Transformer Health Index Research Articles

Calculation of power transformer health index using the combination of principal component analysis and mass-spring-damper model

Calculation of power transformer health index using the combination of principal component analysis and mass-spring-damper model

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.

Investigation of the Influence of Non-Routine and Derived Features in the Development of Early Detection Model for Transformer Health Index Classification

Establishing an effective HI model is challenging because it involves balancing cost, risk, and performance. The currently developed Reduced Features Model (RFM) for the transformer Health Index (HI) prediction may lead to late prediction. The RFM utilised non-routine input features to achieve a high-accuracy model where data availability is the primary concern. Hence, the common goal of Transformer Asset Management (TAM) in achieving acceptable availability and reliability of the transformer may not be achieved. In this paper, the primary objective is to investigate the performance of the HI model by considering routine test features as a baseline for developing the Early Detection Model (EDM). The development of EDM is significant, as the model shall provide a sustainable solution to the utility and plant owners in establishing their TAM strategies. Hence, this paper's case studies include performance investigation using routine, non-routine, and derived features from the routine test. Support Vector Machine (SVM) was used for the prediction modelling, and the model's performance was validated based on a 5-fold cross-validation technique to avoid biases. As a result, it was found that the average accuracy performance of 88.4% was obtained by considering only routine test features during the model validation process. However, complementing the routine test with other features, which were non-routine and derived features, increased the average performance accuracy model to 95.3%. Hence, further development of EDM is feasible and crucial for sustainable TAM solutions.

Analysis of health state before and after fault self-healing based on a high percentage of distributed distribution grid systems

Abstract In this paper, we preprocess the equipment data using by exponential smoothing method, fit the fault information by using the distribution model, and evaluate the fitting degree of the function with the help of the K-S test to derive the equipment fault information function. In accordance with the correlation mapping between the distribution network health index and the existence of faults, the health index of the distribution network equipment in the region before and after the self-healing of faults is comprehensively calculated, and the state assessment of the equipment is carried out. Before and after the fault self-healing of the IEEE33 node system, the system loss is reduced by 58.89%, as evidenced by the results. Before and after the fault self-healing, Condition 1: the line health index ranges from 1.317 to 3.777, and the transformer health index ranges from 2.011 to 4.646. Condition 2: the line health index ranges from 2.284 to 4.059, and the transformer health index ranges from 1.653 to 4.047, respectively. And Condition 3: the health indices all increase by varying from 0.711 to 2.067. Localized equipment degradation has a significant impact on the overall health of the network, with lines affecting the system to a greater extent than transformers. To summarize, the proposed health index state assessment method can effectively determine the health state of distribution networks before and after fault self-healing.

Enhancing Transformer Health Index Prediction Using Dissolved Gas Analysis Data Through Integration of LightGBM and Robust EM Algorithms

Enhancing Transformer Health Index Prediction Using Dissolved Gas Analysis Data Through Integration of LightGBM and Robust EM Algorithms

A Holistic Integration of Conventional and Machine Learning Techniques to Enhance the Analysis of Power Transformer Health Index Considering Data Unavailability

A Holistic Integration of Conventional and Machine Learning Techniques to Enhance the Analysis of Power Transformer Health Index Considering Data Unavailability

Survey on the Advancements of Dielectric Fluids and Experiment Studies for Distribution Power Transformers

The main objective of this work is to summarize the most commonly used dielectric fluids in the power distribution transformers, as well as to discuss what are the latest and the rationale behind those trends. The favorable and unfavorable reasons for any choice behind each of those dielectric fluids will be discussed. Additionally, this work also advances the power distribution transformers health index most commonly used to assess the condition of the transformer.

Evaluation and prediction of the transformer health index based on matter element information entropy and SVM

To solve the problem that the operation state of transformer is difficult to quantify, a method of quantitative evaluation and prediction of transformer operating state is proposed, which combines the information entropy of matter element and Support Vector Machine. In the evaluation, various hydrogen gases in the transformer operation are taken as the evaluation indexes and the three-dimensional cross compound element is constructed. The analytic hierarchy process (AHP) is used to determine the theoretical weight of the evaluation index, and the entropy method is used to determine the objective weight of the evaluation index, and the final weight is the joint weight of the theoretical weight and the objective weight. Transformer Health index is calculated by using complex element correlation entropy. In prediction, the grid search, genetic algorithm (GA) and particle swarm optimization (PSO) are used to optimize the parameters of Support Vector Machine. and the prediction model of Health index is established by SVM. Experiment results show that the Support Vector Machine based on Gauss kernel function and genetic algorithm has a prominent effect on the prediction of health index.

