基于混合多尺度模糊熵的配电网电能质量复合扰动检测-电气工程与自动化-CSCIED科技核心评价数据库-手机版

基于混合多尺度模糊熵的配电网电能质量复合扰动检测

Multiscale fuzzy entropy-based composite disturbance detection for power quality in distribution grids

ES评分 0 浏览量：40 下载量：0

DOI	10.12208/j.jeea.20250076
刊名	电气工程与自动化 Journal of Electrical Engineering and Automation
年，卷(期)	2025, 4(3)
作者	马国煜, 陶锴,
作者单位	南京邮电大学自动化学院、人工智能学院江苏南京
摘要	电能质量扰动检测对保障分布式新能源接入的电力系统运行稳定性至关重要。为提升电能质量扰动检测精度，本文提出了一种融合NRBO (Newton Raphson Based Optimizer)、BiGRU (Gated Recurrent Unit)及AM (Attention Mechanism)的扰动自适应检测方法。首先，通过NRBO优化模态分解的超参数，并提取电能质量扰动信号的混合多尺度模糊熵(Composite Multiscale Fuzzy Entropy, CMFE)特征向量。提取扰动信号特征，为后续检测提供可靠的数据基础。随后，本文提出BiGRU-AM模型以检测多类型电能质量复合扰动。为验证方法的有效性，本文开展了8种单一扰动和8种复合扰动的检测实验，并与其他6种算法对比。结果表明，该方法显著提升了性能，在扰动特征提取和检测准确性方面有好的表现优异。
Abstract	Power quality disturbance detection is crucial for ensuring the operational stability of power systems with integrated distributed renewable energy. To enhance detection accuracy, this paper proposes an adaptive disturbance detection method integrating the NRBO, BiGRU-AM. First, the hyperparameters of modal decomposition are optimized via NRBO, and the composite multiscale fuzzy entropy (CMFE) feature vectors of power quality disturbance signals are extracted. This establishes a reliable data foundation for subsequent detection. Subsequently, a BiGRU-AM model is proposed to detect multiple types of composite power quality disturbances. To validate the method's effectiveness, experiments were conducted on eight types of single disturbances and eight types of composite disturbances, with comparisons against six other algorithms. The results demonstrate that the proposed method significantly improves performance, exhibiting excellent accuracy in both disturbance feature extraction and detection.
关键词	配电网、电能质量扰动、NRBO、CMFE、BiGRU-AM
KeyWord	Distribution Network, Power Quality Disturbance, NRBO, CMFE, BiGRU-AM
基金项目
页码	38-48

参考文献
相关文献

[1] Ren Gang, Zha Xianguang, Jiang Bing, et al. Location of Multiple Types of Faults in Active Distribution Networks Considering Synchronization of Power Supply Area Data
[J]. Applied Sciences, 2022, 12(19): 10024.

[2] 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):232-43.

[3] 时帅, 陈子文, 黄冬梅, 等. 基于MTF可视化和改进DenseNet神经网络的电能质量扰动识别算法
[J]. 电力科学与技术学报, 2024, 39(04): 102-111.

[4] 张成, 赵涛, 朱爱华, 等. 弱电网下并联逆变器稳定性及电能质量治理研究
[J]. 电力工程技术, 2022, 41(03): 224-230.

[5] 王守相, 李慧强, 赵倩宇, 等. 基于时序二维变换和多尺度Transformer的电能质量扰动分类方法
[J]. 电力系统自动化, 2025, 49(07): 198-207.

[6] 贺才郡, 李开成, 董宇飞, 等. 基于知识蒸馏与RP-MobileNetV3的电能质量复合扰动识别
[J]. 电力系统保护与控制, 2023, 51(14): 75-84.

[7] Ni Q, Luo H, Liu J, et al. A Feature Vector Learning-Based Method for Diagnosing Main Circuit Ground Faults in Electrical Traction Drive Systems
[J]. IEEE Transactions on Power Electronics. 2024, 39(2): 2537-45.

[8] Chen X, Ji N, Qin X, et al. Transformer Fault Diagnosis Based on the Improved Sparrow Search Algorithm and Random Forest Feature Selection
[C]. 2024 3rd International Conference on Energy and Electrical Power Systems (ICEEPS), Guangzhou, China, 2024, 1086-1091.

[9] Chen W, Shi K. A deep learning framework for time series classification using Relative Position Matrix and Convolutional Neural Network
[J]. Neurocomputing. 2019, 384-94.

[10] Tao K, Chen G, Wang Q, et al. Ultrasonic Curved Coordinate Transform-RAPID With Bayesian Method for the Damage Localization of Pipeline
[J]. IEEE Transactions on Industrial Electronics. 2024, 71(11):15066-15076.

[11] Tao K, Wang Q, Yue D. Data compression and damage evaluation of underground pipeline with musicalized sonar GMM
[J]. IEEE Transactions on Industrial Electronics. 2023, 71(3): 3093-102.

[12] Tao K, Xu M, Wang Q, et al. Vibration Signal ESSA-CVMD and Entropy Method for The Leakage Assessment of Pipe
[J]. IEEE Transactions on Instrumentation and Measurement. 2025

[13] Alathari A J M, Mashhadany A Y, Bakar A, et- al. COVID-19 IgG Antibodies Detection Based on CNN-BiGRU Algorithm Combined with Fiber-Optic Dataset
[J]. Journal of virological methods, 2024: 115011.

[14] Zheng W, Jiang J, Tao K. A method based on musical-staff-inspired signal processing model for measuring rock moisture content
[J]. Measurement. 2018 : 577-85.

[15] 陈武, 钟建伟, 杨永超, 等. 基于RQA与DAGSVM的电能质量扰动识别方法
[J]. 计算机仿真, 2025, 42(01): 52-56.

引用本文

马国煜, 陶锴. 基于混合多尺度模糊熵的配电网电能质量复合扰动检测 [J]. 电气工程与自动化. 2025; 4; (3). 38 - 48.

文献评论

相关学者

相关机构