Transformer Fault Detection Research Articles

Intelligent Classifiers in Distinguishing Transformer Faults Using Frequency Response Analysis

With the expansion of the use of frequency response analysis (FRA) as a reliable tool for fault detection in transformers, more capabilities of this method are discovered every day. So that today the number of transformer faults that can be identified by FRA method has also increased. One of the most critical steps in fault detection with FRA is to distinguish faults and classify them in different classes. In this paper, well-known intelligent classifiers (probabilistic neural network, decision tree, support vector machine, and k-nearest neighbors) are used to classify transformer faults. For this purpose, the necessary measurements are performed on the model transformers under the healthy condition and under different fault conditions (axial displacement, radial deformation, disc space variation, short-circuits, and core deformation). Then, by dividing the frequency ranges of the measured transfer functions of the transformer, a new feature based on numerical and statistical indices for training and validation of classifiers is proposed. After completing the training process, the performance of the classifiers is evaluated and compared by applying the data obtained from real transformers.

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

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

FEM Simulation and Test Verification of PD Ultrasonic Signal Propagation in a Power Transformer Model

Ultrasonic signals will be generated when partial discharge occurs in internal insulation faults in large oil immersed power transformers: because the ultrasonic signal has strong anti-interference ability and has no direct electromagnetic contact with the equipment, it is widely used in transformer fault detection and positioning. In this paper, the finite element method (FEM) is used to simulate the ultrasonic signal in a 35 kV power transformer. The influence of transformer case on ultrasonic signal propagation is considered, and the propagation law of the ultrasonic signal inside the transformer is obtained. Fabry–Perot (F–P) fibre acoustic sensors with a centre frequency of 28 kHz were fabricated. A partial discharge detection test was carried out in a 35 kV transformer winding model using the F–P sensors. The test results show that the ultrasonic waveform detected by the F–P sensors are in good agreement with the simulation results, and the propagation of the ultrasonic wave inside the transformer is verified. It lays a foundation for detecting and locating PDs in power transformer by F–P acoustic sensors.

A Comparison between Artificial Intelligence Method and Standard Diagnosis Methods for Power Transformer Dissolved Gas Analysis Using Two Public Databases

Oil‐filled power transformers play an important role in modern network systems. Stable power supply can be achieved by early detection of power transformer faults and continuous monitoring of equipment. In recent years, dissolved gas analysis (DGA) has been widely used to diagnose faults in power transformers. Although DGA is an easier and simpler method for the fault diagnosis of transformers, different techniques usually provide different results with real‐world data. In fact, conventional diagnosis approaches for power transformers depend on human experience and available technology of human experts. Therefore, we propose using an artificial intelligence (AI) technique called multilayer perceptron (MLP) for the intelligent diagnosis of power transformer faults. In this work, the MLP model is constructed using the Keras library. The method is tested using two public databases: one based on the Electric Technology Research Association of Japan (ETRA) database and another based on the IEC TC10 database. Results indicate that high‐prediction accuracy is achieved. © 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Development of Full-Automatic Transformer Fault Detection System Based on Gas Chromatography Analysis

In the long-term operation of transformers, some small amounts of gases will be produced in the transformer oil, which will lead to the fault of power transformers. The content of some small amounts of gases can reflect the fault types of power transformers to a certain extent. This study takes transformer as the research object and uses gas chromatographic analysis to detect its fault. First, this study introduces the basic knowledge of the gas chromatography and uses the chromatographic column to separate the measured gap, then converts the concentration of different components into a corresponding voltage signal and analyzes and processes the electrical signal, the fault detection of transformer is made by using neural network and fuzzy mathematics algorithm. Finally, each module of the system is analyzed, and the development of the full-automatic transformer fault detection system based on gas chromatography analysis is completed.

