Transformer Fault Types Research Articles

Exploring transformer fault detection using RFID technology

Real-time monitoring and fault diagnosis of transformers are essential for the stable power system operation. This paper presents an RFID-based transformer fault feature extraction and classification algorithm. Experiments show that monitored current signals are stable while the temperature peak is 356°C. Hilbert decomposition reveals regular current and voltage patterns that can be used as fault indicators. Signal strength classification accuracy reached 80% . At rated load, the transformer temperature soared to 186°C, indicating overheating issues. The monitoring during a sample day showed that overload events were concentrated from 16:00-20:00, which required attention. The approach helps accurately identify transformer fault types from real-time RFID data for proactive maintenance. Compared to reactive repairs after failures, this not only improves employee productivity but also reduces costs. Based on customized RFID deployment, the algorithm contributes to the stability and economy of power infrastructure.

Fault Diagnosis of Oil-Immersed Transformers Based on the Improved Neighborhood Rough Set and Deep Belief Network

As one of the essential components in power systems, transformers play a pivotal role in the transmission and distribution of renewable energy generation. Accurate diagnosis of transformer fault types is crucial for maintaining the safety of power systems. The current focus in research lies in transformer fault diagnosis methods based on Dissolved Gas Analysis (DGA). Traditional diagnostic methods directly utilize the five fault gases from DGA data as model input features, but this approach does not comprehensively reflect all potential fault types in transformers. In this paper, a non-coding ratio method was employed to generate 35 fault gas ratios based on the five fault gases, subsequently refined through correlation analysis to eliminate redundant feature variables, resulting in 15 significantly representative fault gas ratios. To further streamline the feature variables and remove non-contributing elements to fault diagnosis, an improved Neighborhood Rough Set (INRS) algorithm was introduced, leveraging symmetrical uncertainty measurement. By resorting to the proposed INRS, eight most representative fault gas ratios were selected as input variables for constructing a Deep Belief Network (DBN) diagnostic model. Experimental results on Dissolved Gas Analysis (DGA) data confirmed the effectiveness and accuracy of the proposed method.

Transformer fault classification for diagnosis based on DGA and deep belief network

Power transformer plays a very important role in power system, its long-term operation will cause various kinds of faults. Accurate identification and timely elimination of transformer faults are the basis of safe operation of power grid. As one of the most commonly used fault diagnosis methods, dissolved gas analysis (DGA) technology is used to identify fault types through dissolved gas in transformer oil, and its reliability has been proved. In order to analyze these gases and diagnose transformer fault types with the results, many methods have been developed, such as Key Gas Method, Method of Duval, IEC 60599 Method, Method of Dornenburg and Method of Rogers, etc. In some cases, the accuracy of these traditional methods is reduced and cannot be applied for diagnosis, since they have fixed input features and is not flexible for input combination. In order to achieve the propose of solving this defect, this paper introduces a deep belief network-based DGA method to diagnose the faults and states of power transformers with customized input features. For this work, six fault classifications were considered based on the nine characteristics extracted from the gases precipitated from the insulating oil of power transformers. The deep belief network was tested using oil samples collected from power transformers. Experiments have shown that the performance of the network has obtained relatively good accuracy results.

A Comprehensive and Practical Method for Transformer Fault Analysis With Historical Data Trend Using Fuzzy Logic

Dissolved Gas Analysis (DGA) of transformer oil is an important tool to identify incipient faults of transformer. The challenge with the existing research on DGA is that only a single sample is used for the analysis which might lead to inaccurate results. In this paper a comprehensive three stages fuzzy logic approach is proposed to emulate best practices in the industry for transformer health analysis using the current as well as historical data from previous samples. In the first stage, a fuzzy logic is developed for an oil sampling pre-check for better lab acceptance rate which helps to save time and cost. In the second stage fuzzy, the latest IEEE Std C57.104 – 2019 is used to determine the status of transformer health by considering the gas formation rate from past samples and observing the trend. Finally, the third stage fuzzy is used to identify the transformer fault type and determine the corresponding down time. The proposed approach is tested on real data from the industry and the results demonstrate accurate transformer health identification with additional advantages of saving time and cost.

