基于条件网络和知识注入的多标签学习电能质量扰动识别与分类方法

doi:10.19595/j.cnki.1000-6753.tces.242088

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (3871 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The large-scale integration of renewable energy into the new power system has brought numerous power quality disturbances (PQDs), which severely affect the safe and stable operation of the power grid. Accurate identification of PQD types is crucial for ensuring the stable operation of electrical equipment and achieving high-quality power supply. To address the common issues of low recognition accuracy, large model parameters, and high computational complexity in existing PQDs recognition and classification methods, this paper proposes a multi-label learning method for PQDs identification and classification based on conditional networks and knowledge injection.
Firstly, this method integrates a one-dimensional convolutional neural network (1D-CNN) with a one-dimensional group convolutional neural network (1D-GCCN) to construct a one-dimensional multi-fusion convolutional network (1D-MFCN), which effectively extracts key features from PQDs signals while reducing the computational complexity of the model. Subsequently, to further capture the temporal characteristics of PQDs, a long short-term memory (LSTM) network optimized by a simple, parameter-free attention mechanism (SimLSTM) is proposed. Compared with traditional LSTM, the SimLSTM is capable of automatically identifying salient features and assigning appropriate weights, thereby enhancing the precision of temporal feature extraction. In addition, a conditional network is designed to predict the number of PQDs occurring simultaneously, and a knowledge injection module is constructed by leveraging the mutually exclusive nature of swell, sag, and interruption disturbances. By incorporating the conditional network and knowledge injection mechanism, the proposed method alleviates the burden on the main network in distinguishing complex disturbance types and improves the overall classification accuracy. Finally, the outputs from the conditional network and the main network are fused through a label threshold function to produce the final disturbance recognition and classification results.
Simulation results demonstrate that, under the presence of random white noise, the proposed method achieves an accuracy of 99.47% with only 0.093 M parameters, enabling high-precision and lightweight recognition of complex disturbances. Furthermore, when tested on 14 types of PQDs collected from an actual hardware platform, the proposed model attains an average recognition accuracy of 98.45%, with a perfect 100% accuracy on four-type disturbances, further validating the reliability and effectiveness of the proposed approach.

Key words： Power quality disturbances conditional network knowledge injection multi-label learning long short-term memory (LSTM)

Received: 19 November 2024

PACS:

TM761

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Huang Jie
	Li Jianmin
	Zhu Bingfan
	Zhang Chicheng
	Liang Chengbin

Cite this article:

Huang Jie,Li Jianmin,Zhu Bingfan等. A Multi-Label Learning Method Based on Conditional Networks and Knowledge Injection for Power Quality Disturbance Identification and Classification[J]. Transactions of China Electrotechnical Society, 2025, 40(23): 7652-7663.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.242088 OR https://dgjsxb.ces-transaction.com/EN/Y2025/V40/I23/7652

