Transformer Health Condition Research Articles

Multi-parameter-based fuzzy logic diagnostic system for health assessment of power transformer

ABSTRACT Power transformers are the most valuable assets in the power system. An appropriate asset management is therefore essential for ensuring a reliable power supply to the utility managers. This is accomplished through continuous transformer condition monitoring. The transformers’ asset management involves a severe investigation into its insulation health index. It is determined by utilising several diagnostic parameters of transformer insulation. In this context, a novel fuzzy logic-based health index model has been proposed in the present paper to find the overall health condition of transformers. This model utilises the results extracted from several important diagnostic tests of transformer insulation, such as furan analysis and dissolved gas analysis. The validity of the proposed fuzzy logic model has been tested using real data from 200 transformer samples. These samples are collected from different-rated transformers of the Himachal Pradesh State Electricity Board (HPSEB), India. Further, the efficacy of the proposed fuzzy logic model has been validated against the expert model presented in literature. It is revealed from the comparison that the accuracy of the present proposed model is 92%. Also, it is observed that the proposed fuzzy logic model is very effective in interpreting dissolved gases and the other diagnostic test results of the transformer.

Power transformer health condition evaluation: A deep generative model aided intelligent framework

Power transformer health condition evaluation: A deep generative model aided intelligent framework

Improvement of transformer dissolved gas analysis interpretation using j48 decision tree model

<span lang="EN-US">Dissolved gas analysis (DGA) is widely accepted as an effective method to detect incipient faults within power transformers. Gases such as hydrogen, methane, acetylene, ethylene and ethane are normally utilized to identify the transformer fault conditions. Several techniques have been developed to interpret DGA results such as the key gas method, Doernenburg, Rogers, IEC ratio-based methods, Duval Triangles, and the latest Duval Pentagon methods. However, each of these approaches depends on the experts' shared knowledge and experience rather than quantitative scientific methods, therefore different diagnoses may be reported for the same oil sample. To overcome these shortcomings, this paper proposed the use of decision tree method to interpret the transformer health condition based on DGA results. The proposed decision tree model employed three main fault gases; methane, acetylene, ethylene as inputs, and classified the transformer into eight fault conditions. The J48 algorithm is used to train and developed the decision tree model. The performance of the proposed model is validated with the pre-known condition of transformers and compared with the Duval Triangle method. Results show that the proposed model delivers better precision and accuracy in predicting transformer fault conditions compared to DTM with 81% and 69% respectively.</span>

Health condition assessment of transformers based on cross message passing graph neural networks

A method is proposed to assess the health condition of transformers based on cross message passing graph neural networks (CMPGNNs) in this paper. In order to improve the accuracy of transformer health condition assessment, multiple indicators and their strong correlation are taken into account. The evaluation indicators are divided into four comprehensive state categories, and each category has several indicators. First, the correlation between indicators of a state category is extracted by the health index method and the importance of criteria is analyzed through the inter-criteria correlation (CRITIC) method, and the health index of comprehensive indicators is obtained. Then, a diagram of comprehensive indicators is constructed, and the correlation between indicators of different state categories is extracted. Finally, CMPGNN is constructed to achieve the health assessment. The experimental results show that the proposed method can improve the accuracy of transformer health condition assessment.

Transformer Health Index by Prediction Artificial Neural Networks Diagnostic Techniques

This paper presents the artificial neural network diagnostic techniques for predicting the health index in transformer. Collection data is measured and tested from insulation resistance in between phase-ground, phase to phase and also the winding resistance transformer. The data was collected from 10 units of transformers from Company Transformer Manufacturing and Servicing (CTMS) in Malaysia. The data was used to calculate condition transformer index or health index transformer. Condition transformer index can identify whether transformer in good condition or not good condition. The purpose of knowing transformer health index or condition transformer index is to prevent failures functional transformer and ensure transformer in stable condition. Prediction health index or condition transformer index can be determined by artificial neural network. Therefore, it can monitor and observe very closely conditions of the transformer. Data health index transformer is very important because it know the condition transformer and can solve the major problem in transformer or do the maintenance in early stage before the transformer is totally malfunction.