Review of Transformer Health Index from the Perspective of Survivability and Condition Assessment

As a critical indicator for assessing the survivability and condition of transformers in a fleet, the transformer health index has attracted attention from both asset owners and international organizations like CIGRE and IEEE DEIS/PES. To provide a systematic and comprehensive review for further study or to guide transformer asset management, this paper summarizes the state-of-the-art of the transformer health index, from the early proposed weighted-score-sum approaches to the more recently proposed artificial intelligence algorithm-based methods. Firstly, different methods for determining the transformer health index are reviewed. Each of these is specified as belonging to a certain type on the basis of its formulation and composition schematic. Subsequently, the steps to determine each type of health index are summarized, and examples derived from literature are provided for further illustration. Comparisons are finally carried out in order to better understand the pros and cons of different types of transformer health index, and the future development trends for transformer health indexes are also discussed. This work can serve as a valuable reference for the survivability and condition assessment of transformers in the power industry.

Power Transformers Health Index Enhancement Based on Convolutional Neural Network after Applying Imbalanced-Data Oversampling

The transformer health index (HI) concept has been used as an important part of management resources and is implemented for the state assessment and ranking of Power transformers. The HI state is estimated based on many power transformer oil parameters. However, the main problem in the HI procedure as a diagnostic method is the presence of routine measurements and accurate test results. The power transformer HI prediction is carried out in this work using 1361 dataset samples collected from two different utilities. The proposed model is used to predict and diagnose the HI state of the power transformer by using a convolutional neural network (CNN) approach. The imbalance between the training dataset sample classes produces a good prediction of the class with a major number of samples while a low detection of the class has a minor number of samples. The oversampling approach is used to balance the training samples to enhance the prediction accuracy of the classification methods. The proposed CNN model predicts the HI of the power transformers after applying the oversampling approach to the training dataset samples. The results obtained with the proposed CNN model are compared with those obtained with the optimized machine learning (ML) classification methods with the superiority of the CNN results. Feature reductions are applied to minimize testing time, effort, and costs. Finally, the proposed CNN model is checked with uncertain noise in full and reduced features of up to ±25% with a good prediction diagnosis of the power transformer HI.

Development of Power Transformer Health Index Assessment Using Feedforward Neural Network

The role of a power transformer is to convert the electrical power level and send it to the consumer, making it an essential component of a power system. In addition, transformer asset management is essential for monitoring the functioning of transformers in the system to prevent failure and anticipating the health state of transformers, using a technique known as the health index (HI). However, the calculation and computation to determine the transformer HI based on a scoring and ranking technique is complex and required expert validation. Therefore, this paper presents a transformer HI prediction using a feedforward neural network (FFNN) to improve the existing complex scoring and ranking technique. Levenberg–Marquardt (LM), Bayesian Regularized (BR), and Scaled Conjugate Gradient (SCG) are the FFNN training techniques presented in this study to forecast the transformer HI. To validate the techniques, the HI values generated by different FFNN techniques were compared to the scoring and ranking system. Then, the performance of the proposed ANN was evaluated using the correlation coefficient and mean square error (MSE). As a result, the transformer HI was successfully predicted by employing three FFNN techniques, namely the LM, BR, and SCG techniques, which were able to determine whether the transformer's condition is very good, good, fair, or poor. In conclusion, the ANN suggested in this study has also been validated with the ranking and scoring approach, which provides high similarity score in comparison to the transformer health index.

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.

Reliability calculations based on an enhanced transformer life expectancy model

In this paper, The IEEE thermal ageing model is utilized to build an enhanced Transformer Life Expectancy (TLE) model. The enhanced model is developed relying on the current transformer Health Index (HI) in addition to the loading conditions. A direct correlation between the IEEE and the (HI) ageing factors is identified and projected. The model is capable of integrating factors affecting transformers. Transformer faults and maintenance are amongst factors taken into consideration to improve the model. The reliability calculations are applied for assessing the transformers as well as the distribution network. The calculated transformer (HI) score with the aid of historical failure rate are utilized during the calculation of the distribution network reliability. An application on a simple network connectivity including transformers and loads is demonstrated to verify the strategy effectiveness. The results of this research are the basis for an enhancement for the smart grids performance estimation.

