Maintenance Of Power Transformers Research Articles

Power Distribution Transformer Maintenance Skills Required byElectrical Engineering Technology Students ofPolytechnics inNorth-East Nigeria

Electric power distribution industry in North-East, Nigeria is faced with inadequate number of power transformer maintenance personnel which has led to numerous abandonment of broken down power transformers. Transformer faults have been blamed for many power outages of long duration in many towns and communities in North-East, Nigeria.It is against this backdrop that thisstudy determined the power distribution transformer maintenance skills required by Electrical Engineering Technology students of polytechnics in North-East Nigeria. Three research questions and three hypotheses guided the study which employed a descriptive survey research design. The population of the study was 144 comprising of 135 Electrical Engineering Technology Lecturers, 3 Power Transformer Maintenance Technicians and 6 Electric Power Distribution Company-Based Supervisors. The entire population was used hence, there was no sampling. The instrument used for data collection was a structured questionnaire titled: Power Distribution Transformer Maintenance Skills Required Questionnaire (PDTMSRQ) developed by the researchers. The instrument was validated by three experts and a reliability of 0.74 was obtained using Cronbach Alpha reliability method. Mean statistic was used to answer the research questions while ANOVA was used to test the two null hypotheses of the study at 0.05 level of significance. The findings of the study revealed that the Electrical Engineering Technology students of polytechnics in North-East Nigeria required preventive, predictive and corrective maintenance skills. The study recommended the following: Lecturers should encourage the students’ skill acquisition process by exposing them to various maintenance activities in order for them to imbibe the different methods of power transformer maintenance; Students should be trained to recognize sounds and sights of faulty equipment in order to predict the parts or components that needed replacement or repairs.

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.

Application of generative AI-based data augmentation technique in transformer winding deformation fault diagnosis

Accurately diagnosing various winding deformation faults is significant in power transformer maintenance. Among the different fault diagnosis methods, frequency response analysis (FRA) is widely used but still poses challenges. Artificial intelligence (AI)-based methods have recently been proposed to interpret FRA data. Nevertheless, these approaches are either complicated or exhibit limited generalization performance due to real-world FRA fault data scarcity. Inspired by AI-generated content (AIGC), this study proposes a data augmentation technique named conditional Wasserstein generative adversarial network with gradient penalty (Conditional-WGAN-GP) combined with fault diagnosis model. Numerous FRA-based data are automatically generated using the proposed data augmentation technique based on real FRA data obtained from a specially designed 10 kV transformer. The augmented dataset is then used to train fault diagnosis models to detect winding deformation faults. The trained fault diagnosis model is subsequently applied to assess two actual transformers. Experimental results demonstrate that when combined with the proposed method, even simpler fault diagnosis models can achieve high accuracy, exhibiting an improvement of approximately 5 % compared to the previous baseline model. The fault diagnosis models combined with the proposed data augmentation technique demonstrate improved generalization and robustness. (GitHub code: https://github.com/cy1034429432/Diagnosing-Transformer-Winding-Deformation-Fault-Types-from-FRA-Based-on-Conditional-WGAN-GP-/tree/main).

Prediction of dissolved gas content in transformer oil based on multi‐information fusion

AbstractIn order to accurately predict the content and variation trend of dissolved gas in transformer oil and guide the condition maintenance of power transformers, a combined prediction model based on multi‐information fusion is proposed and its effectiveness is analysed. First of all, based on the possibility of pathological and missing historical sample data, a detection and filling method based on variable weight combination samples is established. Second, the authors propose two models. Aiming at the non‐linear and non‐stationary characteristics of gas content, a univariate decomposition prediction mode HBA‐VMD‐TCN which based on the Honey Badger algorithm, variational mode decomposition and time convolutional network (TCN) is established. Then the multivariate Informer prediction model is established for gas content affected by multiple variables. Third, the cross‐entropy theory is used to determine the weight coefficients of the two models, and the multi‐information fusion combined prediction model is formed. Finally, on the basis of the above, a method to determine the time step and the position information of the transition point adaptively in the process of prediction is proposed to further improve the prediction accuracy. The results show that, through a series of simulation experiments of model comparison and transformer anomaly prediction, the accuracy and effectiveness of the combined prediction model are verified.

