Transformer Fault Diagnosis Method Research Articles

Fault diagnosis of power transformers based on t-SNE and ECOC-TEWSO-SVM

Support Vector Machines (SVMs) have achieved significant success in the field of power transformer fault diagnosis. However, challenges such as determining SVM hyperparameters and their suitability for binary classification still exist. This paper proposes a novel method for power transformer fault diagnosis, called ECOC-WSO-SVM, which utilizes a White Shark Optimizer (WSO) and error correcting output codes to optimize SVMs. First, t-distributed Stochastic Neighbor Embedding (t-SNE) is employed to reduce the dimensionality of Dissolved Gas Analysis (DGA) features constructed using the correlation ratio method, from 26 dimensions. In addition, to effectively solve the hyperparameters of SVMs, a multi-strategy fusion method is proposed to improve the WSO, incorporating tent chaos initialization, elite opposite learning, and selection strategies, forming TEWSO, and its superior optimization performance is validated using IEEE CEC2021 test functions. Furthermore, to address the limitations of SVMs as a binary classifier, an error correcting output code fusion SVM is introduced, thus constructing a multi-class SVM model. Finally, the diagnostic performance of the ECOC-TEWSO-SVM model is validated using real-world data. Results demonstrate that the proposed model exhibits the best diagnostic performance compared to traditional models and those in the literature, thereby proving the significance and effectiveness of the proposed model.

Transformer fault diagnosis method based on SMOTE and NGO-GBDT

In order to improve the accuracy of transformer fault diagnosis and improve the influence of unbalanced samples on the low accuracy of model identification caused by insufficient model training, this paper proposes a transformer fault diagnosis method based on SMOTE and NGO-GBDT. Firstly, the Synthetic Minority Over-sampling Technique (SMOTE) was used to expand the minority samples. Secondly, the non-coding ratio method was used to construct multi-dimensional feature parameters, and the Light Gradient Boosting Machine (LightGBM) feature optimization strategy was introduced to screen the optimal feature subset. Finally, Northern Goshawk Optimization (NGO) algorithm was used to optimize the parameters of Gradient Boosting Decision Tree (GBDT), and then the transformer fault diagnosis was realized. The results show that the proposed method can reduce the misjudgment of minority samples. Compared with other integrated models, the proposed method has high fault identification accuracy, low misjudgment rate and stable performance.

Research on transformer fault intelligent diagnosis technology based on improved random forest algorithm

Transformer oil can dissolve a certain amount of gas, which can provide an important basis for transformer fault diagnosis. The relationship between the characteristic amount of dissolved gas in transformers and the type of transformer fault was analyzed, and the main influencing factors were extracted. We studied a transformer fault diagnosis method based on the improved random forest algorithm and combined it with the identification requirements of abnormal data in multiple parts of transformers. We improved the random forest from four aspects: dataset construction, bootstrap sampling, decision tree generation, and multi-node voting. We established an improved random forest diagnosis model with oil chromatogram feature gas ratio as the characteristic parameter and analyzed different input parameter combinations. The effectiveness of improving the random forest diagnosis model under different training times was compared with various machine learning methods. The experimental results show that the diagnostic accuracy of the improved random forest diagnostic model is significantly improved compared to other machine learning methods.

A transformer fault diagnosis method based on EHBA-DHKELM-Adaboost model

Aiming at the problem of inaccurate transformer fault diagnosis in dissolved gas analysis, this paper proposes a novel diagnostic method that integrates an enhanced honey badger algorithm (EHBA) with an ensemble learning-based deep hybrid kernel extreme learning machine (DHKELM). First, kernel principal component analysis (KPCA) was deployed for feature fusion of the gas data, thus extracting more effective features. The DHKELM, combining polynomial and RBF kernel functions, was used as a base learning to build a powerful classifier with Adaboost framework. The EHBA introduces information sharing and firefly perturbation strategies based on HBA. This EHBA was harnessed to optimize the DHKELM’s critical parameters, establishing the EHBA-DHKELM-Adaboost transformer fault diagnosis model. Finally, the features garnered by KPCA were fed into the model, simulating and validating various fault diagnosis models. The findings reveal that EHBA-DHKELM-Adaboost achieves 98.75% diagnostic accuracy in transformer faults, surpassing other models.

