基于深度学习的继电器剩余使用寿命预测研究综述

doi:10.16628/j.cnki.2095-8188.2023.10.001

摘要/Abstract

摘要：

研究继电器个体的可靠性具有重要意义,有必要对继电器进行寿命预测。由于传统预测方法的建模过分依赖于设备的领域知识,故将深度学习应用于寿命预测领域。首先概述了继电器的贮存失效机理,其次介绍了继电器剩余使用寿命预测的研究现状,接着分析了深度学习的几种常见模型方法及其特点,最后对深度学习应用于剩余使用寿命预测进行展望。

关键词: 继电器, 可靠性, 寿命预测, 深度学习

Abstract:

Studying the reliability of individual relays is of great significance. Therefore, it is necessary to predict the lifespan of relays. Due to the excessive reliance of traditional prediction methods on the equipment domain knowledge, the deep learning is applied to the field of life prediction. Firstly, the storage failure mechanism of relays is summarized. Secondly, the current research status of relay remaining useful life prediction is introduced. Then, several common model methods and their characteristics of deep learning are analyzed. Finally, the application of deep learning in the remaining useful life prediction is prospected.

Key words: relay, reliability, life prediction, deep learning

中图分类号:

TM581

李少飞, 王召斌, 张文行. 基于深度学习的继电器剩余使用寿命预测研究综述[J]. 电器与能效管理技术, 2023, 0(10): 1-7.

LI Shaofei, WANG Zhaobin, ZHANG Wenhang. Review of Research on Remaining Useful Life Prediction of Relays Based on Deep Learning[J]. LOW VOLTAGE APPARATUS, 2023, 0(10): 1-7.

