基于微型气体传感阵列的空气绝缘设备放电故障识别方法

doi:10.19595/j.cnki.1000-6753.tces.L10079

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1862 KB)
输出: BibTeX | EndNote (RIS)

摘要

空气作为一种天然的绝缘气体,在电力设备中（开关柜、环网柜等）被广泛应用。研究表明,当电力设备发生放电故障时,空气绝缘介质会产生以NO₂为代表的特征分解产物。放电分解产物的组分及含量能够反映放电故障的严重程度。因此,气体分解产物检测对电力系统安全稳定运行具有重要意义。在不同的电压等级、持续时间下,该文分别模拟了包括电晕放电、火花放电、以及电弧放电在内的15种空气放电故障,并发现NO₂气体的含量在不同故障条件下存在显著差异。对此,设计了一款装载有四种对NO₂气体具有高度选择性气敏材料的微型气体传感阵列。经多次实验测试,传感阵列对15种放电故障气体表现出差异性响应信号,构成丰富的样本数据集。分别采用四种机器学习算法（极限树、决策树、K邻近和随机森林）实现基于传感信号的空气放电故障识别,发现其平均准确率最高可达84.88%、81.82%、76.86%和81.32%。其中,传感阵列对局部放电和电弧放电的识别能力略高于火花放电,可以归因于多次火花放电过程中存在一定的NO₂饱和现象。综上所述,该文提出的基于微型气体传感阵列的检测方法具有操作简单,识别准确率高的显著优势,在空气放电故障诊断领域具有广阔的应用前景。

	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
	王琼苑
	褚继峰
	李秋霖
	杨爱军
	袁欢
	荣命哲
	王小华

关键词 ：空气绝缘, 放电故障模拟, NO₂检测, 微型传感阵列, 故障诊断

Abstract：

As a natural insulating gas, air is widely used in power equipment (switchgear, ring cabinets, etc.). It will produce characteristic decomposition products represented by NO₂ when the power equipment occurs internal faults. The content of composition reflects the severity of the discharge fault. Therefore, the detection of gas decomposition products is helpful to the stable operation of power equipment. The cross-sensitivity of the sensor materials towards NO₂ and CO have seriously restricted the accuracy of fault diagnosis. To address these issues, this paper develops a miniature gas-sensing array with high sensitivity and great reliability, which aimed for the discharge fault diagnosis of air-insulated equipment.
This paper has simulated 15 air discharge faults including corona discharge, spark discharge, and arc discharge at different voltage levels and durations. After that, Fourier infrared tests were performed on the 15 gas samples. However, there has no apparent absorption peak of CO and O₃ in the infrared absorption spectrum. The absorption peak in 1 650~1 550 cm^-1 band corresponds to the antisymmetric stretching vibration of O=N=O chemical bond. This indicates the presence of NO₂ in the decomposition products of air. Besides, discharge with different voltages and times shows significant differences in the content of NO₂.
To discriminate fault characteristic gases, this paper has integrated a micro sensor array loaded with four gas-sensitive nanomaterials (10%WO₃-10%SnCl₂-In₂O₃, 5%NiO-10%SnCl₂-In₂O₃, 10%TiO₂-10%SnCl₂-In₂O₃ and 5%SnO₂-10%SnCl₂- In₂O₃). Then the paper obtains the repeatable gas response recovery curves under different discharge faults, which lays the foundation for the construction of gas identification model. The results demonstrate that the higher voltage and the longer discharge time means the larger response value of sensor array. Accordingly, it is further proved that the higher air-discharge voltages and times generates more characteristic decomposition gas. In addition, t-SNE dimensionality reduction has been employed to explore the identification ability of miniature gas-sensing array. The identification results of different air discharge faults are 84.88%, 81.82%, 76.86%, and 81.32% by four machine learning algorithms (Extra Tree, Decision Tree, KNN, and RF) respectively. And the recognition ability of the micro gas sensing array for partial discharge and arc discharge is slightly higher than that of spark discharge. The essential reason can be ascribed to the saturation of NO₂ in the process of multiple spark discharges.
The following conclusions can be drawn from the simulation analysis: (1) The FTIR of air discharge products shows that the arc discharge (200~400 μL/L) produces more NO₂ than corona and spark discharge (10~50 μL/L). Besides, the NO₂ concentration increases with the increase of discharge voltage and discharge time (times). (2) Compared with corona and spark discharge, the response value of the micro sensor array towards arc discharge products (6 kV, 4 033%) is nearly 3 times higher than that of spark discharge (15 kV, 5 times, 1 142.8%). (3) After the feature reduction of 10-dimensional PCA, we compared four machine learning algorithms, and found that the Extra Tree algorithm obtained the best identification accuracy of air discharge fault (84.88%).

