期刊
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
卷 70, 期 6, 页码 6356-6365出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIE.2022.3194575
关键词
Feature extraction; Signal resolution; Gaussian noise; Time-frequency analysis; Power quality; Renewable energy sources; Discrete wavelet transforms; Ensemble intrinsic timescale decomposition (EITD); global depthwise shufflenet; power quality disturbance (PQD); renewable energy
In this article, an automatic approach for power quality disturbances (PQDs) classification is proposed, which is suitable for complex phenomena. The proposed method includes ensemble intrinsic timescale decomposition (EITD) for decomposing PQDs and a global depthwise shuffle CNN (GSCNN) for improving performance and reducing parameters. Based on EITD and GSCNN, an automatic framework is created to identify and classify complex PQDs.
In the context of unprecedented attention to renewable energy, wind and photovoltaic power generations are widely used. However, this process introduces a large number of solid-state switching and nonlinear loads, which makes power quality disturbances (PQDs) complex and brings unknown challenges to power-pollution control. As a prerequisite for power-pollution control, this article proposes an automatic PQDs classification approach, which is suitable for complicated phenomena. First, an ensemble intrinsic timescale decomposition (EITD) method is proposed to decompose the PQDs, which overcomes the decomposition level's endpoint effect and frequency aliasing by adding Gaussian noise and integrating multiple subcomponents. Then, utilizing the global depthwise convolution layer and parameter rectified linear unit, a global depthwise shuffle CNN (GSCNN) is proposed to improve the performance and reduce the number of parameters. Based on EITD and GSCNN, an automatic framework is proposed to identify and classify complex PQDs. Simulation experiments and hardware platform tests show that the proposed framework has superior performance for complex and even nonlinear disturbances under different noise.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据