Transformer Fault Diagnosis Method Based on TimesNet and Informer

Since the traditional transformer fault diagnosis method based on dissolved gas analysis (DGA) is challenging to meet today’s engineering needs, this paper proposes a multi-model fusion transformer fault diagnosis method based on TimesNet and Informer. First, the original TimesNet structure is improved by adding the MCA module to the Inception structure of the original TimesBlock to reduce the model complexity and computational burden; second, the MUSE attention mechanism is introduced into the original TimesNet to act as a bridge, so that associations can be carried out effectively among the local features, thus enhancing the modeling capability of the model; finally, when constructing the feature module, the TimesNet and Informer multilevel parallel feature extraction modules are introduced, making full use of the local features of the convolution and the global correlation of the attention mechanism module for feature summarization, so that the model learns more time-series information. To verify the effectiveness of the proposed method, the model is trained and tested on the public DGA dataset, and the model is compared and experimented with classical models such as Informer and Transformer. The experimental results show that the model has a strong learning ability for transformer fault data and has an advantage in accuracy compared with other models, which can provide a reference for transformer fault diagnosis.

Transformer Fault Diagnosis Method Based on SCA-VMD and Improved GoogLeNet

Aiming at the influence of the fundamental frequency and its harmonics in transformer vibration signals on fault signals, which cause a low fault identification rate and degradation of classification model performance, a new strategy is proposed for fault diagnosis using periodic map spectrum feature maps as input features. In this study, the optimal decomposition parameters were first found adaptively using the VMD improved by the positive cosine optimisation algorithm; then, the transformer vibration signal was modally decomposed, and the periodic map spectrum features were plotted according to the differences in the energy distribution of the different modal components at different frequencies. Finally, the GoogLeNet classification model with the improved attention mechanism assigned different weights to the feature maps in both spatial and channel dimensions to improve the classification accuracy and achieve transformer fault diagnosis. The experimental results verified the validity of the adopted feature map and the proposed model, and the accuracy was significantly improved to 99.04% compared with the traditional GoogLeNet, which is valuable for engineering applications.

Transformer fault diagnosis method based on TLR-ADASYN balanced dataset

As the cornerstone of transmission and distribution equipment, power transformer plays a very important role in ensuring the safe operation of power system. At present, the technology of dissolved gas analysis (DGA) has been widely used in fault diagnosis of oil-immersed transformer. However, in the actual scene, the limited number of transformer fault samples and the uneven distribution of different fault types often lead to low overall fault detection accuracy or a few types of fault misjudgment. Therefore, a transformer fault diagnosis method based on TLR-ADASYN balanced data set is presented. This method effectively addresses the issue of samples imbalance, reducing the impact on misjudgment caused by a few samples. It delves deeply into the correlation between the ratio of dissolved gas content in oil and fault type, eliminating redundant informations and reducing characteristic dimensions. The diagnostic model SO-RF (Snake Optimization-Random Forest) is established, achieving a diagnostic accuracy rate of 97.06%. This enables online diagnosis of transformers. Comparative analyses using different sampling methods, various features, and diverse diagnostic models were conducted to validate the effectiveness of the proposed method. In conclusion, validation was conducted using a public dataset, and the results demonstrate that the proposed method in this paper exhibits strong generalization capabilities.

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.

Fault Identification Method of Transformer Winding based on Gramian Angular Difference Field and Convolutional Neural Network

Background: As the frequency of transformer winding faults becomes higher and higher, the frequency response analysis used to detect the winding status has attracted more and more attention. At present, there is still a lack of reliable and intelligent technologies for detecting the state of transformer windings in this field. Objective: This paper focuses on studying a high-precision method for transformer fault diagnosis, which can be easily and effectively applied to daily life. Methods: By changing the detection method, the traditional detection method can not distinguish the problem that the detection data are highly overlapping when identifying the same fault of the head and tail symmetric points, and the problem that the phase is too similar is changed. In order to solve the problem that the fault samples of transformer frequency response curve are scarce and the one-dimensional data cannot be read by partial deep learning method, the one-dimensional data of frequency response curve is first converted into characteristic index and then into a three-dimensional image by moving window calculation method and Gramian Angular difference field transformation. The fault classification is realized by a convolutional neural network. Results: The accuracy of the final model for slice classification reached 100%. Conclusion: Illustrative examples show that the method is distinguishable from different fault types. The traditional method only uses the amplitude of the frequency response curve, but this method displays the two features of the amplitude-phase together in the image. Compared with the traditional method, more features and samples are added to further improve the accuracy of the method. The accuracy of diagnosis results reached 100%, which showed the feasibility of the method.