KNOWLEDGE EXTRACTION TECHNIQUES FOR POWER TRANSFORMER MAINTENANCE DATA: REVIEW

The maintenance of power transformers is time or condition-based and at the end of this one, analysis reports are produced to give its status. These different reports produced over time form a large database called the transformer maintenance asset bank. Extracting knowledge from this power transformer maintenance data is now an important subject for the scientific community given the importance of the transformer in the electric power generation chain. The science of data mining finds a field of application for its analysis techniques, the most used in preventive maintenance are predictive techniques. This work reviews knowledge extraction techniques from power transformer maintenance data. For this purpose, 80 articles from a platform are identified and 7 of them are retained at the end after meeting the criteria. Among the predictive analysis techniques namely regression, classification, and prediction, classification is the most used with its ANN (Artificial Neural Network) algorithm. On the other hand, association rule mining (ARM) has the highest accuracy, 98.21% in 2020. In addition, the combination of a classification algorithm preceded by the descriptive one, namely the principal component analysis (PCA), could offer higher accuracy than when they are used individually.

Accurate Assessment of Moisture Content and Degree of Polymerization in Power Transformers via Dielectric Response Sensing.

Power transformers are essential apparatuses used to transfer electrical energy from one voltage-level circuit to another. For reliable systems, preventive maintenance of the transformers is required to ensure good services of all mechanical, electrical, and insulation parts. Oil-immersed paper is most often used for transformer insulation. To ensure such good insulation performance and for assessing insulation conditions, advanced transformer sensing, monitoring, and effective assessment techniques are required. This paper introduces an effective technique for assessing the insulation conditions in power transformers, which are crucial for ensuring reliable energy transfer. The method utilizes advanced transformer sensing and monitoring, focusing on oil-immersed paper insulation commonly used in transformers. The technique employs dielectric response sensing, obtained from frequency-domain spectroscopy tests, to estimate degrees of polymerization (DP) and percentages of moisture content (PMCs) in the oil-immersed paper insulation. These parameters are well-known indicators of insulation performance. The approach is based on the weighted k-nearest neighbor regression, using a database of dielectric loss factors at low frequency and oil conductivities. To overcome limited data availability, linear interpolation and extrapolation techniques are applied to enlarge the database. Experimental verification and comparison with a previously developed method demonstrate the proposed technique's superiority in accuracy and complexity. The maximum deviations of DP and PMC in the validation cases are 6.2% and 18.7%, respectively. In addition, to evaluate the validity of our proposed method in the case of a real power transformer, a comparative analysis of the DP and PMC values determined by the proposed method with those obtained through a previously developed and complicated approach was performed. The predicted results indicate that the DP and PMC values of the oil-immersed insulation fall within the ranges of 800 to 1000 and 1.5 to 2.0, respectively, which agree with the results determined by the complicated approach and closely align with real conditions. By offering a reliable and advanced means of assessing insulation conditions, this technique contributes to the preventive maintenance and overall efficiency of power transformers.

Power Transformers OLTC Condition Monitoring Based on Feature Extraction from Vibro-Acoustic Signals: Main Peaks and Euclidean Distance.

The detection of On-Load Tap-Changer (OLTC) faults at an early stage plays a significant role in the maintenance of power transformers, which is the most strategic component of the power network substations. Among the OLTC fault detection methods, vibro-acoustic signal analysis is known as a performant approach with the ability to detect many faults of different types. Extracting the characteristic features from the measured vibro-acoustic signal envelopes is a promising approach to precisely diagnose OLTC faults. The present research work is focused on developing a methodology to detect, locate, and track changes in on-line monitored vibro-acoustic signal envelopes based on the main peaks extraction and Euclidean distance analysis. OLTC monitoring systems have been installed on power transformers in services which allowed the recording of a rich dataset of vibro-acoustic signal envelopes in real time. The proposed approach was applied on six different datasets and a detailed analysis is reported. The results demonstrate the capability of the proposed approach in recognizing, following, and localizing the faults that cause changes in the vibro-acoustic signal envelopes over time.