Transformer fault diagnosis based on Chaotic Particle Swarm Optimization RBF Neural Network

This article uses logistic chaotic mapping to improve the particle swarm algorithm parameters and construct the chaotic particle swarm optimization (CPSO) algorithm. Then, the CPSO algorithm is used to optimize the width, weight, and center values of the Radial Basis Function Neural Networks (RBFNN) to improve the RBFNN model used to diagnose transformer fault types. Results show that the CPSO-RBFNN model has a small mean square error and high accuracy in diagnosing transformer faults.

Transformer winding mechanical fault diagnosis method based on closing transient acoustic vibration signal

The current conventional transformer winding fault diagnosis method mainly extracts the vibration signal through the time-frequency analysis method, which leads to poor diagnosis due to the lack of analysis of the transformer winding state. In this regard, a transformer winding mechanical fault diagnosis method based on the closing transient acoustic vibration signal is proposed. The closing vibration signals of the transformer in the normal and loose winding states are collected separately, the transformer winding force situation is analysed, and the transformer fault signal characteristics are extracted and combined with a fault classifier to construct a fault diagnosis model. In the experiments, the proposed method is verified for fault identification. The experimental results show that the proposed method has a high correct rate when used to identify different types of transformer faults, and has a more desirable fault diagnosis performance.

Fault Diagnosis of Wind Turbine Generators Based on Stacking Integration Algorithm and Adaptive Threshold.

Fault alarm time lag is one of the difficulties in fault diagnosis of wind turbine generators (WTGs), and the existing methods are insufficient to achieve accurate and rapid fault diagnosis of WTGs, and the operation and maintenance costs of WTGs are too high. To invent a new method for fast and accurate fault diagnosis of WTGs, this study constructs a stacking integration model based on the machine learning algorithms light gradient boosting machine (LightGBM), extreme gradient boosting (XGBoost), and stochastic gradient descent regressor (SGDRegressor) using publicly available datasets from Energias De Portugal (EDP). This model is automatically tuned for hyperparameters during training using Bayesian tuning, and the coefficient of determination (R2) and root mean square error (RMSE) were used to evaluate the model to determine its applicability and accuracy. The fitted residuals of the test set were calculated, the Pauta criterion (3σ) and the temporal sliding window were applied, and a final adaptive threshold method for accurate fault diagnosis and alarming was created. The model validation results show that the adaptive threshold method proposed in this study is better than the fixed threshold for diagnosis, and the alarm times for the GENERATOR fault type, GENERATOR_BEARING fault type, and TRANSFORMER fault type are 1.5 h, 5.8 h, and 3 h earlier, respectively.

Transformer Fault Diagnosis Based on DLH-GWO-SVM

In the field of transformer fault diagnosis, there are many diagnostic methods. These diagnostic methods are either not high accuracy or are used too long. In this paper, a dimension learning-based hunting (DLH) search strategy optimization grey wolf algorithm support vector machine (DLH-GWO-SVM) model was proposed. In the process of initializing the grey wolf population, logistic chaotic mapping was used to improve the quality of the initial wolf position. In the Wolf screening process, the DLH search strategy was adopted to solve the problem that GWO was prone to fall into the local optimal solution, and the improved Grey wolf algorithm (IGWO) was formed. Finally, the transformer fault types were classified by support vector machine (SVM), and IGWO was used to optimize the penalty factor and kernel parameter (g) of the SVM. Through the experimental analysis, the accuracy of transformer fault diagnosis can reach 95.83% after the application of the DLH-GWO-SVM model.