Interaction of Transformer Oil Parameters on Each Other and on Transformer Health Index Using Curve Estimation Regression Method

Power transformers are one of the most significant and expensive equipment in power systems that are exposed to electrical, thermal, and chemical tensions. The transformer health index is a measure that uses test data and field inspections to assess the condition and determine the remaining life of the transformer. The purpose of this article as a new idea is to determine the relationships between electrical, physical, and chemical parameters of transformer oil, dissolved gases, and the transformer health index. One of the advantages of using the regression method in analyzing transformer data compared to the other methods to evaluate the transformer health index is determining the influence of the parameters that have the most impact on each other. Some achievements of this article are as follows: (1) introducing moisture content as the parameter that plays an effective role in reducing dielectric oil breakdown voltage and improving the transformer health index; (2) determining the inverse relationship between acidity and furfural components; (3) determining furfural as a parameter with the greatest role in reducing the Interfacial tension (IFT) of oil (molecular interconnection); (4) determining CO gas as the parameter with the most role in the production of furfural component; (5) determining C2H2 gas as the parameter with the most role in producing the acid component. For example, with a 1 ppm increase in the moisture component, the oil breakdown voltage decreases by 0.583 kV in the compound, growth, exponential, and logistic regressions, or with a 1 ppm increase in the furfural component, the oil interfacial tension decreases by 0.644 mN/m in power regression. In this article, the curve estimation regression method is used and the results are plotted by SPSS statistical software to analyze the interaction between different transformer parameters. To perform the simulations, test data related to 120 transformers have been considered.

A fuzzy inference-based approach for estimating power transformers risk index

Risk assessment is a key point for power system operators interested in the implementation of asset management systems. Among critical electrical assets, the power transformer is probably the most representative. This paper presents a novel method for estimating a risk index for power transformers. The proposed method is based on three Fuzzy Inference Systems (FIS), aimed to integrate expert criteria for the creation of rules and the definition of the membership functions of the entries. The first FIS is dedicated to the calculation of a transformer Health Index (HI), based on the results of the physical-chemical tests normally performed on the insulating liquid of the units. The second FIS is oriented to the determination of a Consequence Factor (CF) of the final failure of the power transformer, and it is determined considering aspects such as overload to other assets, average load supplied by the unit, critical loads supplied, oil volume, proximity to other buildings and penalties for the unavailability of the asset. The last FIS combines the results of the previous FIS, i.e., HI and CF, to provide an estimation of the transformer risk index. The methodology has been designed to perform management of power transformer fleets by allowing decisions to be made, regarding investments, based on risk assessment. The proposal has been tested on a fleet of 15 units. Obtained results show that the FIS for combining HI and the CF leads to more consistent risk indexes, than those obtained when performing the conventional operation of multiplication between HI and FC.

Investigating performance of transformer health index in machine learning application using dominant features

Transformer Health Index (HI) has become a standard tool for performing transformer health evaluations. Due to economic constraints, the recently published paper focuses on developing various techniques to identify the most dominant features for transformer HI prediction. However, the fundamental problems concerning their input features remain unresolved since most suggested features contradict industry practice. In this paper, the primary objective is to investigate the performance of the transformer HI by developing and utilizing only dominant features following the industry recommendation. The investigated dominant features in this paper using 1) CO2/CO ratio and 2) the Incipient fault for detecting temperature abnormalities, and 3) the Dissipation Factor (DF) for detecting oil contamination. The performance validation is carried out using various machine learning (ML) classifiers. Also, the performance of the ML model is validated based on 10-fold type cross-validation to avoid biases in the experiment. As a result, the proposed Artificial Neural Network (ANN) network utilizing the investigated dominant features following the industry practice has produced the highest average accuracy of 80.09% than others ML techniques as a classifier. Hence, additional studies to complement the investigated dominant features may be considered for the subsequent investigation.

