Assessment of UHF Frequency Range for Failure Classification in Power Transformers.

Ultrahigh-frequency (UHF) sensing is one of the most promising techniques for assessing the quality of power transformer insulation systems due to its capability to identify failures like partial discharges (PDs) by detecting the emitted UHF signals. However, there are still uncertainties regarding the frequency range that should be evaluated in measurements. For example, most publications have stated that UHF emissions range up to 3 GHz. However, a Cigré brochure revealed that the optimal spectrum is between 100 MHz and 1 GHz, and more recently, a study indicated that the optimal frequency range is between 400 MHz and 900 MHz. Since different faults require different maintenance actions, both science and industry have been developing systems that allow for failure-type identification. Hence, it is important to note that bandwidth reduction may impair classification systems, especially those that are frequency-based. This article combines three operational conditions of a power transformer (healthy state, electric arc failure, and partial discharges on bushing) with three different self-organized maps to carry out failure classification: the chromatic technique (CT), principal component analysis (PCA), and the shape analysis clustering technique (SACT). For each case, the frequency content of UHF signals was selected at three frequency bands: the full spectrum, Cigré brochure range, and between 400 MHz and 900 MHz. Therefore, the contributions of this work are to assess how spectrum band limitation may alter failure classification and to evaluate the effectiveness of signal processing methodologies based on the frequency content of UHF signals. Additionally, an advantage of this work is that it does not rely on training as is the case for some machine learning-based methods. The results indicate that the reduced frequency range was not a limiting factor for classifying the state of the operation condition of the power transformer. Therefore, there is the possibility of using lower frequency ranges, such as from 400 MHz to 900 MHz, contributing to the development of less costly data acquisition systems. Additionally, PCA was found to be the most promising technique despite the reduction in frequency band information.

Application of Thermography and Adversarial Reconstruction Anomaly Detection in Power Cast-Resin Transformer.

Dry-type power transformers play a critical role in the power system. Detecting various overheating faults in the running state of the power transformer is necessary to avoid the collapse of the power system. In this paper, we propose a novel deep variational autoencoder-based anomaly detection method to recognize the overheating position in the operation of the dry-type transformer. Firstly, the thermal images of the transformer are acquired by the thermal camera and collected for training and testing datasets. Next, the variational autoencoder-based generative adversarial networks are trained to generate the normal images with different running conditions from heavy to light loading. Through the pixel-wise cosine difference between original and reconstructed images, the residual images with faulty features are obtained. Finally, we evaluate the trained model and anomaly detection method on normal and abnormal testing images to demonstrate the effeteness and performance of the proposed work. The results show that our method effectively improves the anomaly accuracy, AUROC, F1-scores and average precision, which is more effective than other anomaly detection methods. The proposed method is simple, lightweight and has less storage size. It reveals great advantages for practical applications.

Fault Diagnosis for Power Transformers through Semi-Supervised Transfer Learning.

The fault diagnosis of power transformers is a challenging problem. The massive multisource fault is heterogeneous, the type of fault is undetermined sometimes, and one device has only met a few kinds of faults in the past. We propose a fault diagnosis method based on deep neural networks and a semi-supervised transfer learning framework called adaptive reinforcement (AR) to solve the above limitations. The innovation of this framework consists of its enhancement of the consistency regularization algorithm. The experiments were conducted on real-world 110 kV power transformers' three-phase fault grounding currents of the iron cores from various devices with four types of faults: Phases A, B, C and ABC to ground. We trained the model on the source domain and then transferred the model to the target domain, which included the unbalanced and undefined fault datasets. The results show that our proposed model reaches over 95% accuracy in classifying the type of fault and outperforms other popular networks. Our AR framework fits target devices' fault data with fewer dozen epochs than other novel semi-supervised techniques. Combining the deep neural network and the AR framework helps diagnose the power transformers, which lack diagnosis knowledge, with much less training time and reliable accuracy.

Optical Fiber Sensors for Structural Monitoring in Power Transformers.

