基于可解释人工智能的SF<sub>6</sub>/N<sub>2</sub>气体直流火花放电光谱解析与临界闪络缺陷识别

doi:10.19595/j.cnki.1000-6753.tces.241857

Abstract
Figure/Table
References (0)
Related Citation (15)

Download: PDF (6878 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Currently, gas-insulated switchgear (GIS) employing an SF₆/N₂ gas mixture with a volume ratio of 37 is considered a highly viable technical solution. This is attributed to its optimal balance among dielectric performance, cost-effectiveness, and environmental impact. To further reveal the microscopic physicochemical reaction mechanisms during discharge and improve both insulation design and fault detection strategies, this study investigates the spectral characteristics of spark discharges in SF₆/N₂ (3$\,\!:$7) mixed gas environment under direct current voltage.
Initially, experimental platforms simulating partial discharges were established within a sealed chamber containing SF₆/N₂ (3$\,\!:$7) mixed gas at 0.6 MPa. The test specimens consisted of scaled electrode models representing insulator surface contamination, conductor protrusion, and floating metallic particles, and were constructed using materials analogous to those found in actual GIS components. The study employed the QE65 Pro high-resolution spectrometer from Ocean Optics with synchronized triggering to capture instantaneous discharge spectra during spark events, while a Lumina series UV-visible imaging system simultaneously recorded the visible discharge process.
Subsequently, this research developed an integrated analytical framework combining quantum optical analysis with artificial intelligence-based data processing. An explainable AI model was designed that identifies key spectral features characterizing different spark discharge types. These features were then visualized through attention heatmaps, assisting experts in interpreting discharge mechanisms based on quantum optical principles. This approach addresses limitations in deep learning models where decision basis lacks interpretability, enabling researchers to identify subtle spectral features that may not be directly perceptible to the human eye.
Moreover, building upon the identified spectral features, an investigation of reaction mechanisms was conducted. The energy-level transitions of key elements were mapped and correlated with discharge conditions. This analysis revealed several critical physicochemical processes: the decomposition of SF₆ into reactive fragments, nitrogen excitation pathways, electrode materials' metal surface sputtering effects, and the decomposition processes of hydroxides and sodium compounds on insulation surfaces. And the influence of these reactions on discharge development was analyzed. Studies of maximum energy transfer thresholds provided insights into discharge-induced damage mechanisms and material tolerance limits. These findings support the development of optimized insulation solutions with enhanced discharge withstand capabilities.
Based on spectral lines identified through theoretical and database analyses, a multi-objective optimization algorithm was employed to select optimal diagnostic bands for defect type identification. Using these optimized spectral bands, we designed and constructed a novel multi-spectral sensor prototype incorporating micro- structured side-emitting optical fiber sensing elements. We validated the sensor's performance using high-power sources that simulated critical flashover conditions, achieving over 98% accuracy in distinguishing between three typical GIS defect types.
This research has established a workflow that organically combines artificial intelligence with human analysis. The approach can guide GIS insulation design optimization, fault prevention, and operational maintenance. Based on these findings, future work can simultaneously advance the optimization of key insulation components, such as insulator materials and protective measures for metallic parts, and develop high-sensitivity multi-spectral online monitoring systems suitable for practical and complex GIS field environments.

Key words： Partial discharge spectral analysis energy level transition multi-objective optimization explainable artificial intelligence (XAI) micro-structured side-emitting optical fiber

Received: 21 October 2024

PACS:

TM85

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Feng Yuning
	Yuan Shun
	Cai Zhiyuan
	Huang Chongyang
	Gao Lei

Cite this article:

Feng Yuning,Yuan Shun,Cai Zhiyuan等. Spectral Analysis and Critical Flashover Defect Identification of DC Spark Discharge in SF₆/N₂ Gas Based on Explainable Artificial Intelligence[J]. Transactions of China Electrotechnical Society, 2025, 40(21): 6856-6870.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.241857 OR https://dgjsxb.ces-transaction.com/EN/Y2025/V40/I21/6856