Investigation on Online DGA Monitoring to Determine Transformer Health Index Using Machine Learning

The Dissolve Gas Analysis (DGA) to determine the ageing and degradation of the transformer is standard and routine periodic maintenance. In general, there are two DGA analysis methods which are conventional (lab-based) and online monitoring. DGA monitoring will be able to access to detect incipient fault and transformer failure. Several techniques are available to analyse, interpret and diagnose the DGA result, such as IEEE standard, IEC 60599 standard, Key Gas Method, and Duval methods. There are several Machine Learning (ML) techniques has been explored such as Support Vector Machine (SVM), Artificial Neural Network (ANN), K-Neural Neighbours (KNN), Random Neural Network (RNN), and Fuzzy Logic for determining the transformer condition, including fault diagnostic and fault detection. However, there are unexplored studies to combine the commercial device to determine the Health Index (HI) of Transformer. In this study, an ML method with the available input feature from the commercial device to the network is trained to determine the HI. In general, the benchmark dataset from the existing work is employed to validate the proposed investigation. There are 730 datasets comprising five different classes; 1) Very Good, 2) Good, 3) Fair, 4) Poor, 5) Very Poor in determining the HI of a transformer. Conventional rule to partition the train and testing dataset with a 70:30 ratio is employed in this study. The maximum accuracy results and method for 1) M1 is 66.67% for ANN, 2) M2 is 68.49% for ANN, 3) M3 is 76.71% for KNN, 4) M5 is 76.26% for ANN, 5) M6 is 79.00% for ANN and 6) M7 is 86.30% for ANN. In conclusion, the multi-gas device will have a good accuracy performance and provide a good HI indicator to classify the condition of the transformer, which can be used for preventive maintenance.

ANALYTICS 4 ASSETS – THE ADVANCED ASSET MANAGEMENT PROJECT APPLIED TO POWER TRANSFORMERS

Digital Transformation, as well as the need of better technical knowledge of the DSOs Assets, justify the efforts that companies carry out to get solutions to retrieve on time information about the condition of their assets and allow to take justified decisions either to rehabilitate or replace them. E-REDES (Portuguese DSO) has developed a project, designed as a Digital Boost and named Analytics for Assets – A4A, to calculate the Health Index and Probability of Failure for some HV assets, namely: HV Overhead Line, HV Circuit Breakers and Power Transformers. Results regarding Power Transformers health index, calculated using CNAIM methodology, will be shared in this paper.

Prediction of Transformer Health Index Using Condition Situation Monitoring (CSM) Diagnostic Techniques

This paper presents newly developed condition situation monitoring (CSM) diagnostic techniques for predicting the health index and health condition of practical cases in any working transformer. Investigation on measurement and testing can produce results on the insulation resistance between phase and ground test, polarization index with different time duration test, winding resistance of transformer while winding tap changer rating transformer can be determined by the performance health index of the transformer. Real data was collected from 8 units of transformers from Company Transformer Manufacturing and Servicing (CTMS) in Malaysia. The data was applied to calculate the healthy index to provide the transformer performance indicator condition. The main purpose for the use of transformer health index is to indicate the condition of the transformer and attend to failures that can be prevented, with consequences on safety and cost.

Application of Statistical Distribution Models to Predict Health Index for Condition-Based Management of Transformers

In this study, statistical distribution model (SDM) is used to predict the health index (HI) of transformers by utilizing the condition parameters data from dissolved gas analysis (DGA), oil quality analysis (OQA), and furanic compound analysis (FCA), respectively. First, the individual condition parameters data were categorized based on transformer age from year 1 to 15. Next, the individual condition parameters data for every age were fitted while using a probability plot to find the representative distribution models. The distribution parameters were calculated based on 95% confidence level and extrapolated from year 16 to 25 through representative fitting models. The individual condition parameters data within the period were later calculated based on the estimated distribution parameters through the inverse cumulative distribution function (ICDF) of the selected distribution models. The predicted HI was then determined based on the conventional scoring method. The Chi-square test for statistical hypothesis reveals that the predicted HI for the transformer data is quite close to the calculated HI. The average percentage of absolute error is 2.7%. The HI that is predicted based on SDM yields 97.83% accuracy for the transformer data.