Y. Benmahamed

Bio: Y. Benmahamed is an academic researcher from École Normale Supérieure. The author has contributed to research in topics: Dissolved gas analysis & Support vector machine. The author has an hindex of 3, co-authored 7 publications receiving 47 citations.

Application of SVM and KNN to Duval Pentagon 1 for transformer oil diagnosis

Abstract: The carried out investigations deal with the application of machine learning algorithms to Duval Pentagon 1 graphical method for the diagnosis of transformer oil. In fact, combined to graphical methods, pattern recognition aims to may complement. For this purpose, we have used the Support Vector Machine (SVM) and the K-Nearest Neighbor (KNN) algorithms combined to the Duval method. The SVM parameters have been optimized with the Particle Swarm Optimization (PSO). Inspired from IEC and IEEE, five classes namely PD, D1, D2, T1&T2, and T3 have been adopted. The combined algorithms were verified using 155 samples from IEC TC 10 and related databases. We found that KNN, SVM may complement the Duval Pentagon 1 diagnosis method.

Accuracy Improvement of Power Transformer Faults Diagnostic Using KNN Classifier With Decision Tree Principle

Abstract: Dissolved gas analysis (DGA) is the standard technique to diagnose the fault types of oil-immersed power transformers. Various traditional DGA methods have been employed to detect the transformer faults, but their accuracies were mostly poor. In this light, the current work aims to improve the diagnostic accuracy of power transformer faults using artificial intelligence. A KNN algorithm is combined with the decision tree principle as an improved DGA diagnostic tool. A total of 501 dataset samples are used to train and test the proposed model. Based on the number of correct detections, the neighbor’s number and distance type of the KNN algorithm are optimized in order to improve the classifier’s accuracy rate. For each fault, indeed, several input vectors are assessed to select the most appropriate one for the classifier’s corresponding layer, increasing the overall diagnostic accuracy. On the basis of the accuracy rate obtained by knots and type of defect, two models are proposed where their results are compared and discussed. It is found that the global accuracy rate exceeds 93% for the power transformer diagnosis, demonstrating the effectiveness of the proposed technique. An independent database is employed as a complimentary validation phase of the proposed research.

Accuracy Improvement of Transformer Faults Diagnostic Based on DGA Data Using SVM-BA Classifier

Abstract: The main objective of the current work was to enhance the transformer fault diagnostic accuracy based on dissolved gas analysis (DGA) data with a proposed coupled system of support vector machine (SVM)-bat algorithm (BA) and Gaussian classifiers. Six electrical and thermal fault classes were categorized based on the IEC and IEEE standard rules. The concentration of five main combustible gases (hydrogen, methane, ethane, ethylene, and acetylene) was utilized as an input vector of the two classifiers. Two types of input vectors have been tested; the first input type considered the five gases in ppm, and the second input type considered the gases introduced in the percentage of the sum of the five gases. An extensive database of 481 had been used for training and testing phases (321 data samples for training and 160 data samples for testing). The SVM model conditioning parameter “λ” and penalty margin parameter “C” were adjusted through the bat algorithm to develop a maximum accuracy rate. The SVM-BA and Gaussian classifiers’ accuracy was evaluated and compared with several DGA techniques in the literature.

Diagnosis of Power Transformer Oil Using PSO-SVM and KNN Classifiers

Abstract: In this paper, a Support Vector Machine (SVM) and the k nearest neighbor (KNN) classifiers are employed to diagnose the power transformer oil insulation using dissolved gas analysis (DGA). Different vectors are used as inputs for classifiers to achieve a maximum accuracy rate. The five input vectors that are considered: DGA in ppm, DGA in percentage, Dornenberg ratios, Rogers ratios and Duval triangle reports. Concerning the classes of faults, five types are adopted as output of classifiers (PD, D1, D2, T1&T2 and T3). In order to perform a better fault classification, The SVM parameters have been optimized with a Particle Swarm Optimization (PSO). Using Duval triangle reports, the PSO-SVM algorithm provides the highest accuracy rate than the KNN algorithm one.

Multi-objective optimization of 400 kV Composite Insulator Corona Ring Design

Abstract: The electric field distribution is one of the main factors governing the long-term reliability of high voltage composite insulators. However, under severe pollution conditions, electric field stresses, when exceeding thresholds and applying for long periods, could lead to degradation and deterioration of the housing materials and, therefore, to failures of the composite insulators. This paper is intended to improve the electric field and potential distributions by minimizing the corona discharge on a 400 kV AC transmission line composite insulator. The performances of three powerful multi-objective meta-heuristic algorithms, namely Ant Lion Optimizer (MOALO), Particle Swarm Optimizer (MOPSO), and non-dominated sorting genetic algorithm (NSGA-II) are established to achieve this goal. First, variations of electrical fields on the critical parts of the string are obtained using three-dimensional finite element method (FEM) software. Then, three objective functions are developed to establish the relationships between the electric field and the guard ring parameters. Finally, the optimization parameters consist of diameter, tube diameter, and installation height of the corona ring. The obtained results confirm the effectiveness of the three algorithms; the MOLAO is the better in terms of computing time and solution quality.

