基于加速退化数据和现场实测退化数据的电机绝缘剩余寿命预测模型

doi:10.19595/j.cnki.1000-6753.tces.221227

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (2322 KB) HTML
输出: BibTeX | EndNote (RIS)

摘要

该文针对机器学习、随机过程、贝叶斯滤波算法等剩余寿命（RUL）预测模型存在的不足,融合热应力作用下电机绝缘加速寿命数据和现场监测数据,结合随机过程和支持向量机模型,提出了基于拓展卡尔曼滤波的电机绝缘寿命预测模型。以剩余击穿电压为状态变量,基于Wiener过程建立了卡尔曼滤波模型的状态方程;以最大局部放电量的加速退化数据及现场监测数据为依据构建卡尔曼滤波模型的观测方程;为解决卡尔曼滤波模型由于无法获取新的监测信息而导致的预测精度不足问题,采用支持向量机建立了最大局部放电量预测模型。最后,针对电机主绝缘用6650聚酰亚胺,基于290℃、300℃、310℃、320℃下的加速退化数据构建状态方程,结合240℃下试样的局部放电数据构建观测方程,并以240℃下60h的试样实测老化数据为基准对模型进行了验证,证明了所提出模型在提高剩余寿命预测精度方面的有效性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张健
	张钦
	黄晓艳
	方攸同
	田杰

关键词 ：电机绝缘寿命预测, Wiener过程, 拓展卡尔曼滤波, 支持向量机

Abstract：

Insulation system is the weakest part of motor reliability. Monitoring its condition and realizing accurate remaining life prediction is an effective means to ensure the reliability and safety of motor operation. Aiming at the disadvantages of mainstream remaining useful life (RUL) prediction models, including machining learning model, stochastic process model and stochastic filtering model, a motor insulation RUL prediction model based on accelerating degradation data and field state monitoring data under thermal stress, which combines extended Kalman filtering (EKF) with support vector machine(SVM) model and stochastic process model, is proposed. This model is mainly oriented to the RUL prediction problem of motor main insulation with thermal aging as the main failure mode. First, the Arrhenius model is used as the acceleration model, and the mapping relationship between the thermal stress level and the Wiener model drift coefficient and diffusion coefficient is constructed based on the Wiener process. Taking the residual breakdown voltage as the state variable, a prediction model of motor insulation life based on accelerated degradation data under actual working conditions is established, and it is used as the state equation of the Kalman filter model. Secondly, the expression of the maximum partial discharge is deduced by the breakdown voltage estimation equation, and the observation equation of the Kalman filter model is constructed based on the accelerated degradation data of the maximum partial discharge and on-site monitoring data; Then, in order to solve the problem of insufficient prediction accuracy caused by the inability to obtain new monitoring information and the inability to update the covariance matrix of the EKF model in life prediction, this paper takes time as the input variable and the maximum partial discharge as the input variable. Based on the support vector machine, a prediction model of the maximum partial discharge is established to realize the continuous update of the covariance matrix. Finally, for the 6650 polyimide film commonly used in motors, an accelerated degradation test is designed, and the test data of insulation resistance, insulation capacitance, dielectric loss tangent, maximum partial discharge and residual breakdown voltage with aging time are recorded. Based on the accelerated degradation data at 290℃, 300℃, 310℃, and 320℃, the maximum likelihood estimation method is used to construct the state equation. The observation equation was constructed by fusing the accelerated degradation data and the partial discharge data of the material sample at 240℃. The model was verified based on the measured aging data of the sample at 240 °C for 60 hours. The results showed that the model prediction error was within 4%. Then, the prediction accuracy of the EKF model and the stochastic process model were compared, and the comparison results showed that the prediction accuracy of the Kalman filter model was higher, which verifies the effectiveness and engineering application value of the proposed model in improving the remaining life prediction accuracy.

