Power quality disturbances classification based on Gramian angular summation field method and convolutional neural networks

Abstract

This paper presents a novel hybrid approach combining Gramian Angular Summation Field (GASF) method with a convolutional neural network (CNN) to classify power quality disturbances. Firstly, a 1-D Power quality disturbance signal is transformed into a 2-D image file using GASF. Subsequently, CNN is implemented for features extraction and image classification. In this work, the synthetic power quality (PQ) disturbances are considered including nine single disturbances and five mixed disturbances. Further, to capture multi-scale aspects of power quality disturbances problem and reduce overfitting, a unit is designed using 2-D convolutional, pooling, and batch-normalization layers.The classification study is further supported by experimental signals obtained on a prototype setup of PV system. The obtained results demonstrate the efficiency and reliability of the proposed method. The proposed method is compared with the other advanced CNNs and other conventional methods to illustrate its effectiveness.

A Review on Intelligent Detection and Classification of Power Quality Disturbances: Trends, Methodologies, and Prospects

“…Feature sparse, and fusion selection was performed on the raw voltage transformed GIP [51] and later combined with ANN to improve the classification accuracy. In addition, GASF was presented to convert one-dimensional PQD signals into two-dimensional image files [52] and subsequently applied to prototype photovoltaic systems. The texture image algorithm was converted into a onedimensional waveform algorithm in [53] with a satisfactory PQD classification effect.…”

Lightweight Gramian Angular Field classification for edge internet of energy applications

“…From another perspective, a related research discussed classifying power quality disturbances using GASF with a CNN [ 30 ]. After GAF representations are generated, a CNN is used to extract features and classify images through 2-D convolutional, pooling, and batch-normalization layers to capture multi-scale features of the power quality disturbances problem and reduce overfitting.…”

A Temporal Ensembling Based Semi-Supervised Graph Convolutional Network for Power Quality Disturbances Classification

“…Balouji et al [12] used PQDs' voltage images obtained from the power grid. Shukla et al [13] used GAF (Gramian Angular Field) to convert PQDs series into an image. Both [12] and [13] classify the PQDs images by using a two-dimensional Convolutional Neural Networks (CNN).…”

“…Shukla et al [13] used GAF (Gramian Angular Field) to convert PQDs series into an image. Both [12] and [13] classify the PQDs images by using a two-dimensional Convolutional Neural Networks (CNN). Wang S. et al [14] proposed a novel full closed-loop approach to detect and classify PQDs based on a deep convolutional neural network.…”

“…Methods for classifying PQDs primarily rely on supervised learning [12][13][14][15][16][17][18], which requires labeled data throughout the dataset. However, in practical production scenarios, labeling data incurs significant costs.…”