基于Faster R-CNN的非侵入式负荷识别方法

杨金成; 王永超; 费守江; 张伟; 曾婧; 李娜

doi:10.16513/j.2096-2185.DE.2207204

PDF(2506 KB)

分布式能源 ›› 2022, Vol. 7 ›› Issue (2) : 26-33. DOI: 10.16513/j.2096-2185.DE.2207204

学术研究

基于Faster R-CNN的非侵入式负荷识别方法

杨金成 ¹ ,
王永超 ¹ ,
费守江 ¹ ,
张伟 ¹ ,
曾婧 ² ,
李娜 ¹

作者信息 +

Non-Intrusive Load Identification Method Based on Faster R-CNN

Author information +

文章历史 +

本文亮点

Aiming at the problems that the non-intrusive load identification terminal cannot realize the identification of similar electrical appliances and the identification of small sample data in household smart meters, a method for high-precision identification of small sample load data using Faster R-CNN is proposed. Based on the traditional Faster R-CNN target detection algorithm, the input image size of the model is increased to retain more details of the load image curve, and the recognition effect of small target image details is improved. The replacement model feature extraction network VGG16 is the Inception V2 network, which widens the network width and reduces the interference caused by the large difference in image curve change size to the recognition of the model, so as to meet the feature extraction of load characteristic image curves of different scales. The feasibility and accuracy of Faster R-CNN identification for non-invasive load equipment were tested on the data set. The results show that the method significantly reduces the computation of data processing and identification network, and greatly improves the accuracy and recall rate of identification.

导出引用

杨金成, 王永超, 费守江, 等. 基于Faster R-CNN的非侵入式负荷识别方法[J]. 分布式能源. 2022, 7(2): 26-33 https://doi.org/10.16513/j.2096-2185.DE.2207204

Jincheng YANG, Yongchao WANG, Soujiang FEI, et al. Non-Intrusive Load Identification Method Based on Faster R-CNN[J]. Distributed Energy Resources. 2022, 7(2): 26-33 https://doi.org/10.16513/j.2096-2185.DE.2207204

中图分类号： TK01; TM93

参考文献

列表( 原文顺序 | 文献年度倒序 | 文中引用次数倒序 ) 可视化分析

[1]	班明飞. 面向电动汽车用电清洁化的车-网联合运行技术研究[D]. 哈尔滨：哈尔滨工业大学，2019. BAN Mingfei. Research on vehicle-network combined operation technology for electric vehicle cleaning[D]. Harbin: Harbin Institute of Technology, 2019. 本文引用 [1]

[2]	陈倩. 基于深度学习模型融合的非侵入负荷识别研究[D]. 北京：华北电力大学，2020. CHEN Qian. Research on non-intrusive load identification based on deep learning model fusion[D]. Beijing: North China Electric Power University, 2020. 本文引用 [1]

[3]	程江洲，谢诗雨，张赟宁，等. 基于聚类加权随机森林的非侵入式负荷识别[J]. 智慧电力，2020, 48(8): 123-129. CHENG Jiangzhou, XIE Shiyu, ZHANG Yunning, et al. Non-invasive load identification based on clustering weighted random forest[J]. Smart Power, 2020, 48(8): 123-129. 本文引用 [1]

[4]	张铁峰，顾明迪. 电力用户负荷模式提取技术及应用综述[J]. 电网技术，2016, 40(3): 804-811. ZHANG Tiefeng, GU Mingdi. Review of power user load pattern extraction technology and application[J]. Power Grid Technology, 2016, 40(3): 804-811. 本文引用 [1]

[5]	NAGI J, YAP K S, TIONG S K, et al. Nontechnical loss detection for metered customers in power utility using support vector machines[J]. IEEE Transactions on Power Delivery, 2010, 25(2): 1162-1171. 本文引用 [1]

[6]	王庆玉，张青青，张高峰，等. 谱聚类算法在家用负荷识别中的应用[J]. 电测与仪表，2015, 52(1): 119-123. WANG Qingyu, ZHANG Qingqing, ZHANG Gaofeng, et al. Application of spectral clustering algorithm in household load identification[J]. Electrical Measurement and Instrumentation, 2015, 52(01): 119-123. 本文引用 [1]

[7]	曲朝阳，于华涛，郭晓利. 基于开启瞬时负荷特征的家电负荷识别[J]. 电工技术学报，2015, 30(): 358-364. 摘要 S1 QU Chaoyang, YU Huatao, GUO Xiaoli. Appliance load identification based on turn-on instantaneous load characteristics[J]. Journal of Electrotechnical Technology, 2015, 30(): 358-364. 本文引用 [1] 摘要 S1

