王秀君,罗林,于淼,曹宇鹏
WANG Xiujun,LUO Lin,YU Miao,CAO Yupeng

• 1:中国电信集团有限公司浙江分公司
• 2:辽宁石油化工大学信息与控制工程学院
• 3:浙江大学电气工程学院
• 4:国网冀北电力有限公司

摘要(Abstract)：

气体绝缘开关设备绝缘故障引起的局部放电会导致绝缘介质SF_6气体分解，分解产生的氟硫化物会与设备中的水分和氧气发生反应，生成SO_2、CS_2和H_2S等化合物，这3种特征气体的浓度能够反映绝缘故障的类型和严重程度。对此，提出一种基于MFT（马尔可夫转移场）和深度学习的方法，用于分析特征气体的紫外光谱图，识别具有重叠吸收峰的痕量气体混合物。该方法首先将一维序列数据转化为二维图像，使混合气体的紫外光谱数据以图像形式呈现，从而使其特征信息更加直观。随后，将这些图像输入至深度学习模型中进行识别分类。实验结果表明，与其他模型相比，该方法具有更高的识别准确率。
Partial discharge caused by insulation faults in gas-insulated switchgear can lead to the decomposition of the insulating medium,SF_6 gas.The byproducts of this decomposition,fluorosulfides,can react with moisture and oxygen in the equipment,generating compounds like SO_2,CS_2,and H_2S.The concentrations of these three characteristic gases can reflect the type and severity of insulation faults in the equipment.To address this,the paper proposes a method based on Markov transfer fields (MTF) and deep learning to analyze the ultraviolet spectra of these characteristic gases and identify trace gas mixtures with overlapping absorption peaks.This method first converts one-dimensional sequence data into two-dimensional images,presenting the ultraviolet spectral data of the mixed gases in a more intuitive image format.Subsequently,these images are input into a deep learning model for classification and recognition.Experimental results demonstrate that this method achieves a higher recognition accuracy compared to other models.

关键词(KeyWords)： 紫外吸收光谱法;马尔可夫转移场;深度学习
ultraviolet absorption spectroscopy;MTF;deep learning

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金青年项目资助（61703191）;; 工业控制技术国家重点实验室开放课题资助（ICT202B41）

