李欣,吕干云,龚彧,毕睿华,叶加星,刘晓宏,于相宜
LI Xin,LYU Ganyun,GONG Yu,BI Ruihua,YE Jiaxing,LIU Xiaohong,YU Xiangyi

• 1:南京工程学院电力工程学院
• 2:国网江苏省盐城供电分公司
• 3:江苏方天电力技术有限公司

摘要(Abstract)：

随着新型电力系统中新能源渗透率逐渐升高，电网结构复杂性增加，PQD（电能质量扰动）呈现多样化和复杂化的趋势。为实现电能质量扰动的精准识别，提出一种基于二维时频谱图与改进YOLOv5的电能质量扰动图像识别的方法。首先，利用S变换将PQD数据映射成二维时频谱图，通过图像来表征时间、频率和幅值的扰动细节特征；然后，搭建引入ASPP（空洞空间卷积池化金字塔）结构和注意力机制的YOLOv5训练网络，扩大特征图的感受野以充分提取扰动图像特征，进而以图像识别方法实现PQD分类识别；最后，利用仿真数据进行扰动识别准确率和鲁棒性的验证。结果表明，该方法的识别准确率较高，且图像识别法的引入有助于PQD识别结果的可视化。
As the penetration rate of renewable energy sources increases in new-type power systems, so too does the complexity of the grid structure, leading to more diverse and complex power quality disturbance(PQD). To accurately identify power quality, a method for PQD image recognition has been proposed, utilizing a two-dimensional time-frequency spectrograms and an improved YOLOv5. Initially, PQD data is projected onto a two-dimensional time-frequency spectrograms using the S-transform. This approach allows for detail-oriented representation of disturbances in terms of time, frequency, and amplitude via imagery. Subsequently, a YOLOv5 training network is constructed that integrates atrous spatial pyramid pooling(ASPP) structure and attention mechanisms. This design broadens the receptive field of the feature map, facilitating a comprehensive extraction of the disturbance image features, and enables PQD classification recognition through image detection methods. Finally, the accuracy and robustness of the disturbance recognition are validated using simulation data. The results evidence that this method offers a high degree of recognition accuracy. Moreover, the integration of the image recognition method enhances the visual representation of the PQD recognition results.

关键词(KeyWords)： 电能质量扰动图像识别;时频谱图像;YOLOv5;空洞空间卷积池化金字塔;注意力机制
PQD image recognition;time-frequency spectrogram;YOLOv5;ASPP;attention module

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金资助项目（51577086）;; 江苏“六大人才高峰”资助（TD-XNY004）

作者(Author): 李欣,吕干云,龚彧,毕睿华,叶加星,刘晓宏,于相宜
LI Xin,LYU Ganyun,GONG Yu,BI Ruihua,YE Jiaxing,LIU Xiaohong,YU Xiangyi