Key words： Motor insulation life prediction Wiener process extended Kalman filter support vector machine

收稿日期: 2022-06-28

PACS:

TM306

基金资助:

国家自然科学基金项目（51977192）和宁波市第一批重大科技攻关暨“揭榜挂帅”项目（20211ZDYF020218）资助

通讯作者: 田杰男,1989年生,博士,研究方向为电力变换装备。E-mail：tianjie_eee_126@126.com

作者简介: 张健男,1980年生,副教授,硕士生导师,研究方向为永磁电机、电机状态监测与智能化故障诊断、面向大数据的装备健康管理等。E-mail：jian_zhang_zju@zju.edu.cn

引用本文:

张健, 张钦, 黄晓艳, 方攸同, 田杰. 基于加速退化数据和现场实测退化数据的电机绝缘剩余寿命预测模型[J]. 电工技术学报, 2023, 38(3): 599-609. Zhang Jian, Zhang Qin, Huang Xiaoyan, Fang Youtong, Tian Jie. Motor Insulation Remaining Useful Life Prediction Method Based on Accelerating Degradation Data and Field Degradation Data. Transactions of China Electrotechnical Society, 2023, 38(3): 599-609.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.221227 https://dgjsxb.ces-transaction.com/CN/Y2023/V38/I3/599