作者(Author): 王秀君,罗林,于淼,曹宇鹏
WANG Xiujun,LUO Lin,YU Miao,CAO Yupeng

DOI: 10.19585/j.zjdl.202503013

参考文献(References)：

• [1]陈鹏，王先培，张军，等.GIS中SO2气体紫外光谱检测及数据处理[J].仪表技术与传感器，2015(12):42-45.CHEN Peng,WANG Xianpei,ZHANG Jun,et al.Ultraviolet spectrum detection of SO2 gas in GIS and data processing[J].Instrument Technique and Sensor,2015(12):42-45.
• [2]王先培，李晨，赵宇，等.基于紫外光谱SF6电气设备内SO2组分在线监测法[J].高电压技术，2015,41(1):152-158.WANG Xianpei,LI Chen,ZHAO Yu,et al.Online detection methodology of decomposition product SO2 in SF6electrical equipment based on ultraviolet spectroscopy[J].High Voltage Engineering,2015,41(1):152-158.
• [3]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.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.
• [4]颜湘莲，宋杲，王承玉，等.基于SF6气体分解产物检测的气体绝缘开关设备状态监测[J].电力自动化设备，2014,34(6):83-88.YAN Xianglian,SONG Gao,WANG Chengyu,et al.Gasinsulated switchgear state monitoring based on SF6 decomposition products detection[J].Electric Power Automation Equipment,2014,34(6):83-88.
• [5]咸日常.大型变压器故障的气相色谱综合分析[J].变压器，2003,40(4):31-35.XIAN Richang. Comprehensive analysis of large transformer faults by gas chromatography[J]. Transformer,2003,40(4):31-35.
• [6]王圆圆，汲胜昌，李金宇，等.多种试验条件下SF6放电及分解特性研究[J].高电压技术，2013,39(8):1952-1959.WANG Yuanyuan,JI Shengchang,LI Jinyu,et al.Investigations on discharge and decomposition characteristics of SF6 under various experimental conditions[J].High Voltage Engineering,2013,39(8):1952-1959.
• [7]张玉欣，程志峰，徐正平，等.参数寻优支持向量机在基于光声光谱法的变压器故障诊断中的应用[J].光谱学与光谱分析，2015,35(1):10-13.ZHANG Yuxin,CHENG Zhifeng,XU Zhengping,et al.Application of optimized parameters SVM based on photoacoustic spectroscopy method in fault diagnosis of power transformer[J].Spectroscopy and Spectral Analysis,2015,35(1):10-13.
• [8]颜湘莲，王承玉，宋杲，等.气体绝缘开关设备中SF6气体分解产物检测与设备故障诊断的研究进展[J].高压电器，2013,49(6):1-9.YAN Xianglian,WANG Chengyu,SONG Gao,et al.Recent progress in detection of SF6 decomposition products and fault diagnosis for gas insulated switchgears[J].High Voltage Apparatus,2013,49(6):1-9.
• [9]季严松，王承玉，杨韧，等.SF6气体分解产物检测技术及其在GIS设备故障诊断中的应用[J].高压电器，2011,47(2):100-103.JI Yansong,WANG Chengyu,YANG Ren,et al.Measuring technique of SF6 decomposition products and its application to fault diagnosis of GIS[J].High Voltage Apparatus,2011,47(2):100-103.
• [10]杨宇玲，郭新良，崔兆仑，等.紫外吸收光谱法检测SF6分解产物中的H2S[J].高电压技术，2018,44(8):2573-2579.YANG Yuling,GUO Xinliang,CUI Zhaolun,et al.Determination of H2S in SF6 decomposition products by ultraviolet absorption spectrometry[J].High Voltage Engineering,2018,44(8):2573-2579.
• [11]雷春丽，夏奔锋，薛林林，等.基于MTF-CNN的滚动轴承故障诊断方法[J].振动与冲击，2022,41(9):151-158.LEI Chunli,XIA Benfeng,XUE Linlin,et al.Rolling bearing fault diagnosis method based on MTF-CNN[J].Journal of Vibration and Shock,2022,41(9):151-158.
• [12]曹洁，马佳林，黄黛麟，等.一种基于多通道马尔可夫转移场的故障诊断方法[J].吉林大学学报（工学版），2022,52(2):491-496.CAO Jie,MA Jialin,HUANG Dailin,et al.A fault diagnosis method based on multi Markov transition field[J].Journal of Jilin University(Engineering and Technology Edition),2022,52(2):491-496.
• [13]蒲姗姗，郑恩让，陈蓓.基于1D-CNN的近红外光谱分类算法研究[J].光谱学与光谱分析，2023,43(8):2446-2451.PU Shanshan,ZHENG Enrang,CHEN Bei.Research on A classification algorithm of near-infrared spectroscopy based on 1D-CNN[J].Spectroscopy and Spectral Analysis,2023,43(8):2446-2451.
• [14]刘咏飞，马勇，赵科，等.SF6分解组分混合气体中CS2的紫外光谱定量分析[J].高压电器，2022,58(2):89-94.LIU Yongfei,MA Yong,ZHAO Ke,et al. Ultraviolet spectroscopy quantitative analysis of CS2 in SF6 decomposition component gas mixture[J]. High Voltage Apparatus,2022,58(2):89-94.
• [15]黄杨珏，周红，汪进锋，等.SF6分解物SO2的紫外吸收波段分析[J].高压电器，2016,52(12):209-214.HUANG Yangjue,ZHOU Hong,WANG Jinfeng,et al.Analysis of ultraviolet absorption bands of SF6 decomposition products SO2[J].High Voltage Apparatus,2016,52(12):209-214.
• [16]姜家国，郭曼利.基于MTF-DenseNet的滚动轴承故障诊断[J].仪器仪表用户，2021,28(9):54-56.JIANG Jiaguo,GUO Manli.Fault diagnosis of rolling bearing based on MTF-DenseNet[J].Instrumentation,2021,28(9):54-56.
• [17]刘文洁，林磊，孙承杰.基于迁移学习的语义推理网络[J].智能计算机与应用，2018,8(6):195-198.LIU Wenjie,LIN Lei,SUN Chengjie.Semantic inference network based on transfer learning[J]. Intelligent Computer and Applications,2018,8(6):195-198.
• [18]王彦光，朱鸿斌，徐维超.ROC曲线及其分析方法综述[J].广东工业大学学报，2021,38(1):46-53.WANG Yanguang,ZHU Hongbin,XU Weichao. A review on ROC curve and analysis[J].Journal of Guangdong University of Technology,2021,38(1):46-53.