基于深度学习的冲击电压老炼过程中真空击穿机制甄别优化方法

doi:10.19595/j.cnki.1000-6753.tces.230617

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (3613 KB)
输出: BibTeX | EndNote (RIS)

摘要

冲击电压老炼技术是提高真空电极间隙绝缘能力的有效手段,快速准确地甄别真空击穿机制对揭示冲击电压老炼过程的物理演化机理具有重要意义。该文提出了一种基于深度学习的通过突显击穿前过程提高真空击穿机制甄别准确度的优化方法。对五对相同的无氧铜球形电极开展同样的冲击电压老炼试验,分别获得时间提取范围为0~400 μs的完整击穿电压电流波形样本和0~200 μs的突显击穿前过程的击穿电压电流波形样本,并通过深度学习模型对两种击穿电压电流波形样本开展脉冲电流诱发、场致发射诱发和微粒诱发三种真空击穿机制的甄别训练与测试,并将测试结果与真实结果进行了对比分析与评估。结果显示：时间提取范围为0~200 μs的突显击穿前过程的击穿电压电流波形样本的击穿机制甄别准确度均在87.99%以上,平均提高了2.55%,其对应的精确率、召回率和F1分数均也更优。研究结果表明,突显击穿前过程的击穿电压电流波形处理能够有效地优化真空击穿机制甄别的效果,具有良好的工程应用前景。

	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
	李世民
	徐勋晨
	张潮海

关键词 ：冲击电压老炼, 击穿机制, 深度学习, 突显击穿前过程, 击穿波形

Abstract：

Impulse voltage conditioning technology is an effective means to improve the insulation ability of vacuum circuit breaker (VCB). Classifying the breakdown mechanism quickly and accurately has a great significance to reveal the physical evolution of impulse voltage conditioning and improve the VCB withstanding voltage level. The traditional method to classify the breakdown mechanism needs to eliminate the displacement current through mathematical compensation algorithm and fit the Fowler-Nordheim formula, which is complicated to obtain the breakdown mechanism. Deep learning has an obvious advantage in image recognition and feature extraction. In this paper, an optimized method to classify the breakdown mechanism was proposed through enlarging the pre-breakdown period in breakdown waveform based on deep learning.
Five identical sphere oxygen-free copper electrode pairs A, B, C, D and E were applied the same impulse conditioning. All the breakdown waveforms were processed into two kinds: 0~400 μs, containing the whole breakdown waveform, and 0~200 μs, pre-breakdown period enlarged breakdown waveform. The corresponding breakdown mechanisms of A and B were labeled as pulsed current induced vacuum breakdown (PB), field emission induced vacuum breakdown (FEBD) and particle induced vacuum breakdown (PBD) through the traditional method. Then, breakdown waveforms of A and B (1 530) in 0~400 μs and 0~200 μs were for the breakdown mechanism classification training, and breakdown waveforms of C, D and E (1 398) in 0~400 μs and 0~200 μs were for breakdown mechanism classification test, respectively. The corresponding breakdown mechanisms of C, D and E were classified into PB, FEBD and PBD with deep learning. In addition, the breakdown mechanisms of C, D and E were also obtained through the traditional method. The deep learning outputs were compared with that through the traditional method. The test results were evaluated and analyzed by the evaluation parameters such as precision, recall, F1-score and so on.
The results showed that the breakdown mechanism classification accuracies of C, D and E (0~200 μs) were 88.92%, 87.99% and 92.78%, respectively, and all the accuracies of 0~200 μs were higher than 87.99%. The breakdown mechanism classification accuracies of C, D and E (0~400 μs) were 85.23%, 84.90% and 91.90%, respectively. Compared with 0~400 μs, the breakdown mechanism classification accuracies of 0~200 μs were improved by 3.69%, 3.09% and 0.88%, respectively. The accuracy of 0~200 μs had an average improvement by 2.55% than that of 0~400 μs. Precision, recall and F1-score of 0~200 μs were also higher than those of 0~400 μs. The results showed that 0~200 μs, pre-breakdown period enlarged breakdown waveform had a better performance in breakdown mechanism classification.
Conclusions were drawn as following: (1) The classification accuracy for breakdown mechanism through deep learning could be improved by enlarging the pre-breakdown period in the breakdown waveform. (2) The breakdown mechanism classification can be completed quickly and accurately, whose accuracy could be higher than 87.99% with the effectiveness verified by precision, recall and F1-score. It has a theoretical guidance for a promising conditioning technology to improve the VCB voltage level in industry application.