[1] 周勤勇. 多直流馈入受端电网直流受电规模研究[D]. 济南: 山东大学, 2015.
Zhou Qinyong.Studies on maximum multi-infeed HVDCs' capacity to receiving end powor grid[D]. Jinan: Shandong University, 2015.
[2] 戴志辉, 张程, 刘宁宁, 等. 特高压直流线路保护原理及动作策略分析[J]. 电力系统自动化, 2019, 43(21): 1-11.
Dai Zhihui, Zhang Cheng, Liu Ningning, et al.Analysis of UHVDC line protection principle and operation strategy[J]. Automation of Electric Power Systems, 2019, 43(21): 1-11.
[3] 孙鹏程, 王帮田, 洪文芳, 等. SF₆/N₂混合气体绝缘特性的实验研究[J]. 中国电力, 2012, 45(12): 71-75.
Sun Pengcheng, Wang Bangtian, Hong Wenfang, et al.Experimental studies on electrical insulation performances of SF₆/N₂ gas mixtures[J]. Electric Power, 2012, 45(12): 71-75.
[4] 赵彦杰, 陈丽安, 袁传镇. 252 kV GIS用SF₆/N₂混合气体局放特性研究[J]. 高压电器, 2023, 59(9): 169-175, 183.
Zhao Yanjie, Chen Li'an, Yuan Chuanzhen.Research on partial discharge characteristics of SF₆/N₂ gas mixture in 252 kV GIS[J]. High Voltage Apparatus, 2023, 59(9): 169-175, 183.
[5] 王艳新, 闫静, 王建华, 等. 基于多级二阶注意力孪生网络的小样本GIS局部放电诊断方法[J]. 电工技术学报, 2023, 38(8): 2255-2264.
Wang Yanxin, Yan Jing, Wang Jianhua, et al.Few-shot partial discharge diagnosis for gas-insulated switchgear using a novel multi-level second-order attention Siamese network[J]. Transactions of China Electrotechnical Society, 2023, 38(8): 2255-2264.
[6] 张国治, 田晗绿, 张磊, 等. 具备局部放电超声波感知功能的PZT基特高频传感技术[J]. 电工技术学报, 2024, 39(19): 6215-6227.
Zhang Guozhi, Tian Hanlü, Zhang Lei, et al.Research on PZT-based ultrasonic-ultra high frequency composite partial discharge sensing technology[J]. Transactions of China Electrotechnical Society, 2024, 39(19): 6215-6227.
[7] 李泽, 钱勇, 刘伟, 等. GIS局部放电光信号检测技术及光学图像诊断方法[J]. 电工技术学报, 2025, 40(1): 253-263.
Li Ze, Qian Yong, Liu Wei, et al.Optical signal detection technology and optical image diagnostic method of partial discharge in GIS[J]. Transactions of China Electrotechnical Society, 2025, 40(1): 253-263.
[8] 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.Spectros- copy analysis of emission spectrum characteristics and discharge recognition of SF₆ gas discharge[J]. Transactions of China Electrotechnical Society, 2022, 37(7): 1866-1874.
[9] 李红月. SF₆/Ar及SF₆/N₂混合气体脉冲放电等离子体的光谱研究[D]. 大连: 大连理工大学, 2019.
Li Hongyue.Spectroscopic study on pulsed discharge plasma of SF₆/Ar and SF₆/N₂ mixed gases[D]. Dalian: Dalian University of Technology, 2019.
[10] Sasamoto R, Matsumoto T, Orii H, et al.Quantitative visualization of gas temperature distribution in atmosp- heric DC glow corona by spectral image processing[C]//2016 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP), Toronto, ON, Canada, 2016: 203-206.
[11] Wang Taiqi, Cheng Yongkang, Xu Chao, et al.Spatial spectral characteristics of partial discharge with different electrode models[J]. Photonics, 2023, 10(7): 788.
[12] Zhang Wanxia, Xia Lingzhi, Sun Hao, et al.On the distribution of $\text{N}_{2}^{+}$ and N₂ bands in ionization region of positive DC corona discharge[C]//Proceedings of the 4th International Symposium on Plasma and Energy Conversion, Singapore, 2023: 352-365.
[13] 曾鑫, 张帅, 白晗, 等. 基于原子光谱Stark展宽高压放电等离子体电子密度计算[J]. 中国电机工程学报, 2024, 44(11): 4579-4589.
Zeng Xin, Zhang Shuai, Bai Han, et al.Method for calculating plasma electron density based on stark broadening of atomic spectrum[J]. Proceedings of the CSEE, 2024, 44(11): 4579-4589.