Power transformers are central elements of power transmission systems and their deterioration can lead to system failures, causing major disruptions in service. Catastrophic failures can occur, posing major environmental hazards due to fires, explosions, or oil spillage. Early fault detection can be accomplished or estimated using electrical sensors or a chemical analysis of oil or gas samples. Conventional methods are incapable of real-time measurements with a low electrical noise due to time-consuming analyses or susceptibility to electromagnetic interference. Optical fiber sensors, passive elements that are immune to electromagnetic noise, are capable of structural monitoring by being enclosed in power transformers. In this work, optical fiber sensors embedded in 3D printed structures are studied for vibration monitoring. The fiber sensor is encapsulated between two pressboard spacers, simulating the conditions inside the power transformer, and characterized for vibrations with frequencies between 10 and 800 Hz, with a constant acceleration of 10 m/s2. Thermal aging and electrical tests are also accomplished, aiming to study the oil compatibility of the 3D printed structure. The results reported in this work suggest that structural monitoring in power transformers can be achieved using optical fiber sensors, prospecting real-time monitoring.

Color Index of Transformer Oil: A Low-Cost Measurement Approach Using Ultraviolet-Blue Laser.

The color of transformer oil can be one of the first indicators determining the quality of the transformer oil and the condition of the power transformer. The current method of determining the color index (CI) of transformer oil utilizes a color comparator based on the American Society for Testing and Materials (ASTM) D1500 standard, which requires a human observer, leading to human error and a limited number of samples tested per day. This paper reports on the utilization of ultra violet-blue laser at 405- and 450-nm wavelengths to measure the CI of transformer oil. In total, 20 transformer oil samples with CI ranging from 0.5 to 7.5 were measured at optical pathlengths of 10 and 1 mm. A linear regression model was developed to determine the color index of the transformer oil. The equation was validated and verified by measuring the output power of a new batch of transformer oil samples. Data obtained from the measurements were able to quantify the CI accurately with root-mean-square errors (RMSEs) of 0.2229 for 405 nm and 0.4129 for 450 nm. This approach shows the commercialization potential of a low-cost portable device that can be used on-site for the monitoring of power transformers.

Partial Discharge Localization Using Time Reversal: Application to Power Transformers.

In this work, we present a novel technique to locate partial discharge (PD) sources based on the concept of time reversal. The localization of the PD sources is of interest for numerous applications, including the monitoring of power transformers, Gas Insulated Substations, electric motors, super capacitors, or any other device or system that can suffer from PDs. To the best of the authors' knowledge, this is the first time that the concept of time reversal is applied to localize PD sources. Partial discharges emit both electromagnetic and acoustic waves. The proposed method can be used to localize PD sources using either electromagnetic or acoustic waves. As a proof of concept, we present only the results for the electromagnetic case. The proposed method consists of three general steps: (1) recording of the waves from the PD source(s) via proper sensor(s), (2) the time-reversal and back-propagation of the recorded signal(s) into the medium using numerical simulations, and (3) the localization of focal spots. We demonstrate that, unlike the conventional techniques based on the time difference of arrival, the proposed time reversal method can accurately localize PD sources using only one sensor. As a result, the proposed method is much more cost effective compared to existing techniques. The performance of the proposed method is tested considering practical scenarios in which none of the former developed methods can provide reasonable results. Moreover, the proposed method has the unique advantage of being able to locate multiple simultaneous PD sources and doing so with a single sensor. The efficiency of the method against the variation in the polarization of the PDs, their length, and against environmental noise is also investigated. Finally, the validity of the proposed procedure is tested against experimental observations.

Study of the Influence of Winding and Sensor Design on Ultra-High Frequency Partial Discharge Signals in Power Transformers.

