Transformer Insulation Condition Research Articles

Residual LSTM-based short duration forecasting of polarization current for effective assessment of transformers insulation

The empirical application of polarization and depolarization current (PDC) measurement of transformers facilitates the extraction of critical insulation-sensitive parameters. This technique, rooted in time-domain dielectric response analysis, forms the bedrock for parameterization and insulation modeling. However, the inherently time-consuming nature of polarization current measurements renders them susceptible to data corruption. This article explores deep-learning-based short-duration techniques for forecasting polarization current to address this limitation. By incorporating spatial shortcuts, the residual long short-term memory (LSTM) network facilitates the seamless propagation of spatial and temporal gradients. Furthermore, the relative forecasting assessment of the proposed residual LSTM model’s performance is made against traditional LSTM, attention LSTM, gated recurrent units (GRU), and convolutional neural network (CNN) models. Thus, optimal model selection strategies are evaluated based on their capability to capture extended dependencies and short-term information present in the data. In addition, the Monte Carlo dropout prediction is employed to estimate uncertainty in polarization current forecasts. The findings demonstrate that the proposed residual LSTM network model for polarization current forecasting yields the lowest error metrics and maintains prediction consistency over the testing duration. Thus, the proposed approach significantly reduces PDC measurement time, providing an effective means to develop proactive maintenance strategies for evaluating the insulation condition of transformers.

Insulation aging condition assessment of transformer in the visual domain based on SE-CNN

The aging of transformer oil–paper insulation (OPI) contributes significantly to transformer failure and reduced service life. Therefore, reliable and precise evaluation of the aging status of transformer insulation condition is crucial in averting transformer failure. This article proposes a novel deep learning-based aging condition assessment technique of transformers by combining FDS (Frequency domain spectroscopy) and squeeze-and-excitation-enabled convolutional neural network (SE-CNN). An intrinsic product-based transformation using a Gramian angular field is employed to dimensionally expand the 1-D FDS signals acquired from OPI samples into 2D images. Each feature extraction channel in the SE-CNN-based aging diagnosis framework is assigned a specific weight, enabling the model to concentrate on the most relevant features while discarding the rest. Furthermore, the effect of moisture variation on the model is also considered under three different conditions to ensure the consequence of compensation for the effect of moisture on FDS. A comparison with traditional machine learning models has also been made to ensure the viability of the proposed methodology. Additionally, the model is interpreted by creating explanation weight plots of the feature coefficients using a local interpretable model-agnostic explanations (LIME) method in Python. The findings demonstrate that the novel aging diagnosis framework visually assesses the transformer’s OPI system with the highest accuracy of 99.12% in the test set. Furthermore, it facilitates the automatic extraction of deep aging features, thus providing better generalization and convergence capability.

Application of graphene gas sensor technological convergence PSO-SVM in distribution transformer insulation condition monitoring and fault diagnosis

This study aims to improve the real-time monitoring and fault diagnosis of distribution transformers by utilizing a combination of five thin film gas detectors, these detectors include metal-modified graphene composite films and SnO2/RGO humidity sensors, which were prepared using the hydrothermal method. The experiment focused on investigating humidity and main fault characteristic gases that can reflect the insulation status of transformers. Additionally, a gas sensor array was constructed using a deep confidence neural network model. Based on the analysis of dissolved gas in transformer oil, the study extensively discusses the insulation fault diagnosis model and constructs the transformer fault diagnosis model using various methods including TRM, Particle swarm optimization support vector machine. The results demonstrated that the SnO2/RGO thin film humidity sensor exhibited high humidity sensitivity, and the other thin film gas sensors also exhibited good sensitivity. The average accuracy of the three classification methods mentioned is 80%, 92%, and 96%, respectively. These findings highlighted that the vector machine model not only improved the fault diagnosis accuracy but also possessed the characteristics of fewer parameters and a fast rate of convergence. Consequently, it effectively addressed the issue of early diagnosis of potential transformer faults. This study was of significant practical importance for ensuring the secure operation of the power grid.