[8]	马平，王茂海，吴新振，等. 基于PMU实测小扰动数据的负荷参数辨识方法[J]. 电力系统自动化，2016, 40(2): 43-48. MA Ping, WANG Maohai, WU Xinzhen, et al. Load parameter identification method based on PMU measured small disturbance data[J]. Automation of Electric Power Systems, 2016, 40(2): 43-48. 本文引用 [1]

[9]	李刚，于长海，王天军，等. 居民负荷设备的非侵入式识别方法研究[J]. 电力信息与通信技术，2017, 15(5): 54-60. LI Gang, YU Changhai, WANG Tianjun, et al. Research on non-intrusive identification method of residential load equipment[J]. Power Information and Communication Technology, 2017, 15(5): 54-60. 本文引用 [1]

[10]	王瑶. 基于改进的Faster R-CNN的快递识别系统研究[D]. 南京：南京邮电大学，2021. WANG Yao. Research on express recognition system based on improved Faster R-CNN[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2021. 本文引用 [1]

[11]	赵瑞珍. 小波理论及其在图像、信号处理中的算法研究[D]. 西安：西安电子科技大学，2001. ZHAO Ruizhen. Research on wavelet theory and its algorithm in image and signal processing[D]. Xian: Xidian University, 2001. 本文引用 [1]

[12]	杨凯. 基于深度学习的精密铸件缺陷检测方法研究与应用[D]. 太原：太原科技大学，2020. YANG Kai. Research and application of precision casting defect detection method based on deep learning[D]. Taiyuan: Taiyuan University of Science and Technology, 2020. 本文引用 [1]

[13]	范海兵，胡锡幸，刘明一，等. 深度学习在电力设备锈蚀检测中的应用[J]. 广东电力，2020, 33(9): 154-165. FAN Haibing, HU Xixing, LIU Mingyi, et al. Application of deep learning in power equipment corrosion detection[J]. Guangdong Electric Power, 2020, 33(9): 154-165 本文引用 [1]

[14]	BAO J, WEI S, LV J, et al. Optimized faster R-CNN in real-time facial expression classification[J]. IOP Conference Series Materials Science and Engineering, 2020, 790: 012148. 本文引用 [1]

[15]	常亮，邓小明，周明全，等. 图像理解中的卷积神经网络[J]. 自动化学报. 2016, 42(9): 1300-1312. CHANG Liang, DENG Xiaoming, ZHOU Mingquan, et al. Convolutional neural networks in image understanding[J]. Journal of Automation. 2016, 42(9): 1300-1312. 本文引用 [1]

[16]	顾桂梅，陈充，余晓宁，等. 基于改进Faster R-CNN的接触网管帽目标定位算法[J]. 激光与光电子学进展. 2022, 59(4): 140-150. GU Guimei, CHEN Chong, YU Xiaoning, et al. Target location algorithm for catenary cap based on improved Faster R-CNN[J]. Progress in Lasers and Optoelectronics. 2022, 59(4): 140-150. 本文引用 [1]

[17]	徐敏，罗劲，刘华. 基于Faster R-CNN级联的输电塔螺栓缺失检测[J]. 广东电力，2021, 34(6): 65-71. XU MIN, LUO Jin, LIU Hua. Detection of missing pylon bolts based on Faster R-CNN cascade[J]. Guangdong Electric Power, 2021, 34(6): 65-71. 本文引用 [3]

[18]	杨可军，杨建旭，陈思宝，等. 基于深度可分离卷积及SVD输电线路缺陷检测[J]. 智慧电力，2020, 48(10): 64-69, 77. YANG Kejun, YANG Jianxu, CHEN Sibao, et al. Methods of defect detection in transmission line based on depthwise separable convolution and SVD[J]. Smart Power, 2020, 48(10): 64-69, 77. 本文引用 [1]

[19]	赵永强，饶元，董世鹏，等. 深度学习目标检测方法综述[J]. 中国图象图形学报. 2020, 25(4): 629-654. ZHAO Yongqiang, RAO Yuan, DONG Shipeng, et al. A review of deep learning target detection methods[J]. Chinese Journal of Image Graphics. 2020, 25(4): 629-654. 本文引用 [1]

[20]	黄银燕. 基于多特征融合与机器学习的短期楼宇负荷预测[D]. 南宁：广西大学，2021. HUANG Yinyan. Short-term building load forecasting based on multi-feature fusion and machine learning[D]. Nanning: Guangxi University, 2021. 本文引用 [1]

[21]	DEBAETS L, RUYSSINCK J, DEVELDER C, et al. Appliance classification using VI trajectories and convolutional neural networks[J]. Energy and Buildings, 2018, 158: 32-36. 本文引用 [1]