Key words： Impulse voltage conditioning breakdown mechanism deep learning pre-breakdown period enlarged breakdown waveform

收稿日期: 2023-05-04

PACS:

TM561.2

基金资助:

国家自然科学基金项目（52207162）和江苏省自然科学基金项目（BK20210307）资助

通讯作者: 李世民男,1988年生,讲师,硕士生导师,研究方向高压真空断路器、真空放电与绝缘、深度学习、等离子体模拟等。E-mail：dianqilishimin@163.com

作者简介: 徐勋晨男,2000年生,硕士研究生,研究方向真空击穿与深度学习。E-mail: xuxunchen@nuaa.edu.cn

引用本文:

李世民, 徐勋晨, 张潮海. 基于深度学习的冲击电压老炼过程中真空击穿机制甄别优化方法[J]. 电工技术学报, 0, (): 239627-239627. Li Shimin, Xu Xunchen, Zhang Chaohai. Optimization Method for Classifying Breakdown Mechanism During Impulse Voltage Conditioning Process Based on Deep Learning. Transactions of China Electrotechnical Society, 0, (): 239627-239627.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.230617 https://dgjsxb.ces-transaction.com/CN/Y0/V/I/239627

[1] 李彦飞, 汤贝贝, 韩冬, 等. SF₆放电的发射光谱特性分析与放电识别[J]. 电工技术学报, 2022, 37(7): 1866-1874.
Li Yanfei, Tang Beibei, Han Dong, et al.Spectroscopy analysis of emission spectrum characteristics and discharge recognition of SF₆ gas discharge[J]. Transactions of China Electrotechnical Society, 2022, 37(7): 1866-1874.
[2] 周朕蕊, 韩冬, 赵明月, 等. SF₆替代气体分解特性的研究综述[J]. 电工技术学报, 2020, 35(23): 4998-5014.
Zhou Zhenrui, Han Dong, Zhao Mingyue, et al.Review on decomposition characteristics of SF₆ alternative gases[J]. Transactions of China Electrotechnical Society, 2020, 35(23): 4998-5014.
[3] 李昊天, 曾福平, 颜伊鸣. Ag表面对SF₆初级分解产物氧化反应的影响作用研究[J/OL]. 电工技术学报, 2023: 1-10[2023-07-16]. DOI: 10.19595/j.cnki.1000-6753.tces.230199.
Li Haotian, Zeng Fuping, Yan Yiming. Effect of Ag surface on the oxidation of SF6 primary decomposition products[J/OL]. Transactions of China Electrotechnical Society, 2023: 1-10[2023-07-16]. DOI: 10.19595/j.cnki.1000-6753.tces.230199.
[4] 何彦良, 丁未, 孙安邦, 等. 电场不均匀系数对SF₆/N₂混合气体负直流电晕电流脉冲特性的影响[J]. 电工技术学报, 2021, 36(15): 3124-3134.
He Yanliang, Ding Wei, Sun Anbang, et al.Effect of electric field non-uniformity coefficient on current pulse characteristics of negative DC corona in SF₆/N₂ gas mixtures[J]. Transactions of China Electrotechnical Society, 2021, 36(15): 3124-3134.
[5] 高克利, 颜湘莲, 刘焱, 等. 环保气体绝缘管道技术研究进展[J]. 电工技术学报, 2020, 35(1): 3-20.
Gao Keli, Yan Xianglian, Liu Yan, et al.Progress of technology for environment-friendly gas insulated transmission line[J]. Transactions of China Electrotechnical Society, 2020, 35(1): 3-20.
[6] 张晓星, 陈琪, 张季, 等. 高气压下环保型C₄F₇N/CO₂混合气体工频击穿特性[J]. 电工技术学报, 2019, 34(13): 2839-2845.
Zhang Xiaoxing, Chen Qi, Zhang Ji, et al.Power frequency breakdown characteristics of environmental-friendly C₄F₇N/CO₂ gas mixtures under high pressure conditions[J]. Transactions of China Electrotechnical Society, 2019, 34(13): 2839-2845.
[7] 王宝山, 余小娟, 侯华, 等. 六氟化硫绝缘替代气体的构效关系与分子设计技术现状及发展[J]. 电工技术学报, 2020, 35(1): 21-33.
Wang Baoshan, Yu Xiaojuan, Hou Hua, et al.Review on the developments of structure-activity relationship and molecular design of the replacement dielectric gases for SF₆[J]. Transactions of China Electrotechnical Society, 2020, 35(1): 21-33.