DOI: 10.19585/j.zjdl.202410004

参考文献(References)：

• [1]黎博，陈民铀，钟海旺，等.高比例可再生能源新型电力系统长期规划综述[J].中国电机工程学报，2023,43(2):555-581.LI Bo,CHEN Minyou,ZHONG Haiwang,et al.A review of long-term planning of new power systems with large share of renewable energy[J].Proceedings of the CSEE,2023,43(2):555-581.
• [2]张华赢，朱正国，姚森敬，等.基于大数据分析的暂态电能质量综合评估方法[J].南方电网技术，2015,9(6):80-86.ZHANG Huaying,ZHU Zhengguo,YAO Senjing,et al.Comprehensive evaluation method of transient power quality based on big data analysis[J].Southern Power System Technology,2015,9(6):80-86.
• [3]汪飞，全晓庆，任林涛.电能质量扰动检测与识别方法研究综述[J].中国电机工程学报，2021,41(12):4104-4121.WANG Fei,QUAN Xiaoqing,REN Lintao. Review of power quality disturbance detection and identification methods[J]. Proceedings of the CSEE,2021,41(12):4104-4121.
• [4]黄建明，瞿合祚，李晓明.基于短时傅里叶变换及其谱峭度的电能质量混合扰动分类[J].电网技术，2016,40(10):3184-3191.HUANG Jianming,QU Hezuo,LI Xiaoming. Classification for hybrid power quality disturbance based on STFT and its spectral kurtosis[J]. Power System Technology,2016,40(10):3184-3191.
• [5]杨晓梅，郭林明，肖先勇，等.基于可调品质因子小波变换和随机森林特征选择算法的电能质量复合扰动分类[J].电网技术，2020,44(8):3014-3020.YANG Xiaomei,GUO Linming,XIAO Xianyong,et al.Classification of multiple power quality disturbances based on TQWT and random forest feature selection algorithm[J].Power System Technology,2020,44(8):3014-3020.
• [6]张若兵，金森，杜钢.基于EMD与DTW算法的振荡波下电缆局部放电定位方法[J].高电压技术，2020,46(1):273-281.ZHANG Ruobing,JIN Sen,DU Gang.Method of partial discharge localization for cable under oscillatory wave voltage conditions based on EMD and DTW algorithm[J].High Voltage Engineering,2020,46(1):273-281.
• [7]李琦，许素安，施阁，等.基于S变换和IWOA-SVM的复合电能质量扰动识别[J].智慧电力，2023,51(5):30-35.LI Qi,XU Su′an,SHI Ge,et al.Identification of composite power quality disturbance based on S-transform and IWOA-SVM[J].Smart Power,2023,51(5):30-35.
• [8]陈诺，吕干云，叶加星.基于SVM级联决策树的复合电能质量扰动识别[J].电气工程学报，2023,18(2):149-156.CHEN Nuo,LüGanyun,YE Jiaxing.Recognition of complex PQ disturbances based on SVM cascaded decision tree[J]. Journal of Electrical Engineering,2023,18(2):149-156.
• [9]易吉良，彭建春，谭会生.S变换在电能质量扰动分析中的应用综述[J].电力系统保护与控制，2011,39(3):141-147.YI Jiliang,PENG Jianchun,TAN Huisheng.A summary of S-transform applied to power quality disturbances analysis[J]. Power System Protection and Control,2011,39(3):141-147.
• [10]程志友，杨猛.基于二维离散余弦S变换的电能质量扰动类型识别[J].电力系统保护与控制，2021,49(17):85-92.CHENG Zhiyou,YANG Meng.Power quality disturbance type identification based on a two-dimensional discrete cosine S-transform[J]. Power System Protection and Control,2021,49(17):85-92.
• [11]檀何凤，刘政怡.基于标签相关性的K近邻多标签分类方法[J].计算机应用，2015,35(10):2761-2765.TAN Hefeng,LIU Zhengyi.Multi-label K nearest neighbor algorithm by exploiting label correlation[J].Journal of Computer Applications,2015,35(10):2761-2765.
• [12]赵俊，杨洪耕，李伟.利用S变换与变尺度模板标准化的短时电能质量扰动分类[J].南方电网技术，2010,4(3):72-76.ZHAO Jun,YANG Honggeng,LI Wei. Classification of short duration power quality disturbance using S-transform and scale zooming standardization[J]. Southern Power System Technology,2010,4(3):72-76.
• [13]李建闽，林海军，梁成斌，等.基于双分辨率S变换和学习向量量化神经网络的电能质量扰动检测方法[J].电工技术学报，2019,34(16):3453-3463.LI Jianmin,LIN Haijun,LIANG Chengbin,et al. Detection method of power quality disturbances based on double resolution S transform and learning vector quantization neural network[J].Transactions of China Electrotechnical Society,2019,34(16):3453-3463.
• [14] JAMALI S,FARSA A R,GHAFFARZADEH N.Identification of optimal features for fast and accurate classification of power quality disturbances[J].Measurement,2018,116:565-574.