[1] 郑大勇, 张品佳. 交流电机定子绝缘故障诊断与在线监测技术综述[J]. 中国电机工程学报, 2019, 39(2): 395-406, 637.
Zheng Dayong, Zhang Pinjia.A review of fault diagnosis and online condition monitoring of stator insulation in AC electrical machine[J]. Proceedings of the CSEE, 2019, 39(2): 395-406, 637.
[2] 高俊国, 孟睿潇, 胡海涛, 等. 电机定子绝缘老化寿命预测研究进展[J]. 电工技术学报, 2020, 35(14): 3065-3074.
Gao Junguo, Meng Ruixiao, Hu Haitao, et al.Research progress on prediction of aging life of motor stator insulation[J]. Transactions of China Electrotechnical Society, 2020, 35(14): 3065-3074.
[3] 李福兴. 大型发电机定子绝缘诊断和剩余寿命预测[J]. 华东电力, 2004, 32(2): 54-56.
[4] Shinkarenko G V.Determination of the dielectric characteristics of electric equipment insulation in the presence of utility-frequency interference currents[J]. Power Technology and Engineering, 2016, 50(3): 341-346.
[5] Terase H, Hirabayashi S, Hasegawa T, et al. A new AC current testing method for non-destructive insulation tests[J]. IEEE Transactions on Power Apparatus and Systems, 1980, PAS-99(4): 1557-1566.
[6] Kimura K, Kaneda Y, Itoh K.A new approach to breakdown voltage and nondestructive parameters of micaceous insulation systems[C]// Proceedings of the 3rd International Conference on Properties and Applications of Dielectric Materials, Tokyo, Japan, 1991: 769-772.
[7] 胡波, 梁智明, 漆临生, 等. 电极系统对电机定子线棒绝缘介质损耗的影响[J]. 电气技术, 2011, 12(1): 13-17.
Hu Bo, Liang Zhiming, Qi Linsheng, et al.Study on effects of electrode system on dissipation factor of insulation of stator bar in rotating machine[J]. Electrical Engineering, 2011, 12(1): 13-17.
[8] 徐佳宁, 倪裕隆, 朱春波. 基于改进支持向量回归的锂电池剩余寿命预测[J]. 电工技术学报, 2021, 36(17): 3693-3704.
Xu Jianing, Ni Yulong, Zhu Chunbo.Remaining useful life prediction for lithium-ion batteries based on improved support vector regression[J]. Transactions of China Electrotechnical Society, 2021, 36(17): 3693-3704.
[9] 黄凯, 丁恒, 郭永芳, 等. 基于数据预处理和长短期记忆神经网络的锂离子电池寿命预测[J]. 电工技术学报, 2022, 37(15): 3753-3766.
Huang Kai, Ding Heng, Guo Yongfang, et al.Prediction of remaining useful life of lithium-ion battery based on adaptive data preprocessing and long short-term memory network[J]. Transactions of China Electrotechnical Society, 2022, 37(15): 3753-3766.
[10] 王义军, 左雪. 锂离子电池荷电状态估算方法及其应用场景综述[J]. 电力系统自动化, 2022, 46(14): 193-207.
Wang Yijun, Zuo Xue.Review on estimation methods for state of charge of lithium-ion battery and their application scenarios[J]. Automation of Electric Power Systems, 2022, 46(14): 193-207.
[11] 曲正伟, 董一兵, 王云静, 等. 用于电力系统动态状态估计的改进鲁棒无迹卡尔曼滤波算法[J]. 电力系统自动化, 2018, 42(10): 87-92.
Qu Zhengwei, Dong Yibing, Wang Yunjing, et al.Improved robust unscented Kalman filtering algorithm for dynamic state estimation of power systems[J]. Automation of Electric Power Systems, 2018, 42(10): 87-92.
[12] 于永进, 姜雅男, 李长云. 基于鲸鱼优化-长短期记忆网络模型的机-热老化绝缘纸剩余寿命预测方法[J]. 电工技术学报, 2022, 37(12): 3162-3171.
Yu Yongjin, Jiang Yanan, Li Changyun.Prediction method of insulation paper remaining life with mechanical-thermal synergy based on whale optimization algorithm-long-short term memory model[J]. Transactions of China Electrotechnical Society, 2022, 37(12): 3162-3171.
[13] 熊大顺, 李颖晖, 朱喜华, 等. 基于EMD的随机Wiener过程电机剩余寿命预测方法[J]. 微电机, 2013, 46(11): 14-17.
Xiong Dashun, Li Yinghui, Zhu Xihua, et al.Random Wiener process residual life prediction method for motor based on EMD[J]. Micromotors, 2013, 46(11): 14-17.
[14] 刘帼巾, 李想, 王泽, 等. 基于Wiener过程电子式漏电断路器的剩余寿命预测[J]. 电工技术学报, 2022, 37(2): 528-536.