Measurement of Tan-delta and DC Resistivity of Synthetic Ester Based Oil Filled with Fe2O3, TiO2 and Al2O3 Nanoparticles

ABSTRACT The dielectric properties of insulating liquids are very important for their application as insulation and coolant in electrical devices like transformers. It is important to monitor the health condition of transformers for uninterrupted and economical power supply. For this purpose, the simple insulating materials like pressboard and mineral oils are used. This paper presents an eco-friendly alternative to mineral oil in the form of the synthetic ester oil-based nanofluids. This paper aims to present the effect of nanoparticles on the dielectric dissipation factor and electrical resistivity of ester-based oil. In this paper, we are testing synthetic ester oils for DC resistivity and dielectric dissipation factor (Tan-delta) at different temperatures starting from room temperature up to 80°C by incorporating nanoparticles with 0.02 weight% concentration. Nanoparticles used in this study are Fe2O3, TiO2 and Al2O3. Synthetic ester oil is used as the base oil for testing. These oils are manufactured from raw materials that are basically formed by combining acids and alcohols. The heating chamber is used to heat the oil for different temperatures. Insulation resistance (IR) tester and oil dissipation factor meter are used to determine DC resistivity and dielectric dissipation factor (DDF) of simple synthetic ester oil and nano oil respectively. This paper presents the effect of nanoparticles and temperature on dielectric properties of synthetic ester-based oils.

Health Management of Dry-Type Transformer Based on Broad Learning System

This article presents a novel health management method of the dry-type transformer to diagnose the early unhealthy behavior and evaluate the transformer's health condition by health score. The health condition diagnosis implemented by a proposed dynamic-weighted-feed-back broad learning system (BLS) (DW-FB-BLS) method, which helps to determine the BLS network structure effectively, and adjusts the weight of features in the online application to avoid reduction of accuracy caused by concept drift. Then, a rational score rule is set to evaluate the health condition of the dry-type transformer by health score, which allows intuitive presentation and preservation of transformer's health condition over a long period. Finally, the effectiveness and validity of the proposed method are verified based on the real field data of dry-type transformer. Satisfactory results for unhealthy behavior diagnosis and health evaluation are obtained, it shows that health management of this article can reflect the real health condition of dry-type transformer appropriately.

Evaluation of in-service power transformer health condition for Inspection, Repair, and Replacement (IRR) maintenance planning in electric utilities

Evaluation of in-service power transformer health condition for Inspection, Repair, and Replacement (IRR) maintenance planning in electric utilities

An Efficient Approach With Application of Linear and Nonlinear Models for Evaluation of Power Transformer Health Index

In this paper, efficient and accurate linear and nonlinear models are proposed for indicating comprehensive health requirements of the transformer using health index (HI) concept. The models are established with 336 experimental datasets including oil characteristics and dissolved gas analysis (DGA) of various types of transformers placed in different areas. The significance of DGA parameters in transformer health condition is considered with the inclusive DGA factor ( DGAF ) parameter, which considers the weighting importance of seven dissolved gases. Nonlinear models used in this paper are artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS), which represent the behavior of transformer insulation parameters. The nonlinear models are compared with multiple linear regression (MLR) which is a linear statistical model. The models are established with 80 percent of the experimental dataset. The other 20 percent of data are utilized for the efficiency assessment of the models. The results demonstrate that the models provide an assessment of the health condition of the transformers comparable to existing models with high accuracy. The contributions of this paper are: 1) Evaluating the overall HI of the transformer employing a complete set of 15 input parameters of transformer oil-paper insulation system. 2) Adding DGAF , %WaterPaper , IFT parameters and showing the importance of these parameters. 3) Regarding the condition of solid insulation of the transformer particularly. 4) Applying a diverse and large practical dataset composed of 336 different transformers located in different country areas. 5) Using the MLR method for three purposes. 6) Providing linear (MLR) and nonlinear (ANN, ANFIS) models for HI calculation of the dataset, simultaneously. 7) Verifying the applicability and efficiency of the ANFIS model for simulating HI value.