An intelligent system based on optimized ANFIS and association rules for power transformer fault diagnosis

This research work put forward an intelligent method for diagnosis and classification of power transformers faults based on the instructive Dissolved Gas Analysis Method (DGAM) attributes and machine learning algorithms. In the proposed method, 14 attributes obtained through DGAM are utilized as the initial and unprocessed inputs of Adaptive Neuro-Fuzzy Inference System (ANFIS). In this method, attribute selection and improved learning algorithm are utilized to enhance fault detection and recognition precision. In the propounded fault detection and classification method, the most instructive attributes obtained by DGAM are selected by association rules learning technique (ARLT). Using efficient enlightening attributes and eliminating tautological attributes lead to higher accuracy and superior operation. Furthermore, appropriate training of ANFIS has significant effect on its precision and robustness. Therefore, Black Widow Optimization Algorithm (BWOA) is applied to train the ANFIS. Having excellent exploration and extraction capability, fast convergence speed and simplicity is the main reason for choosing the BWOA as the learning algorithm. Two industrial datasets are utilized to test and evaluate the performance of the put forward method. The results show that the propounded diagnosis system has high accuracy, robust performance and short run time. Selecting the most educative attributes of DGAM, training ANFIS optimally, improving the robustness of ANFIS and increasing the classification accuracy are the main contribution of this paper in the field of power transformer fault detection and classification.

Low-cost and Efficient Fault Detection and Protection System for Distribution Transformer

Distribution transformers are a vital component of electrical power transmission and distribution system. Frequent Monitoring transformers faults before it occurs can help prevent transformer faults which are expensive to repair and result in a loss of energy and services. The present method of the routine manual check of transformer parameters by the electricity board has proven to be less effective. This research aims to develop a low-cost protection system for the distribution transformer making it safer with improved reliability of service to the users. Therefore, this research work investigated transformer fault types and developed a microcontroller-based system for transformer fault detection and protection system using GSM (the Global System of Mobile Communication) technology for fault reporting. The developed prototype system was tested using voltage, current and temperature, which gave a threshold voltage higher than 220 volts to be overvoltage, a load higher than 200 watts to be overload and temperature greater than 39 degrees Celsius to be over temperature was measured. From the results, there was timely detection of transformer faults of the system, the transformer protection circuits were fully functional, and fault reporting was achieved using the GSM device. Overall, 99% accuracy was achieved. The system can thus be recommended for use by the Electricity Distribution Companies to protect distribution transformers for optimal performance, as the developed system makes the transformers more robust, and intelligent. Hence, a real-time distribution transformer fault monitoring and prevention system is achieved and the cost of transformer maintenance is reduced to an extent.

Prediction Model for Dissolved Gas Concentration in Transformer Oil Based on Modified Grey Wolf Optimizer and LSSVM with Grey Relational Analysis and Empirical Mode Decomposition

Oil-immersed transformer is one of the most important components in the power system. The dissolved gas concentration prediction in oil is vital for early incipient fault detection of transformer. In this paper, a model for predicting the dissolved gas concentration in power transformer based on the modified grey wolf optimizer and least squares support vector machine (MGWO-LSSVM) with grey relational analysis (GRA) and empirical mode decomposition (EMD) is proposed, in which the influence of transformer load, oil temperature and ambient temperature on gas concentration is taken into consideration. Firstly, GRA is used to analyze the correlation between dissolved gas concentration and transformer load, oil temperature and ambient temperature, and the optimal feature set affecting gas concentration is extracted and selected as the input of the prediction model. Then, EMD is used to decompose the non-stationary series data of dissolved gas concentration into stationary subsequences with different scales. Finally, the MGWO-LSSVM is used to predict each subsequence, and the prediction values of all subsequences are combined to get the final result. DGA samples from two transformers are used to verify the proposed method, which shows high prediction accuracy, stronger generalization ability and robustness by comparing with LSSVM, particle swarm optimization (PSO)-LSSVM, GWO-LSSVM, MGWO-LSSVM, EMD-PSO-LSSVM, EMD-GWO-LSSVM, EMD-MGWO-LSSVM, GRA-EMD-PSO-LSSVM and GRA-EMD-GWO-LSSVM.

EFFECT OF THE ASYMMETRICAL AXIAL DISPLACEMENT OF TRANSFORMER WINDINGS ON FRA CHARACTERISTICS

Frequency response analysis (FRA) is one of the most reliable and useful methods for mechanical fault detection in transformers. The winding axial displacement is one of the mechanical fault types that can occur in transformers. Axial displacements causes the detailed model parameters changing, in response to which FRA characteristics will also change. Numerous researchers have considered winding axial displacements as a symmetrical movement of disks. However, one of the most prevalent types of winding axial displacements is asymmetrical axial displacement which has not been considered by any prior studies. In this paper, physical asymmetrical and symmetrical axial displacements of the first disk of the LV winding were simulated and FRA characteristics were obtained for these cases. Finally, experimental tests were performed on an experimental transformer to validate the simulation results.