Filter-wrapper combined feature selection and adaboost-weighted broad learning system for transformer fault diagnosis under imbalanced samples

Intelligent fault diagnosis is a rapidly evolving field within power engineering. Using gas-in-oil data is a reliable method for transformer fault diagnosis that has been widely adopted in the power industry. However, traditional machine learning methods often suffer from low diagnostic accuracy due to the lack of a clear and effective feature set for gas-in-oil data as well as an imbalance between classes of sample size. To overcome this challenge, this paper proposes a novel transformer fault diagnosis model that utilizes a Filter-Wrapper Combined Feature Selection method and an AdaBoost integrated weighted broad learning system (AdaBoost-WBLS). More specifically, the original data is expanded to extract meaningful features, and the Filter-Wrapper combined feature selection method is used to eliminate preliminary redundancy, relevance, and significance of current features. The Wrapper algorithm is then used for precise screening to obtain the optimal feature subset, which effectively improves the quality of transformer features. Furthermore, to address the issue of imbalanced transformer samples, an improved BLS and AdaBoost integration method is introduced, and a fault diagnosis model based on AdaBoost-WBLS is proposed. Compared with existing power transformer fault diagnosis methods, the proposed method has a more accurate and balanced effect on fault classification. Overall, this paper provides a comprehensive and effective approach to transformer fault diagnosis, which has important implications for the reliability and safety of power systems.

Power transformer fault diagnosis based on a self-strengthening offline pre-training model

Accurate transformer fault diagnosis is crucial for maintaining the power system stability. Due the complex operation condition of the transformer, its faults are with the characteristic of multi-class faults, class-imbalance, and limited diagnosis data of availability. Additionally, some fault samples are only with overheating or discharge labels when collected, it is a challenge that how to how to use these samples. To address these issues, in this paper, a novel transformer fault diagnosis method based on a hybrid model of Res-Variational-Auto-Encoder (ResVAE) and ensemble learning (EL) model is proposed. Through a self-strengthening strategy, fault characteristics are extracted category-by-category by using a residual convolutional neural network, and low dimensional characteristics are mapped into characteristic fusion samples by VAE. Based on this strategy, an offline pre-training model is built based on ResVAE and EL. The hybrid model can obtain more information from offline source domain, enabling the EL to diagnose multiple fault types as well as undetermined faults. Considering 11 categories of imbalanced classification scenarios with limited sample sizes, the comparison is made between eight expansion and six diagnosis algorithms. The results show that the offline pre-training EL model increased the diagnostic accuracy up to 11.224% compared with tradition ratios method. The ResVAE-EL model achieves the highest diagnostic accuracy of 91.011%, which is 10.112% higher than that of the single offline pre-training model.

LiConvFormer: A lightweight fault diagnosis framework using separable multiscale convolution and broadcast self-attention

In recent studies, Transformer collaborated with convolution neural network (CNN) have made certain progress in the field of intelligent fault diagnosis by leveraging their respective advantages of global and local feature extraction. However, the multihead self-attention block used by Transformer and cross-channel convolution mechanism existing in CNN would make the collaborative models overly complex, leading to higher hardware requirements and limited industrial application scenarios. Therefore, this paper proposes a lightweight fault diagnosis framework called LiConvFormer to address the aforementioned challenges. First, a separable multiscale convolution block is designed to extract multilocal receptive field features of vibration signals and greatly reduce the learning parameters and computations. Second, a broadcast self-attention block is developed to capture critical fine-grained features within the signal’s global scope, while avoiding cumbersome operations such as matrix multiplication and multidimensional exponentiation. Experimental results on three mechanical systems show that the proposed framework can accommodate advantages of lightweight and robustness compared to the recent Transformer and CNN-based fault diagnosis methods; moreover, the superiority of the above two blocks is also verified. The code library is available at: https://github.com/yanshen0210/LiConvFormer-a-lightweight-fault-diagnosis-framework.