A Methodology to Diagnose Transformer Faults Based on the Multi-Objective Optimization and the Case-Based Reasoning

There exists a complicated mapping relationship between the types of transformer faults and the compositions and concentrations of dissolved gases in transformer oil. A methodology based on multi-objective optimization and case-based reasoning (CBR) is proposed to diagnose transformer faults by analyzing the dissolved gas analysis data. Considering the characteristics of the features used in the transformer diagnosis model, the targeted improvements are made in the preprocessing phase of the features to protect the diversities of samples. The quality of the feature subset is quantified by the internal cross-validation based on the CBR, and the feature subset is optimized by NSGA-II, considering both the classification performance and the size of the feature subset. The effect of the algorithm parameters on the performance is investigated, and the results validate the robustness of the proposed methodology. The proposed methodology is applied to diagnose cases from the IEC TC 10 database, achieving a fault type recognition accuracy and a severity evaluation accuracy.

Fault Voiceprint Signal Diagnosis Method of Power Transformer Based on Mixup Data Enhancement.

A voiceprint signal as a non-contact test medium has a broad application prospect in power-transformer operation condition monitoring. Due to the high imbalance in the number of fault samples, when training the classification model, the classifier is prone to bias to the fault category with a large number of samples, resulting in poor prediction performance of other fault samples, and affecting the generalization performance of the classification system. To solve this problem, a method of power-transformer fault voiceprint signal diagnosis based on Mixup data enhancement and a convolution neural network (CNN) is proposed. First, the parallel Mel filter is used to reduce the dimension of the fault voiceprint signal to obtain the Mel time spectrum. Then, the Mixup data enhancement algorithm is used to reorganize the generated small number of samples, effectively expanding the number of samples. Finally, CNN is used to classify and identify the transformer fault types. The diagnosis accuracy of this method for a typical unbalanced fault of a power transformer can reach 99%, which is superior to other similar algorithms. The results show that this method can effectively improve the generalization ability of the model and has good classification performance.

Transformer Fault Synthetic Diagnosis Method Based on Fusion of Multi-Neural Networks and Evidence Theory in Cloud Computing

As the core equipment of power system, the failure of transformer will result in paralysis of the whole system. Therefore, timely diagnosis of transformer fault types is the most important task to ensure the stable operation of power system. Through the cloud computing method, the neural network is combined with the advantages of evidence theory, by comparing the chromatographic data of the transformer and the electrical test data. A comprehensive diagnosis method of transformer fault based on the fusion of multi neural network and evidence theory based on cloud computing is proposed. The fault diagnosis performance of the transformer is measured by the inspection of the fault transformer. The results show that compared with the traditional single data comparison, this method can improve the reliability and accuracy of diagnosis by comparing many kinds of data.

Transformer fault type discrimination based on window calculation method and frequency response analysis

Frequency response analysis (FRA), one of the methods for the diagnosis of transformer mechanical faults, is improving quickly to result in easier fault detection. Recently, the window calculation method has been introduced in the literature to interpret the FRA results. In this method, the interpretation algorithm divides the transfer function (TF) into small frequency windows and analyses overall behavior of these windows. This contribution studies the window method on a test transformer in which three mechanical defects are exerted to determine the type of winding fault. For this purpose, various numerical indices acquire the corresponding window curves from TFs obtained in four different connections. Afterward, the trend of the generated curves is utilized to give an interpretation of the results. In this regard, two novel numerical indices, based on the trend of maximum points of window curves, are introduced that facilitate the discrimination of the winding fault type.

