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

doi:10.19595/j.cnki.1000-6753.tces.210110

Abstract
Figure/Table
References
Related Citation (11)

Download: PDF (1857 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract As the key equipment in the UHV DC transmission system, remaining life prediction of insulation paper for transformers can provide a reference for the operation and maintenance of converter transformers. Therefore, a prediction method based on whale optimization algorithm (WOA) and long-short term memory (LSTM) was proposed. Firstly, combined with the accelerated mechanical- thermal aging test of insulation paper, the multi-feature fusion of the aging characterization parameters, including degree of polymerization, furfural content, and dielectric dissipation factors at different characteristic frequencies, was carried out by the principal component analysis (PCA) method. The quantitative expression between the comprehensive evaluation index and the tensile strength of insulation paper was obtained, and then the tensile strengths corresponding to the excellent insulation performance and the serious deterioration condition were taken as the positive and negative ideal values respectively. In combination with the proximity, constructing the degradation index sequence as model input, the remaining life prediction of insulation paper is realized. Next, WOA is used to optimize the relevant super parameters in the LSTM. Finally, a WOA-LSTM model is constructed to predict insulation paper remaining life. The results show that the WOA-LSTM model proposed not only incorporates multiple feature quantities that can characterize the aging state of insulation paper, but also significantly improves the prediction accuracy, which can provide a strong guarantee for the safe and stable operation of the insulation system of converter transformers.

Key words： Whale optimization long-short term memory mechanical-thermal synergy multi- feature fusion remain life prediction

Received: 21 January 2021

PACS:

TM85

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors

Cite this article:

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.210110 OR https://dgjsxb.ces-transaction.com/EN/Y2022/V37/I12/3162