[1] 李勇, 常樊睿, 彭衍建, 等. 分散式新能源并网稳定性问题分析与控制方法[J]. 高电压技术. 2025, 51(4): 1543-1559.
Li Yong, Chang Fanrui, Peng Yanjian, et al.analysis and control methods of stability problems for decentra-lized renewable generations integrated into grid[J]. High Voltage Engineering, 2025, 51(4): 1543-1559.
[2] Li Jianmin, Hong Dian, Lin Haijun, et al.A generic flicker measurement method based on feature sequence reconstruction[J]. IEEE Transactions on Instrumen-tation and Measurement, 2023, 72: 9003709.
[3] 刘伟, 王凯. 基于通道选择多尺度融合深度残差网络的电能质量扰动识别[J]. 电气技术, 2023, 24(5): 11-15.
Liu Wei, Wang Kai.Power quality disturbance identification of multi-scale fusion depth residual network based on channel selection[J]. Electrical Engineering, 2023, 24(5): 11-15.
[4] 吴建章, 梅飞, 郑建勇, 等. 基于改进经验小波变换和XGBoost的电能质量复合扰动分类[J]. 电工技术学报, 2022, 37(1): 232-243, 253.
Wu Jianzhang, Mei Fei, Zheng Jianyong, et al.Recognition of multiple power quality disturbances based on modified empirical wavelet transform and XGBoost[J]. Transactions of China Electrotechnical Society, 2022, 37(1): 232-243, 253.
[5] 张逸, 李渴, 邵振国, 等. 基于数据关联性分析的工业用户电能质量特征识别[J]. 电工技术学报. 2023, 38(13): 3512-3526.
Zhang Yi, Li Ke, Shao Zhenguo, et al.power quality characteristics identification of industrial users based on data correlation analysis[J]. Transactions of China Electrotechnical Society, 2023, 38(13): 3512-3526.
[6] 朱琴跃, 于逸尘, 占岩文, 等. 基于短时傅里叶变换和深度网络的模块化多电平换流器子模块IGBT开路故障诊断[J]. 电工技术学报, 2024, 39(12): 3840-3854.
Zhu Qinyue, Yu Yichen, Zhan Yanwen, et al.IGBT open-circuit fault diagnosis of modular multilevel converter sub-module based on short-time Fourier transform and deep networks[J]. Transactions of China Electrotechnical Society, 2024, 39(12): 3840-3854.
[7] 肖贤贵, 李开成, 贺才郡, 等. 基于稀疏分解和复合熵编码的电能质量扰动数据高效压缩算法[J]. 电工技术学报, 2023, 38(23): 6318-6331.
Xiao Xiangui, Li Kaicheng, He Caijun, et al.A highly efficient compression algorithm for power quality disturbance data using sparse decomposition and hybrid entropy encoding[J]. Transactions of China Electrotechnical Society, 2023, 38(23): 6318-6331.
[8] 刘云鹏, 来庭煜, 刘嘉硕, 等. 特高压直流换流阀饱和电抗器振动声纹特性与松动程度声纹检测方法[J]. 电工技术学报, 2023, 38(5): 1375-1389.
Liu Yunpeng, Lai Tingyu, Liu Jiashuo, et al.vibration voiceprint characteristics and looseness detection method of UHVDC converter valve saturable reactor[J]. Transactions of China Electrotechnical Society. 2023, 38(5): 1375-1389.
[9] 姜涛, 刘博涵, 李雪, 等. 基于自适应投影多元经验模态分解的电力系统强迫振荡源定位[J]. 电工技术学报, 2023, 38(13): 3527-3538.
Jiang Tao, Liu Bohan, Li Xue, et al.Forced oscillation location in power systems using adaptive projection intrinsically transformed multiple empirical mode decomposition[J]. Transactions of China Electrotechnical Society, 2023, 38(13): 3527-3538.
[10] 王玉梅, 郑义. 基于参数优化的VMD与TEO融合的微电网电能质量检测方法[J]. 电气工程学报, 2023, 18(2): 164-173.
Wang Yumei, Zheng Yi. microgrid power quality detection method based on parameter optimization fusion of VMD and TEO[J]. Journal of Electrical Engineering, 2023, 18(2): 164-173.
[11] 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, Lü Ganyun, Ye Jiaxing.Recognition of complex PQ disturbances based on SVM cascaded decision tree[J]. Journal of Electrical Engineering, 2023, 18(2): 149-156.
[12] Motlagh S Z T, Akbari Foroud A. Power quality disturbances recognition using adaptive chirp mode pursuit and grasshopper optimized support vector machines[J]. Measurement, 2021, 168: 108461.
[13] 许广林, 陈文涛, 刘涛, 等. 基于AO-ST-ANN的电能质量扰动分类方法[J]. 电气技术与经济, 2024(08): 70-75.
Xu Guanglin, Chen Wentao, Liu Tao, et al.Power quality disturbance classification method based on AO-ST-ANN[J]. Electrical equipment and economy. 2024(08): 70-75.
[14] Upendra Vishwanath Y S, Esakkirajan S, Keerthiveena B, et al. A generalized classification framework for power quality disturbances based on synchrosqueezed wavelet transform and convolutional neural networks[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 2525313.
[15] 罗溢, 李开成, 肖贤贵, 等. 基于马尔可夫转移场和深度残差网络的电能质量复合扰动多标签分类[J]. 中国电机工程学报, 2024, 44(7): 2519-2531.