Digital twin real-time hybrid simulation platform for power system stability

This paper offers a comprehensive exploration of the application of digital twin technology for power system stability. Leveraging both physics-based and data-driven modeling techniques, we propose a novel digital twin framework that provides high fidelity simulations of power systems. Several case studies, including voltage stability assessment, dynamic stability analysis, predictive maintenance of power transformers, and renewable energy integration optimization, substantiate the efficacy of the framework under different real-world operating conditions. Our research conclusively indicates that the digital twin framework significantly enhances prediction accuracy, accelerates analysis speed, improves system reliability, and aids in efficient risk management in power systems. As a significant outcome, the framework has demonstrated its potential to revolutionize power system management and operations by facilitating predictive maintenance and efficient renewable energy integration. The paper concludes by emphasizing that strategic partnerships between academia and industry, robust cybersecurity measures, and the development of comprehensive standards and guidelines are key to unlocking the full potential of digital twin technology in power systems.

STCGCN: a spatio-temporal complete graph convolutional network for remaining useful life prediction of power transformer

PurposeRemaining useful life (RUL) prediction for power transformer maintenance is a challenging task on heterogeneous data. Monitoring data of power transformers are not always compatible or in an identical format; therefore, RUL predictions traditionally work separately on different data. Moreover, chemical molecules used in RUL prediction can be transformed into each other under different conditions, thus forming a complete graph with uncertain adjacency matrix (UAM). This study aims to find and evaluate a new model to achieve better results of RUL prediction than the other baselines.Design/methodology/approachIn this work, the authors propose a spatiotemporal complete graph convolutional network (STCGCN) for RUL prediction in two branches, in which daily and hourly features are extracted from correlated heterogeneous data separately. This study provides a thorough evaluation of the proposed model on real-world data and compare the proposed model with state-of-the-art RUL prediction models.FindingsBy using the multibranch structure and EucCos similarity aggregation, STCGCN was able to capture the dynamic spatiotemporal patterns on a variety of heterogeneous data and obtain more accurate prediction results, compared to other time series prediction methods.Originality/valueIn this work, the authors propose a novel multibranch structure to compute feature maps from two heterogeneous data sources efficiently and a novel similarity aggregation method to compute the spatial UAM within the complete graph. Compared with traditional time series prediction models, the model pays attention to the spatial relationships in time series data.

Power Transformer Condition-Based Evaluation and Maintenance (CBM) Using Dempster–Shafer Theory (DST)

Transformers are the most important elements in the power system. Due to their mass and complexity, they require constant monitoring and maintenance. Maintenance of power transformers increases the availability of the power system. The large number of substations and the specifics of their locations make condition-based maintenance (CBM) useful as part of the system's on-demand response. Unlike other system responses, the transformer contains a large amount of uncertain information, both qualitative and numerical. A large amount of information is necessary to implement CBM, but due to the often incomplete information, an analysis tool is essential. In this paper, a multi-level condition assessment framework based on evidential reasoning is proposed. A model for condition-based maintenance of a power transformer and procedures for the aggregation process based on evidential reasoning are presented. The implementation of the decomposition model with appropriate weights of a baseline and general attributes was made. Based on the decomposition model, the data and ratings of baseline attributes were collected. By carrying out the aggregation process, the ratings of the baseline attributes, as well as the ratings of the condition of the individual elements and the overall rating of the system condition as a whole, for several points in time, were obtained. The scientific contribution of the work is the proposal of an analysis that provides an insight into the condition of a complex technical system based on a single numerical value, thus determining its priority in the maintenance process.

