Power Transformer Failure Research Articles

Enhancing Predictive Maintenance of Power Transformers Through Machine Learning Approaches

This paper focuses on the use of machine learning algorithms to assist in predictive maintenance, aiming to reduce downtime and associated costs for electrical equipment. It introduces two machine learning predictive indicators: the Chromatographic Assay Indicator (CAI) and the Electrical Failure Risk Indicator (EFRI), which leverage chromatographic and sensor data, respectively. The CAI indicator was trained on external data, and its generalization capability was assessed using company-specific chromatographic data with expert assistance. The evaluation involved two heuristics, both focusing on keyword identification in free-text diagnoses. Results showed over 90% accuracy in predicting failures in reactors and power transformers, and an AUC of nearly 85% for reactors. Additionally, CAI outperformed classical Dissolved Gas Analysis (DGA) methods. On the other hand, the EFRI indicator was trained using company’s internal data from a monitoring system of operational sensors and maintaining power transformer data. The classification model achieved over 95% accuracy and an AUC of almost 90% on the test set. These results indicate that both indicators can be integrated into a solution to support maintenance specialists in their decision-making processes.

Implementation of Fuzzy Logic Scheme for Assessment of Power Transformer Oil Deterioration Using Imprecise Information

This research aims to analyze the implementation of a fuzzy logic-based approach in improving the diagnosis of power transformer oil deterioration, which is critical for maintaining the efficient performance and operational life of transformers. Traditional diagnoses are based on strict measurements that do not account for the factors of variability and uncertainty of the actual data. In this article, we perform six different types of tests in this regard, and data have been collected during the period of 2021 to 2022 of 188 power transformer failures in the New KotLakhpat Lahore unit, whose voltage range is 132/66 kv and rating capacity is 40/50 MVA. In this case, a fuzzy logic-based scheme is developed based upon the membership function, a rule-based and defuzzification method that works with imprecision and the implementation of uncertainty in assessing the condition of transformer oils. Moisture, acidity, and a dissolved gas analysis indicator, along with other indication approaches such as interfacial tension, viscosity, and tangent delta measurement, are used to analyze the deterioration process in transformer oils. In the visual representation, oil samples with the following properties were first fuzzified: 19.9 mm2/s of viscosity, 0.453 mgKOH/g of acidity, 695 ppm of DGA, 20.8 mg/kg of moisture, 19.98 of IFT, and 4.35 × 100.14 of tangent delta. The output that was generated by software using the values entered into the parameters (HI and Age) after defuzzification is 45. Fuzzy logic serves as a concrete framework for transforming the diagnostics system and deterring the threats to the entire transformer’s health and reliability in the future. By using this technique, various faults were hypothetically and practically analyzed in a transformer to implement early detection technologies with the possibility to reduce maintenance costs and extend operational life up to 45 years. Various case studies indicate the effectiveness of fuzzy logic in comparison to traditional diagnostics.

Electromagnetic–Structural Finite Element Analysis of Copper and Aluminum Windings in Power Transformers under Short-Circuit Conditions

Electromagnetic forces can lead to the structural failure of power transformers due to extreme loading conditions, vibration, and/or fatigue. Therefore, studying the nature and the magnitude of these forces is a key task in the design and failure analysis of such important equipment. Keeping this issue in mind, this work aims at conducting a numerical analysis in order to evaluate the mechanical stresses and displacements of windings in power transformers due to the action of electromagnetic forces. With this purpose, a finite element model is developed considering electromagnetic and mechanical effects assuming short-circuit conditions. The study compares the cases employing copper and aluminum windings with header tap, in different temperatures. The model developed in this work is verified against analytical solutions. The numerical calculations allow for performing a detailed analysis in terms of the distribution of both displacements and stresses along the windings, which is of great relevance for identifying critical structural points and avoiding structural failure. Overall, the obtained results demonstrate that the finite element model is a useful tool for the structural design of power transformers that allow for investigating and optimizing key aspects before manufacturing.