Ultra-high frequency (UHF) partial discharge (PD) measurements in power transformers are becoming popular because of the advantages of the method. Therefore, it is necessary to improve the basic understanding of the propagation of signals inside the transformer tank and the factors that influence the sensitivity of the measurement. Since the winding represents a major obstacle to the propagation of the UHF signals, it is necessary to study the effect of winding design on signal propagation. Previous research activities have studied these effects using simplified models, and it is essential to consider the complexity of propagation in a complete transformer tank. Additionally, the quality of UHF PD measurements depends, to a large extent, on the sensitivity of the UHF sensors. In this contribution, a simulation model consisting of a simple, grounded enclosure with multiple winding designs is used to study the propagation characteristics of UHF signals when an artificial PD source is placed inside the winding. After analysis of the results, the winding designs are incorporated in an existing and validated simulation model of a 420 kV power transformer and analyzed to observe the influence in a more complex structure. Two commonly used sensor designs are also used in the simulation model to receive the signals. In all cases, the propagation and signal characteristics are analyzed and compared to determine the influence of the winding and sensor design on the UHF signals. It is found that the level of detail of winding design has a significant impact on the propagation characteristics. However, the attenuation characteristics of the UHF signals received by the two sensor designs are similar, with the electric field distribution around the sensor being the key difference.

Wavelet-Like Transform to Optimize the Order of an Autoregressive Neural Network Model to Predict the Dissolved Gas Concentration in Power Transformer Oil from Sensor Data.

Dissolved gas analysis (DGA) is one of the most important methods to analyze fault in power transformers. In general, DGA is applied in monitoring systems based upon an autoregressive model; the current value of a time series is regressed on past values of the same series, as well as present and past values of some exogenous variables. The main difficulty is to decide the order of the autoregressive model; this means determining the number of past values to be used. This study proposes a wavelet-like transform to optimize the order of the variables in a nonlinear autoregressive neural network to predict the in oil dissolved gas concentration (DGC) from sensor data. Daubechies wavelets of different lengths are used to create representations with different time delays of ten DGC, which are then subjected to a procedure based on principal components analysis (PCA) and Pearson's correlation to find out the order of an autoregressive model. The representations with optimal time delays for each DGC are applied as input in a multi-layer perceptron (MLP) network with backpropagation algorithm to predict the gas at the present and future times. This approach produces better results than choosing the same time delay for all inputs, as usual. The forecasts reached an average mean absolute percentage error (MAPE) of 5.763%, 1.525%, 1.831%, 2.869%, and 5.069% for C2H2, C2H6, C2H4, CH4, and H2, respectively.

UV-Vis Spectroscopy: A New Approach for Assessing the Color Index of Transformer Insulating Oil.

Monitoring the condition of transformer oil is considered to be one of the preventive maintenance measures and it is very critical in ensuring the safety as well as optimal performance of the equipment. Various oil properties and contents in oil can be monitored such as acidity, furanic compounds and color. The current method is used to determine the color index (CI) of transformer oil produces an error of 0.5 in measurement, has high risk of human handling error, additional expense such as sampling and transportations, and limited samples can be measured per day due to safety and health reasons. Therefore, this work proposes the determination of CI of transformer oil using ultraviolet-to-visible (UV-Vis) spectroscopy. Results show a good correlation between the CI of transformer oil and the absorbance spectral responses of oils from 300 nm to 700 nm. Modeled equations were developed to relate the CI of the oil with the cutoff wavelength and absorbance, and with the area under the curve from 360 nm to 600 nm. These equations were verified with another set of oil samples. The equation that describes the relationship between cutoff wavelength, absorbance and CI of the oil shows higher accuracy with root mean square error (RMSE) of 0.1961.

Novel Simulation Technique of Electromagnetic Wave Propagation in the Ultra High Frequency Range within Power Transformers.

Diagnoses of power transformers by partial discharge (PD) measurement are effective to prevent dielectric failures of the apparatus. Ultra-high frequency (UHF) method has recently received attention due to its various advantages, such as the robustness against external noise and the capability of PD localization. However, electromagnetic (EM) waves radiated from PD tend to suffer attenuation before arriving at UHF sensors, because active part of the transformer disturbs the EM wave propagation. In some cases, that results in poor detection sensitivity. To understand propagation and attenuation characteristics of EM waves and to evaluate the detection sensitivity quantitatively, a computational approach to simulate the EM wave propagation is important. Although many previous researches have dealt with EM wave simulation for transformers, validations of those simulations by comparing with the experimental ones have seldom been reported. In this paper, cumulative energies, signal amplitudes and propagation times of EM waves were measured using a 630 kVA transformer. EM wave propagation was computed using the time-domain finite integration technique and the results were compared with the experimentally obtained ones. These simulation results showed good agreement with the experimental ones. The results can serve as guidelines to improve the efficiency of UHF PD detection and offer the possibility to achieve optimal placement of UHF sensors in power transformers.

