Fault diagnosis of power transformer based on multi-layer SVM classifier

Accurate faults diagnosis in power transformers is important for utilities to schedule maintenance and minimises the operation cost. Dissolved gas analysis (DGA) is one of the proven and widely accepted tools for incipient fault diagnosis in power transformers. To improve the accuracy and solve the cases that cannot be classified using Rogers’ Ratios, IEC ratios and Duval triangles methods, a novel DGA technique based on Parzen window estimation have been presented in this study. The model uses the concentrations of five combustible hydrocarbon gases: methane, ethane, ethylene, acetylene and hydrogen to compute the probability of transformers fault categories. Performance of the proposed method has been evaluated against different conventional techniques and artificial intelligence‐based approaches such as support vector machines, artificial neural networks, rough sets analysis and extreme learning machines for the same set of transformers. A comparison with other soft computing approaches shows that the proposed method is reliable and effective for incipient fault diagnosis in power transformers.

The condition monitoring and fault diagnosis of power transformers plays a significant role in the safe, stable and reliable operation of the whole power system. Dissolved gas analysis (DGA) methods are widely used for fault diagnosis, however, their accuracy is limited by the selection of DGA features and the performance of fault diagnosis models, for example, the classical support vector machine (SVM), is easily affected by unbalanced training samples. This paper presents a transformer fault diagnosis model based on chemical reaction optimization and a twin support vector machine. Twin support vector machines (TWSVMs) are used as classifiers for solving problems involving unbalanced and insufficient samples. Restricted Boltzmann machines (RBMs) are used for data preprocessing to ensure the effective identification of feature parameters and improve the efficiency and accuracy of fault diagnosis. The chemical reaction optimization (CRO) algorithm is used to optimize TWSVM parameters to select the optimal training parameters. The cross-validation (CV) method is used to ensure the reliability and generalization ability of the diagnostic model. Finally, the validity of the model is verified using real fault samples and random testing.

PurposePower transformers are vital components of an electrical network. A defective transformer can cause instability and blackouts in parts of the network. An accurate classification of different transformer faults results in a relatively accurate fault diagnosis and timely corrective actions. It is possible to increase productivity and reduce costs by using fault detection of power transformers through the analysis of gases dissolved in oil. The proposed technique is a suitable tool to help the utilities and engineers in charge of preventive maintenance by reducing the costs of different fault diagnosis tests for power transformers.Design/methodology/approachIn this paper, the IEC 60599 standard along with clustering and classification methods are used to classify power transformer’s fault types. K-means and Fuzzy C-means clustering methods are used for clustering, and the support vector machine (SVM) method is used for classification of different types of faults in ‎power ‎transformers. The performance of K-means and SVM methods is improved by using the Grasshopper Optimization Algorithm (GOA). The efficiency of the proposed methods is evaluated using real field data of power transformers. The purpose of this study is to propose hybrid methods including K-means-GOA clustering and SVM-GOA classification for accurate fault diagnosis. These methods have been used for the first time in fault diagnosis determination of power transformers through gas analysis. The Silhouette criteria is used in this paper to compare the efficiency of different clustering methods.FindingsSimulation results of the paper are based on the gas chromatography data related to 266 different real power transformers. They show the high accuracy and high-performance speed of intelligent clustering and classification methods compared to conventional ones. This analysis would be helpful in performing the required maintenance check and plan for repairs.Originality/valueThe applicability and efficiency of the proposed hybrid K-means-GOA and SVM-GOA models are verified for transformer fault detection using the experimental diverse data set including 266 set of real field test parameters of power transformers.

The power transformer is a valuable asset of the electrical system. A damage causes the interruption of electrical service and high repair costs for companies. Therefore, the detection of faults in incipient conditions is essential. In the recent literature Dissolved Gas Analysis (DGA) is the best accepted technique to the diagnosis of incipient faults in power transformers. This paper presents an approach to diagnosis fault by DGA using deep neural network, the drawbacks of the number of training patterns (amount of data) is satisfactory solved with using the Mean Shift algorithm. Likewise, the input and output parameters are conveniently selected, the input parameters being the gas relations established in the IEC 60599 standard acting in parallel with a new ratio of proposed gas (Rnew=C2H2 / C2H6) and a binary output. The proposed approach achieved an accuracy of 100%, both in the training and validation process as well.

Failure of power transformer is very complex, so that it is difficult to use the mathematical model to describe their faults. In this study, an intelligent diagnostic method based on ant colony-support vector machine (AC-SVM) approach is presented for fault diagnosis of power transformer. The AC-SVM selects kernel function parameter and soft margin constant C penalty parameter of support vector machine (SVM) classifier. The performance of the AC-SVM system proposed in this study is evaluated by cases in China. The test results show that this AC-SVM model is effective to detect failure of power transformer.