A causal reasoning approach for power transformer failure diagnosis

A causal reasoning approach for power transformer failure diagnosis

Effective Power Transformer Maintenance Strategy Decision-Making: Health Index, Statistical Analysis, and Life Cycle Cost

As a State-Owned Enterprise, PLN must provide sufficient quantity and quality electricity for the public interest. Still, on the other hand, according to the articles of association, PLN is required to make a profit. Power transformer failures significantly impact electrical system reliability, as they can disrupt electricity delivery. Many studies have been conducted on the health index of power transformers. However, previous studies only considered health indexes from one or several aspects of testing results. Life Cycle Cost is a method that helps select the best cost approach for establishing an effective maintenance strategy over the transformer's lifetime. A transformer lifetime uses a Weibull Analysis of a failure transformer in PLN TJBT from 2017-2022. This study uses a comprehensive health index by considering failure modes in transformers that integrate results from various aspects, such as observations while in operation, field inspections, and on-site and laboratory testing. After conducting a comprehensive health index, a risk evaluation was performed to simulate the impact of different maintenance decisions. Considering the health index and life cycle cost of the transformer, a new maintenance decision-making model was developed to choose the best maintenance strategy based on the current condition of the transformer.

THE RELIABILITY ASSESSMENT OF POWER TRANSFORMERS

This research investigated the assessment of power transformer reliability with emphasis on the transmission network within Rivers State in Nigeria, focusing on the perspectives of electricity consumers, organizational personnel, and business operators using descriptive survey. The study encompassed the entire population of 725,372 electricity consumers in the Port Harcourt Electricity Distribution Company (PEDC) in Rivers State, which included both households and business owners. To select a representative sample, the Convenience Sampling Technique was employed, resulting in the inclusion of 390 electricity consumers in Rivers State. Data collection utilized the Consumers Perception of Electricity Power Transformer Reliability (COPEPT) questionnaire and Structured Interview, with the instrument's reliability established through the test-retest technique, yielding a reliability coefficient for each investigation. Research questions were addressed through the weighted mean score (WMS) analysis. Key findings indicated dissatisfaction among electricity consumers in Rivers State, primarily attributed to factors such as transformer age, overall condition, uncontrolled overloading, adverse weather conditions, and inadequate transformer capacity to meet increasing demand. Addressing these issues, different approaches including upgrading or replacing outdated transformers, implementing limits on transformer loading, introducing robust earthing systems, and increasing transformer capacity, were recommended to enhance consumer satisfaction and overall reliability. The study further revealed that persistent power transformer failures resulted in power outages, adversely impacting businesses, households, communication, and contributing to reduced production and national income. Based on these findings, recommendations in the form of strategies were provided, emphasizing a comprehensive analysis of power surge control during adverse weather conditions, a plan for upgrading or replacing outdated transformers, an assessment of power transformer capacity needs, and collaboration with relevant stakeholders to develop strategies mitigating the negative economic impact and enhancing communication with consumers.
 Keywords: Reliability Assessment, Power Transformers, Rivers State and Transmission Network.

Improving the Reliability of Online Bushing Monitoring

This paper discusses the common issue of bushing failures in power transformers and presents methods for preventing such failures through online monitoring. The paper presents a method based on the comparison of bushing leakage currents from different transformers connected to the same busbars to overcome problems with unreliable measurement results due to grid voltage imbalance or frequent transformer outages.

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.

Data Restoration of dissolved gas content in transformer oil based on the CS-SVR model

Accurate monitoring of the dissolved gas content in transformer oil is crucial for transformers’ safe and stable operation. The early identification for detecting potential power transformer failures is necessary for the stability of an electrical grid. Dissolved gas analysis is an essential technology in transformers diagnosing insulation faults. Missing dissolved gas data can directly impact the reliability of monitoring results of a transformer. This study presents a data plug-in model based on support vector regression (SVR) to restore missing dissolved gas data. To further improve the accuracy of data restoration, the cuckoo search algorithm (CS) is used for optimizing SVR parameters. By verifying H2 and C2H4, the CS-SVR model demonstrates superiority over other plug-in procedures in repairing dissolved gas data.

Research on Changes in the Phase Shift Angle and Admittance of the Cellulose–Bio-Oil Composite under the Influence of Increasing Moisture during the Long-Term Operation of Power Transformers

