Transformer Winding Faults Research Articles

A transformer winding and core mechanical fault diagnosis approach based on VMD-MFE and GWO-MKELM

A transformer winding and core mechanical fault diagnosis approach based on VMD-MFE and GWO-MKELM

Research on new method of transformer winding deformation detection

As one of the most important electrical equipment in power system, the stable operation of transformer is the key factor to ensure the safety of power grid system. Winding deformation is the most common fault of transformer, which will seriously affect the reliable operation of the whole power system. Therefore, the detection of transformer winding deformation is of great significance to prevent transformer accidents. In order to further improve the reliability of transformer winding deformation detection, this paper proposes a transformer winding deformation detection method based on oscillation wave method. Firstly, the equivalent circuit model of transformer winding is established, and the transformer winding fault is simulated by changing the inductance and capacitance parameters in the model, and the law between the change of oscillation wave curve and the change of related performance indexes and equivalent parameters is obtained. Finally, the field test verification is carried out on a 10 kV transformer in the laboratory. The results show that the oscillation wave method can diagnose the transformer winding deformation and can be used for the actual transformer winding deformation detection.

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.

Transformer winding faults diagnosis using the transfer function of its high-frequency lumped equivalent model from the measured FRA data

The frequency response analysis (FRA) of the transformer is the data obtained in a wide frequency range that represents the transfer function (TF) that reflects the physical behavior of its coil. However, it can be considered one of the best tools for a better understanding of the electromagnetic characteristics of the winding. This article proposes the TF as a tool to locate and assess transformer winding failures. So, an autonomous algorithm has been developed to construct the TF in ‘s domain’ proposed in previous research. The TF has been determined from experimental measured FRA data from an isolated air-core winding, where the TF has been calculated for the axial defects (AD) realized on the winding discs. Besides, the diagnostic approach is based on the scaling factor (K) and the real zero (τ) of the TF that can be obtained from the measured equivalent capacitance, equivalent inductance, and the DC resistance of the winding in high and low-frequency ranges. However, the K, τ, and the slope of the equivalent inductance characteristics as a function of the winding defects degree have been used for locating and assessing the severity of the winding faults.

Toward unique electrical ladder network model synthesis of a transformer winding high-frequency modeling using K-means and metaheuristic-based method

PurposeAlthough, numerous optimization algorithms have been devoted to construct an electrical ladder network model (ELNM), they suffer from some frail points such as insufficient accuracy as well as the majority of them are unconstrained, which result in optimal solutions that violate certain security operational constraints. For this purpose, this paper aims to propose a flexible-constraint coyote optimization algorithm; the novelty lies in these points: penalty function is introduced in the objective function to discard any unfeasible solution, an advanced constraint handling technique and empirical relationship between the physical estimated parameters and their natural frequencies.Design/methodology/approachFrequency response analysis (FRA) is very significant for transformer winding diagnosis. Interpreting results of a transformer winding FRA is quite challenging. This paper proposes a new methodology to synthesize a nearly unique ELNM physically and electrically coupled for power transformer winding, basing on K-means and metaheuristic algorithm. To this end, the K-means method is used to cluster the setting of control variables, including the self-mutual inductances/capacitances, and the resistances parameters. Afterward, metaheuristic algorithm is applied to determine the cluster centers with high precision and efficiency.FindingsFRA is performed on a power transformer winding model. Basing on the proposed methodology, the prior knowledge in selecting the initial guess and search space is avoided and the global solution is ensured. The performance of the abovementioned methodology is compared using evaluation expressions to verify its feasibility and accuracy.Originality/valueThe proposed method could be generalized for diagnosis of faults in power transformer winding.