Luo Yi, Li Kaicheng, Xiao Xiangui, et al.Multi-label classification of power quality composite disturbances based on Markov transfer field and ResNet[J]. Proceedings of the CSEE, 2024, 44(7): 2519-2531.
[16] Ekici S, Ucar F, Dandil B, et al.Power quality event classification using optimized Bayesian convolutional neural networks[J]. Electrical Engineering, 2021, 103(1): 67-77.
[17] Gu Dexi, Gao Yunpeng, Li Yunfeng, et al.A novel label-guided attention method for multilabel classification of multiple power quality disturbances[J]. IEEE Transactions on Industrial Informatics, 2022, 18(7): 4698-4706.
[18] 付宽, 王洪新, 刘杰, 等. 基于马尔可夫变迁场和EfficientNet的复合电能质量扰动识别[J]. 电网与清洁能源, 2024, 40(4): 74-83.
Fu Kuan, Wang Hongxin, Liu Jie, et al.Recognition of composite power quality disturbances based on MTF EfficientNet convolutional neural network[J]. Power System and Clean Energy, 2024, 40(4): 74-83.
[19] Ma Jun, Liu Jie, Qiu Wei, et al.An intelligent classification framework for complex PQDs using optimized KS-transform and multiple fusion CNN[J]. IEEE Transactions on Industrial Informatics, 2024, 20(2): 1776-1785.
[20] 兰名扬, 刘宇龙, 金涛, 等. 基于可视化轨迹圆和ResNet18的复合电能质量扰动类型识别[J]. 中国电机工程学报, 2022, 42(17): 6274-6285.
Lan Mingyang, Liu Yulong, Jin Tao, et al.an improved recognition method based on visual trajectory circle and ResNetn18 for complex power quality disturbances[J]. Proceedings of the CSEE. 2022, 42(17): 6274-6285.
[21] Qiu Wei, Tang Qiu, Liu Jie, et al.An automatic identification framework for complex power quality disturbances based on multifusion convolutional neural network[J]. IEEE Transactions on Industrial Informat-ics, 2020, 16(5): 3233-3241.
[22] 龚正, 邹阳, 金涛, 等. 基于特征融合并行优化模型的电能质量扰动分类方法[J]. 中国电机工程学报, 2023, 43(3): 1017-1026.
Gong Zheng, Zou Yang, Jin Tao, et al.classification method of power quality disturbances based on optimized parallel model of features merging[J]. Proceedings of the CSEE, 2023, 43(3): 1017-1026.
[23] IEEE Power & Energy Society. IEEE Std 1159TM-2019 IEEE recommended practice for monitoring electric power quality: IEEE Std 1159TM-2019[S]. Washington, USA: IEEE, 2019.
[24] Mohan N, Soman K P, Vinayakumar R.Deep power: Deep learning architectures for power quality disturbances classification[C]//2017 International Conference on Technological Advancements in Power and Energy(TAP Energy), Kollam, India, 2017: 1-6.
[25] Wang Shouxiang, Chen Haiwen.A novel deep learning method for the classification of power quality disturbances using deep convolutional neural network[J]. Applied Energy, 2019, 235: 1126-1140.
[26] 金涛, 陈煌滨, 郑熙东, 等. 基于差分编码嵌入的两阶段多通道电能质量扰动分类与时间定位网络[J/OL]. 中国电机工程学报, 2025:1-16[2025-06-20]. http://kns.cnki.net/kcms/detail/11.2107.tm.20250325.1106.002.html.
Jin Tao, Chen Huangbin, Zheng Xidong, et al.A two-stage multi-channel power quality disturbance classification and time localizationnetwork based on differential encoding and embedding[J]. Proceedings of the CSEE, 2025: 1-16[2025-06-20]. http://kns.cnki.net/kcms/detail/11.2107.tm.20250325.1106.002.html.
[27] Wang Qingle, Jin Yu, Li Xinhao, et al.An advanced quantum support vector machine for power quality disturbance detection and identification[J]. EPJ Quantum Technology, 2024, 11(1): 70.
[28] Ray P K, Mohanty S R, Kishor N, et al.Optimal feature and decision tree based classification of power quality disturbances in distributed generation systems[C]//2014 IEEE PES General Meeting | Conference & Exposition, National Harbor, MD, USA, 2014: 1.
[29] Cui Chenhui, Duan Yujie, Hu Hongli, et al.Detection and classification of multiple power quality disturbances using stockwell transform and deep learning[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 2519912.
[30] 贺才郡, 李开成, 杨王旺, 等. 基于双通道GAF和深度残差网络的电能质量复合扰动识别[J]. 电网技术, 2023, 47(1): 369-376.
He Caijun, Li Kaicheng, Yang Wangwang, et al.Power quality compound disturbance identification based on dual channel GAF and depth residual network[J]. Power System Technology, 2023, 47(1): 369-376.