Power Transformer Fault Diagnosis Based on Improved BP Neural Network

Power transformers are complex and extremely important piece of electrical equipment in a power system, playing an important role in changing voltage and transmitting electricity. Its operational status directly affects the stability and safety of power grids, and once a fault occurs, it may lead to significant economic losses and social impacts. The traditional detection methods rely on the technical level of power system operation and maintenance personnel, and are based on Dissolved Gas Analysis (DGA) technology, which analyzes the components of dissolved gases in transformer oil for preliminary fault diagnosis. However, with the increasing accuracy and intelligence requirements for transformer fault diagnosis in power grids, the DGA analysis method is no longer able to meet the requirements. Therefore, this article proposes an improved transformer fault diagnosis method based on a residual BP neural network. This method deepens the BP neural network by stacking multiple residual network modules, and fuses and expands gas feature information through an improved BP neural network. In the improved residual BP neural network, SVM is introduced to judge the extracted feature vectors at each layer, screen out feature vectors with high accuracy, and increase their weights. The feature vector with the highest cumulative weight is selected as an input for transformer fault diagnosis. This method utilizes multi-layer neural network mapping to extract gas feature information with more significant feature differences after fusion expansion, thereby effectively improving diagnostic accuracy. The experimental results show that, compared with traditional BP neural network methods, the proposed algorithm has higher accuracy in transformer fault diagnosis, with an accuracy rate of 92%, which can ensure the sustainable, normal, and safe operation of power grids.

Transformer fault diagnosis method based on two-dimensional cloud model under the condition of defective data

Transformer fault diagnosis method based on two-dimensional cloud model under the condition of defective data

Transformer Fault Diagnosis Method Based on Incomplete Data and TPE-XGBoost

Dissolved gas analysis is an important method for diagnosing the operating condition of power transformers. Traditional methods such as IEC Ratios and Duval Triangles and Pentagon methods are not applicable in the case of abnormal or missing values of DGA data. A novel transformer fault diagnosis method based on an extreme gradient boosting algorithm is proposed in this paper. First, the traditional statistical method is replaced by the random forest regression algorithm for filling in missing values of dissolved gas data. Normalization and feature derivation of the outlier data is adopted based on the gas content. Then, hyperparameter optimization of the transformer fault diagnosis model based on an extreme gradient boosting algorithm is carried out using the tree-structured probability density estimator algorithm. Finally, the influence of missing data and optimization algorithms on transformer fault diagnosis models is analyzed. The effects of different algorithms based on incomplete datasets are also discussed. The results show that the performance of the random forest regression algorithm on missing data filling is better than classification and regression trees and traditional statistical methods. The average accuracy of the fault diagnosis method proposed in the paper is 89.5%, even when the missing data rate reaches 20%. The accuracy and robustness of the TPE-XGBoost model are superior to other machine learning algorithms described in this paper, such as k-nearest neighbor, deep neural networks, random forest, etc.

Multi-filter semi-supervised transformer model for fault diagnosis

Dissolved Gas Analysis (DGA) is the most commonly used method for power transformer fault diagnosis. However, very few reliable and labeled fault DGA samples are available in the transformer substation whilst DGA data without labels is easier to obtain, which makes it difficult to train fault detectors in high-dimensional input space or select features using wrapper methods. Therefore, in order to improve the fault diagnosis accuracy using limited labeled DGA samples but more unlabeled DGA data, this paper proposes a novel multi-filter semi-supervised feature selection method for selecting optimal DGA features and building effective fault diagnosis models. A confidence criterion is also proposed for selecting high confidence unlabeled data to expand the training data set. Five filter techniques based on different evaluation criteria are employed to rank input DGA features, and a feature combination method is then applied to aggregate feature ranks by multiple filters and form a lower-dimensional candidate feature subset. The proposed method has been tested by using the IEC T10 dataset and compared with traditional supervised diagnostic models. The results show that the proposed method works well in optimizing DGA features and improving fault diagnosis accuracy significantly. Besides, the robustness of the selection of optimal feature subset is validated by testing DGA samples from the local power utility.