In this study, the temperature–frequency dependencies of the pressboard–bio-oil–water nanoparticle composite’s fundamental parameters—phase shift angle and admittance—were examined using the Frequency Domain Spectroscopy method. Measurements were conducted in a frequency range of 10−4 Hz to 5 × 103 Hz at temperatures ranging from 293.15 K to 343.15 K, with a step of 10 K. The temperature stabilization accuracy was less than ±0.05 K. A total of 15 Arrhenius plots were determined for various phase shift angle values, from which 15 values and the average activation energy of relaxation time were determined. Similarly, the values of the activation energy of admittance relaxation time and the activation energy of admittance were determined. It was established that all three average values are identical within the bounds of uncertainty. Based on 45 values, a generalized activation energy was determined, with a value of ΔW ≈ (1.032 ± 0.0196) eV. Using the generalized activation energy value, the phase shift angle curves determined for all temperatures were recalculated to a temperature of 293.15 K. It was found that after conversion, all curves perfectly overlap. A similar operation was carried out for the frequency dependencies of admittance. In this case, too, the recalculated dependencies perfectly match. This means that the shape of the frequency dependencies of the phase shift angle and admittance depends solely on the moisture content in the pressboard–bio-oil–water nanodrop composite. The position of the curves in doubly logarithmic coordinates depends only on temperature and is determined by the generalized activation energy Using the generalized activation energy determined in this study will allow for the development of accurate methods for estimating moisture content in cellulose insulation of power transformers containing bio-oil. This will contribute to the detection of critical moisture content, which is about 5% by weight, and to the elimination of the risk, associated with such a high moisture content, of catastrophic failure of power transformers.

Development of fuzzy classifier for technical condition ranking of power transformer

The work aim is to develop a fuzzy classifier for technical condition ranking of power transformer under condition of vagueness and ambiguity diagnostic information. Methodology. The fuzzy classifier developing for technical condition ranking of power transformer was based on approach of using fuzzy set theory and optimization methods. The proposed approach for power transformer rank assessment by using a classifier was developed on the basis of Takagi-Sugeno fuzzy inference system. The input indicators choice is justified and their efficiency for classifier is evaluated by expert evaluation method. This makes it possible to formalize expert assessments regarding the development of power transformer defects. Results. The formalization of technical condition assessment of power transformer in knowledge base form, which implemented in expert system prototype for technical condition assessment, was carried out. The complex technical condition assessment for each functional unit of power transformer was determined based on expert evaluations with using the test and measurement parameters results. Originality. The considered approach to formalization of uncertainty regarding technical condition of power transformer allows building a deterministic decision-making scheme for further maintenance strategy, in which the ranking and decommissioning procedures for specific objects are implemented on the basis of objective criteria. Practical value. The proposed fuzzy classifier allows determination with a high probability degree of technical condition assessment of power transformer based on the test and measurement parameters results. Thus, an applied aspect of using the obtained scientific result is the possibility to objectively rank of power transformers park based on the identified possible defects and their development degree. This constitutes the prerequisites for determining the failure probability evaluation of power transformer at nearest observation period and emergency risk assessment in integrated electric power systems under power transformer failures.

Monitoring Transformer Condition with MLP Machine Learning Model

Failures of large power transformers in transmission system are always followed by significant costs, which is especially problematic because they present an unplanned expenditure. Aside from derailing financial plans, these events can lead to lower system reliability. This paper describes the development and potential application of transformer model based on multilayer perceptron class of artificial neural networks. Model is built in Python programming language and data collected over the span of one year for a single transformer. Three input features (oil temperature, winding current and outside temperature) are used in the input layer, with the goal of predicting the winding temperature in the transformer. Predicted temperature of the windings can then be compared with the actual winding temperature, which can serve as an indicator of transformers internal condition. Two types of transformer condition degradation are simulated to show the model in action, and certain indicators are explored.

전력용 변압기의 고장 메커니즘 분석을 통한 실규모 화재폭발 시험 기법 개발

Failures in high voltage power transformers are classified as a kind of disaster accompanied by fires and explosions. It could lead enormous loss of property due to equipment damage and restoration, and black-out of power grid can take place by separating the fault section from the power system. In particular, power facilities including transformers have been intensively installed in Republic of Korea since the 1988 Seoul Olympics. These power equipment is operated for more than 30 years from then. The power transformers in long-term operation are aged and a number of failures tend to increase, therefore, necessity of developing transformer fire prevention and suppression technology is emerging. This paper deals with the development of 154 kV class power transformer real-scale fire test method through its fire and explosion mechanism analysis to advancement fire prevention and suppression technology on power transformer. The test method includes, test items, subjects, facilities, and test site. The established transformer fire mechanism could be applied to develop new investigation method for cause of transformer fire, and real-scale test methodology could be widely utilized for various research such as transformer fire and explosion test, development of its extinguishing technology.

