构：
  
  火箭军工程大学控制工程系，陕西西安 710025
- 作者简介：
  
  [ "裴洪男，1992年生于安徽霍邱. 现为火箭军工程大学讲师. 主要研究方向为装备的剩余寿命预测与维修决策. E-mail: ph2010hph@sina.com" ]
  [ "司小胜男，1984年生于甘肃通渭. 现为火箭军工程大学教授、博士生导师. 主要研究方向为复杂系统寿命预测与维修决策.E⁃mail: sixiaosheng@126.com" ]
  [ "胡昌华男，1966年生于湖北罗田. 现为火箭军工程大学教授、博士生导师. 主要研究方向为复杂系统故障诊断、寿命预测与容错控制.E⁃mail: hch66603@163.com" ]
  [ "郑建飞男，1980年生于河北霸州. 现为火箭军工程大学副教授、硕士生导师. 主要研究方向为复杂系统寿命预测与维修决策.E⁃mail: zjf302@126.com" ]
  [ "张建勋男，1988年生于四川南充. 现为火箭军工程大学讲师，硕士生导师. 主要研究方向为预测与健康管理、退化过程建模、剩余寿命估计. E-mail: zhang200735@163.com" ]
  [ "董青男，1996年生于河北邯郸. 现为火箭军工程大学博士研究生. 主要研究方向为装备的剩余寿命预测与维修决策.E-mail: 18756528162@163.com" ]
- 基金信息：
  
  国家自然科学基金(62103433;62233017;62227814;62073336)
- DOI：10.12263/DZXB.20221201
  中图分类号： TP18;TB114.3;V239
- 收稿：2022-10-25，
  
  修回：2023-02-03，
  
  纸质出版：2023-07-25
- 稿件说明：
移动端阅览
裴洪,司小胜,胡昌华等.零寿命标签下退化设备剩余寿命预测方法[J].电子学报,2023,51(07):1939-1948.

PEI Hong,SI Xiao-sheng,HU Chang-hua,et al.Prognostic Method of Remaining Useful Life for Degraded Equipment Under Zero Life Label[J].ACTA ELECTRONICA SINICA,2023,51(07):1939-1948.
裴洪,司小胜,胡昌华等.零寿命标签下退化设备剩余寿命预测方法[J].电子学报,2023,51(07):1939-1948. DOI： 10.12263/DZXB.20221201.

PEI Hong,SI Xiao-sheng,HU Chang-hua,et al.Prognostic Method of Remaining Useful Life for Degraded Equipment Under Zero Life Label[J].ACTA ELECTRONICA SINICA,2023,51(07):1939-1948. DOI： 10.12263/DZXB.20221201.

摘要

考虑到安全性与经济性因素，同类历史设备的性能退化数据大多属于截尾型，采用深度学习训练时往往面临零寿命标签的挑战，量化剩余寿命（Remaining Useful Life，RUL）不确定性更是难上加难，并且现有深度学习模型进行RUL预测时忽略了首达与非首达时间意义之间的区别.为了克服以上困难，本文提出一种零寿命标签下退化设备RUL预测方法，采用数据预处理技术生成以退化信息为标签的样本，利用贝叶斯双向长短期记忆（Bayesian Bidirectional Long Short-Term Memory，B-Bi-LSTM）模型描述设备性能退化演变规律，同时借助变分推断技术实现了性能退化的不确定性度量.进一步，从可靠性角度分析了性能退化预测分布与RUL分布间的关系，分别围绕首达与非首达两类情形推导设备RUL概率分布，通过锂电池案例对所提方法进行实例验证.实验结果表明，所提方法能够提供RUL预测的点估计与概率分布式结果，有效确保了预测结果的科学性.

Abstract

Considering the safety and economic factors

most of the performance degradation data of historical equipment are truncated type. The challenge of zero life label is encountered when deep learning training is adopted

quantifying the uncertainty of remaining useful life (RUL) is even more difficult

and what is more

the existing deep learning models ignore the difference between the first hitting and non-first hitting time meanings when predicting the RUL. To overcome the above difficulties

this paper proposes a method over RUL prediction for degraded equipment under zero life label. Data preprocessing technology is utilized to generate samples labeled with degradation information

and the evolution law of equipment performance degradation is described by Bayesian bidirectional long short-term memory (B-Bi-LSTM) model. At the same time

the uncertainty measurement of performance degradation is realized by means of variational inference technology. Furthermore

the relationship between the performance degradation prediction distribution and the RUL distribution is analyzed from the perspective of reliability

and the RUL probability distribution of the equipment is derived from the point of the first hitting and non-first hitting time respectively. The proposed method is verified by a case of lithium battery. The experimental results show that the proposed method can provide the point estimation and probability distribution results of RUL prediction

which can effectively ensure the scientificity of the prediction results.