A Nonlinear Regression-Based Approach to Assess Transformer Insulation Condition Using Dielectric Response Recorded for Short Duration

A Nonlinear Regression-Based Approach to Assess Transformer Insulation Condition Using Dielectric Response Recorded for Short Duration

Health Assessment of Oil-Paper Insulation Using Short Duration Frequency Domain Response

Cellulosic paper moisture is widely considered an important factor for assessing the condition of transformer insulation. An increase in paper moisture accelerates the aging of the cellulosic parts and reduces the lifespan of the transformers. The proposed paper presents a methodology that is capable of identifying moisture within a few seconds. The methodology is based on an analysis of insulation response measured at 1 Hz. The method employs a Lissajous pattern-based technique for identifying dissipation factor (tan <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\delta $ </tex-math></inline-formula> ) and % paper moisture in oil paper insulation. Unlike available frequency domain spectroscopy (FDS)-based commercial equipment, the proposed method is observed to take significantly less time to operate without sacrificing accuracy.

Convenient Online Approach to Multisource Partial Discharge Localization in Transformer

Partial discharge (PD) online monitoring is an essential part of transformer insulation condition based maintenance and prognostics and health management in industrial power system. In order to realize online localization of multiple PD sources conveniently, an approach that uses single-channel mixed acoustic emission (AE) signal is proposed in this article. First, the combined method based on the singular spectrum analysis and the independent component analysis is used to calculate the number of PD sources and realize the separation of mixed AE signals. Next, a difference selection algorithm is proposed to solve the problem that the inherent disorder of signal blind source separation makes the time difference of arrival technology difficult to localize the multiple PD sources directly. Then, the simulation signals and measured signals have verified that the signal separation effect of the proposed single-channel-based method is no less than that of the multichannel-based method. Finally, the proposed approach is applied to a transformer. The disordered separated signals were successfully grouped to realize multisource PD localization.

Lightning caused overvoltages on power transformers recorded by on-line transient overvoltage monitoring system

Transient overvoltages generated by lightning strikes or switching operations represent a significant risk to bushings and windings of power transformers. They cause stress on the insulation system and can, over time, cause dielectric failure and damage to power transformers. Many transformer failures are reported as dielectric failures and they are not necessarily linked to any particular event when they occur but may be the result of prior damage from transient overvoltage events. Lightning and switching overvoltage waveforms appearing at transformer terminals in real operating conditions may significantly differ from standard impulse voltage waveforms used during laboratory testing. The number and amplitudes of overvoltages which stress the insulation depend on various parameters such as the lightning strike density in the considered area, since it determines how often the transformer is stressed by lightning overvoltages. Since the overvoltage amplitudes at transformer terminals are usually unknown, an on-line overvoltage transient recorder can be used with the ability to sample, analyse and store transients in real-time. In this paper, an on-line transient overvoltage monitoring system (TOMS) for power transformers is presented that is capable to continuously record in real-time various kinds of transient overvoltages such as lightning or switching overvoltages. Special attention is paid to lightning caused transient overvoltages recorded at the terminals of 150 MVA power transformer. Recorded waveforms originating from lightning strikes to overhead lines are correlated with data from the lightning location system (LLS) and supervisory control and data acquisition (SCADA) system. Collected data about overvoltage stresses can be used as the basis for the assessment of the transformer insulation condition, estimation of health index and for analysis of various kinds of events such as faults or equipment failures.

Fuzzy Algorithms for Diagnosis of Furnace Transformer Insulation Condition

Implementation of the smart transformer concept is critical for the deployment of IIoT-based smart grids. Top manufacturers of power electrics develop and adopt online monitoring systems. Such systems become part of high-voltage grid and unit transformers. However, furnace transformers are a broad category that this change does not affect yet. At the same time, adoption of diagnostic systems for furnace transformers is relevant because they are a heavy-duty application with no redundancy. Creating any such system requires a well-founded mathematical analysis of the facility’s condition, carefully selected diagnostic parameters, and setpoints thereof, which serve as the condition categories. The goal hereof was to create an expert system to detect insulation breach and its expansion as well as to evaluate the risk it poses to the system; the core mechanism is mathematical processing of trends in partial discharge (PD). We ran tests on a 26-MVA transformer installed on a ladle furnace at a steelworks facility. The transformer is equipped with a versatile condition monitoring system that continually measures apparent charge and PD intensity. The objective is to identify the condition of the transformer and label it with one of the generally recognized categories: Normal, Poor, Critical. The contribution of this paper consists of the first ever validation of a single generalized metric that describes the condition of transformer insulation based on the online monitoring of the PD parameters. Fuzzy logic algorithms are used in mathematical processing. The proposal is to generalize the set of diagnostic variables to a single deterministic parameter: insulation state indicator. The paper provides an example of calculating it from the apparent charge and PD power readings. To measure the indicativeness of individual parameters for predicting further development of a defect, the authors developed a method for testing the diagnostic sensitivity of these parameters to changes in the condition. The method was tested using trends in readings sampled whilst the status was degrading from Normal to Critical. The paper also shows a practical example of defect localization. The recommendation is to broadly use the method in expert systems for high-voltage equipment monitoring.