Diagnosis method of transformer winding mechanical deformation fault based on sliding correlation of FRA and series transfer learning

Frequency response analysis (FRA) is a common method for diagnosing transformer winding faults. There are many ways to interpret FRA, however, extracting fault features from FRA still faces challenges because the FRA signature of each transformer is different, which can make the generalization of FRA diagnosis difficult. Based on this, this paper proposes a diagnosis method based on FRA sliding correlation and series transfer learning. The study collected FRA data from three transformers, two obtained through simulation, while the third obtained through experiment. During the simulation, the synthetic minority over-sampling technique (smote) algorithm was used to expand the data set to solve the problem of unbalanced and insufficient data sets for different fault types. The FRA signature was processed by sliding correlation to extract fault features, and the FRA sequence data was transformed into a heat map with correlation coefficient values distinguished by color. Next, the AlexNet network was transferred twice using the simulation data, and the experimental data was used for the third transfer learning. The experimental results showed that the diagnosis method has high accuracy and strong generalization.

The use of power information technology in fault diagnosis of electrical equipment

Abstract As the electric power industry rapidly advances, diagnosing faults in electrical equipment has emerged as a critical challenge. In this study, we leverage advancements in power information technology to develop a method for extracting feature volumes, incorporating multiple characteristics to address mixed faults. Our approach begins with the application of a Backpropagation (BP) neural network to extract fault features from electrical equipment. Subsequently, we employ a Bayesian-optimized Correlation Vector Machine (CVM) classifier for precise diagnosis of mixed faults in transformer windings. We evaluated the performance of our BP-RVM model against traditional diagnostic models through real-world electrical fault diagnosis tests. The results demonstrated high diagnostic accuracy, with a maximum of 99.19%, a minimum of 96.41%, and an average accuracy of 97.73%, indicating a significant success rate in diagnosing types of electrical equipment faults. By providing new theoretical support and technical guidance, this study can improve the accuracy and efficiency of electrical equipment fault diagnosis.

Fault detection and identification in three phase transformer using AI based FSA and PVR analysis

The objective of this paper is to identify the winding faults in three phase transformer. A prototype model of the transformer has been designed and simulated using finite element method (FEM) based CAD package called Infolitica MagNet 6.11.2 in transient 2D solver. From the simulated results the peak variation response in flux linkage signature, flux density magnitude has been captured to identify the transformer winding faults. Then the faulty transformer result has been compared with simulated healthy transformer result. The design incorporated with external taps to create winding short circuit faults. The flux linkage simulation results are verified and validated with an experimental setup by the help of LabVIEW software.

Power Transformer Winding Deformation Diagnosis Based on the Sum of Two‐Way Shortest Distance

Frequency response analysis (FRA) method has been widely used in the world, but the interpretation of its signatures is still a hard problem to solve. This paper introduces a method of the sum of two‐way shortest distance for transformer winding deformation fault diagnosis, which is based on trajectory similarity between FRA signatures. Compared with most existing methods, it does not need order preservation; however, it focuses more on the trajectory itself. The geometric principle of the sum of two‐way shortest distance is introduced and analyzed in detail. By using the circuit analysis software, the equivalent circuit model of the transformer is established, a group of the FRA signatures of three types of transformer winding fault, including axial displacement, radial deformation, and disk space variation fault, are obtained. The distribution of different type of faults is studied by using the sum of two‐way shortest distance to process the FRA signatures in three different frequency bands. Using the sum of two‐way shortest distance as input, the support vector machine (SVM) is employed to train a predictive engine for transformer winding deformation fault diagnosis. Result shows that the proposed method can well classify and diagnose transformer winding deformation fault. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.

Using MLP to locate transformer winding fault based on digital twin

There is no doubt that transformer plays a fundamental role in power system. At the same time, transformer winding fault diagnosis is an important topic. Many works put the most emphasis on the identification of fault type and degree, while ignoring the fault location. However, fault location is an urgent problem to be solved, which is worth studying and discussing. The contribution of this paper lies in the location of Disk space variation (DSV) fault. The introduction of digital twin can solve the problem of insufficient fault cases, and pave the way for the intellectualization of fault diagnosis. In this paper, the digital twin of transformer winding is established based on double ladder network, in which the distributed parameters are calculated by finite element method. Frequency response analysis (FRA) is one of the most widely accepted methods for transformer winding mechanical deformation fault diagnosis. Aiming at the interpretation code of FRA, this paper disproves the view that phase information is useful. Then, by extracting the mathematical index of FRA, multi-layer perceptron (MLP) is trained and DSV fault location is realized. In addition, the popular support vector machine is also compared with the MLP model in this paper, which further highlights the advantages of MLP. The proposed method is verified by an actual transformer, and the results are satisfactory.

