Diagnosis of Power Transformer Oil Using KNN and Nave Bayes Classifiers

Benmahamed, Youcef; Kemari, Y.; Teguar, M.; Boubakeur, A.

doi:10.1109/icd.2018.8514789

Cited by 15 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this regard, various research scholars have undertaken several studies to explore novel approaches of automated faultfinding on the electrical grid. For instance in [24], Benmahamed et al evaluated the kNN algorithm and Naïve Bayes to diagnose transformer oil insulation through the analysis of DGA data. Five input vectors namely the Duval triangle reports, Dornrenberg ratios, Rogers ratios, DGA data (in percentages and ppm) were used in the study to map to five output classes.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Multinomial DGA Classifier for Incipient Fault Detection in Oil-Impregnated Power Transformers

2021

View full text Add to dashboard Cite

This study investigates the use of machine-learning approaches to interpret Dissolved Gas Analysis (DGA) data to find incipient faults early in oil-impregnated transformers. Transformers are critical pieces of equipment in transmitting and distributing electrical energy. The failure of a single unit disturbs a huge number of consumers and suppresses economic activities in the vicinity. Because of this, it is important that power utility companies accord high priority to condition monitoring of critical assets. The analysis of dissolved gases is a technique popularly used for monitoring the condition of transformers dipped in oil. The interpretation of DGA data is however inconclusive as far as the determination of incipient faults is concerned and depends largely on the expertise of technical personnel. To have a coherent, accurate, and clear interpretation of DGA, this study proposes a novel multinomial classification model christened KosaNet that is based on decision trees. Actual DGA data with 2912 entries was used to compute the performance of KosaNet against other algorithms with multiclass classification ability namely the decision tree, k-NN, Random Forest, Naïve Bayes, and Gradient Boost. Investigative results show that KosaNet demonstrated an improved DGA classification ability particularly when classifying multinomial data.

show abstract

Section: Related Workmentioning

confidence: 99%

“…where m, n are two observations in the Euclidean space. The k-NN algorithm is easy to implement but performs poorly as the number of predictor variables increase [24].…”

mentioning

confidence: 99%

A Multinomial DGA Classifier for Incipient Fault Detection in Oil-Impregnated Power Transformers

2021

View full text Add to dashboard Cite

show abstract

“…For example, k=3 expresses class 1 because only two squares and only one triangle exist. By contrast, k=5 refers to class 2 because the number of samples is five, which consists of three triangles and two squares [40]. The different metric distance methods used for KN are Euclidean, city block, Chebyshev, Minkowski (cubic), Mahalanobis, cosine, Spearman correlation, Hamming, and Jaccard.…”

Section: K-nearest Neighbor (Knn) Classifiermentioning

confidence: 99%

Comparative Study of Full and Reduced Feature Scenarios for Health Index Computation of Power Transformers

Ghoneim

Taha

2020

IEEE Access

View full text Add to dashboard Cite

Power transformer health index (PTHI) computation is performed based on the results of different tests, such as dissolved gas analysis (DGA), oil quality (OQ) evaluation, and depolarization factor (DP) testing. In this study, PTHI computation is performed using 631 dataset samples from Malaysia and 730 samples from the Gulf Region. A new model is proposed to predict the PTHI state by adopting intelligent classification methods (e.g., decision tree, support vector machine, k-nearest neighbor, and ensemble methods). The model is built via two-stage data processing. The first stage separates the test results into three modules that represent DGA, OQ, and DP factor codes. In the second stage, the output of the three modules is processed to predict the PTHI state. The four classification methods are applied to the proposed model, and the prediction accuracy of the PTHI state is determined. Results indicate that the proposed model has superior classification accuracy for each AI method compared with recent work. Furthermore, feature reductions are applied to minimize the testing time, effort, and costs. The reduced-feature models reveal the effectiveness of the adopted feature reduction technique. A slight difference in accuracy is observed between the full-and reduced-feature scenarios. Thus, the reduced-feature scenario is considered to decrease the effort and time of the computation process and the experimental cost. The proposed model is validated against uncertain noise in features of up to ±20%.

show abstract

“…Para melhorar o desempenho do KNN existem diversas propostas de técnicas, como por exemplo, ponderar a distância (Gou et al, 2012), ponderar os K vizinhos mais próximos, usar conjunto de dados sintéticos ou usar o classificador médio Cmeans (Sarma et al, 2011). Aplicações que envolvem DGA, podem ser encontradas em Benmahamed et al (2018) e Samirmi et al (2013) .…”

Section: K Vizinhos Mais Próximos -Knnunclassified

Análise de Incertezas em Amostras de Gases Usadas no Diagnóstico de Falhas em Transformadores de Potência

Ikeshoji

Souza

Costa

et al. 2020

Anais Do Simpósio Brasileiro De Sistemas Elétricos 2020

View full text Add to dashboard Cite

Grandes transformadores de potência são importantes ativos do sistema elétrico. A saída inesperada de operação desses equipamentos por ocorrência de falhas não observadas, causa grandes prejuízos financeiros, sociais e ambientais. A análise dos gases dissolvidos no óleo e o uso de ferramentas analíticas para o diagnóstico de falhas incipientes nos transformadores, podem apresentar baixa assertividade e/ou ausência de diagnóstico. Por outro lado, o aprimoramento de técnicas de inteligência computacional, aliada a novas tecnologias de medição tem permitido aumentar a confiança nos diagnósticos produzidos. Neste contexto, para eliminar ou reduzir erros no processo de classificação de falhas, empregou-se estatísticas adicionais para obter informações, avaliar e tratar a presença de outliers no conjunto disponível de dados dos gases dissolvidos. Portanto, com o objetivo de reduzir os efeitos deletérios de interrupções intempestivas e imprevisíveis dos transformadores, este artigo propõe metodologias de eliminação de outliers com base em valores limites determinados através de técnicas de identificação e processamento com algoritmos de aprendizado de máquinas.

show abstract

Diagnosis of Power Transformer Oil Using KNN and Nave Bayes Classifiers

Cited by 15 publications

References 8 publications

A Multinomial DGA Classifier for Incipient Fault Detection in Oil-Impregnated Power Transformers

A Multinomial DGA Classifier for Incipient Fault Detection in Oil-Impregnated Power Transformers

Comparative Study of Full and Reduced Feature Scenarios for Health Index Computation of Power Transformers

Análise de Incertezas em Amostras de Gases Usadas no Diagnóstico de Falhas em Transformadores de Potência

Contact Info

Product

Resources

About