Transformer fault diagnosis using dissolved gas analysis technology and Bayesian networks

Lakehal, Abdelaziz; Ghemari, Zine; Saad, Salah

doi:10.1109/icosc.2015.7152759

Cited by 13 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For power big data, there are many methods of fault diagnosis, such as a support vector machine [18], decision tree [19], neural network [20], Bayes [21], etc. In this study, association rules were selected for research, and the Apriori algorithm was improved to obtain better fault diagnosis performance.…”

Section: Discussionmentioning

confidence: 99%

Archives of Electrical Engineering

Qian,

Zhu,

et al. 2020

View full text Add to dashboard Cite

Power big data contains a lot of information related to equipment fault. The analysis and processing of power big data can realize fault diagnosis. This study mainly analyzed the application of association rules in power big data processing. Firstly, the association rules and the Apriori algorithm were introduced. Then, aiming at the shortage of the Apriori algorithm, an IM-Apriori algorithm was designed, and a simulation experiment was carried out. The results showed that the IM-Apriori algorithm had a significant advantage over the Apriori algorithm in the running time. When the number of transactions was 100 000, the running of the IM-Apriori algorithm was 38.42% faster than that of the Apriori algorithm. The IM-Apriori algorithm was little affected by the value of support min . Compared with the Extreme Learning Machine (ELM), the IM-Apriori algorithm had better accuracy. The experimental results show the effectiveness of the IM-Apriori algorithm in fault diagnosis, and it can be further promoted and applied in power grid equipment.

show abstract

Section: Discussionmentioning

confidence: 99%

Archives of Electrical Engineering

Qian,

Zhu,

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Methodical reliability, as a rule, is associated with the processing of measurement results, the choice of diagnostic features, and criteria for assessing the technical condition of the equipment [6]- [9]. One of the promising directions for improving the methodical reliability of diagnosing oil-filled power transformers using the results of various control methods is the use of statistical solutions based on the processing of multi-parameter measurement data [10]- [14]. Methods for transformers diagnosing have different frequencies of application, sensitivity to the occurrence of malfunctions, and, as a result, different information content in terms of statistical estimates.…”

Section: Introductionmentioning

confidence: 99%

An innovative method of fault detection in power transformers

Levin

Yahya

2022

IJECE

View full text Add to dashboard Cite

The Bayesian classifier is a priori the optimal solution for minimizing the total error in problems of statistical pattern recognition. The article suggests using the classifier as a regular tool to increase the reliability of defect recognition in power oil-filled transformers based on the results of the analysis of gases dissolved in oil. The wide application of the Bayesian method for solving tasks of technical diagnostics of electrical equipment is limited by the problem of the multidimensional distribution of random parameters (features) and the nonlinearity of classification. The application of a generalized feature of a defect in the form of a nonlinear function of the transformer state parameters is proposed. This simultaneously reduces the dimension of the initial space of the controlled parameters and significantly improves the stochastic properties of the random distribution of the generalized feature. A special algorithm has been developed to perform statistical calculations and the procedure for recognizing the current technical condition of the transformer using the generated decision rule. The presented research results illustrate the possibility of the practical application of the developed method in the conditions of real operation of power transformers.

show abstract

“…He specified that although a simple SVM has a superior generalisation capability, it is less efficient than multiple SVM. Techniques such as the k-nearest neighbour (KNN) [26], Bayesian network (BN), [27], and others are also used to explore information from DGA data; however, they still have a limited use.…”

Section: Introductionmentioning

confidence: 99%