Multiple partial discharge sources separation using a method based on laplacian score and correlation coefficient techniques

Partial discharge (PD) activity can be destructive to the transformer insulation, and ultimately may result in total breakdown of the insulation. Partial discharge sources identification in a power transformer enables the operator to evaluate the transformer insulation condition during its lifetime. In order to identify the PD source; in the case of presence of multiple sources; the first step is to capture the PD signals and to extract their specific features. In this contribution, the frequency domain analysis, the time domain analysis and the wavelet transform are employed for feature extraction purpose. In practice, there might be plenty of features, and in each scenario, only some of them may be effective. Therefore, among the extracted features, those useful for discrimination of the multiple PD sources are studied. Then, a method, using laplacian score, and the correlation coefficient algorithms; is developed for feature selection. In order to discriminate among the multiple partial discharge sources, a density-based algorithm spatial clustering of applications with noise (DBSCAN) have been employed to cluster among available PD sources and the noise. The results of some case studies demonstrated the great ability of this method in proper discrimination of multiple PD sources.

Evaluation of power transformer health analysis by internal fault criticalities to prevent premature failure using statistical data analytics approach

Transformers are key players at transmission and distribution level in electrical grid to deliver reliable, efficient, smooth and quality power at consumer end. Power transformers plays a crucial role in the interconnected power systems and is therefore considered as one of the most important and critical assets. Any deterioration occurring due to electrical, thermal, chemical as well as environmental stresses can be identified from health indices and immediate actions can be proposed to avoid any premature failure. This research paper includes the multi criterion based mathematical approach to identify the health indices of power transformers. The proposed approach gives more precise result compared to the conventional methods used for transformer faults diagnosis like gas ratio and traditional experiment based methods to measure health index. The multi criterion considered here are dielectric strength, acidity, breakdown voltage, dissolved gas analysis, furan compounds, dielectric dissipation factor, moisture presence, interfacial tension, winding DC resistance, tan delta etc. It becomes more reliable and proficient to measure the health indices using multi criteria decision making along with piece wise linear equations and Residual Analysis approach for accurate measurement for newly manufactured transformer as well as in service aged transformers. Further, 100 test data set have been added to analyze the performance and implications of health index of 20 completely healthy transformers, 60 partial deformed transformers and 20 complete deformed transformers or on verge of failure. This work gives detailed insights of health status and insulation condition of new transformer, in service transformers or any failure transformer.

Frequency-Domain Spectroscopy of Oil and Oil-impregnated Pressboard with DC Bias

Dielectric response measurement is widely used to characterize oil/oil-impregnated pressboards in order to evaluate the condition of transformer insulation. Insulation systems with oil can exhibit voltage dependence at low frequencies. This is due to the limited number of mobile charges in the liquid, rather than to the dielectric relaxation processes that may, in some cases, be of more interest to study. This work investigates the voltage-dependent properties of oil/oil-impregnated pressboards under ac voltages with regard to the complex permittivities. Frequency-domain spectroscopy (FDS) measurements are made with a dc voltage added to the ac voltage stimulus. Considered influences are the voltage amplitudes and polarity as well as the dependence on temperature. Properties of the space-charge polarization in the oil and oil-impregnated pressboard are calculated and discussed based on the dc-biased measurements. It is seen that using the dc bias in the FDS measurements of oil/oil-impregnated pressboard can significantly decrease the voltage dependence of the results that are caused by ion drift and consequent depletion of ions from the bulk liquid. Based on the dc-biased measurements, the complex permittivity due to the linear and nonlinear polarization can be separated.

Estimation of Moisture Content in Oil-impregnated Pressboard through Analyzing Dielectric Response Current under Switching Impulse

This paper proposes an advanced technique for estimating the paper moisture content within oil-impregnated pressboard by analyzing its dielectric response current signature under switching impulse voltage. The present work is oriented towards development of a method which can assess the condition of transformer insulation through measuring the dielectric response current during its switching on or off operation to the grid. In order to investigate the effectiveness of the method, the dielectric response current of a few oil-impregnated pressboards containing different moisture contents, are measured using switching impulse in laboratory. Based on the applied switching impulse and corresponding response current, the branch parameters of the equivalent circuit of insulation are evaluated which have been employed for formulating its transfer function. The zero and pole calculated from the transfer function are found to be sensitive to the paper moisture of insulation. Correlation of transfer function zero and pole with the paper moisture of insulation are derived using the experimental results. These correlations are validated through the experimental investigation on few other test samples.