Fault Detection and Protection of Power Transformer Using Fuzzy Logic

Abstract: Power transformer malfunctions cause significant power outages and, as a result, material damage. This critical issue must be resolved. Power transformers must be protected from various fault conditions and power system failure. Fuzzy logic is used in this study to detect and protect power system transformer faults. In the simulation system that diagnoses transformer faults and monitors its operating conditions, the fuzzy logic (FL) toolbox in MATLAB/ SIMULINK software was used. The input variables, current and rate of change of current with time, have been identified as "Error" and "Error-Dot" in the programme. The study's findings show that when the output response is zero, the current in the transformer is normal. This is obtained by injecting [0] and [0] input values into the system, resulting in a response of "6e(-017)," which is close to zero. If the output response is greater than zero, the transformer current is rising above normal and the protection scheme should be notified. This condition is achieved by giving the system input values of [-1.5] and [5] and expecting a response of "+5". If the response is less than zero, the transformer current is less than normal, and the protection scheme should be notified. The study concluded that electrical faults and mechanical failures in power transformers can be quickly identified using Fuzzy logic. Thus, power transformer damage is avoided by controlling relays more effectively and quickly. This has resulted in significant savings in maintenance and repair costs. It is assumed that the study was a success.

FAULT DETECTION AND PROTECTION OF POWER TRANSFORMER USING FUZZY LOGIC

Power transformer malfunctions cause significant power outages and, as a result, material damage. This critical issue must be resolved. Power transformers must be protected from various fault conditions and power system failure. Fuzzy logic is used in this study to detect and protect power system transformer faults. In the simulation system that diagnoses transformer faults and monitors its operating conditions, the fuzzy logic (FL) toolbox in MATLAB/ SIMULINK software was used. The input variables, current and rate of change of current with time, have been identified as "Error" and "Error-Dot" in the programme. The study's findings show that when the output response is zero, the current in the transformer is normal. This is obtained by injecting [0] and [0] input values into the system, resulting in a response of "6e(-017)," which is close to zero. If the output response is greater than zero, the transformer current is rising above normal and the protection scheme should be notified. This condition is achieved by giving the system input values of [-1.5] and [5] and expecting a response of "+5". If the response is less than zero, the transformer current is less than normal, and the protection scheme should be notified. The study concluded that electrical faults and mechanical failures in power transformers can be quickly identified using Fuzzy logic. Thus, power transformer damage is avoided by controlling relays more effectively and quickly. This has resulted in significant savings in maintenance and repair costs. It is assumed that the study was a success. Keywords: Fuzzy logic, Transformer, fault, Detection, Current, Protection

Математична модель емпіричного закону розподілу виходу з ладу силових трансформаторів через пошкодження обмоток

The work is devoted to the identification of the law of distribution according to statistical data of failure of power transformers of 6–10 kV due to damage to their windings for a three-year period: from 2018 to 2020. According to statistical data, it has been established that there is a tendency to reduce damage to power transformers by almost two times. But the number of these failures still remains quite large. The main cause of power transformers failure is damage to their windings, which accounts for 82.17 % of other causes. Therefore, the statistics that characterize the failure of power transformers due to damage to the windings were taken for research. It was established that in 2018 and 2019, the largest number of damages to power transformer windings occurred in April—July with a peak in June, and in 2020, the maximum damages were recorded in November and December. The prerequisite for building mathematical models for predicting the failure of power transformers due to the damage to the windings in order to ensure the necessary number of spare parts for their quick recovery is the study of the nature of the failure of transformers. The following methods were used to solve the tasks: passive experiment — to collect information about the failure of power transformers; statistical analysis — to build an empirical law of distribution. After analyzing the view of the histogram of the variation series of the sample of failure of power transformers due to damage to the windings, a hypothesis was put forward about the logarithmic normal distribution law of the failure of transformers due to damage to the windings. Pearson's c2-test was used to check it. As a result of the study, the proposed hypothesis was confirmed. Using Student's tables and the c2-distribution table with a confidence probability of g2 = 0.98, confidence intervals were determined for statistical estimates of the mean value, variance and root mean square deviation, which characterize the failure of power transformers due to damage to the windings. With further research, it will be possible to build mathematical models for predicting the failure of power transformers due to damage to the windings.

