Accurate classification of power quality disturbance based on 3D visualized spiral curve and hybrid ER-MVCNN model

• Published in: Measurement : journal of the International Measurement Confederation 2024-05, Vol.231, p.114654, Article 114654
• Main Authors: Song, Juncai, Wu, Jing, Wang, Xiaoqing, Duan, Zhangling, Wang, Xiaoxian, Lu, Siliang
• Format: Article
• Language: English
• Subjects: 3D-visualized spiral curve; Efficient channel attention-ResNet multi-view convolution neural network (ER-MVCNN); Multi-view convolutional neural network (MVCNN); Power quality disturbance; Recognition and classification
• ISSN: 0263-2241
• DOI: 10.1016/j.measurement.2024.114654

•Propose a new PQD accurate recognition method based on 3D- VSC and ER-MVCNN.•PQD signal is converted into 3D spiral curve to realize visual enhancement.•Multichannel image feature of 3D-VSC is fused by MVCNN.•Hybrid model is consisted by MVCNN and ECA-Resnet to improve performances.•Real experiment and IEEE PES datasets are used to certify advantages of proposed method. This work proposes a new method for accurate power quality disturbance (PQD) classification. Firstly, 3D-visualized spiral curve (3D-VSC) is innovatively proposed to convert 1D PQD signal into 3D spiral curve. It can display time-frequency information in multi-dimensional perspectives and the disturbance characteristics more intuitively in image visual sense, which can realize PQD features enhancement. Secondly, efficient channel attention-ResNet multi-view convolution neural network (ER-MVCNN) hybrid model is creatively proposed by introducing ECA-ResNet as feature extraction module. It can solve limitations of multi-view convolution neural network (MVCNN) in single-view feature extraction and defects of multi-view feature fusion in the weighting problem, which can effectively achieve classification accuracy to 99.68 %. Comparison experiments with MVCNN, AlexNet-MVCNN, VGGNet-MVCNN, ResNet18-MVCNN, and SENet-ResNet-MVCNN show that ER-MVCNN has higher accuracy by 12.4 %, 6.79 %, 6.14 %, 3.86 %, and 0.88 % respectively. Finally, through establishing PQD experiment platform and IEEE PES datasets to verify high accuracy and robustness of proposed method.