A Method of Winding Fault Classification in Transformer Based on Moving Window Calculation and Support Vector Machine

Winding fault is one of the most common types of transformer faults. The frequency response method is a common diagnosis method for winding fault detection. In order to improve the feature extraction ability of the frequency response curve before and after the winding fault, this paper proposes a winding fault feature extraction method based on the moving window algorithm to improve the Euclidean distance and correlation coefficient and uses a support vector machine to diagnose winding fault. “Moving window meter algorithm” refers to the fixed moving window width and window moving interval, scanning the entire frequency response curve from the initial point to the end point of the frequency response curve, using the correlation coefficient (CC) and Euclidean distance (ED) to calculate the mathematical index of each window. The mathematical index of each window is used as the characteristic quantity of fault type classification. Finally, the grid search algorithm is used to optimize the support vector machine to classify and identify the type of winding fault. At the same time, the standard support vector machine s(SVM) and back propagation neural network algorithm (BPNN) are compared with the support vector machine optimized by the grid search method to diagnose the fault type. The research shows that the improved correlation coefficient and Euclidean distance using the moving window algorithm are more sensitive to winding faults than the traditional calculation methods. The combination of the two calculation methods makes up for the shortcomings of their respective methods. The fault features obtained meet the requirements of the support vector machine for fault diagnosis, and the grid search method-optimized support vector machine classification algorithm has a good classification and recognition effect on the identification of fault types. The effectiveness and superiority of this method are further illustrated.

The Vibroacoustic Characteristics Analysis of Transformer Core Faults Based on Multi-Physical Field Coupling

Power transformers play an important role in the safe and reliable operation of the whole power grid. Once a fault occurs, it will endanger the normal operation of the transformer, and even result in power grid accidents. Accurate and practical methods of transformer fault monitoring and type identification have attracted extensive attention in the field of electrical engineering. However, it is difficult to obtain a large number of measurement data for different fault types on a large power transformer. The vibroacoustic characteristics of transformer faults have significant asymmetry. For the power transformer in service, it is complex and uneconomic to obtain the vibroacoustic signals under different fault conditions. To handle this problem, this paper proposes simulation methods of several common transformer core faults, based on multi-physical field coupling, and then analyzes the vibroacoustic signals generated by the operating transformer. Finally, it verifies the results of acoustic and vibration signals under several faults, through physical experiments. The results show that the transformer fault simulation method is reasonable and accurate. Furthermore, a change in the transformer core state will cause a change in the transformer vibroacoustic characteristics, and different types of core faults can be distinguished by the analysis of vibroacoustic characteristics.

Hierarchical Federated Learning for Power Transformer Fault Diagnosis

Accurate diagnosis of power transformer fault type is critical to maintaining its safe and stable operation. Existing methods require a large number of labeled data and are implemented in a centralized manner. However, the labeled samples are owned by different electricity companies, and they are unwilling to share their private data due to commercial competition and personal data privacy. In this paper, a federated learning (FL) model, called FL-CA-CNN, is proposed to infer the transformer fault type. Specifically, a channel attention-based convolutional neural network (CA-CNN) is designed to bridge the dissolved gases and the fault types. Its model layers are divided into shallow and deep layers. A hierarchical parameter aggregation strategy is adopted to update the model in the FL framework, through which only the model parameters are shared, and the data privacy is protected. Experiments on the actual dataset demonstrate the effectiveness of the proposed method.

A Novel Feature Extraction Method for Power Transformer Vibration Signal Based on CEEMDAN and Multi-Scale Dispersion Entropy.

Effective diagnosis of vibration fault is of practical significance to ensure the safe and stable operation of power transformers. Aiming at the traditional problems of transformer vibration fault diagnosis, a novel feature extraction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and multi-scale dispersion entropy (MDE) was proposed. In this paper, CEEMDAN method is used to decompose the original transformer vibration signal. Additionally, then MDE is used to capture multi-scale fault features in the decomposed intrinsic mode functions (IMFs). Next, the principal component analysis (PCA) method is employed to reduce the feature dimension and extract the effective information in vibration signals. Finally, the simplified features are sent into density peak clustering (DPC) to get the fault diagnosis results. The experimental data analysis shows that CEEMDAN-MDE can effectively extract the information of the original vibration signals and DPC can accurately diagnose the types of transformer faults. By comparing different algorithms, the practicability and superiority of this proposed method are verified.