Artificial Intelligence-Based Power Transformer Health Index for Handling Data Uncertainty

Power transformer is a critical and expensive asset in electric transmission and distribution networks. It is essential to monitor the health condition of all power transformer fleet in such networks to avoid unwanted outages. The health index (HI) is a quick and efficient way to assess the condition of power transformers based on multi-criteria. While Power transformer HI method has been well presented in the literature, not much attention was given to handle the uncertainty and reliability of this method due to unavailability of used data. Therefore, this paper aims to tackle this issue through employing Artificial Intelligence (AI)-based techniques to reveal the health condition of power transformers with high accuracy and at the same time handling data uncertainty. The proposed HI approach assesses the power transformer insulation system based on oil quality, dissolved gas analysis (DGA), and paper condition. In this regard, collected data from 504, 150-kV transformers are used to establish the proposed AI-models. Seven AI algorithms including k-Nearest Neighbor (kNN), Support Vector Machine (SVM), Random Forest (RF), Naive Bayes (NB), Artificial Neural Network (ANN), Adaptive Boosting (AdaBoost), and Decision Tree are investigated. A performance comparison of the proposed AI-based HI models is carried out using the scoring-weighting-based HI method as the reference. Results show that RF model provides the best performance in predicting power transformer HI with an accuracy of 97.3%.

Application of Machine Learning in Transformer Health Index Prediction

The presented paper aims to establish a strong basis for utilizing machine learning (ML) towards the prediction of the overall insulation health condition of medium voltage distribution transformers based on their oil test results. To validate the presented approach, the ML algorithms were tested on two databases of more than 1000 medium voltage transformer oil samples of ratings in the order of tens of MVA. The oil test results were acquired from in-service transformers (during oil sampling time) of two different utility companies in the gulf region. The illustrated procedure aimed to mimic a realistic scenario of how the utility would benefit from the use of different ML tools towards understanding the insulation health index of their transformers. This objective was achieved using two procedural steps. In the first step, three different data training and testing scenarios were used with several pattern recognition tools for classifying the transformer health condition based on the full set of input test features. In the second step, the same pattern recognition tools were used along with the three training/testing scenarios for a reduced number of test features. Also, a previously developed reduced model was the basis to reduce the needed number of tests for transformer health index calculations. It was found that reducing the number of tests did not influence the accuracy of the ML prediction models, which is considered as a significant advantage in terms of transformer asset management (TAM) cost reduction.

Evaluation of transformer health condition using reduced number of tests

This paper presents a method to find a reliable health index (HI) for oil-immersed transformers using reduced number of tests. The method depends on using the most important tests that are directly related to the transformer health. Field data for 90 working transformers were used to validate and test the proposed method. A linear relationship between the transformer HI and all available tests is proposed. The weights of the transformer tests are modeled exponentially according to the importance of each test. Subsequently, the HI is calculated using the three most important tests and the two most important tests. The results were compared with the results of existing research that uses a larger number of tests. The comparison shows that the proposed method gives acceptable results compared to other techniques that use a larger number of tests. As a result, the HI can be evaluated at lower cost, and a transformer health condition can be better monitored due to the ability to repeat HI evaluation at closer intervals.