[8] 张晓星, 田双双, 肖淞, 等. SF₆替代气体研究现状综述[J]. 电工技术学报, 2018, 33(12): 2883-2893.
Zhang Xiaoxing, Tian Shuangshuang, Xiao Song, et al.A review study of SF₆ substitute gases[J]. Transactions of China Electrotechnical Society, 2018, 33(12): 2883-2893.
[9] 张晓星, 王宇非, 崔兆仑, 等. 不同填充材料对介质阻挡放电降解SF₆的实验研究[J]. 电工技术学报, 2021, 36(2): 397-406.
Zhang Xiaoxing, Wang Yufei, Cui Zhaolun, et al.Experimental study on the degradation of SF₆ by dielectric barrier discharge with different packing materials[J]. Transactions of China Electrotechnical Society, 2021, 36(2): 397-406.
[10] 程显, 杜帅, 葛国伟, 等. 环保型罐式多断口真空断路器均压配置研究[J]. 电工技术学报, 2021, 36(15): 3154-3162.
Cheng Xian, Du Shuai, Ge Guowei, et al.Study on voltage-sharing configuration of environment-friendly tank type multi-break vacuum circuit breakers[J]. Transactions of China Electrotechnical Society, 2021, 36(15): 3154-3162.
[11] 邹积岩, 刘晓明, 于德恩. 基于智能模块的高压直流真空断路器研究[J]. 电工技术学报, 2015, 30(13): 47-55.
Zou Jiyan, Liu Xiaoming, Yu Deen.Investigations on the HVDC vacuum circuit breaker based on intelligent models[J]. Transactions of China Electrotechnical Society, 2015, 30(13): 47-55.
[12] 王季梅. 真空开关的现状及发展趋势[J]. 电力设备, 2005(2): 1-5.
Wang Jimei.Present situation and development tendency of vacuum switch[J]. Electrical Equipment, 2005(2): 1-5.
[13] 王季梅, 钱予圭. 论高压真空灭弧室和真空断路器的产品开发[J]. 高压电器, 2003, 39(1): 65-67.
Wang Jimei, Qian Yugui.Discussion on the product development of high voltage vacuum interrupters and vacuum circuit breakers[J]. High Voltage Apparatus, 2003, 39(1): 65-67.
[14] 何俊佳, 邹积岩, 张汉明, 等. 火花老炼对真空灭弧室绝缘强度的影响[J]. 电工技术学报, 1997, 12(3): 33-36.
He Junjia, Zou Jiyan, Zhang Hanming, et al.Effect of spark conditioning treatment on electrical strength of vacuum interrupters[J]. Transactions of China Electrotechnical Society, 1997, 12(3): 33-36.
[15] Fukuoka Y, Yasuoka T, Kato K, et al.Breakdown conditioning characteristics of long gap electrodes in a vacuum[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2007, 14(3): 577-582.
[16] Li Shimin, Yamano Y, Geng Yingsan, et al.Conditioning saturation diagnosis with breakdown electric field and breakdown time in vacuum[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2023, 30(2): 862-868.
[17] Li Shimin, Yang Wei, Jiang Xixi, et al.Breakdown time characteristics under uniform electric field in vacuum[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2022, 29(1): 193-198.
[18] Okubo H, Yasuoka T, Kato T, et al.Electrode conditioning mechanism based on pre-breakdown current under non-uniform electric field in vacuum[C]//2008 23rd International Symposium on Discharges and Electrical Insulation in Vacuum, Bucharest, Romania, 2008: 13-16.
[19] Kojima H, Hayakawa N, Nishimura R, et al.Conditioning mechanism of Cu-Cr electrode based on electrode surface state under impulse voltage application in vacuum[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2011, 18(6): 2108-2114.