Aging assessment of transformer solid insulation: A review

Power transformer is one of the key equipment in electrical transmission and distribution network. Most of power transformers, cellulose made solid and petroleum extracted liquid as chief insulation. In transformers, liquid insulation plays a vital role in providing insulation as well as cooling. There are mainly few mechanisms that exposed to the insulation degradation because of the aging, high temperature and chemical reactions such as the hydrolysis, oxidation and pyrolysis. The condition of oil has to be checked on the basis of repeatedly and retrieved when it necessary, to avoid the quick failure of transformer. Failures of transformer can have controlled to strong effect on security, reliability of power supply and cost. Because of higher operating temperature earlier degradation of paper/oil insulation system of transformer leads to variation in some insulation characteristics, therefore remaining life time of power transformer is degraded. Conventional time-based maintenance and subsequent replacement is not possible for transformer safety. Online monitoring and condition based maintenance are necessary. Various electrical and chemical diagnostic techniques are existing for monitoring of insulation condition of power transformers. This paper presents a study of generally used solid insulation diagnostics techniques along with their analysis its schemes.

On Site Oscillating Lightning Impulse Test and Insulation Diagnose for Power Transformers

This letter proposed a new lightning impulse test method for power transformers based on oscillating lightning impulse(OLI) waveform. The OLI has high generation efficiency and is easy to generate for field test. Partial discharge detection and transfer function analysis are used to evaluate the transformer insulation condition during the impulse test. The OLI waveform for transformer test satisfied with the requirements of the standard is obtained by altering the value of resistance and inductance in the circuit. The experiment was carried out on a transformer scale model to prove the validity of the proposed method. The results show that the current pulse method and the UHF method detect the PDs simultaneously as the insulation defect is excited at high voltage. Meanwhile, the transfer function changes due to the discharge in winding. It provides a new test and insulation diagnose method with application prospects for transformer lightning impulse test on site.

Partial discharge feature extraction based on synchrosqueezed windowed Fourier transform and multi-scale dispersion entropy

The recognition of partial discharge mode is an important indicator of the insulation condition in transformers, based on which maintenance can be arranged. Discharge feature extraction is the key to recognize discharge mode. To solve the problem of poor stability and low recognition rate of partial discharge mode, this paper proposes a feature extraction method based on synchrosqueezed windowed Fourier transform and multi-scale dispersion entropy. First, the four partial discharge signals collected under laboratory conditions are decomposed by synchrosqueezed windowed Fourier transform, then a number of band-limited intrinsic mode type functions are obtained, and the original feature quantities of partial discharge signals are obtained by calculating the multi-scale dispersion entropies of each intrinsic mode type function. Based on that, original feature quantity is optimized by using the maximum relevance and minimum redundancy criteria. Finally, the classification is implemented by the support vector machine. Experimental results show that in the case of noise interference, the proposed synchrosqueezed windowed Fourier transform–multi-scale dispersion entropy method can still accurately describe the feature of different discharge signals and has a higher recognition rate than both the empirical mode decomposition–multi-scale dispersion entropy method and the direct multi-scale dispersion entropy method.

De‐noising of time‐domain spectroscopy data for reliable assessment of power transformer insulation

Polarisation-depolarisation current (PDC) measurement and its analysis is a popular technique for assessing the condition of transformer insulation. Owing to the low magnitude of PDC, recording noise-free PDC data from in-situ power transformers is a challenge. Once the relaxation current data get affected by noise, it becomes difficult to formulate insulation model (as recorded data loses its characteristic shape). This further makes the data difficult to analyse and predict insulation condition. In this study, two de-noising techniques are discussed (one is based on Wavelet Transform while the other is based on Stockwell Transform) for eliminating low-frequency non-stationary noise from recorded PDC data. Comparison between these two techniques suggests de-noising using Stockwell Transform is advantageous over wavelet analysis. The proposed methodology is first tested on data recorded from the sample prepared in the laboratory and then on data measured from real-life in-service power transformer.

Internal insulation condition identification for high-voltage capacitor voltage transformers based on possibilistic fuzzy clustering.

