Health indexes for power transformers: a case study

Fernández, Federico; Fernández, Inmaculada; Ortiz, Alfredo; Estébanez, Carlos Javier Renedo; Delgado, F.; Fernández, Cristina

doi:10.1109/mei.2016.7552372

Cited by 39 publications

(29 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…104-2008 and IEEE Std. C57.106-2015 as tabulated in Tables 1 and 2 [4,31,32]. State 1 and State 5 represent "very good" and "very poor" conditions respectively.…”

Section: Modelling Of Transformer Future Conditionmentioning

confidence: 99%

Application of Markov Model to Estimate Individual Condition Parameters for Transformers

et al. 2018

View full text Add to dashboard Cite

This paper presents a study to estimate individual condition parameters of the transformer population based on Markov Model (MM). The condition parameters under study were hydrogen (H2), methane (CH4), acetylene (C2H2), ethylene (C2H4), ethane (C2H6), carbon monoxide (CO), carbon dioxide (CO2), dielectric breakdown voltage, interfacial tension, colour, acidity, water content, and 2-furfuraldehyde (2-FAL). First, the individual condition parameter of the transformer population was ranked and sorted based on recommended limits as per IEEE Std. C57. 104-2008 and IEEE Std. C57.106-2015. Next, the mean for each of the condition parameters was computed and the transition probabilities for each condition parameters were obtained based on non-linear optimization technique. Next, the future states probability distribution was computed based on the MM prediction model. Chi-square test and percentage of absolute error analysis were carried out to find the goodness-of-fit between predicted and computed condition parameters. It is found that estimation for majority of the individual condition parameter of the transformer population can be carried out by MM. The Chi-square test reveals that apart from CH4 and C2H4, the condition parameters are outside the rejection region that indicates agreement between predicted and computed values. It is also observed that the lowest and highest percentages of differences between predicted and computed values of all the condition parameters are 81.46% and 98.52%, respectively.

show abstract

“…104-2008 and IEEE Std. C57.106-2015 as tabulated in Tables 1 and 2 [4,31,32]. State 1 and State 5 represent "very good" and "very poor" conditions respectively.…”

Section: Modelling Of Transformer Future Conditionmentioning

confidence: 99%

Application of Markov Model to Estimate Individual Condition Parameters for Transformers

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Nonetheless, operational and internal revision experiences [17] show that, depending on the quality of service, the technical condition of the active part of such a transformer is satisfactory considering their age, and after a minor renovation their operation period can be extended by another 10-15 years [18]. In a similar study [19], in an analyzed group of twelve fifty-year-old transformers, all of the transformers were ranked as bad or risky during the five years of the experiment, but none of them ended their lives despite the critical evaluation obtained with algorithm I.…”

Section: Discussionmentioning

confidence: 99%

Condition Assessment of Power Transformers Based on Health Index Value

Bohatyrewicz

Płowucha²,

Subocz

2019

Applied Sciences

View full text Add to dashboard Cite

In electric power systems, health index algorithms are mostly used for evaluation of the transformer population. In this method, some assessment criteria are insensitive when it comes to judging the technical state of the edges of the age spectrum. This paper presents a new health index calculation method that aims to improve the overall effectiveness of the assessment. The proposed algorithm is based on regularly conducted oil diagnostics and easily available maintenance data to enable estimation and updating of the device’s health status in short intervals from an operational point of view. This method is compared to another health index algorithm built from the same parameters, but with different weights and an alternative result assessment philosophy. The two health index calculation methods are tested on a population of 96 power transformers and then compared to results obtained with an expert system, which is based on much more advanced diagnostic tests to determine the technical condition of the unit. The results of the experiment show that proper selection of weighting factors of the transformer’s technical condition parameters during health index calculation may help in simplifying its assessment while maintaining satisfactory accuracy in comparison to a highly advanced expert method.

show abstract

“…Collectively, laboratory tests on dissolved gases, oil, and paper quality would be used to compute the HI value based on a given formula that is developed by experts in the TAM field. Examples of such different formulas can be found in [6][7][8][9][10][11][12][13], with the method illustrated in [6,7] being solely used for computing the HI for the majority of publications.…”

Section: Insulation Health Index Computationmentioning

confidence: 99%

Application of Machine Learning in Transformer Health Index Prediction

Alqudsi

El-Hag

2019

Energies

View full text Add to dashboard Cite

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. current health condition, and all related financial costs (maintenance, operation, and failure) would result in an economic risk management plan with adequate subsequent decisions.

show abstract

Health indexes for power transformers: a case study

Cited by 39 publications

References 6 publications

Application of Markov Model to Estimate Individual Condition Parameters for Transformers

Application of Markov Model to Estimate Individual Condition Parameters for Transformers

Condition Assessment of Power Transformers Based on Health Index Value

Application of Machine Learning in Transformer Health Index Prediction

Contact Info

Product

Resources

About