关键词

Keywords

references

PAN Y N , CHENG D L , WEI T T , et al . Rolling bearing performance degradation assessment based on deep belief network and improved support vector data description [J]. Mechanical Systems and Signal Processing , 2022 , 181 : 109458 .

PEI H , SI X S , HU C H , et al . An adaptive prognostics method for fusing CDBN and diffusion process: application to bearing data [J]. Neurocomputing , 2021 , 421 : 303 - 315 .

SI X S , REN Z Q , HU X X , et al . A novel degradation modeling and prognostic framework for closed-loop systems with degrading actuator [J]. IEEE Transactions on Industrial Electronics , 2020 , 67 ( 11 ): 9635 - 9647 .

LEI Y G , LI N P , GUO L , et al . Machinery health prognostics: A systematic review from data acquisition to RUL prediction [J]. Mechanical Systems and Signal Processing , 2018 , 104 : 799 - 834 .

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 H , HU C H , SI X S , et al . Review of machine learning based remaining useful life prediction methods for equipment [J]. Journal of Mechanical Engineering , 2019 , 55 ( 8 ): 1 - 13 . (in Chinese)

李天梅 , 司小胜 , 张建勋 . 多源传感监测线性退化设备数模联动的剩余寿命预测方法 [J/OL]. 航空学报 , 2022 : 1 - 19 [ 2022-10-20 ]. https://kns.cnki.net/kcms/detail/11.1929.V.20220608.1202.006.ht-ml https://kns.cnki.net/kcms/detail/11.1929.V.20220608.1202.006.ht-ml .

LI T M , SI X S , ZHANG J X . Data-model interactive remaining useful life prediction method for multi-sensor monitored linear stochastic degrading devices [J/OL]. Acta Aeronautica et Astronautica Sinica , 2022 : 1 - 19 [ 2022-10-20 ]. https://kns.cnki.net/kcms/detail/11.1929.V.20220608.1202.006.html. https://kns.cnki.net/kcms/detail/11.1929.V.20220608.1202.006.html. (in Chinese)

孙国玺 , 张清华 , 文成林 , 等 . 基于随机退化数据建模的设备剩余寿命自适应预测方法 [J]. 电子学报 , 2015 , 43 ( 6 ): 1119 - 1126 .

SUN G X , ZHANG Q H , WEN C L , et al . A stochastic degradation modeling based adaptive prognostic approach for equipment [J]. Acta Electronica Sinica , 2015 , 43 ( 6 ): 1119 - 1126 . (in Chinese)

张浩 , 胡昌华 , 杜党波 , 等 . 多状态影响下基于Bi-LSTM网络的锂电池剩余寿命预测方法 [J]. 电子学报 , 2022 , 50 ( 3 ): 619 - 624 .

ZHANG H , HU C H , DU D B , et al . Remaining useful life prediction method of lithium-ion battery based on Bi-LSTM network under multi-state influence [J]. Acta Electronica Sinica , 2022 , 50 ( 3 ): 619 - 624 . (in Chinese)

LIAO L X , JIN W J , PAVEL R . Enhanced restricted boltzmann machine with prognosability regularization for prognostics and health assessment [J]. IEEE Transactions on Industrial Electronics , 2016 , 63 ( 11 ): 7076 - 7083 .

YU W N , KIM II Y , MECHEFSKE C . Remaining useful life estimation using a bidirectional recurrent neural network based autoencoder scheme [J]. Mechanical Systems and Signal Processing , 2019 , 129 : 764 - 780 .

DEUTSCH J , HE D . Using deep learning-based approach to predict remaining useful life of rotating components [J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems , 2018 , 48 ( 1 ): 11 - 20 .