Minor fault diagnosis of transformer winding using polar plot based on frequency response analysis

Power transformer is a significant transmission and distribution equipment. Irreversible minor mechanical failures frequently occur in the transformer winding, which is difficult to detect in the early latent stage. Frequency response analysis (FRA) is widely used to detect transformer winding faults. However, the current interpretations of Frequency response analysis pay more attention to amplitude-frequency characteristics without phase-frequency characteristics, which is inaccurate in identifying minor flaws, detecting fault states, and quantifying fault severity. To fill these issues, this paper proposes a transformer winding fault diagnosis method based on the polar plot. The ratio of excitation-response is put forward for calculating the relative factor to detect the minor fault. And then, the fault states are diagnosed by the distribution of the polar plot, which combines amplitude-frequency and phase-frequency characteristics. Finally, the Minkowski distance of the frequency sampling points quantifies the extent of the failure. The experiments are implemented in a 10KV power transformer and COMSOL platform simulation. The fault status contains axial displacement, axial deformation, radial displacement, and radial deformation. The experimental results show that different states greatly influence the distribution of sampling points in polar plot. The proposed method effectively detects the minor flaw of transformer winding and performs well in judging the degree of fault severity and location.

Transformer Winding Fault Classification and Condition Assessment Based on Random Forest Using FRA

At present, the condition assessment of transformer winding based on frequency response analysis (FRA) measurements demands skilled personnel. Despite many research efforts in the last decade, there is still no definitive methodology for the interpretation and condition assessment of transformer winding based on FRA results, and this is a major challenge for the industrial application of the FRA method. To overcome this challenge, this paper proposes a transformer condition assessment (TCA) algorithm, which is based on numerical indices, and a supervised machine learning technique to develop a method for the automatic interpretation of FRA results. For this purpose, random forest (RF) classifiers were developed for the first time to identify the condition of transformer winding and classify different faults in the transformer windings. Mainly, six common states of the transformer were classified in this research, i.e., healthy transformer, healthy transformer with saturated core, mechanically damaged winding, short-circuited winding, open-circuited winding, and repeatability issues. In this research, the data from 139 FRA measurements performed in more than 80 power transformers were used. The database belongs to the transformers having different ratings, sizes, designs, and manufacturers. The results reveal that the proposed TCA algorithm can effectively assess the transformer winding condition with up to 93% accuracy without much human intervention.

Evaluating the Severity of Transformer Winding Faults using FRA and Artificial Intelligence

Evaluating the Severity of Transformer Winding Faults using FRA and Artificial Intelligence

A confidence level estimation technique for reliable Data-Driven FRA interpretation in air-core winding faults

Frequency response analysis (FRA) data interpretation is among highly challenging tasks in transformer fault diagnosis. Among different quantitative methods, employing statistical indicators on FRA results for mechanical integrity assessment is well-stablished. However, the boundary values of indices that differentiate normal/healthy, suspicious, and abnormal transformer operating conditions are not yet agreed upon. This will make the FRA data interpretation using SIs subjective and unreliable. In this study, data-driven critical boundaries of the most frequently used SIs are introduced. To address the uncertainty of the decision boundaries, a confidence level estimation technique is developed to quantify the probability of a transformer being in a particular operating condition. Reporting a confidence level along with the classified conditions facilitates objective decision-making that can support utility operators during on-site transformer evaluation. The confidence level estimation technique proposed in this work was inspired by bolstered error estimation method widely applied in pattern recognition. Moreover, this study provides a new comprehensive technique of transformer winding fault modeling using SPICE netlists. The proposed analytical winding model is validated through practical FRA measurements with high precision. It is further used to generate various scenarios of common active part faults, such as disk space variation, radial displacement, and disk tilting. Consequently, the proposed method of confidence level estimation is examined on different winding deformations and demonstrated a high potential for comprehensive transformer winding diagnosis.