A Machine Learning approach to fault detection in transformers by using vibration data

Transformer Vibration Technique is considered an effective method to monitor structural elements of transformers, in particular, to detect loose or deformed windings. As it is well known, vibrations vary with the sensor location on the transformer tank, which makes the number and the placement of sensors critical aspects for fault detection. In this paper, we investigate this issue by analyzing vibration spectra collected from various sensors installed on the tank of a typical oil filled power transformer operating under two limit cases, namely absence or presence of clamping looseness on windings. Support Vector Machines (SVM) are employed and an extensive analysis is performed to understand the informativeness of data corresponding to various sensors so as to figure out the appropriate number of sensors and their best location. This way fault detection is eventually achieved with a reduced and optimized number of sensors, resulting in a significant saving of time and costs.

Real time outlier monitoring for power transformer fault diagnosis based on isolated forest

In order to improve the accuracy and efficiency of transformer fault detection, this paper uses the isolated forest algorithm combined with the historical transformer characteristic gas data to establish the characteristic gas outlier recognition model, and then uses the uncoded ratio method to establish the abnormal event strategy and abnormal event library for the transformer historical fault information. Finally, the state of the transformer is diagnosed based on the established outlier detection model and the exception event library. The experimental results show that the proposed method has a great improvement in the detection efficiency and stability of outliers, and is more accurate in transformer fault diagnosis combine with abnormal event database.

Frequency response signature analysis for winding mechanical fault detection of power transformer using sensitivity method

Frequency response signature analysis for winding mechanical fault detection of power transformer using sensitivity method

Method of inter‐turn fault detection for next‐generation smart transformers based on deep learning algorithm

In this study, an inter-turn fault diagnosis method is proposed based on deep learning algorithm. 12-channel data is obtained in MATLAB/Simulink as the time-domain monitoring signals and labelled with 16 different fault tags, including both primary and secondary voltage and current waveforms. An auto-encoder is presented to classify the fault type of the abundant and comprehensive fault waveforms. The overall waveforms compose a two-dimension data matrix and the auto-encoder is trained to extract the features in the multi-channel waveforms. The selected features are convoluted with the original data, generating a one-dimensional vector as the input to the softmax classifier. Variables such as type, activation function and depth of auto-encoder, sparsity of sparse auto-encoder, number of features and pooling strategies are studied, which gives an intuitive process to train a proper learning model. The overall recognition accuracy reaches 99.5%. Signal characteristics such as channel selection, time span of the input signal and signal sampling frequency are studied to find the best solution for the inter-turn fault detection of the three-phase transformer. The proposed method under deep learning framework increases the accuracy and robustness in transformer fault diagnosis, indicating its potential and prospect in the next-generation smart transformers.

Interpretation of frequency response analysis of power transformer based on evidence theory

Power transformers are one of the key components of power systems. Therefore, they must be operated efficiently to obtain satisfactory system performance, since any distortion or failure in power transformer structures may cause drastic damages. In order to detect deficiencies in power transformers, various methods are utilised. Frequency response analysis (FRA) is one of the most well-known methods used for fault detection in power transformers. However, the interpretation of FRA results is subjective, and depends primarily on the opinion of a human expert. In other words, there is no comprehensive, accepted and standardised method to interpret FRA results. Subsequently, fault detection based on FRA is prone to error. In this study, a new mathematical approach is used to interpret the frequency response of power transformers based on evidence theory method. This method is more accurate and less computationally burdensome compared to conventional methods. Simulations are implemented on an operating 125 MVA, 230/132/20 kV autotransformer using finite-element method and the results are compared to the corresponding FRA results of the same autotransformer in order to evaluate the proposed method. The obtained results indicate the efficiency of the proposed method in detecting probable faults of transformer windings through analysing the FRA results.

A review on fault detection and condition monitoring of power transformer

A review on fault detection and condition monitoring of power transformer

Immersion photoacoustic spectrometer (iPAS) for arcing fault detection in power transformers.

We report on the development of the first immersion photoacoustic spectrometer (iPAS) for arcing fault detection in power transformers. The spectrometer consists of a detection system and an all-optical photoacoustic sensing head mounted inside a small permeable chamber where dissolved C2H2 diffuses while the transformer oil is kept out. Our all-optical iPAS sensor can be placed directly inside an oil bath and measure dissolved C2H2 with the sensitivity and linearity needed for in situ arcing fault detection. Moreover, its fast response time holds great promise for extra-early fault diagnosis.