[14] Fatima H, Ullah M U, Ahmad S, et al.Spectroscopic evaluation of vibrational temperature and electron density in reduced pressure radio frequency nitrogen plasma[J]. SN Applied Sciences, 2021, 3(6): 646.
[15] 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.
[16] Zhang Xiaoxing, Liu Heng, Ren Jiangbo, et al.Fourier transform infrared spectroscopy quantitative analysis of SF₆ partial discharge decomposition components[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2015, 136: 884-889.
[17] Zhao Yu, Wang Xianpei, Dai Dangdang, et al.Partial discharge early-warning through ultraviolet spectroscopic detection of SO₂[J]. Measurement Science and Techno- logy, 2014, 25(3): 035002.
[18] Shcherbanev S A, Nadinov I U, Auvray P, et al.Emission spectroscopy of partial discharges in air- filled voids in unfilled epoxy[J]. IEEE Transactions on Plasma Science, 2016, 44(7): 1219-1227.
[19] Ren Ming, Zhou Jierui, Miao Jin.Adopting spectral analysis in partial discharge fault diagnosis of GIS with a micro built-in optical sensor[J]. IEEE Trans- actions on Power Delivery, 2021, 36(2): 1237-1240.
[20] Xia Changjie, Ren Ming, Chen Rongfa, et al.Multispectral optical partial discharge detection, recognition, and assessment[J]. IEEE Transactions on Instrumentation Measurement, 2022, 71: 3162284.
[21] 任明, 王玥, 关浩斌, 等. 沿面放电光脉冲发展特征与临界击穿判据研究[J]. 中国电机工程学报, 2024, 44(10): 4123-4134.
Ren Ming, Wang Yue, Guan Haobin, et al.Develop- ment characteristics and critical breakdown criterion of surface discharge light pulse[J]. Proceedings of the CSEE, 2024, 44(10): 4123-4134.
[22] Nazir M T, Phung B T, Hoffman M.Performance of silicone rubber composites with SiO₂ micro/nano-filler under AC corona discharge[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2016, 23(5): 2804-2815.
[23] Li Yao, Li Sisi, Feng Yi, et al.Fast breakdown process and characteristics diagnosis of nanosecond pin-pin discharge[J]. Journal of Physics D: Applied Physics, 2024, 57(22): 225201.
[24] Yoshida S, Kojima H, Hayakawa N, et al.Light emission spectrum depending on propagation of partial discharge in SF₆[C]//Conference Record of the 2008 IEEE International Symposium on Electrical Insulation, Vancouver, BC, Canada, 2008: 365-368.
[25] Barredo Arrieta A, Díaz-Rodríguez N, Del Ser J, et al.Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward respon- sible AI[J]. Information Fusion, 2020, 58: 82-115.
[26] Bai Xiao, Wang Xiang, Liu Xianglong, et al.Explai- nable deep learning for efficient and robust pattern recognition: a survey of recent developments[J]. Pattern Recognition, 2021, 120: 108102.
[27] 王小君, 窦嘉铭, 刘曌, 等. 可解释人工智能在电力系统中的应用综述与展望[J]. 电力系统自动化, 2024, 48(4): 169-191.
Wang Xiaojun, Dou Jiaming, Liu Zhao, et al.Review and prospect of explainable artificial intelligence and its application in power systems[J]. Automation of Electric Power Systems, 2024, 48(4): 169-191.
[28] 刘煦阳, 段潮舒, 蔡文生, 等. 可解释深度学习在光谱和医学影像分析中的应用[J]. 化学进展, 2022, 34(12): 2561-2572.
Liu Xuyang, Duan Chaoshu, Cai Wensheng, et al.Explainable deep learning in spectral and medical image analysis[J]. Progress in Chemistry, 2022, 34(12): 2561-2572.
[29] 卓然. 气体绝缘电器局部放电联合检测的特征优化与故障诊断技术[D]. 重庆: 重庆大学, 2014.
Zhuo Ran.Feature optimization and fault diagnosisof GIS based on combined detection[D]. Chongqing: Chongqing University, 2014.
[30] Feng Yuning.Spectral analysis and critical flashover defect identification of DC spark discharge in SF₆/N₂ gas based on XAI-complete mathematical description of algorithms and data analysis presentation[DB/OL]. [2024-09-30].https://osf.io/5x9vz/.