Research on gas production law of free gas in oil-immersed power transformer under discharge fault of different severity

Dissolved gas analysis (DGA) is a common technology used in the on-site maintenance of oil-immersed power transformers in the power industry at present. However, when the content of dissolved gas in the oil reaches the attention value DGA method can effectively diagnose the operating state of the transformer. Due to the lack of gas production data of free gas which was detected when the faults occur, DGA method cannot timely diagnose the transformer status. To solve the above problem, an experimental platform is built for studying the free gas generation law in oil-immersed transformers under discharge faults, and the characteristic free gas information under discharge fault of transformer is obtained through the experiment. It is found that the existing DGA method cannot accurately analyze the types and severity of sudden serious insulation faults. When high-energy partial discharge fault occurred in the equipment, CO, CO2, CH4, and H2 will be collected in large quantities on the oil surface. These four gases can be used as the basis for characterizing high-energy partial discharge faults. When spark discharge occurred in the equipment, C2H6, C2H4, and C2H2 also be collected on the oil surface which can be used as a diagnostic basis for spark discharge. Moreover, it is found that the existing three-ratio method cannot be used for accurate analysis of oil free characteristic gas, so it is necessary to explore new diagnostic methods. The aim of this study is to explore the pattern of free gas production law by experiments when discharge faults occur and to provide data for a new diagnostic method.

ISSUES OF IMPROVING THE MOISTURE CONTENT CRITERIA FOR THE INSULATION OF OIL-FILLED TRANSFORMERS IN THE CONTEXT OF THE DEVELOPMENT OF TECHNOLOGIES FOR ITS AUTOMATED RECOVERY

The operational reliability of oil-filled transformers largely depends on the characteristics of the insulation, which is confirmed by the failure statistics. Moisture significantly affects both the reliability and the overload capacity and durability of power transformers. Drying insulation by traditional methods is a complex and expensive job, the complexity of which depends on the size of the transformer and the percentage of paper moisture, the more, the more difficult. An equally difficult task is to reliably measure the moisture content of the paper. To improve the accuracy of diagnosing insulation in terms of oil quality, changes are proposed to the requirements for the sampling procedure of a number of standards. To improve the efficiency of service maintenance of power transformers, improved criteria for the moisture content of solid insulation are proposed. The period of the most effective use of automated insulation restoration systems of the TRANSEC type has been determined. Field tests of the TRANSEC technology were carried out in an operating electrical installation. The high efficiency of automated insulation restoration systems was established, the dependence of insulation characteristics on temperature was confirmed, the admissibility of using the indicator of relative moisture saturation to assess the dynamics of the insulation restoration process, the comparability of the results of the measured and calculated values of paper moisture at an insulation temperature of at least 40 °C.

Preprocessing Approach for Power Transformer Maintenance Data Mining Based on k-Nearest Neighbor Completion and Principal Component Analysis

The accuracy of a knowledge extraction algorithm in a large database depends on the quality of the data preprocessing and the methods used. The massive amounts of data that we collect every day are putting storage capacity at a premium. In reality, many databases are characterized by attributes with outliers, redundant, and even more missing values. Missing data and outliers are ubiquitous in our databases, and imputation techniques will help us mitigate their influence. To solve this problem, as well as the problem of data size, this paper proposes a data preprocessing approach based on the k-nearest neighbor (KNN) completion for imputation of missing data and principal component analysis (PCA) for processing redundant data, thus reducing the data size by generating a significant quality sample after imputation of missing and outlier data. A rigorous comparison is made between our approach and two others. The dissolved gas data from Rio Tinto Alcan’s transformer T0001 were imputed by KNN, where k equals 5. For 6 imputed gases, the average percentage error is about 2%, 17.5% after average imputation, and 23.65% after multiple imputations. For data compression, 2 axes were selected based on the elbow rule and the Kaiser threshold.