Diagnosis of Power Transformer Winding Deformation Based on Centroid Analysis of 3D Frequency Response Curve

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. Methods: In this paper, a transformer winding deformation diagnosis method based on centroid analysis of 3D frequency response curve is proposed. A 3D coordinate system is established with frequency, amplitude, and phase as the x, y, and z, respectively. The proposed method calculates the centroid of each 3D frequency response curve through an algorithm, and establishes a 3D coordinate system with the centroid of the normal winding 3D frequency response curve as the origin. The deviation distance and deviation angle between the centroid of mass of the 3D frequency response curve of the faulty winding in different frequency bands and the centroid of the 3D frequency response curve of the normal winding and the correlation coefficient of the traditional Frequency Response Analysis (FRA) curve. are calculated. The deviation distance and angle of the centroid and the correlation coefficient of the calculated frequency band are input as features into the Support Vector Machine (SVM) for intelligent diagnosis to achieve fault classification and optimizing its parameters with three optimization algorithms respectively. Results: The fault classification is realized by analyzing the distribution intervals of the centroids of the 3D frequency response curves of the three simulated faults. The accuracy of fault diagnosis using the 3D frequency response curve feature is significantly higher than the accuracy when using the traditional FRA curve feature and it proves the effectiveness of the proposed method. Conclusion: The proposed model can effectively identify different fault types and the diagnostic rate of the fault type is 100%.

Approach for Identification of Inter-Turn Fault Location in Transformer Windings Using Sweep Frequency Response Analysis

As inter-turn faults in transformer windings are the most severe, their delayed detection and localization may create extensive damage to the winding. Therefore, a new inter-turn fault localization methodology based on sweep frequency response analysis (SFRA) through calculation of Pre-fault Inter-Turn Fault Factor ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ITFF_pre</i> ) for all possible fault locations by estimating the values of series and shunt capacitance of the windings during healthy conditions is presented. For a faulty transformer, Post-fault Inter-Turn Fault Factor ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ITFF_post</i> ) is calculated by determining the value of equivalent capacitance using SFRA. The exact fault location in the faulty transformer is obtained by comparing the single calculated value of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ITFF_post</i> of the faulty transformer with the values stored in the lookup table. The efficacy of the suggested approach is verified by performing faults at various locations on the transformer model developed in the laboratory. Its authenticity is also verified on an existing 400 kVA, 11 kV/440 V distribution transformer installed in the real field. The results indicate that the suggested method is capable to identify inter-turn fault location with the minimum ladder network parameters. Finally, a relative assessment of the suggested approach with numerous other methods confirms the superiority in terms of inter-turn fault localization.

A Robust Approach for Locating and Assessing Mechanical Faults in an Actual Transformer Winding Using the State Space of Its Lumped Equivalent Model

A Robust Approach for Locating and Assessing Mechanical Faults in an Actual Transformer Winding Using the State Space of Its Lumped Equivalent Model

A Novel Method to Identification Type, Location, and Extent of Transformer Winding Faults Based on FRA and SMOTE-SVM

A Novel Method to Identification Type, Location, and Extent of Transformer Winding Faults Based on FRA and SMOTE-SVM

Classifying Transformer Winding Fault Type, Location and Extent using FRA based on Support Vector Machine

Wydawnictwo SIGMA-NOT wydaje czasopisma fachowe informujące swoich czytelników o najnowszych osiągnięciach naukowych i nowoczesnych rozwiązaniach technicznych w Polsce i na świecie, popularyzuje problemy techniczne oraz poszerza wiedzę i kulturę techniczną.

A Novel Hyperbolic Fuzzy Entropy Measure for Discrimination and Taxonomy of Transformer Winding Faults

A Novel Hyperbolic Fuzzy Entropy Measure for Discrimination and Taxonomy of Transformer Winding Faults