Assessing the power transformer insulation health condition using a feature-reduced predictor mode

Condition monitoring (CM) techniques in the form of electrical, chemical and physical tests are conducted to assess the ageing of transformers on the basis of its oil-paper insulation strength. A thorough examination of the transformer insulation condition can only be done through a complete set of CM standard tests. Some of the conducted tests are considered expensive in terms of the required facilities and experienced personnel. The concept of the health index (HI) was developed to assess the transformer's health condition and effective remnant age as a function of all CM tests. The main components involved in the HI computation are related to the transformers' insulation condition, service record and design. Several computational methods have been developed to calculate the transformer HI. Each method has a different interpretation of how the tests are correlated with the HI value. The drawback of these methods is the associated cost of the required monitoring test inputs for an accurate HI computation. Thus, alternative methods are needed to predict the HI value with a smaller number of CM tests. Artificial intelligent (AI) methods, such as artificial neural networks (ANN), can learn how to map the response output (HI) to a given correlated set of inputs (monitoring tests). The presented work introduces a general cost-effective ANN based HI predictor model that achieved 95% prediction accuracy using only a subset of the required input features. Moreover, the developed model has been tested on a set of transformer database from another utility company and achieved 89% prediction accuracy.

CO2/CO concentration ratio: A complementary method for determining the degree of polymerization of power transformer paper insulation

Since power transformers are valuable components of power networks, reliable determination of the remaining lifetime of a transformer is very important for power utilities. Power transformers consist of oil, a core, wire, and paper (cellulose), and their performance and remaining useful lifetime depend on the state of the oil-impregnated paper. Changing the oil over the lifetime of a transformer is possible, but it is not possible to change the insulation paper. Thus, the end of the paper lifetime will also be the end of the transformer lifetime (typically more than 40 years). The health condition of an in-service power transformer can be assessed by chemical and electrical tests of the oil and the paper [1].

Effects of Distribution Approximations to Expanded Uncertainty of Breakdown Strength of Mineral Insulating Oil in IEC 60156

Breakdown Strength test identifies the health condition of oil-immersed power transformers. The erratic and non-homogeneity behavior affects much the results of breakdown strength test. The inclusion of expanded uncertainty in test results of breakdown strength bounds the compensated test results in a defined confidence level, which is not defined in IEC 60156. This paper presents the analysis of the effects of distribution approximations used in the estimation of expanded uncertainty. The study involved Normal distribution (Gaussian), t-distribution (student distribution), Rectangular distribution and Triangular distribution in estimating an expanded uncertainty which incorporated Type A and Type B errors. The Expanded Uncertainty was based on a standard uncertainty multiplied by a coverage factor of k = 2, which provided a minimum confidence level of 95% in all approximated distributions. Normal distribution (Gaussian) showed the validity in the estimation of expanded uncertainty for a sufficiently large number of test results (of up to 25 tests per sample) while Student-t distribution showed invalidity for all test results. Since it is not a good practice to test insulating oil up to 25 tests, expanded uncertainty based on Normal distribution seemed to be valid for any test results less than 25. The inclusion of expanded uncertainty may predict the validity and avoid re-running of the test.

Research on multi‐attribute decision‐making in condition evaluation for power transformer using fuzzy AHP and modified weighted averaging combination

Power transformers are of vital importance for the stable operation of power system. Hence, to grasp transformers’ health condition is of imminent importance. However, the evaluation of transformers’ health condition is bound with fuzzy, uncertainty, and even conflict information. To address these problems, a novel evaluation model for transformer, by integrating the merits of fuzzy set theory, fuzzy analytical hierarchical process (AHP), and modified weighted averaging combination, is proposed in this study. The evaluation model contains four factors: dissolved gas analysis, electrical testing, oil testing, and miscellaneous factors, as well as 20 indices. The evaluation process consists of three steps. First, the fuzzy set theory is used to obtain assessment grades for each quantified indices. Second, the fuzzy AHP using fuzzy preference programming, which extends classical AHP and can better tackle the uncertainty existed in the comparison matrix given by experts, is introduced to calculate the weights of indices. Finally, the assessment is processed through the modified weighted averaging combination, which is able to handle the conflicts among evidences. The proposed method is verified by evaluating a realistic transformer, and the results of field examples indicate that the method can evaluate the transformer health condition effectively.