Sustainable maintenance of power transformers using computational intelligence

The technical and financial management of power substations involves the evaluation of the operational condition of power transformers. Evaluation is an essential stage for maintaining electricity supply and resource efficiency by guiding the process of maintaining and/or upgrading a transformers park. This process aims at identifying assets with critical operational condition in a substation that may convey risks to operators, installed equipment and customers. The use of computational intelligence techniques aims at assisting the evaluation process, which is not simple because it requires combining measurements that evaluate different aspects of the power transformers. A deep technical knowledge of chemical, electrical and physical measurements is necessary to infer a correct diagnosis. Thus, computational intelligence techniques can reduce the need for human expertise, since they are able to extract patterns of known information and optimize the identification of critical assets. In this paper, computational intelligence techniques are applied aiming at composing a numerical index, termed Health Index, for asset prioritization. Prioritization helps classify assets based on criticality levels. Information regarding the measurements used to compose the index is based on measurements done on real transformers. In this work, computational intelligence techniques are especially explored for the composition of the Health Index, as there are no publications with the application of these techniques to solve this kind of prioritization problem. We seek the most appropriate set of methods to support decision making in prioritizing assets for maintenance. The effectiveness of the proposed methods is evaluated, seeking strategies that add greater sustainability, flexibility, simplicity and high accuracy rate in asset prioritization.

Predictive maintenance scheduling for multiple power equipment based on data-driven fault prediction

In view of the maintenance of multiple power equipment operating in abnormal conditions in large-scale power plants, based on the prediction of fault state, a predictive maintenance scheduling method is proposed to schedule the maintenance activities. Firstly, based on the actual operating data, combined with the influencing factors of fault state deterioration by Pareto analysis, a time-variant function is improved to predict the deterioration state of potential fault in future maintenance interval. Then, maintenance priority is divided based on the fault state, considering the constraints of maintenance resources and equipment downtime, with the objective of minimizing the total maintenance cost, a scheduling model is built for the maintenance of multiple equipment. Finally, aiming at the continuity of maintenance time, a two-stage algorithm is proposed, which divides the maintenance time-window to transform the complex continuous time optimization problem into a combinatorial optimization problem of time periods, and then develops the optimal maintenance scheme. Taking the maintenance of multiple power transformers as an example, combined with the data resources provided by Yunnan power grid of China, the effectiveness of the improved prediction function of fault state is proved. In addition, by comparing with the traditional maintenance strategy based on the principle of first-fault-first-repair, the superiority of the proposed maintenance scheduling method is verified in reducing cost and improving system stability.

Method of Evaluating Probability of Pressboard Failure in Power Transformer with Disc‐Type Winding Due to Electromagnetic Force by External Short Circuit

The evaluation of the failure probability is essential in the reliability‐centered and risk‐based maintenance of power transformers. The breakage of the pressboard in disc‐type transformers is one of the critical factors determining the lifetimes of power transformers. In this paper, a hierarchical method for evaluating the probability of pressboard failure, which is the breakage of the pressboard, in power transformers that considers the axial displacement of the winding is introduced. In the method, the diagnosis of the axial displacement is classified into three distinct classes. In class 1, no diagnosis is implemented, and the probability of failure is evaluated with the maximum possible axial displacement. In class 2, the diagnosis determines whether the winding is axially displaced. When the winding is diagnosed to be displaced, the probability of failure is evaluated with the maximum possible axial displacement. In class 3, the axial displacement is diagnosed quantitatively, and the probability of failure is then evaluated using the diagnosis result. Examples of the evaluated probabilities of pressboard failure are introduced, and the extension of the evaluated lifetimes of power transformers via the diagnosis of winding axial displacement is demonstrated. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

An experimental validation of partial discharge localization using electromagnetic time reversal

The localization of partial discharge (PD) sources is of importance for the monitoring and maintenance of power transformers. Time difference of arrival (TDoA) based methods are widely adopted in the literature for the localization of PDs. Recently, time reversal (TR) was suggested as an efficient means to locate PD sources. As opposed to TDoA, which needs at least 4 sensors, TR is able to locate PD sources in power transformers with only one sensor. Moreover, it needs neither line-of-sight wave propagation from the PD sources to the sensor nor time synchronization. In this study, we present for the first time an experimental demonstration of the ability of the TR process to locate PD sources. A typical TR process includes three steps: (1) recording the PD-emitted field by a sensor, (2) time reversing and back injecting the signal into the medium, (3) using a proper criterion to obtain the focusing point which corresponds to the location of the PD source. In this work, we present a laboratory setup in which steps one and two are performed experimentally, both in the frequency and in the time domain. The obtained peak electric field value is used as a criterion in the third step. It is found that the accuracy of the proposed method is better than 2.5 cm in a transformer tank model with dimensions 73 × 73 × 103 cm3. The effects of the presence of scatterers such as transformer windings are also investigated experimentally and found not to affect the location accuracy of the method.