[31] National Institute of Standards and Technology. Atomic spectra database lines form[DB/OL].[2024-09-30]. https://physics.nist.gov/PhysRefData/ASD/lines_form.html.
[32] National Institute of Standards and Technology. Strong lines of fluorine (F)[DB/OL].[2024-09-30]. https://physics.nist.gov/PhysRefData/Handbook/Tables/fluorinetable2.htm.
[33] Sieck L W, Ausloos P J.The ionization energy of SF₅ and the SF₅-F bond dissociation energy[J]. The Journal of Chemical Physics, 1990, 93(11): 8374-8378.
[34] Joshi S, Barden S, Mayer P M.Anionic reactions degrading SF₆ using metals: insights from the gas phase[J]. Rapid Communications in Mass Spectrometry, 2025, 39(3): e9948.
[35] National Institute of Standards and Technology. Strong lines of sulfur (S)[DB/OL].[2024-09-30]. https:// physics.nist.gov/PhysRefData/Handbook/Tables/sulfurtable2_a.htm.
[36] National Institute of Standards and Technology. Nitrogen (N₂)[DB/OL].[2024-09-30]. https://webbook.nist.gov/cgi/cbook.cgi?ID=7727-37-9.
[37] National Institute of Standards and Technology. Nitrogen neutral atom data[DB/OL].[2024-09-30]. https://physics.nist.gov/PhysRefData/Handbook/Tables/nitrogentable2_a.htm.
[38] Chou S, Lo J, Peng Y, et al.Emission spectra of atomic and molecular nitrogen from photolysis of ammonia in solid neon[J]. AIP Advances, 2019, 9(5).
[39] National Institute of Standards and Technology. Energy levels of neutral aluminum (Al Ⅰ)[DB/OL].[2024-09-30]. https://www.physics.nist.gov/PhysRefData/Handbook/Tables/aluminumtable2_a.htm.
[40] Zhang Xiaoxing, Wu Yunjian, Chen Xiaoyu, et al.Theoretical study on decomposition mechanism of insulating epoxy resin cured by anhydride[J]. Polymers, 2017, 9(8): 341.
[41] Karthikeyan L, Desakumaran D, Mol P B S, et al. Non-isothermal cure and decomposition kinetics of hydroxyl and propargyl functional poly (ether ether ketone): epoxy resins[J]. Journal of Thermal Analysis and Calorimetry, 2022, 147(12): 6793-6805.
[42] Steinberg M, Schofield K.A reevaluation of the vaporization behavior of sodium oxide and the bond strengths of NaO and Na₂O: Implications for the mass spectrometric analyses of alkali/oxygen systems[J]. The Journal of Chemical Physics, 1991, 94(5): 3901-3907.
[43] Li Zhibing, Deng Shaozhi, Xu Ningsheng.Mechanism of field electron emission from carbon nanotubes[J]. Frontiers of Physics in China, 2006, 1(3): 305-316.
[44] Doolittle W A, Matthews C M, Ahmad H, et al.Prospectives for AlN electronics and optoelectronics and the important role of alternative synthesis[J]. Applied Physics Letters, 2023, 123(7): 070501.
[45] Cunha C L A, Pimenta T C, Amorim Fraga M. Development and applications of aluminum nitride thin film technology[M]//Yang Dongfang. Thin Films: Deposition Methods and Applications. London: IntechOpen, 2023.
[46] 钱新伟, 涂峰, 刘德明, 等. 掺杂对光纤紫外传输性能的影响[J]. 光子学报, 2010, 39(2): 247-250.
Qian Xinwei, Tu Feng, Liu Deming, et al.Study of doping influence the fiber's UV transmission perfor- mance[J]. Acta Photonica Sinica, 2010, 39(2): 247-250.
[47] 陈光辉. 掺杂二氧化硅玻璃光敏性及光纤光栅器件研究[D]. 上海: 复旦大学, 2005.
[48] 许渊. 运行中GIS绝缘子表面金属颗粒诱发放电研究[D]. 北京: 华北电力大学, 2020.
Xu Yuan.Investigation on mechanism of metallic particle induced flashover of GIS insulators in operation condition[D]. Beijing: North China Electric Power University, 2020.