Classification of Partial Discharge Images Using Deep Convolutional Neural Networks

Abstract

Artificial intelligence-based solutions and applications have great potential in various fields of electrical power engineering. The problem of the electrical reliability of power equipment directly refers to the immunity of high-voltage (HV) insulation systems to operating stresses, overvoltages and other stresses—in particular, those involving strong electric fields. Therefore, tracing material degradation processes in insulation systems requires dedicated diagnostics; one of the most reliable quality indicators of high-voltage insulation systems is partial discharge (PD) measurement. In this paper, an example of the application of a neural network to partial discharge images is presented, which is based on the convolutional neural network (CNN) architecture, and used to recognize the stages of the aging of high-voltage electrical insulation based on PD images. Partial discharge images refer to phase-resolved patterns revealing various discharge stages and forms. The test specimens were aged under high electric stress, and the measurement results were saved continuously within a predefined time period. The four distinguishable classes of the electrical insulation degradation process were defined, mimicking the changes that occurred within the electrical insulation in the specimens (i.e., start, middle, end and noise/disturbance), with the goal of properly recognizing these stages in the untrained image samples. The results reflect the exemplary performance of the CNN and its resilience to manipulations of the network architecture and values of the hyperparameters. Convolutional neural networks seem to be a promising component of future autonomous PD expert systems.

Partial Discharge Online Detection for Long-Term Operational Sustainability of On-Site Low Voltage Distribution Network Using CNN Transfer Learning

“…The extracted pattern was finally classified using a fully connected layer and softmax function. The article [22] investigated CNN models with several layers, max pooling, and dropout with PD images. The models were used and tested for high voltage insulation defects.…”

Anomaly Detection, Trend Evolution, and Feature Extraction in Partial Discharge Patterns

“…Simultaneously, the PD images were recorded in a long time-stamped sequence. The details about the experiment and setting of the CNN are presented in [36]. The four characteristic classes of the HV insulation aging were associated with the stages of the insulation deterioration, and were denoted as Stage 1, Stage 2, and Stage 3.…”

“…The application of machine learning, especially neural networks in this field, was observed in the early 1990s, e.g., [3][4][5][6][7][8][9][10][11][12][13][14], which is when the first automated analyzers and expert systems with AI elements were designed, e.g., [7][8][9]13,[15][16][17][18][19]. Therefore, one can observe a continuous strive for advancements in evaluation methods, instrumentation, methodologies, and algorithms of future diagnostics and monitoring systems of HV insulation of power equipment [21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38][39][40]. Over the last decade, strong attention in pattern recognition was paid on deep neural networks as a technique presenting high performance, e.g., [22,[25][26][27][33]…”

“…Therefore, one can observe a continuous strive for advancements in evaluation methods, instrumentation, methodologies, and algorithms of future diagnostics and monitoring systems of HV insulation of power equipment [21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38][39][40]. Over the last decade, strong attention in pattern recognition was paid on deep neural networks as a technique presenting high performance, e.g., [22,[25][26][27][33][34][35][36], not only with respect to PD images but also for waveform analysis, e.g., [11,32]. Nowadays, state-of-the-art in partial discharge acquisition are phase-resolved PD (PRPD) patterns, which can be interpreted also as images.…”

Detection and Localization of Partial Discharge in Connectors of Air Power Lines by Means of Ultrasonic Measurements and Artificial Intelligence Models

“…An increasing number of researches that use deep learning (DL) neural networks for PD classification can be noticed recently. Florkowski [27] used convolutional neural networks (CNN) to detect deterioration of electrical insulation from the phased resolved PD images. In contrast to machine learning methods, DL do not require feature extraction, can handle large datasets and provide better accuracy [28,29].…”