Key words： Air insulation discharge simulation NO₂ detection micro sensor array fault diagnosis

收稿日期: 2023-01-13

PACS:

TM930

基金资助:

国家自然科学基金（U2166214, 52207170）、中国博士后科学基金（2022M712510, 2022TQ0252）和西安交通大学分析测试共享中心资助项目

通讯作者: 杨爱军男,1986年生,教授,博士生导师,研究方向为微纳传感器、能量收集、人工智能技术。E-mail：yangaijun@mail.xjtu.edu.cn

作者简介: 王琼苑女,1998年生,博士研究生,研究方向为电力装备智能感知与运行维护。E-mail：wqy13994558885@stu.xjtu.edu.cn

引用本文:

王琼苑, 褚继峰, 李秋霖, 杨爱军, 袁欢, 荣命哲, 王小华. 基于微型气体传感阵列的空气绝缘设备放电故障识别方法[J]. 电工技术学报, 0, (): 149-149. Wang Qiongyuan, Chu Jifeng, Li Qiulin, Yang Aijun, Yuan Huan, Rong Mingzhe, Wang Xiaohua. Miniature Gas-sensing Array Employed for the Discharge Fault Diagnosis of Air-insulated Equipment. Transactions of China Electrotechnical Society, 0, (): 149-149.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.L10079 https://dgjsxb.ces-transaction.com/CN/Y0/V/I/149