Transformer Fault Diagnosis Method based on PSO-GMNN Model

Background: Oil-immersed distribution transformer is an important power transmission and distribution equipment in the power system. If it fails, it will cause huge economic losses and safety hazards. It is of great significance to identify and diagnose its faults, find potential faults in time, and restore normal operation. Objective: To detect transformer fault, a transformer fault diagnosis method based on Graph Markov Neural Networks for Particle Swarm Optimization algorithm (PSO-GMNN) is proposed. Methods: Five common dissolved gases in transformer oil are used to construct a 22-dimensional feature set to be selected, and then the similarity between each feature vector is calculated by using Mahalanobis Distance. The graph structure is constructed with feature vectors as vertices and similarities as edges. Finally, the Particle Swarm Optimization algorithm is used to optimize the initial weights of Graph Markov Neural Networks, and then transformer fault diagnosis is realized. Results: The experiments are performed in the environment of Python 3.7, PyTorch 1.6.0, and the validity of the proposed method is verified by a comparative analysis of the detection accuracy between the proposed method and existing mainstream methods. Conclusion: A transformer fault diagnosis method based on Graph Markov Neural Networks for Particle Swarm Optimization algorithm is proposed to detect transformer fault, and the experimental results demonstrate the effectiveness and advantage of the proposed method.

An EHV Transformer Fault Diagnosis Method Based on Acoustic Perception and Sparse Autoencoder-BNCNN

The EHV transformer is one of the core transmission equipment of China’s EHV/UHV transmission system, and its reliability directly affects the operational stability of the power grid. In the long-term operation process, affected by sudden short-circuit, resonance, and aging, it will produce faults such as loose winding, loose iron core, inverted discharge, and shim block shedding. Most of the methods for transformer fault diagnosis need off-line monitoring and cause some damage to transformer equipment. At present, the use of transformer acoustic signal for diagnosis and identification is in the initial stage, and there is still room for improvement in the accuracy of fault diagnosis, and how to classify the unbalanced data samples also deserves attention. Therefore, an EHV transformer fault diagnosis method based on acoustic perception and sparse autoencoder-BNCNN is proposed in this paper. Firstly, the sparse autoencoder is trained to ensure the processing ability of the network on imbalanced data. Then, the high-step CNN network is optimized using the BN layer, the data is fed into the improved CNN network for feature extraction, and the classifier outputs the fault diagnosis results. Finally, the transformer acoustic data are processed, and the dataset is formed to evaluate the performance of the proposed method. The experimental results show that the proposed method not only improves the accuracy substantially compared with other methods but also has the ability to handle imbalanced data.

A novel power transformer fault diagnosis method based on data augmentation for KPCA and deep residual network

Because transformer plays an important role in power system, it rarely runs in fault or abnormal state. Therefore, it is difficult to obtain sufficient transformer fault samples. In this paper, aiming at the problem of less fault sample data and data imbalance, a novel data augmentation method based on kernel principal component analysis is proposed to non-linearly map the original data to a high-dimensional feature space. In this way, the new sample data retaining the feature information of the original data can be obtained. Second, the deep residual network is introduced with the identity path to construct the fault diagnosis model, which enables the weight parameters to be effectively transferred and updated. The simulation results show that the proposed method can effectively expand the data samples with high similarity with the original data, and the residual network model has strong feature extraction ability, which improves the accuracy of fault diagnosis.

Transformer DGA Fault Diagnosis Method Based on Stacked Sparse Auto-Encoders

In the field of transformer fault diagnosis, the imbalance of fault samples seriously affects the fault identification performance of the diagnosis model. Focusing on the problems of low accuracy and high leakage rate of diagnosis model caused by unbalanced fault samples of transformer, a transformer fault diagnosis method is proposed. First of all, the Borderline SMOTE algorithm is used to balance the fault data set from a few samples on the boundary, so as to achieve the effect of power transformer fault sample equalization. Secondly, a diagnosis model of the stacked sparse auto-Encoders with the gas in oil as input characteristic parameter is built. Finally, an evaluation system consisting of accuracy rate, recall rate and F1 score is selected to compare the diagnosis effect of the model before and after category equalization, the experiment proves the effectiveness of this method.