Partial discharge localization in power transformer tanks using machine learning methods.

This paper presents a comparison of machine learning (ML) methods used for three-dimensional localization of partial discharges (PD) in a power transformer tank. The study examines ML and deep learning (DL) methods, ranging from support vector machines (SVM) to more complex approaches like convolutional neural networks (CNN). Multiple case studies are considered, each with different attributes, including sensor position, frequency content of the PD signal, and size of the transformer tank. The paper focuses on predicting the PD location in three-dimensional space using single-sensor electric field measurements. Various aspects of each method are analyzed, such as the input signal, core methodology, correlation coefficient between the predicted location and the actual location, and root mean square error (RMSE). These features are discussed and compared across the different methods. The results indicate that the CNN model exhibits superior performance in terms of location accuracy among the methods considered.

Modeling the impact of high thermal conductivity paper on the performance and life of power transformers.

Degradation of insulation paper is a key contributor to the failure of power transformers. Insulation degradation accelerates at elevated temperatures, which highlights the potential for better thermal management to prolong life. While several studies have analyzed the benefits of high thermal conductivity oil for reducing temperatures inside a transformer, this study is an initial assessment of the benefits of high thermal conductivity paper on transformer life. Blending particulates with cellulosic fibers offers a pathway for high thermal conductivity paper (with good dielectric properties), which can reduce internal temperatures. Presently, life extensions that can be achieved by the use of such thermally conducting papers were estimated, with the thermal conductivity of the paper being the key parameter under study. The analytical-numerical thermal model used in this study was validated against experimental measurements in a distribution transformer, adding confidence to the utility of the model. This model was then used to provide estimates of hot-spot temperature reduction resulting from the use of papers with higher thermal conductivity than baseline. Transformer life was predicted conventionally by tracking the degree of polymerization of paper over time, based on an Arrhenius model. Results indicate that increasing the thermal conductivity of paper from 0.2 W/mK (baseline) to 1 W/mK reduces the hot spot temperature by 10 °C. While degradation significantly depends on the moisture and oxygen content, the model shows that such a temperature reduction can increase life for all conditions, by as much as a factor of three.

A study of correlation between the ect and ehd properties of different aged insulating oil mixtures that can Be an alternative to mineral oil for the insulation and cooling of power transformers.

This article presents the hypothetical steps leading to the damage of power transformers in order to examine whether there is a correlation between the electrostatic properties (ECT) and the electro-hydrodynamic properties (EHD) of insulating oils. Vegetable oils such as, olive oil (OO) and sunflower oil (SO) have been tested as alternative oils for the insulation and cooling of transformers and their blends with naphthenic mineral oil (MO) on the basis of well-defined ratios and for a remarkable aging time, which is an original contribution and insight offered by this paper. The results obtained for the different mixtures with regard to the electrostatic properties and the electro-hydrodynamic properties as well as the physico-chemical properties (power factor "tgδ", resistivity, conductivity and viscosity) in terms of the aging time were compared with that of the mineral oil. The study of the physico-chemical properties of insulating oils and their mixtures is carried out according to international standards.

Experimental dataset on the compressive mechanical properties of high-density pressboard used in power transformers spacers.

The structural elements within power transformers are commonly constructed from high-density pressboard, chosen for its favourable mechanical and dielectric properties. Among these elements are the spacers employed in the windings of transformers, which endure compressive loading during operation. The spacers are immersed in dielectric fluid and exposed to high temperatures and chemical reactions over the transformer's lifespan, resulting in the degradation of their dielectric and mechanical properties. The mechanical integrity of the power transformer significantly relies on these factors; hence, it is imperative to comprehend how ageing deteriorates the mechanical response of the high-density pressboard. The present article presents experimental data on the compressive mechanical properties of a commercially available high-density pressboard, commonly employed in power transformer spacers, under various ageing conditions (induced through accelerated thermal ageing and assessed by the degree of polymerisation). These data hold potential for diverse applications. They can enhance the existing comprehension of the mechanical behaviour and degradation mechanisms of cellulosic insulation in power transformers and provide reference benchmarks for comparison with factory-obtained values by manufacturers. In the realm of engineering failure analysis, these values can be utilised to evaluate the mechanical failures of paper-based materials utilised as structural components in power transformers.