[1] 杜伯学, 朱闻博, 李进, 等. 换流变压器阀侧套管油纸绝缘研究现状[J]. 电工技术学报, 2019, 34(6): 1301-1309.
Du Boxue, Zhu Wenbo, Li Jin, et al.Research status of oil-paper insulation for valve side bushing of con-verter transformer[J]. Transactions of China Electro-technical Society, 2019, 34(6): 1301-1309.
[2] 邹阳, 何倩玲, 蔡金锭, 等. 基于组合赋权-双基点法的变压器油纸绝缘状态综合评估[J]. 电工技术学报, 2019, 34(20): 4400-4408.
Zou Yang, He Qianling, Cai Jinding, et al.Com-prehensive evaluation of transformer oil-paper state based on combined weight-double base point method[J]. Transactions of China Electrotechnical Society, 2019, 34(20): 4400-4408.
[3] 李长云, 郝爱东, 娄禹. 直流偏磁条件下电力变压器振动特性研究进展[J]. 电力自动化设备, 2018, 38(6): 215-223.
Li Changyun, Hao Aidong, Lou Yu.Status and progress of research on transformer vibration charac-teristics with DC bias[J]. Electric Power Automation Equipment, 2018, 38(6): 215-223.
[4] 李长云, 刘亚魁. 直流偏磁条件下变压器铁芯磁化特性的Jiles-Atherton修正模型[J]. 电工技术学报, 2017, 32(19): 193-201.
Li Changyun, Liu Yakui.Modified Jiles-Atherton model of transformer iron core magnetization charac-teristics with DC bias[J]. Transactions of China Electrotechnical Society, 2017, 32(19): 193-201.
[5] 李京峰, 陈云翔, 项华春, 等. 基于LSTM-DBN的航空发动机剩余寿命预测[J]. 系统工程与电子技术, 2020, 42(7): 1637-1644.
Li Jingfeng, Chen Yunxiang, Xiang Huachun, et al.Remaining useful life prediction for aircraft engine based on LSTM-DBN[J]. Systems Engineering and Electronics, 2020, 42(7): 1637-1644.
[6] 张明泽, 刘骥, 陈昕, 等. 基于Wiener模型的变压器油纸绝缘老化剩余寿命评估方法[J]. 电工技术学报, 2018, 33(21): 5098-5108.
Zhang Mingze, Liu Ji, Chen Xin, et al.Residual life assessment method of transformer oil-paper insulation aging based on Wiener model[J]. Transactions of China Electrotechnical Society, 2018, 33(21): 5098-5108.
[7] 史华洁, 薛颂东. 退化数据驱动的设备剩余寿命在线预测[J]. 计算机工程与应用, 2016, 52(23): 249-254.
Shi Huajie, Xue Songdong.Degradation data driven online prediction for equipment residual life[J]. Com-puter Engineering and Applications, 2016, 52(23): 249-254.
[8] 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.
[9] Zheng Shuai, Ristovski K, Farahat A, et al.Long shortterm memory network for remaining useful life estimation[C]//IEEE International Conference on Pro-gnostics and Health Management, Harbin, China, 2017: 88-95.
[10] 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(7): 57-70.
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(7): 57-70.
[11] Xie Peng.Analysis of fault of insulation aging of oiled paper of a large-scale power transformer and the prediction of its service life[J]. IEEE Transactions on Electrical and Electronic Engineering, 2019, 14(8): 1139-1144.
[12] 王智越. 基于PCA与层次分析法的电力变压器健康状态评估方法研究[D]. 郑州: 华北水利水电大学, 2020.
[13] 唐成顺, 孙丹, 唐威, 等. 基于LSTM循环神经网络的汽轮机转子表面应力预测模型[J]. 中国电机工程学报, 2021, 41(2): 451-461.
Tang Chengshun, Sun Dan, Tang Wei, et al.A turbine rotor surface stress prediction model based on LSTM recurrent neural network[J]. Proceedings of the CSEE, 2021, 41(2): 451-461.
[14] 武大硕, 张传雷, 陈佳, 等. 基于遗传算法改进LSTM神经网络股指预测分析[J]. 计算机应用研究, 2020, 37(增刊1): 86-88, 107.
Wu Dashuo, Zhang Chuanlei, Chen Jia, et al.Improved LSTM stock index forecast analysis based on genetic algorithm[J]. Application Research of Computers, 2020, 37(S1): 86-88, 107.
[15] 刘可真, 苟家萁, 骆钊, 等. 基于粒子群优化-长短期记忆网络模型的变压器油中溶解气体浓度预测方法[J]. 电网技术, 2020, 44(7): 2278-2785.
Liu Kezhen, Gou Jiaqi, Luo Zhao, et al.Prediction method of dissolved gas concentration in transformer oil based on PSO-LSTM model[J]. Power System Technology, 2020, 44(7): 2278-2785.
[16] Prakash D B, Lakshminarayana C.Optimal siting of capacitors in radial distribution network using whale optimization algorithm[J]. Alexandria Engineering Journal, 2017, 56(4): 499-509.
[17] 詹怀宇. 纤维化学与物理[M]. 北京: 科学出版社, 2005.
[18] 赵彤, 石雷, 张远涛, 等. 基于分子模拟的绝缘纸高温裂解过程水分产生及其破坏作用研究[J]. 中国电机工程学报, 2017, 37(15): 4548-4567.
Zhao Tong, Shi Lei, Zhang Yuantao, et al.Study on H₂O formation during the pyrolysis of insulating paper and its destructive effect based on molecular simulation[J]. Proceedings of the CSEE, 2017, 37(15): 4548-4567.
[19] Ding Hongzhi, Wang Zhongdong.On the degradation evolution equations of cellulose[J]. Cellulose, 2008, 15(1): 205-224.
[20] 李长云, 郝爱东. 机-热协同老化对纤维素绝缘纸频域介电谱的影响[J]. 电工技术学报, 2019, 34(17): 3705-3712.
Li Changyun, Hao Aidong.Influence of the mechanical-thermal aging on the frequency-domain dielectric spectroscopy of cellulose insulation paper[J]. Transa-ctions of China Electrotechnical Society, 2019, 34(17): 3705-3712.
[21] Lin Yuandi, Yang Lijun, Liao Ruijin, et al.Effect of oil replacement on furfural analysis and aging assessment of power transformers[J]. IEEE Transa-ctions on Dielectrics and Electrical Insulation, 2015, 22(5): 2611-2619.
[22] Hill D, Darveniza M, Saha T, et al.A study of degradation of cellulosic insulation materials in a power transformer. part 2: tensile strength of cellulose insulation paper[J]. Polymer Degradation and Stability, 1995, 49(3): 429-435.
[23] 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]. Transa-ctions of China Electrotechnical Society, 2021, 36(17): 3693-3704.
[24] 肖伊, 李庆民. 基于多特征参量的油纸绝缘老化状态定量表征方法[J]. 绝缘材料, 2019, 52(8): 54-59.
Xiao Yi, Li Qingmin.Quantitative characterization method of oil-paper insulation ageing condition based on multi-characteristic parameters[J]. Insulation Materials, 2019, 52(8): 54-59.
[25] Shen Hongtao, Tao Peng, Zhao Pei, et al.Massive power device condition monitoring data feature extraction and clustering analysis using MapReduce and graph model[J]. CES Transactions on Electrical Machines and Systems, 2019, 3(2): 221-230.
[26] 李长云, 王铮. 机-热协同作用下绝缘纸机械性能的劣化机理[J]. 电工技术学报, 2018, 33(21): 5090-5097.
Li Changyun, Wang Zheng.The degradation mechanism of insulation paper mechanical properties with mechanical-thermal synergy[J]. Transactions of China Electrotechnical Society, 2018, 33(21): 5090-5097.
[27] 肖迁, 焦志鹏, 穆云飞, 等. 基于LightGBM的电动汽车形式工况下电池剩余使用寿命预测[J]. 电工技术学报, 2021, 36(24): 5176-5185.
Xiao Qian, Jiao Zhipeng, Mu Yunfei, et al.LightGBM based remaining useful life prediction of electric vehicle lithium-ion battery under dring conditions[J]. Transa-ctions of China Electrotechnical Society, 2021, 36(24): 5176-5185.