Performance Assessment of Solar-Transformer-Consumption System Using Neural Network Approach

Solar energy is one of the immeasurable renewable energy in power generation for a green, clean and healthier environment. The silicon-layer solar panels absorb sun energy and converts it into electricity by off-grid inverter. Electricity is transferred either from this inverter or from transformer, consumed by consumption unit(s) available for residential or economic purposes. The artificial neural network is the foundation of artificial intelligence and solves many complex problems which are difficult by statistical methods or by humans. In view of this, the purpose of this work is to assess the performance of the Solar - Transformer - Consumption (STC) system. The system may be in complete breakdown situation due to failure of both solar power automation subsystem and transformer simultaneously or consumption unit; otherwise it works with fully or lesser efficiency. Statistically independent failures and repairs are considered. Using the elementary probabilities phenomenon incorporated with differential equations is employed to examine the system reliability, for repairable and non-repairable system, and to analyze its cost function. The accuracy and consistency of the system can be improved by feed forward- back propagation neural network (FFBPNN) approach. Its gradient descent learning mechanism can update the neural weights and hence the results up to the desired accuracy in each iteration, and aside the problem of vanishing gradient in other neural networks, that increasing the efficiency of the system in real time. MATLAB code for FFBP algorithm is built to improve the values of reliability and cost function by minimizing the error up to 0.0001 precision. Numerical illustrations are considered with their data tables and graphs, to demonstrate and analyze the results in the form of reliability and cost function, which may be helpful for system analyzers.

Life Span Assessment of the Insulation for Power Transformers: A Review

A power transformer is a vital link for any electrical transmission and distribution network, used to raise the voltage levels of the generators, and transformers at local substations to supply loads. However, an unexpected failure of power transformers cause an electricity shortage to the consumer, involve the loss of millions of dollars for utility companies, industrial failure costs, environmental hazard costs due to oil spillage and also indirectly to the national security. Hence, predicting the lifespan of a power transformer has been considered an important issue for energy companies in order to reduce the transformer failure. Power transformers that reach the end of its life usually do so unexpectedly, causing power reliability problems, which cost a lot of money. Therefore, knowing the factors that play part in the degrading process of a power transformer could help power companies determine how long a power transformer have before breaking down and allow them to perform any necessary action before the power transformer starts giving problems. This research paper therefore focuses on the life assessment of the insulation for power transformers. In this paper, different approaches used for the evaluation of lifespan of power transformers were reviewed. These approaches have become powerful tools to overcome the problem of transformer failure and aging, because these tests are carried out more frequently by utilities. This research paper therefore, will help utilities to monitor the major parameters, to determine the remaining life and the lifespan of power transformers. Keywords: Power Transformers, Electrical Transmission Network, Electrical Distribution Network, Lifespan, Consumers, Transformer Failure, Reliability, Transformer Aging. DOI: 10.7176/JETP/12-3-02 Publication date: August 31 st 2022

Power Transformer Fault Prediction using Naive Bayes and Decision tree based on Dissolved Gas Analysis

Power transformers are the basic elements of the power grid, which is directly related to the reliability of the electrical system. Many techniques were used to prevent power transformer failures, but the Dissolved Gas Analysis (DGA) remains the most effective one. Based on the DGA technique, this paper describes the use of two of the most effective machine learning algorithms: Naive Bayes and Decision Tree for the identification of power transformer’s faults. In our investigation, 9 different input vectors have been developed from widely known DGA techniques. 481 samples have been used and 6 types of faults have been considered. The evaluation result of the implementation of the proposed methods shows an effectiveness of 86.25% in power transformer’s fault recognition.

On the Development of the Theory of Resonant Processes in Power Transformer Windings. Part 3. Transients in a Circuit with Two PI Sections

The development of electrical networks and widely used technical solutions lead to more frequent winding insulation failures in power transformers operating together with cable lines or long busbars, which are caused by resonant overvoltages. Recently, there have been cases of failures of 110–750 kV generator step-up transformers, 10–110 kV distribution transformers, and wind turbine transformers for voltage levels up to 35 kV. In the first and second parts of the article, an attempt is made to develop the theory of resonant processes in power transformer windings. The results of theoretical studies of the frequency responses in a homogeneous chain circuit containing two and four PI section were presented, and conclusions about the voltage resonance occurrence conditions were drawn. The third part of the article presents the results of theoretical studies of transients in a homogeneous chain circuit containing two PI sections. Analytical expressions are obtained for the transient voltage under the impact of a step voltage impulse and a voltage impulse with an exponentially rising front. The influence of the impulse front duration on the free transient voltage component amplitude is analyzed. Analytical expressions for the transient voltage in the considered equivalent circuit under the influence of undamped and damped sinusoidal voltage are given. Expressions for estimating the maximum resonant voltage amplification ratio under the influence of a damped sinusoidal voltage are obtained.