[1] Chu Jifeng, Li Weijuan, Yang Xu, et al.Identification of gas mixtures via sensor array combining with neural networks[J]. Sensors and Actuators B: Chemical, 2021, 329: 129090.
[2] 林涛, 韩冬, 钟海峰, 等. 工频交流电晕放电下SF₆气体分解物形成的影响因素[J]. 电工技术学报, 2014, 29(2): 219-225.
Lin Tao, Han Dong, Zhong Haifeng, et al.Influence factors of formation of decomposition by-products of SF₆ in 50Hz AC corona discharge[J]. Transactions of China Electrotechnical Society, 2014, 29(2): 219-225.
[3] 李进, 赵仁勇, 杜伯学, 等. 电工环氧绝缘件缺陷无损检测方法研究进展[J]. 电工技术学报, 2021, 36(21): 4598-4607.
Li Jin, Zhao Renyong, Du Boxue, et al.Research progress of nondestructive detection methods for defects of electrical epoxy insulators[J]. Transactions of China Electrotechnical Society, 2021, 36(21): 4598-4607.
[4] Zhang Xiaoxing, Li Yi, Tian Shuangshuang, et al.Decomposition mechanism of the C5-PFK/CO₂ gas mixture as an alternative gas for SF₆[J]. Chemical Engineering Journal, 2018, 336: 38-46.
[5] Zhang Xiaoxing, Gui Yingang, Zhang Ying, et al.Influence of humidity and voltage on characteristic decomposition components under needle-plate discharge model[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2016, 23(5): 2633-2640.
[6] Chu Jifeng, Wang Qiongyuan, Liu Yuyang, et al.Fault diagnosis of SF₆-insulated equipment by micro gas sensor array[J]. IEEE Transactions on Power Delivery, 2023, 38(1): 222-230.
[7] Li Yi, Zhang Xiaoxing, Zhang Ji, et al.Assessment on the toxicity and application risk of C₄F₇N: a new SF₆ alternative gas[J]. Journal of Hazardous Materials, 2019, 368: 653-660.
[8] 李康, 郭润睿, Hassan Javed, 等. 空气局部放电衍生物气体生成规律的研究[J]. 电工电能新技术, 2017, 36(8): 1-7.
Li Kang, Guo Runrui, Javed H, et al.Study of air by-products formation characteristics under corona discharge[J]. Advanced Technology of Electrical Engineering and Energy, 2017, 36(8): 1-7.
[9] 张振宇, 晋涛, 王天正, 等. 基于气体检测的空气开关柜绝缘缺陷识别[J]. 武汉大学学报(工学版), 2021, 54(8): 761-768.
Zhang Zhenyu, Jin Tao, Wang Tianzheng, et al.Insulation defect recognition of air switchgear based on gas detection[J]. Engineering Journal of Wuhan University, 2021, 54(8): 761-768.
[10] 张晓星, 周磊, 裘吟君, 等. 针-板缺陷开关柜局部放电与空气分解组分的关联特性[J]. 高电压技术, 2016, 42(12): 3948-3954.
Zhang Xiaoxing, Zhou Lei, Qiu Yinjun, et al.Correlation character between switch gear’s partial discharge quantity and air decomposition components under needle-plate defect model[J]. High Voltage Engineering, 2016, 42(12): 3948-3954.
[11] Tang Ju, Zeng Fuping, Zhang Xiaoxing, et al.Relationship between decomposition gas ratios and partial discharge energy in GIS, and the influence of residual water and oxygen[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2014, 21(3): 1226-1234.
[12] Luo Zongchang, Han Fangyuan, Tang Bin, et al.Optical properties and decomposition mechanisms of SF₆ at different partial discharge determined by infrared spectroscopy[J]. AIP Advances, 2018, 8(6): 065107.
[13] Rai P, Raj S, Ko K J, et al.Synthesis of flower-like ZnO microstructures for gas sensor applications[J]. Sensors and Actuators B: Chemical, 2013, 178: 107-112.
[14] Nam B, Ko T K, Hyun S K, et al.NO₂ sensing properties of WO₃-decorated In₂O₃ nanorods and In₂O₃-decorated WO₃ nanorods[J]. Nano Convergence, 2019, 6(1): 40.
[15] Kumar R, Goel N, Kumar M.UV-activated MoS₂ based fast and reversible NO₂ sensor at room temperature[J]. ACS Sensors, 2017, 2(11): 1744-1752.
[16] Na C W, Kim J H, Kim H J, et al.Highly selective and sensitive detection of NO₂ using rGO-In₂O₃ structure on flexible substrate at low temperature[J]. Sensors and Actuators B: Chemical, 2018, 255: 1671-1679.
[17] Wang Jing, Wang Caileng, Liu Ao, et al.High-response mixed-potential type planar YSZ-based NO₂ sensor coupled with CoTiO₃ sensing electrode[J]. Sensors and Actuators B: Chemical, 2019, 287: 185-190.
[18] 谭桂霞, 陈烨璞, 徐引娟, 等. 氧气中臭氧分解规律[J]. 上海大学学报(自然科学版), 2007, 13(1): 82-84.
Tan Guixia, Chen Yepu, Xu Yinjuan, et al.Rules of ozone decomposition in oxygen[J]. Journal of Shanghai University (Natural Science Edition), 2007, 13(1): 82-84.
[19] Perrin A, Toon G, Orphal J.Detection of atmospheric ¹⁵NO₂ in the ν₃ spectral region (6.3μm)[J]. Journal of Quantitative Spectroscopy and Radiative Transfer, 2015, 154: 91-97.
[20] Chaisriratanakul W, Bunjongpru W, Pankiew A, et al.Modification of polyvinyl chloride ion-selective membrane for nitrate ISFET sensors[J]. Applied Surface Science, 2020, 512: 145664.
[21] Chu Jifeng, Wang Qiongyuan, Yang Aijun, et al.Method of sieving the optimal NO₂ sensitive material[J]. Sensors and Actuators B: Chemical, 2023, 375: 132929.
[22] 张晓星, 姚尧, 唐炬, 等. SF₆放电分解气体组分分析的现状和发展[J]. 高电压技术, 2008, 34(4): 664-669, 747.
Zhang Xiaoxing, Yao Yao, Tang Ju, et al.Actuamity and perspective of!Proximate analysis of SF₆ decomposed products under partial discharge[J]. High Voltage Engineering, 2008, 34(4): 664-669, 747.
[23] Kumar R, Al-Dossary O, Kumar G, et al.Zinc oxide nanostructures for NO₂ gas-sensor applications: a review[J]. Nano-Micro Letters, 2015, 7(2): 97-120.
[24] 韩翔宇, 纽春萍, 何海龙, 等. 电磁式断路器状态监测与智能评估技术综述[J/OL]. 电工技术学报, 2022: 1-19. DOI:10.19595/j.cnki.1000-6753.tces. 220204.
Han Xiangyu, Niu Chunping, He Hailong, et al.Review of condition monitoring and intelligent assessment of electromagnetic circuit breaker[J/OL]. Transations of China Electrotechnical Society, 2022: 1-19. DOI:10.19595/j.cnki.1000-6753.tces.220204.
[25] 顾崇寅, 徐潇源, 王梦圆, 等. 基于CatBoost算法的光伏阵列故障诊断方法[J]. 电力系统自动化, 2023, 47(2): 105-114.
Gu Chongyin, Xu Xiaoyuan, Wang Mengyuan, et al.CatBoost algorithm based fault diagnosis method for photovoltaic arrays[J]. Automation of Electric Power Systems, 2023, 47(2): 105-114.
[26] 彭莎, 孙铭阳, 张镇勇, 等. 机器学习在电力信息物理系统网络安全中的应用[J]. 电力系统自动化, 2022, 46(9): 200-215.
Peng Sha, Sun Mingyang, Zhang Zhenyong, et al.Application of machine learning in cyber security of cyber-physical power system[J]. Automation of Electric Power Systems, 2022, 46(9): 200-215.
[27] 姜雅男, 于永进, 李长云. 基于改进TOPSIS模型的绝缘纸机-热老化状态评估方法[J]. 电工技术学报, 2022, 37(6): 1572-1582.
Jiang Yanan, Yu Yongjin, Li Changyun.Evaluation method of insulation paper deterioration status with mechanical-thermal synergy based on improved TOPSIS model[J]. Transactions of China Electrotechnical Society, 2022, 37(6): 1572-1582.
[28] 崔芮华, 李泽, 佟德栓. 基于三维熵距和熵空间的航空电弧故障检测与分类技术[J]. 电工技术学报, 2021, 36(4): 869-880.
Cui Ruihua, Li Ze, Tong Deshuan.Arc fault detection and classification based on three-dimensional entropy distance and entropy space in aviation power system[J]. Transactions of China Electrotechnical Society, 2021, 36(4): 869-880.