Thermal stability of cellulose insulation in electrical power transformers - A review.

Cellulosic pulp has been processed into insulation paper since the earliest days of electrical engineering. This polymer synthetized by nature has proved to be competitive to man-made plastics throughout the last century and is still widely used in electrical power transformers. The high working temperatures prevailing in such apparatuses and the desired lifespans of up to 40 years shifted the thermal stability of cellulose to the center of attention of many researchers. In this literature review, a summary of theories and recent insights regarding the processes upon thermal degradation of cellulose in the temperature range relevant for electrical power transformers is given, followed by an overview of strategies to improve the thermal stability of cellulosic insulators. Special emphasis is placed on the discussion of additives and modification agents and their action modes, and on the understanding how successful upgrading of cellulose towards high thermal stability is achieved.

Experimental dataset on the tensile and compressive mechanical properties of plain Kraft and crepe papers used as insulation in power transformers after ageing in mineral oil.

The solid insulation in the windings of power transformers, which generally consists of oil-impregnated thin paper, is one of the key elements for the performance and durability of these electrical machines. Insulation paper is subjected to static and dynamic forces of electromagnetic origin, in combination with high temperatures and chemical reactions, during the operating life of a power transformer. The mechanical properties of the cellulosic insulation are relevant parameters because its breakage could result in the electric failure of the transformer. Indeed, paper manufacturers usually provide values of the tensile strength and elongation at breakage of the insulating paper in its two principal material directions, the MD (machine direction) and CD (cross-direction). However, paper is a highly anisotropic material and its material properties evolve as the paper insulation ages. The paper insulation in an operating transformer is subjected to a multiaxial stress state field including compressive and shear stresses. This article reports experimental data on the tensile and compressive mechanical properties of two types of paper, plain Kraft and crepe paper, typically used as insulation in power transformers, under different ageing states (which were induced through accelerated thermal ageing and quantified by means of the degree of polymerisation). These data could be reused for several purposes. They can improve the current understanding of the mechanical response and degradation processes of the cellulosic insulation in power transformers, and give some reference values that can be compared with others obtained in the factory by manufacturers. In the field of engineering failure analysis, those values could be reused for the assessment of mechanical failure of paper materials used in power transformers, see [1].

A Novel Fault Diagnosis System on Polymer Insulation of Power Transformers Based on 3-stage GA⁻SA⁻SVM OFC Selection and ABC⁻SVM Classifier.

Dissolved gas analysis (DGA) has been widely used in various scenarios of power transformers' online monitoring and diagnoses. However, the diagnostic accuracy of traditional DGA methods still leaves much room for improvement. In this context, numerous new DGA diagnostic models that combine artificial intelligence with traditional methods have emerged. In this paper, a new DGA artificial intelligent diagnostic system is proposed. There are two modules that make up the diagnosis system. The two modules are the optimal feature combination (OFC) selection module based on 3-stage GA⁻SA⁻SVM and the ABC⁻SVM fault diagnosis module. The diagnosis system has been completely realized and embodied in its outstanding performances in diagnostic accuracy, reliability, and efficiency. Comparing the result with other artificial intelligence diagnostic methods, the new diagnostic system proposed in this paper performed superiorly.

A performance-oriented power transformer design methodology using multi-objective evolutionary optimization.

Transformers are regarded as crucial components in power systems. Due to market globalization, power transformer manufacturers are facing an increasingly competitive environment that mandates the adoption of design strategies yielding better performance at lower costs. In this paper, a power transformer design methodology using multi-objective evolutionary optimization is proposed. Using this methodology, which is tailored to be target performance design-oriented, quick rough estimation of transformer design specifics may be inferred. Testing of the suggested approach revealed significant qualitative and quantitative match with measured design and performance values. Details of the proposed methodology as well as sample design results are reported in the paper.