图/表 5

参考文献 38

[1]	陆俭国, 王景芹, 陆宾. 电器可靠性工作概况与发展前景[J]. 低压电器, 2014(2):1-7.
[2]	余琼, 任立, 翟国富. 航天继电器寿命试验技术的探讨[J]. 低压电器, 2008(21):60-62,65.
[3]	乔维德. 电磁继电器剩余电寿命智能预测研究[J]. 电工电气, 2020(12):30-34.
[4]	刘百鑫, 王召斌, 乔青云, 等. 基于深度学习的继电器寿命预测方法研究综述[J]. 电器与能效管理技术, 2021(12):1-6,33.
[5]	刘惠, 刘振宇, 郏维强, 等. 深度学习在装备剩余使用寿命预测技术中的研究现状与挑战[J]. 计算机集成制造系统, 2021, 27(1):34-52.
[6]	马东娟. 基于数据驱动的电器产品寿命预测方法研究[D]. 天津: 河北工业大学, 2016.
[7]	许丽佳. 电子系统的故障预测与健康管理技术研究[D]. 西安: 电子科技大学, 2009.
[8]	李久鑫, 王召斌, 朱佳淼. 继电器贮存可靠性研究方法综述[J]. 电器与能效管理技术, 2022(6):1-5,31.
[9]	乔青云, 王召斌, 陈康宁, 等. 继电器贮存可靠性分析和加速退化试验综述[J]. 电器与能效管理技术, 2022(1):1-6.
[10]	孙训俊. 电器产品贮存寿命分析方法的研究[D]. 天津: 河北工业大学, 2014.
[11]	王召斌, 蔡昭文, 翟国富, 等. 航天继电器加速贮存退化可靠性建模和统计分析[J]. 低压电器, 2012(17):1-7.
[12]	苗建伟, 王文军, 李斌. 低压继电器寿命的智能预测分析[J]. 电器与能效管理技术, 2018(4):61-65.
[13]	PARIS P, ERDOGAN F. A critical Analysis of Crack Propagation Laws[J]. Journal of Basic Engineering, 1963, 85(4):528-533. doi: 10.1115/1.3656900
[14]	季文强. 基于深度学习和不确定性量化的数据驱动剩余寿命预测方法研究[D]. 合肥: 中国科学技术大学, 2020.
[15]	WANG Z Q, HU C H, FAN H D. Real-time remaining useful life prediction for a nonlinear degrading system in service:application to bearing data[J]. IEEE/ASME Transactions on Mechatronics, 2018, 23(1):211-222. doi: 10.1109/TMECH.3516
[16]	PANDEY M D, YUAN X X, VAN NOORTWIJK J M. The influence of temporal uncertainty of deterioration on life-cycle management of structures[J]. Structure & Infrastructure Engineering, 2009, 5(2):145-156.
[17]	KHAROUFEH J P. Explicit results for wear processes in a Markovian environment[J]. Operations Research Letters, 2003, 31(3):237-244. doi: 10.1016/S0167-6377(02)00229-8
[18]	GEBRAEEL N Z, LAWLEY M A, RONG L I. Residual-life distributions from component degradation signals:A Bayesian approach[J]. IIE Transactions, 2005, 37(6):543-557. doi: 10.1080/07408170590929018
[19]	李雅. 基于数据驱动的航空发动机剩余寿命预测研究[D]. 郑州: 河南大学, 2022.
[20]	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. doi: 10.3901/JME.2019.08.001
[21]	SIKORSKA J Z, HODKIEWICZ M, MA L. Prognostic modelling options for remaining useful life estimation by industry[J]. Mechanical Systems & Signal Processing, 2011, 25(5):1803-1836.
[22]	LIAO H, TIAN Z. A framework for predicting the remaining useful life of a single unit under time-varying operating conditions[J]. IIE Transactions, 2013, 45(9):964-980. doi: 10.1080/0740817X.2012.705451
[23]	WANG W B, CARR M, XU W J, et al. A model for residual life prediction based on Brownian motion with an adaptive drift[J]. Microelectronics and reliability, 2011, 51(1):285-293. doi: 10.1016/j.microrel.2010.09.013
[24]	BEZAZI A, PIERCE S G, WORDEN K. Fatigue life prediction of sandwich composite materials under flexural tests using a Bayesian trained artificial neural network[J]. International Journal of Fatigue, 2007, 29(4):738-747. doi: 10.1016/j.ijfatigue.2006.06.013
[25]	PIERCE S G, WORDEN K, BEZAZI A. Uncertainty analysis of a neural network used for fatigue lifetime prediction[J]. Mechanical Systems and Signal Processing, 2008, 22(6):1395-1411. doi: 10.1016/j.ymssp.2007.12.004
[26]	MITRENTSIS G, LENS H. Data-driven dynamic models of active distribution networks using unsupervised learning techniques on field measurements[J]. IEEE Transactions on Smart Grid, 2021, 12(4):2952-2965. doi: 10.1109/TSG.2021.3057763
[27]	BAO Y, TANG Z, LI H, et al. Computer vision and deep learning-based data anomaly detection method for structural health monitoring[J]. Structural Health Monitoring, 2019, 18(2):401-421. doi: 10.1177/1475921718757405
[28]	HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science (New York,N.Y.), 2006, 313(5786):504-507. doi: 10.1126/science.1127647
[29]	刘嘉. 多目标演化深度神经网络模型与应用[D]. 西安: 西安电子科技大学, 2019.
[30]	BABU G S, ZHAO P, LI X L. Deep convolutional neural network based regression approach for estimation of remaining useful life[C]// International Conference on Database Systems for Advanced Applications, 2016.
[31]	崔和臣. 交流接触器电寿命预测的深度学习模型及实验[D]. 温州: 温州大学, 2019.
[32]	曹宇. 基于深度循环网络的舰船位置预测方法研究[D]. 南京: 南京邮电大学, 2022.
[33]	张露, 颜宏文, 马瑞. 基于改进DBSCAN-RNN的电力负荷建模及可调特征提取[J]. 智慧电力, 2023, 51(3):39-45..
[34]	HOCHREITER S, SCHMIDHVBE R. LSTM can solve hard long time lag problems[C]// Advances in Newral Information Processing System 9, 1996:473-479.
[35]	韩忠华, 黎恺嘉, 陈赵琦, 等. 改进的门控循环单元模型研究与应用[J]. 计算机仿真, 2022, 39(12):429-435,541.
[36]	MUGHEE N, MOHSIN S A, MUGHEES A, et al. Deep sequence to sequence Bi-LSTM neural networks for day-ahead peak load forecasting[J]. Expert Systems with Applications, 2021, 175:114844. doi: 10.1016/j.eswa.2021.114844
[37]	高士珍. 基于深度学习的交流接触器剩余寿命预测研究[D]. 沈阳: 沈阳工业大学, 2022.
[38]	陈自强. 基于LSTM网络的设备健康状况评估与剩余寿命预测方法的研究[D]. 合肥: 中国科学技术大学, 2019.