Improved Genetic Algorithm and XGBoost Classifier for Power Transformer Fault Diagnosis

Power transformer is an essential component for the stable and reliable operation of electrical power grid. The traditional transformer fault diagnostic methods based on dissolved gas analysis are limited due to the low accuracy of fault identification. In this study, an effective transformer fault diagnosis system is proposed to improve identification accuracy. The proposed approach combines an improved genetic algorithm (IGA) with the XGBoost to form a hybrid diagnosis network. The combination of the improved genetic algorithm and the XGBoost (IGA-XGBoost) forms the basic unit of the proposed method, which decomposes and reconstructs the transformer fault recognition problem into several minor problems IGA-XGBoosts can solve. The results of simulation experiments show that the IGA performs excellently in the combined optimization of input feature selection and the XGBoost parameter, and the proposed method can accurately identify the transformer fault types with an average accuracy of 99.2%. Compared to IEC ratios, dual triangle, support vector machine and common vector approach the diagnostic accuracy of the proposed method is improved by 30.2, 47.2, 11.2, and 3.6%, respectively. The proposed method can be a potential solution to identify the transformer fault types.

Evaluation and Interpretation of Dissolved Gas Analysis of Soybean-Based Natural Ester Insulating Liquid

The electrical industry needs a better understanding in the topic related to the fault diagnosis, since these fluids are chemically different in comparison with conventional mineral oils, therefore, its performance in field changes, for example the generated gases. This paper presents an investigation related to the gas generation of a new soybean-based natural ester liquid, which includes a data compilation of distribution and power transformers diagnosis during factory tests by dissolved gas analysis (DGA) method. This work covers an evaluation of the generated gases for three common types of transformer faults (overheating, partial discharge and high energy discharges) at lab scale testing and their interpretation by using different diagnostic methods to predict the fault type. It is found that overheating problems in natural esters can be associated with ethylene, while acetylene and hydrogen are linked for high energy fault and partial discharge faults, respectively. On the other hand, it is confirmed that Duval triangle is the most reliable method to diagnose natural esters liquids. The authors consider that the DGA data presented in this work represent valuable information for the transformer industry.

Two Graphical Shapes Based on DGA for Power Transformer Fault Types Discrimination

Different graphical diagnostic methods, which are based on dissolved gas analysis (DGA) are widely used for fault diagnosis and monitoring of dielectric liquid filled transformers. The aforementioned graphical diagnostic methods mainly focus on three, four, five or seven gases. In this work, an alternative approach is proposed by means of a two-shapes graphical method in order to discriminate between different fault types guided from the acetylene percentage derived from the DGA analysis. Low thermal faults are studied through the first shape (square), while electrical discharge faults are depicted in the second shape (pentagon). The accuracy of the proposed method is calculated based on 375 DGA data; the overall obtained accuracy is 78.93%.

Ensemble Machine Learning Methods for better Dynamic Assessment of Transformer Status

Analyzing dissolved gases in the transformer's mineral oil helps to detect and classify the systemic faults in electric power transformers. Formerly, empirical methods such as Rogers ratio, Duval triangles 1–4–5, and pentagons 1–2 were used for transformer fault classification. Loose fit for every transformer type is one of the most prominent disadvantages of conventional methods. Formulating robust machine learning algorithms, such as the decision trees, can significantly overcome the loose fit issue. This paper focuses on implementing four different decision tree algorithms, including a regular decision tree classifier, a bagging classifier, a boosting classifier, and a stacking classifier to classify six different transformer fault types distinctly. Further, this study shows that the efficacy and accuracy of the four mentioned classifiers could be far exceeded when combined using a wisdom of the crowd approach. The wisdom of the crowd approach essentially merges the predicted classes from the four individual classifiers and decides on the final prediction via a hard-voting routine. The computational evaluation revealed that the given voting approach could significantly improve power transformers' online diagnostic accuracy up to 91%, thus aiding early forecast of power transformers' preventive maintenance.