Liu Guojin, Li Xiang, Wang Ze, et al.Remaining life prediction of electronic residual current circuit breaker based on Wiener process[J]. Transactions of China Electrotechnical Society, 2022, 37(2): 528-536.
[15] 刘芳, 马杰, 苏卫星, 等. 基于自适应回归扩展卡尔曼滤波的电动汽车动力电池全生命周期的荷电状态估算方法[J]. 电工技术学报, 2020, 35(4): 698-707.
Liu Fang, Ma Jie, Su Weixing, et al.State of charge estimation method of electric vehicle power battery life cycle based on auto regression extended Kalman filter[J]. Transactions of China Electrotechnical Society, 2020, 35(4): 698-707.
[16] Stone G C, Culbert I, Boulter E A, et al.Electrical insulation for rotating machines-design, evaluation, aging, testing, and repair[M]. 2nd ed. Piscataway: Wiley-IEEE Press, 2014.
[17] Stone G C, Sedding H G, Lloyd B A, et al.The ability of diagnostic tests to estimate the remaining life of stator insulation[J]. IEEE Transactions on Energy Conversion, 1988, 3(4): 833-841.
[18] Pang Zhenan, Si Xiaosheng, Hu Changhua, et al.A Bayesian inference for remaining useful life estimation by fusing accelerated degradation data and condition monitoring data[J]. Reliability Engineering & System Safety, 2021, 208: 107341.
[19] 王浩伟. 加速退化数据建模与统计分析方法及工程应用[M]. 北京: 科学出版社, 2019.
[20] 王浩伟, 周源, 滕飞, 等. 基于加速因子不变原则的加速退化试验优化设计[J]. 机械工程学报, 2018, 54(18): 212-219.
Wang Haowei, Zhou Yuan, Teng Fei, et al.Optimal design of accelerated degradation test based on acceleration factor constant principle[J]. Journal of Mechanical Engineering, 2018, 54(18): 212-219.
[21] 马宏忠. 电机状态监测与故障诊断[M]. 北京: 机械工业出版社, 2008.
[22] 吴崇明, 王晓丹, 白冬婴, 等. 利用KKT条件与类边界包向量的SVM增量学习算法[J]. 计算机工程与设计, 2010, 31(8): 1792-1794, 1798.
Wu Chongming, Wang Xiaodan, Bai Dongying, et al.Fast SVM incremental learning algorithm using KKT conditions and between-class convex hull vectors[J]. Computer Engineering and Design, 2010, 31(8): 1792-1794, 1798.
[23] 刘学艺, 李平, 郜传厚. 极限学习机的快速留一交叉验证算法[J]. 上海交通大学学报, 2011, 45(8): 1140-1145.
Liu Xueyi, Li Ping, Gao Chuanhou.Fast leave-one-out cross-validation algorithm for extreme learning machine[J]. Journal of Shanghai Jiao Tong University, 2011, 45(8): 1140-1145.
[24] 李明干, 孙健利, 刘沛. 基于卡尔曼滤波的电力系统短期负荷预测[J]. 继电器, 2004, 32(4): 9-12.
Li Minggan, Sun Jianli, Liu Pei.Short-term load forecast of power system based on Kalman filter[J]. Relay, 2004, 32(4): 9-12.
[25] 国家质量监督检验检疫总局, 中国国家标准化管理委员会. GB/T 13542.6—2006 电气绝缘用薄膜第6部分:电气绝缘用聚酰亚胺薄膜[S]. 北京: 中国标准出版社, 2006.
[26] 周远翔, 莫雅俊, 刘慧芳, 等. 加速热老化下聚酰亚胺材料力学性能和寿命模型研究[J]. 绝缘材料, 2017, 50(7): 31-35.
Zhou Yuanxiang, Mo Yajun, Liu Huifang, et al.Mechanical properties and life model of polyimide materials under accelerated thermal ageing[J]. Insulating Materials, 2017, 50(7): 31-35.
[27] 赵延召, 陈红生, 朱菲菲, 等. 聚酰亚胺薄膜热老化特性试验与分析[J]. 机械研究与应用, 2015, 28(1): 91-93.
Zhao Yanzhao, Chen Hongsheng, Zhu Feifei, et al.Experimental analysis on thermal aging characteristics of polyimide film[J]. Mechanical Research ＆ Application, 2015, 28(1): 91-93.
[28] 莫雅俊, 张灵, 周远翔, 等. 基于理化分析的热老化聚酰亚胺薄膜的电导特性[J]. 高电压技术, 2019, 45(4): 1241-1248.
Mo Yajun, Zhang Ling, Zhou Yuanxiang, et al.Conduction Current characteristics of thermally aged polyimide films based on physico-chemical analysis[J]. High Voltage Engineering, 2019, 45(4): 1241-1248.
[29] 国家质量监督检验检疫总局, 中国国家标准化管理委员会. GB/T 13542.2—2009 电气绝缘用薄膜第2部分:试验方法[S]. 北京: 中国标准出版社, 2009.
[30] 国家质量监督检验检疫总局. GB/T 7354—2003 局部放电测量[S]. 北京: 中国标准出版社, 2003.
[31] 国家质量监督检验检疫总局, 中国国家标准化管理委员会. GB/T 1408.2—2016 绝缘材料电气强度试验方法第2部分:对应用直流电压试验的附加要求[S]. 北京: 中国标准出版社, 2016.
[32] 朱德恒, 严璋. 高电压绝缘[M]. 北京: 清华大学出版社, 1992.