DGA is the best technique which is used to identify the incipient fault of the power transformer. The recently most advanced technology used for online fault diagnosis of the transformer is dissolved gas analysis (DGA) and it is technically acceptable. There are some methods on DGA based which are used to solve this analysis are Key-Gas method, Dornenburg method, International Electro technical Commission (IEC) ratio codes, Duval triangle and Rogers's ratio method. Also, the most well-known strategies are key gas and Roger's ratio. Artificial Neural Network (ANN), Fuzzy logic (FL), Neuro-Fuzzy, Support vector machine etc are the techniques which are used to solve dissolved gas analysis. Taking the concentrations of key gases(CO, CO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> , H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> , C <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">6</sub> , C <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sub> , C <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> & CH <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sub> ) of different fault conditions for the same sample unit, we can be identified the fault by using various techniques. Because of the assortment of gas data and operational natures, sometimes it is difficult to identify fault by the traditional method and hence fails to diagnose. And because of that it is important to build up a preventive maintenance technique for detection of an incipient fault of transformer automatically through dissolved gas analysis in transformer insulating oil. In this paper, we focus on two methods, Roger's ratio and IEC for the fault diagnosis of transformer insulating oil with Fuzzy interface system (FIS). This diagnosis is totally based on the ratio of concentration gases generated from single or numerous faults however with same predominant nature. At the point when gases generated from two or more faults then the relation between different gases becomes too complicated and unable to match the predefined ratio codes and fails to diagnose. Hence, to avoid such kind of issues we briefly focused on fuzzy logic and carried out diagnosis using Roger's ratio and IEC ratio codes.

This study presents a multi-class least square support vector machines (LS-SVM)-based classifier for transformer fault diagnosis. First, the original binary classifier is extended for multi-class classification that is common in fault diagnosis by using combination schemes, that is, the minimal output coding, error correcting output codes, one-against-one and one-against-all schemes. Second, the algorithm of particle swarm optimisation is implemented to select the optimal feature parameters for the multi-class LS-SVM classifiers. Then the effectiveness of the proposed approach is verified on the basis of the experiments on benchmark classification data and real-world transformer data. For comparison purpose, three widely used transformer diagnosis methods such as the IEC criteria, back propagation neural network and standard support vector machines are utilised. The results show the proposed approach has a better performance both in training and testing accuracies.

Dissolved gas analysis (DGA) is one of the most useful techniques to detect incipient faults in power transformers. However, the identification of the faulted location by the traditional method is not always an easy task due to the variability of gas data and operational variables. A novel extension method, which is based on the matter-element model and extended relation functions, is presented for fault diagnosis of power transformers. Thus, incipient faults in power transformers can be identified directly by the degree of relation. The application of this new method to some transformers has given promising results.

Power transformers are vital components of electrical power systems, ensuring reliable and efficient energy transfer between high-voltage transmission and low-voltage distribution networks. However, they are prone to various faults, such as insulation breakdowns, winding deformations, partial discharges, and short circuits, which can disrupt electrical service, incur significant economic losses, and pose safety risks. Traditional fault diagnosis methods, including visual inspection, dissolved gas analysis (DGA), and thermal imaging, face challenges such as subjectivity, intermittent data collection, and reliance on expert interpretation. To address these limitations, this paper proposes a novel distributed approach for multi-fault diagnosis of power transformers based on a self-organizing neural network combined with data augmentation and incremental learning techniques. The proposed framework addresses critical challenges, including data quality issues, computational complexity, and the need for real-time adaptability. Data cleaning and preprocessing techniques improve the reliability of input data, while data augmentation generates synthetic samples to mitigate data imbalance and enhance the recognition of rare fault patterns. A two-stage classification model integrates unsupervised and supervised learning, with k-means clustering applied in the first stage for initial fault categorization, followed by a self-organizing neural network in the second stage for refined fault diagnosis. The self-organizing neural network dynamically suppresses inactive nodes and optimizes its training parameter set, reducing computational complexity without sacrificing accuracy. Additionally, incremental learning enables the model to continuously adapt to new fault scenarios without modifying its architecture, ensuring real-time performance and adaptability across diverse operational conditions. Experimental validation demonstrates the effectiveness of the proposed method in achieving accurate, efficient, and adaptive fault diagnosis for power transformers, outperforming traditional and conventional machine learning approaches. This work provides a robust framework for integrating advanced machine learning techniques into power system monitoring, paving the way for automated, real-time, and reliable transformer fault diagnosis systems.