The internal insulation condition of capacitor voltage transformers (CVTs) is a key influence factor that affects their measurement performance and safe operation. However, the internal insulation would age along with long-time operation and degrade due to environmental factors, and once the insulation degradation grows, serious damage and even explosion may happen in CVTs; hence, it is necessary to monitor the internal insulation condition of CVTs, and the fault type and fault degree need to be identified. In this paper, a data-driven internal insulation condition identification method for CVTs is proposed. Both the amplitude and phase of the output voltage of CVTs are collected, and then, recognition models based on the combination of the output voltages and distribution topology of CVTs in substations are built. A possibilistic fuzzy clustering method is used to monitor the internal insulation condition of CVTs, and different types and different degrees of insulation faults could be identified effectively. Finally, the proposed method is verified in several cases; not only the preset typical faults in the method could be identified effectively but also the faults beyond the preset faults could be diagnosed.

Condition Assessment of Power Transformer Insulation Using Short-Duration Time-Domain Dielectric Spectroscopy Measurement Data

Utilities prefer noninvasive methods for assessing the condition of power transformer insulation. Analysis of polarization–depolarization current (PDC) is one such popular method. One such analysis involves the estimation of trapped charge released from the interfacial region of oil–paper insulation. The literature shows that such charges can be reliably used for the diagnosis of transformer insulation. However, such analysis requires a complete profile of PDC. PDC measurement (an offline technique) takes a large amount of time (several hours) to complete. The magnitude of PDC data for a larger value of time is also sensitive to changes in environmental conditions and field noise as its magnitude is low. Hence, a reliable estimation of detrapped charge may require numerous PDC measurements. This situation is not convenient for utilities as it prolongs shut down time. In this article, a method has been proposed which is capable of estimating detrapping charge using PDC data measured for a short span of time. The proposed method is tested on data collected from several real-life in-service transformers.

Methanol Marker for the Detection of Insulating Paper Degradation in Transformer Insulating Oil

This manuscript presents a comprehensive literature review with the aim to provide readers a reference document with up-to-date information on the field of methanol use as a chemical marker. It has been a little more than a decade since methanol was first introduced as a marker for assessing solid insulation condition in power transformers. It all started when methanol was identified in the laboratory during thermal ageing tests carried out with oil-immersed insulating papers and was subsequently also identified in transformer field samples. The first publication on the subject was released in 2007 by our research group. This review covers the methanol fundamentals such as the analytical methods for its determination in transformer oil, which is generally performed by headspace gas chromatography with mass spectrometry or flame ionization as a detector. Current standardization efforts for its determination include ASTM working group 30948 and IEC TC10. Kinetic studies have confirmed the relationship between methanol generation, the number of broken 1,4-β-glycosidic bonds of cellulose and changes in mechanical properties. Laboratory tests have confirmed its stability at different accelerated ageing temperatures. Several utilities have identified methanol during field measurements, case studies on power and some distribution transformers are presented, as well as transformer postmortem investigations. These field-testing results demonstrate its utility in monitoring cellulosic insulation degradation. Recently, a model of methanol interpretation has become available that allows for evaluation of the average degree of polymerization of core type transformer cellulose winding. Methanol has a role as an indicator of cellulosic solid insulation ageing in transformer mineral oil, and it is expected that in the future it will be in routine use by utilities.

Power Transformer Fault Severity Estimation Based on Dissolved Gas Analysis and Energy of Fault Formation Technique

Decision making on transformer insulation condition based on the evaluated incipient faults and aging stresses has been the norm for many asset managers. Despite being the extensively applied methodology in power transformer incipient fault detection, solely dissolved gas analysis (DGA) techniques cannot quantify the detected fault severity. Fault severity is the core property in transformer maintenance rankings. This paper presents a fuzzy logic methodology in determining transformer faults and severity through use of energy of fault formation of the evolved gasses during transformer faulting event. Additionally, the energy of fault formation is a temperature-dependent factor for all the associated evolved gases. Instead of using the energy-weighted DGA, the calculated total energy of related incipient fault is used for severity determination. Severity of faults detected by fuzzy logic-based key gas method is evaluated through the use of collected data from several in-service and faulty transformers. DGA results of oil samples drawn from transformers of different specifications and age are used to validate the model. Model results show that correctly detecting fault type and its severity determination based on total energy released during faults can enhance decision-making in prioritizing maintenance of faulty transformers.