Research on Multi-Attribute Decision-Making in Condition-Based Maintenance for Power Transformers Based on Cloud and Kernel Vector Space Models

Decision-making for the condition-based maintenance (CBM) of power transformers is critical to their sustainable operation. Existing research exhibits significant shortcomings; neither group decision-making nor maintenance intention is considered, which does not satisfy the needs of smart grids. Thus, a multivariate assessment system, which includes the consideration of technology, cost-effectiveness, and security, should be created, taking into account current research findings. In order to address the uncertainty of maintenance strategy selection, this paper proposes a maintenance decision-making model composed of cloud and vector space models. The optimal maintenance strategy is selected in a multivariate assessment system. Cloud models allow for the expression of natural language evaluation information and are used to transform qualitative concepts into quantitative expressions. The subjective and objective weights of the evaluation index are derived from the analytic hierarchy process and the grey relational analysis method, respectively. The kernel vector space model is then used to select the best maintenance strategy through the close degree calculation. Finally, an optimal maintenance strategy is determined. A comparison and analysis of three different representative maintenance strategies resulted in the following findings: The proposed model is effective; it provides a new decision-making method for power transformer maintenance decision-making; it is simple, practical, and easy to combine with the traditional state assessment method, and thus should play a role in transformer fault diagnosis.

Research on identification methods of gas content in transformer insulation oil based on deep transfer network

When a transformer is running, the insulation oil gradually becomes degraded due to various factors such as electricity and heat, during which low molecular weight gases are formed upon decomposition. By analyzing the gas content in the oil, the state of the insulation oil can be identified, thereby providing an effective basis for transformer fault analysis and diagnosis. However, when the types and severity of the internal faults inside the transformer are different, the components and contents of the gases dissolved in the oil also differ. Sometimes when the types of faults are the same, the gas content may be different. Therefore, if the characteristic of the specific gas content corresponding to a type of fault can be obtained, the transformer faults can be accurately identified according to the contents of different gases, which can most efficiently ensure the reliable operation and maintenance of power transformers. In this paper, an identification method based on the deep transfer network was proposed. According to this method, by studying the existing gas contents and states based on a large number of training data to discover their characteristics, the states of gases in the oil can be precisely identified. Experiments have proved the effectiveness of this method. The ability of state identification by this method is far superior to that of the other existing methods.

Improving Preventive Maintenance Management in an Energy Solutions Company

In industry, production processes and assets are constantly evolving, Thus, continually improving and updating them is essential to their sustainability. This work intended to apply a set of methods and philosophies to improve the Preventive Maintenance Management process in a case study company dedicated to the development, production and maintenance of power and distribution transformers. Thus, a Action – Research methodology was used. After identifying the main problems, a mixed maintenance strategy based on Reliability Centered Maintenance (RCM) and Total Productive Maintenance (TPM) was applied. The following achievements were obtained by this work: (a) method of grading equipment critically based on its importance to the production process was developed and implemented;(b) a new flowchart of decisions and actions was developed for Preventive Maintenance Plan Management; (c) a reduction of the waste time in Preventive Maintenance (PM) was obtained; (d) the implementation of Autonomous Maintenance (AM) resulted in a reduction of 66% in equipment failures; (e) a set of new Key Performance Indicators (KPI´s) were introduced; (f) maintenance plans compliance rates increased by 12%. At the end of the work a reduction of € 120 060 could be achieved. Thus, the main contribution of this work was to show that bringing to the action different tool together in an organized way and share the information and responsibilities with the workers can result in important savings to the company, becoming the maintenance function more effective.