A Review of Graph Neural Networks and Their Applications in Power Systems

Abstract: Deep neural networks have revolutionized many machine learning tasks in power systems, ranging from pattern recognition to signal processing. The data in these tasks is typically represented in Euclidean domains. Nevertheless, there is an increasing number of applications in power systems, where data are collected from non-Euclidean domains and represented as graph-structured data with high dimensional features and interdependency among nodes. The complexity of graph-structured data has brought significant challenges to the existing deep neural networks defined in Euclidean domains. Recently, many publications generalizing deep neural networks for graph-structured data in power systems have emerged. In this paper, a comprehensive overview of graph neural networks (GNNs) in power systems is proposed. Specifically, several classical paradigms of GNNs structures (e.g., graph convolutional networks) are summarized, and key applications in power systems, such as fault scenario application, time series prediction, power flow calculation, and data generation are reviewed in detail. Furthermore, main issues and some research trends about the applications of GNNs in power systems are discussed.

Power Transformer Fault Diagnosis Based on DGA Using a Convolutional Neural Network With Noise in Measurements

Abstract: Fault type diagnosis is a very important tool to maintain the continuity of power transformer operation. Dissolved gas analysis (DGA) is one of the most effective and widely used techniques for predicting the power transformer fault types. In this paper, a convolutional neural network (CNN) model is proposed based on the DGA approach to accurately predict transformer fault types under different noise levels in measurements. The proposed model is applied with three categories of input ratios: conventional ratios (Rogers’4 ratios, IEC 60599 ratios, Duval triangle ratios), new ratios (five gas percentage ratios and new form six ratios), and hybrid ratios (conventional and new ratios together). The proposed model is trained and tested based on 589 dataset samples collected from electrical utilities and literature with varying noise levels up to ±20%. The results indicate that the CNN model with hybrid input ratios has superior prediction accuracy. The high accuracy of the proposed model is validated in comparison with conventional and recently published AI approaches. The proposed model is implemented based on MATLAB/toolbox 2020b.

Adaptive Dynamic Meta-Heuristics for Feature Selection and Classification in Diagnostic Accuracy of Transformer Faults

Abstract: Detection of transformer faults avoids the transformer’s undesirable loss from service and ensures utility service continuity. Diagnosis of transformer faults is determined using dissolved gas analysis (DGA). Several traditional DGA techniques, such as IEC code 60599, Rogers’ ratio method, Dornenburg method, Key gas method, and Duval triangle method, but these DGA techniques suffer from poor diagnosis transformer faults. Therefore, more research was used to diagnose transformer fault and diagnostic accuracy by combining traditional DGA techniques with artificial intelligence and optimization techniques. In this paper, a proposed Adaptive Dynamic Polar Rose Guided Whale Optimization algorithm (AD-PRS-Guided WOA) improves the classification techniques’ parameters that were used to enhance the transformer diagnostic accuracy. The results showed that the proposed AD-PRS-Guided WOA provides high diagnostic accuracy of transformer faults as 97.1%, which is higher than other DGA techniques in the literature. The statistical analysis based on different tests, including ANOVA and Wilcoxon’s rank-sum, confirms the algorithm’s accuracy.

Accuracy Improvement of Power Transformer Faults Diagnostic Using KNN Classifier With Decision Tree Principle

Abstract: Dissolved gas analysis (DGA) is the standard technique to diagnose the fault types of oil-immersed power transformers. Various traditional DGA methods have been employed to detect the transformer faults, but their accuracies were mostly poor. In this light, the current work aims to improve the diagnostic accuracy of power transformer faults using artificial intelligence. A KNN algorithm is combined with the decision tree principle as an improved DGA diagnostic tool. A total of 501 dataset samples are used to train and test the proposed model. Based on the number of correct detections, the neighbor’s number and distance type of the KNN algorithm are optimized in order to improve the classifier’s accuracy rate. For each fault, indeed, several input vectors are assessed to select the most appropriate one for the classifier’s corresponding layer, increasing the overall diagnostic accuracy. On the basis of the accuracy rate obtained by knots and type of defect, two models are proposed where their results are compared and discussed. It is found that the global accuracy rate exceeds 93% for the power transformer diagnosis, demonstrating the effectiveness of the proposed technique. An independent database is employed as a complimentary validation phase of the proposed research.