Health index calculation for power transformers using technical and economical parameters

In this study technical diagnostic tests and economical lifetime assessment of transformers are investigated to evaluate the overall health condition of working transformers. Two artificial intelligence models including artificial neural network and adaptive neuro-fuzzy inference system models are presented to determine the health index for transformers. The technical and economical parameters are used as input parameters to develop the models. Technical parameters are extracted from oil characteristics and dissolved gas analysis of different transformers. Economical parameters are constructed with transformer capital investments, maintenance and operating costs. The models are developed using 226 experimental field datasets of transformers technical and economical parameters. The models are trained using 80% of the experimental datasets. The remaining 20% is used to evaluate the performance and applicability of the models. The results prove that the models can be used to determine the health condition of transformers with high accuracy.

An Integrated Decision-Making Model for Transformer Condition Assessment Using Game Theory and Modified Evidence Combination Extended by D Numbers

The power transformer is one of the most critical and expensive components for the stable operation of the power system. Hence, how to obtain the health condition of transformer is of great importance for power utilities. Multi-attribute decision-making (MADM), due to its ability of solving multi-source information problems, has become a quite effective tool to evaluate the health condition of transformers. Currently, the analytic hierarchy process (AHP) and Dempster–Shafer theory are two popular methods to solve MADM problems; however, these techniques rarely consider one-sidedness of the single weighting method and the exclusiveness hypothesis of the Dempster–Shafer theory. To overcome these limitations, this paper introduces a novel decision-making model, which integrates the merits of fuzzy set theory, game theory and modified evidence combination extended by D numbers, to evaluate the health condition of transformers. A four-level framework, which includes three factors and seventeen sub-factors, is put forward to facilitate the evaluation model. The model points out the following: First, the fuzzy set theory is employed to obtain the original basic probability assignments for all indices. Second, the subjective and objective weights of indices, which are calculated by fuzzy AHP and entropy weight, respectively, are integrated to generate the comprehensive weights based on game theory. Finally, based on the above two steps, the modified evidence combination extended by D numbers, which avoids the limitation of the exclusiveness hypothesis in the application of Dempster–Shafer theory, is proposed to obtain the final assessment results of transformers. Case studies are given to demonstrate the proposed modeling process. The results show the effectiveness and engineering practicability of the model in transformer condition assessment.

Calculation of a Health Index of Oil-Paper Transformers Insulation with Binary Logistic Regression

This paper presents a new method for calculating the insulation health index (HI) of oil-paper transformers rated under 110 kV to provide a snapshot of health condition using binary logistic regression. Oil breakdown voltage (BDV), total acidity of oil, 2-Furfuraldehyde content, and dissolved gas analysis (DGA) are singled out in this method as the input data for determining HI. A sample of transformers is used to test the proposed method. The results are compared with the results calculated for the same set of transformers using fuzzy logic. The comparison results show that the proposed method is reliable and effective in evaluating transformer health condition.

A new image-oriented feature extraction method for partial discharges

Partial discharge (PD) measurement and recognition is of great importance to assess the health condition of power transformers. However, the variation of defect size, applied voltage as well as insulation aging gives rise to the dispersion and crossover of PD features, which would influence PD recognition reliability of transformers. An image-oriented two-directional modified fuzzy-weighted two-dimensional linear discriminant analysis (TD-MFW-2DLDA) for feature extraction of PD gray images, aiming at solving the above problem, is proposed in this paper. Two classification models including fuzzy C-means (FCM) clustering and support vector machine with genetic algorithm (GA-SVM) are designed for features evaluation and PD pattern recognition. 419 PD samples of four typically artificial defect models are measured in laboratory, in which the multi-factors of defect size, applied voltage and insulation aging are taken into account, and further adopted for algorithms testing. It is shown that TD-MFW-2DLDA achieves optimal successful FCM clustering rate of about 93% and GA-SVM recognition accuracy of about 96%, which are better than that of typical PD features influenced by the multi-factors. Additionally, FCM clustering validity measures provide better compactness within class and separability between classes of TD-MFW-2DLDA which is suitable for on-site PD diagnostic applications.