Dissolved gas analysis (DGA) approach is extensively applied to detect incipient faults of power transformers. This paper presents a novel DGA method for power transformer incipient fault diagnosis based on integrated adaptive neuro fuzzy inference system (ANFIS) and Dempster-Shafer Theory (DST). Four out of seven common conventional methods which are studied and compared for better consistency and accuracy, are used to develop new ANFIS based fault diagnosis models. To promote fault diagnostic performance further and make fault decision process more reliable and reasonable, an improved DST is introduced to integrate outputs of each ANFIS based model, and to provide comprehensive and convincing fault diagnosis results. The fault diagnosis capability of the proposed method is validated by a reported fault dataset and 10-fold cross validation experiment. The performance of the proposed method is compared with conventional approaches and ANFIS based models which demonstrate that the proposed method is superior to other methods and is more effective and stable for power transformer fault diagnosis with high accuracy and consistency.

Fault diagnosis can insure the power transformer safety and economic operation, and the data mining is the key technology of fault diagnosis for power transformer. In order to achieve the fast parallel fault diagnosis for power transformer, we need to put cloud computing technology into the smart grid. We give a parallel method of K-means based on MapReduce framework on the Hadoop distributed systems cluster to diagnose operation state of power transformer. Finally, through transformer fault diagnosis experimentations of massive DGA data, the results indicate closely linear speedup with an increasing number of node computers.

BA-PNN-based methods for power transformer fault diagnosis

Fault detection and diagnosis has an effective role for the safe operation and long life of systems. Condition monitoring is an appropriate way of the maintenance techniques which is applicable in the fault diagnosis of rotating machinery faults. We considered the Support Vector Machine (SVM) method for classifying the condition of centrifugal pump into two types of faults through six features: flow, temperature, suction pressure, discharge pressure, velocity, and vibration. The SVM method is based on statistical learning theory (SLT) and powerful for the problem with small sampling, nonlinear and high dimension. (L.V. Ganyun et al 2005). The SVM classifying is implemented with 4 kernel functions and the results of them are compared. We use an Artificial Neural Network (ANN) as the second classifying method to have comparison among the performance of two methods. After applying the two methods to our data set we make the data set noisy and again we try our SVMs and ANN to compare their robustness in noisy conditions and the results obtained from two methods confirmed the superiority of SVM with some specific kernel functions.

Most fault diagnosis technologies for transformers use artificial intelligence algorithms. Despite the emergence of artificial intelligence algorithms that have significantly enhanced the limitations of conventional diagnostic techniques and significantly improved the precision of fault diagnosis, several issues remain, including sluggish convergence, inadequate stability, restricted learning capacity, and inapplicability to train a considerable amount of samples. Thus, it is highly important for the secure functioning of the power grid to analyse rapid and precise transformer failure detection technologies and techniques. In this document, we initially examine the principles of gas generation, the process of gas generation, and the principle of analysis of dissolved gases (ADG) in transformer oil. Subsequently, we examine the related connection and differentiation technique among various elements of dissolved gas in transformers and transformer malfunctions and suggest a split technique for diagnosing and investigating transformer malfunctions. We utilise a large number of engineering sample data to test and tune the DBN and compare it with two transformer fault diagnosis methods: backpropagation neural network and support vector machine. The results show that DBN has better fault diagnosis performance and stronger expansibility, which can fully meet the actual engineering needs.

Power transformers undertake the task of transforming voltage and transmitting electrical energy. Its operating status is directly connected with the stability and safety of the whole power system, and it is very important to judge the operating conditions of power transformers and diagnose fault types. The use of dissolved gas analysis technology in oil can provide preliminary fault diagnosis for transformers. However, with the increasing demand for fault diagnosis accuracy in modern electrical equipment, relying only on dissolved gas analysis technology in oil cannot satisfy the demands. To lift the transformer fault diagnosis accuracy, this study introduces the K‐means algorithm into the model and constructs a high‐precision and fast convergence diagnosis method and a power transformer fault location recognition model. In the example analysis, kernel functions were selected for training five typical gases to obtain the optimal parameters, and their prediction curves and errors were analyzed. Its diagnostic accuracy is 98.4%, and the error in all five gases is within 1 (uL/L). The average error of the improved support vector machine intelligent algorithm is lower than that of the previous model and other prediction methods. By testing the same sample data, the correctness of this method was verified. The significance of improving support vector machines lies in further improving the performance and applicability of the original support vector machine algorithm, providing a basis for future transformer maintenance and contributing to social development and continuous improvement of economic benefits.