• [15]陈华丰，张葛祥.基于决策树和支持向量机的电能质量扰动识别[J].电网技术，2013,37(5):1272-1278.CHEN Huafeng,ZHANG Gexiang.Power quality disturbance identification using decision tree and support vector machine[J]. Power System Technology,2013,37(5):1272-1278.
• [16]王维博，张斌，曾文入，等.基于特征融合一维卷积神经网络的电能质量扰动分类[J].电力系统保护与控制，2020,48(6):53-60.WANG Weibo,ZHANG Bin,ZENG Wenru,et al.Power quality disturbance classification of one-dimensional convolutional neural networks based on feature fusion[J].Power System Protection and Control,2020,48(6):53-60.
• [17]曾纪钧，温柏坚，梁哲恒.基于深度学习的安全帽识别算法研究与模型训练[J].电力系统保护与控制，2021,49(21):107-112.ZENG Jijun,WEN Bojian,LIANG Zheheng. Research and model training of helmet recognition algorithm based on deep learning[J]. Power System Protection and Control,2021,49(21):107-112.
• [18]赵振兵，王帆帆，刘良帅，等.基于注意力特征融合YOLOv5模型的无人机输电线路航拍图像金具检测方法[J].电测与仪表，2023,60(3):145-152.ZHAO Zhenbing,WANG Fanfan,LIU Liangshuai,et al.Hardware detection method of aerial image of UAV transmission line based on attention feature fusion YOLOv5model[J]. Electrical Measurement&Instrumentation,2023,60(3):145-152.
• [19]董卓元，高永亮，袁斌，等.一种改进型YOLOv4输电线路防外破检测方法[J].电网与清洁能源，2023,39(6):17-25.DONG Zhuoyuan,GAO Yongliang,YUAN Bin,et al.An external damage detection method of transmission lines based on improved YOLOv4[J].Power System and Clean Energy,2023,39(6):17-25.
• [20]顾晓东，唐丹宏，黄晓华.基于深度学习的电网巡检图像缺陷检测与识别[J].电力系统保护与控制，2021,49(5):91-97.GU Xiaodong,TANG Danhong,HUANG Xiaohua.Deep learning-based defect detection and recognition of a power grid inspection image[J]. Power System Protection and Control,2021,49(5):91-97.
• [21]王杨杨，曹晖，莫文昊.基于深度学习的改进型YOLOv4输电线路鸟巢检测与识别[J].智慧电力，2023,51(1):101-107.WANG Yangyang,CAO Hui,MO Wenhao. Bird’s nest detection and identification on improved YOLOv4 transmission line based on deep learning[J]. Smart Power,2023,51(1):101-107.
• [22]李季，刘乐，牛雨潇，等.融入注意力的YOLOv3绝缘子串识别方法[J].高压电器，2022,58(11):67-74.LI Ji,LIU Yue,NIU Yuxiao,et al.YOLOv3 identification method incorporating attention for insulator string[J].High Voltage Apparatus,2022,58(11):67-74.
• [23]陆云才，廖才波，李群，等.基于声纹特征和集成学习的变压器缺陷诊断方法[J].电力工程技术，2023,42(5):46-55.LU Yuncai,LIAO Caibo,LI Qun,et al.Transformer fault diagnosis method based on voiceprint feature and ensemble learning[J].Electric Power Engineering Technology,2023,42(5):46-55.
• [24]陈鹏，刘攀，郑逐隧，等.基于轻量化YOLO模型的电力机房设备状态快速检测[J].制造业自动化，2023,45(5):30-35.CHEN Peng,LIU Pan,ZHENG Zhusui,et al.Rapid detection of equipment status in power rooms based on lightweight YOLO model[J]. Manufacturing Automation,2023,45(5):30-35.
• [25]陈杰，安之焕，唐占元，等.基于改进YOLOv4模型的无人机巡检图像杆塔缺陷检测方法研究[J].电测与仪表，2023,60(10):155-160.CHEN Jie,AN Zhihuan,TANG Zhanyuan,et al.Research on tower defect detection method of UAV patrol inspection image based on improved YOLOv4 model[J].Electrical Measurement&Instrumentation,2023,60(10):155-160.
• [26]肖发龙，吴岳忠，沈雪豪，等.基于深度学习和知识图谱的变电站设备故障智能诊断[J].电力建设，2022,43(3):66-74.XIAO Falong,WU Yuezhong,SHEN Xuehao,et al.Intelligent fault diagnosis of substation equipment on the basis of deep learning and knowledge graph[J].Electric Power Construction,2022,43(3):66-74.
• [27]王婷婷，丁浩，张周胜.基于深度学习和多模型融合的局部放电模式识别方法[J].电力工程技术，2023,42(3):188-195.WANG Tingting,DING Hao,ZHANG Zhousheng.A partial discharge pattern recognition method based on deep learning and multi-model fusion[J].Electric Power Engineering Technology,2023,42(3):188-195.
• [28] IEEE. Recommended practice for monitoring electric power quality:IEEE 1159—2009[S]. USA:Institute of Electrical and Electronic Engineers,2009.
• [29] LIN T Y,DOLLAR P,GIRSHICK R,et al.Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR),21-26 July,2017,Honolulu,USA.IEEE,2017:936-944.
• [30] HE K M,ZHANG X Y,REN S Q,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.