Novel Transformer Fault Identification Optimization Method Based on Mathematical Statistics

Most power transformer faults are caused by iron core and winding faults. At present, the method that is most widely used for transformer iron core and winding faults identification is the vibration analysis method. The vibration analysis method generally determines the degree of fault by analyzing the energy spectrum of the transformer vibration signal. However, the noise reduction step in this method is complicated and costly, and the effect of denoising needs to be further improved to make the fault identification results more accurate. In addition, it is difficult to perform an accurate determination of the early mild failure of the transformer due to the effect of noise on the results. This paper presents a novel mathematical statistics method based on the vibration signal to optimize the vibration analysis method for the short-circuit failure of the transformer winding. The proposed method was used for linear analysis of the transformer vibration signal with different degrees of short-circuit failure of the transformer winding. By comparing the slope value of the transformer vibration signal cumulative probability distribution curve and analyzing the energy spectrum of the signal, the degree of short-circuit failure of the transformer winding was identified quickly and accurately. This method also simplified the signal denoising process in transformer fault detection, improved the accuracy of fault detection, reduced the time of fault detection, and provided good predictability for early mild faults of the transformer, thereby reducing the hidden hazards of operating the power transformer. The proposed optimization procedure offers a new research idea in transformer fault identification.

Fault detection in power transformers using random neural networks

This paper discuss the application of artificial neural network-based algorithms to identify different types of faults in a power transformer, particularly using DGA (Dissolved Gas Analysis) test. The analysis of Random Neural Network (RNN) using Levenberg-Marquardt (LM) and Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithms has been done using the data of dissolved gases of power transformers collected from Punjab State Transmission Corporation Ltd.(PSTCL), Ludhiana, India. Sorting of the preprocessed data have been done using dimensionality reduction technique, i.e., principal component analysis. The sorted data is used as inputs to the Random Neural Networks (RNN) classifier. It has been seen from the results obtained that BFGS has better performance for the diagnosis of fault in transformer as compared to LM.

A Novel Power Transformer Condition Monitoring System Based on Wide-Band Measurement of Core Earth Signals and Correlation Analysis With Multi-Source Data

On-line condition monitoring and real-time fault detection are essential to protect power transformers from unscheduled outage of services. The core earth signals (CES) are valuable for fault detection and diagnosis of power transformers, as they are related to multiple transformer defects and faults, such as core multi-point earthing fault and core deep saturation. Moreover, the CES also contain valuable information of transient impulses intruded into power transformers such as very fast transient overvoltage (VFTO) impulses. This paper develops a novel power transformer condition monitoring system (NCMS), which makes full use of CES to detect and diagnose the external impulses and internal defects and faults. Firstly, the NCMS carries out the wide-band measurement of CES. Secondly, the NCMS obtains data from supervisory control and data acquisition system (SCADAS), dissolved gases analysis (DGA) system, and other monitoring systems, and correlates these data using grey relational analysis (GRA). Finally, the NCMS detects the impulses and diagnoses defects and faults based on the correlation relationships, then presents the monitoring results to the users. This novel system has been applied to the field and successfully diagnosed many defects and faults. It has high accuracy (<; 3%) at the power and harmonic frequencies and possesses the capability to capture VFTO-pulses.

Assessment of computational intelligence and conventional dissolved gas analysis methods for transformer fault diagnosis

Transformers are vital components of power systems as they are situated between energy generation and consumers and their failure disrupts the use of electrical energy. Therefore, diagnosing an incipient fault is essential in avoiding hazardous operating conditions and minimizes downtime cost. In transformers, faults take place due to electrical or thermal stresses that cause insulation decomposition in transformers. In oil-filled transformers, insulations are cellulose and oil, and the products of the insulation decomposition are gases which can be dissolved in the oil. Therefore, dissolved gas analysis (DGA) can be used for fault diagnosis in oil filled transformers. In this paper, DGA interpretation methods, conventional and intelligence, are investigated and compared. For evaluating consistency and accuracy of the methods, No Result cases are not considered. It can help the newcomers to this field to have access to a comprehensive comparison about the application of computational intelligence and conventional methods in transformer fault detection using DGA.