[20] Kato K, Fukuoka Y, Saitoh H, et al.Effect of electrode surface roughness on breakdown conditioning under non-uniform electric field in vacuum[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2007, 14(3): 538-543.
[21] 李世民, 江希茜, 李镇廷, 等.脉冲电压老炼过程中真空击穿机制演化机理[J/OL]. 高电压技术, 2022: 1-9[2022-10-20]. DOI:10.13336/j.1003-6520.hve.20221211.
Li Shimin, Jiang Xixi, Li Zhenting, et al. Evolution mechanism of vacuum breakdown mechanism during pulse voltage aging process[J/OL]. High Voltage Engineering, 2022: 1-9[2022-10-20]. DOI:10.13336/j.1003-6520.hve.20221211.
[22] Li Shimin, Geng Yingsan, Liu Zhiyuan, et al.Discharge and breakdown mechanism transition in the conditioning process between plane-plane copper electrodes in vacuum[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2019, 26(2): 539-546.
[23] 王建华, 耿英三, 刘志远. 输电等级单断口真空断路器理论及其技术[M]. 北京: 机械工业出版社, 2017.
[24] Li Shimin, Yamano Y, Geng Yingsan, et al.Gas desorption induced discharge in vacuum and its polarity effect[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2020, 27(3): 799-805.
[25] Li Shimin, Yamano Y, Geng Yingsan, et al.Polarity effect of impulse conditioning characteristics under a uniform electric field in vacuum[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2021, 28(3): 838-844.
[26] 王卓, 王玉静, 王庆岩, 等. 基于协同深度学习的二阶段绝缘子故障检测方法[J]. 电工技术学报, 2021, 36(17): 3594-3604.
Wang Zhuo, Wang Yujing, Wang Qingyan, et al.Two stage insulator fault detection method based on collaborative deep learning[J]. Transactions of China Electrotechnical Society, 2021, 36(17): 3594-3604.
[27] 徐建军, 黄立达, 闫丽梅, 等. 基于层次多任务深度学习的绝缘子自爆缺陷检测[J]. 电工技术学报, 2021, 36(7): 1407-1415.
Xu Jianjun, Huang Lida, Yan Limei, et al.Insulator self-explosion defect detection based on hierarchical multi-task deep learning[J]. Transactions of China Electrotechnical Society, 2021, 36(7): 1407-1415.
[28] 王晓辉, 朱永利, 王艳, 等. 基于深度学习的电容器介损角在线辨识[J]. 电工技术学报, 2017, 32(15): 145-152.
Wang Xiaohui, Zhu Yongli, Wang Yan, et al.Online identification method of power capacitor dielectric loss angle based on deep learning[J]. Transactions of China Electrotechnical Society, 2017, 32(15): 145-152.
[29] 赵书涛, 徐晓会, 尹子会, 等. 基于深度学习断路器储能机构故障诊断方法研究[J]. 高压电器, 2022, 58(10): 25-32.
Zhao Shutao, Xu Xiaohui, Yin Zihui, et al.Research on fault diagnosis method of charging operating mechanism of circuit breaker based on deep learning[J]. High Voltage Apparatus, 2022, 58(10): 25-32.
[30] 周秀, 朱洪波, 马云龙, 等. 基于深度学习的变压器局部放电模式识别研究[J]. 高压电器, 2019, 55(12): 98-105.
Zhou Xiu, Zhu Hongbo, Ma Yunlong, et al.Partial discharge pattern recognition of transformer based on deep learning[J]. High Voltage Apparatus, 2019, 55(12): 98-105.
[31] Li Shimin, Jiang Xixi, Xu Xunchen, et al. Classification of vacuum breakdown during conditioning based on deep learning[J/OL]. IEEE Transactions on Dielectrics and Electrical Insulation, 2023: 1-7[2023-04-10]. DOI:10.1109/TDEI.2023.3264728.