DEUTSCH J , HE M , HE D . Remaining useful life prediction of hybrid ceramic bearings using an integrated deep learning and particle filter approach [J]. Applied Sciences , 2017 , 7 ( 7 ): 649 .

HUANG C G , HUANG H Z , LI Y F . A bidirectional LSTM prognostics method under multiple operational conditions [J]. IEEE Transactions on Industrial Electronics , 2019 , 66 ( 11 ): 8792 - 8802 .

SONG Y , SHI G , CHEN L Y , et al . Remaining useful life prediction of turbofan engine using hybrid model based on autoencoder and bidirectional long short-term memory [J]. Journal of Shanghai Jiaotong University (Science) , 2018 , 23 ( 1 ): 85 - 94 .

PAISLEY J , BLEI D M , JORDAN M I . Variational Bayesian inference with stochastic search [C]// Proceedings of the 29th International Coference on International Conference on Machine Learning . New York : ACM , 2012 : 1363 - 1370 .

GAL Y , GHAHRAMANI Z . Dropout as a Bayesian approximation: Representing model uncertainty in deep learning [C]// Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48 . New York : ACM , 2016 : 1050 - 1059 .

PENG W W , YE Z S , CHEN N . Bayesian deep-learning-based health prognostics toward prognostics uncertainty [J]. IEEE Transactions on Industrial Electronics , 2020 , 67 ( 3 ): 2283 - 2293 .

WANG B , LEI Y G , YAN T , et al . Recurrent convolutional neural network: A new framework for remaining useful life prediction of machinery [J]. Neurocomputing , 2020 , 379 : 117 - 129 .

LI G Y , YANG L , LEE C G , et al . A Bayesian deep learning RUL framework integrating epistemic and aleatoric uncertainties [J]. IEEE Transactions on Industrial Electronics , 2021 , 68 ( 9 ): 8829 - 8841 .

LIN Y H , LI G H . A Bayesian deep learning framework for RUL prediction incorporating uncertainty quantification and calibration [J]. IEEE Transactions on Industrial Informatics , 2022 , 18 ( 10 ): 7274 - 7284 .

陈云翔 , 王泽洲 , 蔡忠义 , 等 . 基于EM-EKF与隐含比例退化模型的机载电子设备剩余寿命自适应预测 [J]. 电子学报 , 2021 , 49 ( 3 ): 500 - 509 .

CHEN Y X , WANG Z Z , CAI Z Y , et al . Adaptive prediction of remaining useful lifetime for the airborne electronic equipment based on the EM-EKF algorithm and hidden degradation model with the proportion relationship [J]. Acta Electronica Sinica , 2021 , 49 ( 3 ): 500 - 509 . (in Chinese)

ELSHEIKH A , YACOUT S , OUALI M S . Bidirectional handshaking LSTM for remaining useful life prediction [J]. Neurocomputing , 2019 , 323 : 148 - 156 .

ZHENG S , RISTOVSKI K , FARAHAT A , et al . Long short-term memory network for remaining useful life estimation [C]// 2017 IEEE International Conference on Prognostics and Health Management (ICPHM) . Piscataway : IEEE , 2017 : 88 - 95 .

SONG S L , COIT D W , FENG Q M . Reliability analysis of multiple-component series systems subject to hard and soft failures with dependent shock effects [J]. IIE Transactions , 2016 , 48 ( 8 ): 720 - 735 .

张正新 , 胡昌华 , 司小胜 , 等 . 双时间尺度下的设备随机退化建模与剩余寿命预测方法 [J]. 自动化学报 , 2017 , 43 ( 10 ): 1789 - 1798 .

ZHANG Z X , HU C H , SI X S , et al . Degradation modeling and remaining useful life prediction with bivariate time scale [J]. Acta Automatica Sinica , 2017 , 43 ( 10 ): 1789 - 1798 . (in Chinese)

PECHT M . CALCE Battery Group[DS/OL] . https://web.calce.umd.edu/batteries/data.htm https://web.calce.umd.edu/batteries/data.htm .

YU Y , HU C H , SI X S , et al . Averaged Bi-LSTM networks for RUL prognostics with non-life-cycle labeled dataset [J]. Neurocomputing , 2020 , 402 : 134 - 147 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

多状态影响下基于Bi‑LSTM网络的锂电池剩余寿命预测方法

多核相关向量机优化模型的锂电池剩余寿命预测方法