摘要
Power Quality (PQ) combined disturbances become common along with ubiquity of voltage flickers and harmonics. This paper presents a novel approach to classify the different patterns of PQ combined disturbances. The classification system consists of two parts, namely the feature extraction and the automatic recognition. In the feature extraction stage, Phase Space Reconstruction (PSR), a time series analysis tool, is utilized to construct disturbance signal trajectories. For these trajectories, several indices are proposed to form the feature vectors. Support Vector Machines (SVMs) are then implemented to recognize the different patterns and to evaluate the efficiencies. The types of disturbances discussed include a combination of short-term dis-turbances (voltage sags, swells) and long-term disturbances (flickers, harmonics), as well as their homologous single ones. The feasibilities of the proposed approach are verified by simulation with thousands of PQ events. Comparison studies based on Wavelet Transform (WT) and Artificial Neural Network (ANN) are also reported to show its advantages.
Power Quality （PQ） combined disturbances become common along with ubiquity of voltage flickers and harmonics. This paper presents a novel approach to classify the different patterns of PQ combined disturbances. The classification system consists of two parts, namely the feature extraction and the automatic recognition. In the feature extraction stage, Phase Space Reconstruction （PSR）, a time series analysis tool, is utilized to construct disturbance signal trajectories. For these trajectories, several indices are proposed to form the feature vectors. Support Vector Machines （SVMs） are then implemented to recognize the different patterns and to evaluate the efficiencies. The types of disturbances discussed include a combination of short-term disturbances （voltage sags, swells） and long-term disturbances （flickers, harmonics）, as well as their homologous single ones. The feasibilities of the proposed approach are verified by simulation with thousands of PQ events. Comparison studies based on Wavelet Transform （WT） and Artificial Neural Network （ANN） are also reported to show its advantages.
基金
Project (No. 50437010) supported by the Key Program of the Na-tional Natural Science Foundation of China
关键词
轴承质量
网络分析
相位重建
矢量
Power Quality （PQ）, Combined disturbance, Classification, Phase Space Reconstruction （PSR）, Support Vector Machines （SVMs）
