A fault diagnostic method for oil-immersed transformer based on multiple probabilistic output algorithms and improved DS evidence theory

Yue, Hua; Sun, Yuanyuan; Xu, Gongde; Sun, Shengya; Wang, Erdong; Pang, Yanqing

doi:10.1016/j.ijepes.2021.107828

Cited by 31 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A number of previous works have studied DS fusion, whether to interpret the relationship between different data sources (DGA [14], Ratio methods [28], etc. ), or the merging of several discriminator outputs [1,7,31,32], and have highlighted the theory contribution in the PTD problem.…”

Section: Study Motivations and Innovationsmentioning

confidence: 99%

Using Generic Direct M-SVM Model Improved by Kohonen Map and Dempster–Shafer Theory to Enhance Power Transformers Diagnostic

Hendel,

Meghnefi,

Senoussaoui

et al. 2023

Sustainability

View full text Add to dashboard Cite

Many power transformers throughout the world are nearing or have gone beyond their theoretical design life. Since these important assets represent approximately 60% of the cost of the substation, monitoring their condition is necessary. Condition monitoring helps in the decision to perform timely maintenance, to replace equipment or extend its life after evaluating if it is degraded. The challenge is to prolong its residual life as much as possible. Dissolved Gas Analysis (DGA) is a well-established strategy to warn of fault onset and to monitor the transformer’s status. This paper proposes a new intelligent system based on DGA; the aim being, on the one hand, to overcome the conventional method weaknesses; and, on the other hand, to improve the transformer diagnosis efficiency by using a four-step powerful artificial intelligence method. (1) Six descriptor sets were built and then improved by the proposed feature reduction approach. Indeed, these six sets are combined and presented to a Kohonen map (KSOM), to cluster the similar descriptors. An averaging process was then applied to the grouped data, to reduce feature dimensionality and to preserve the complete information. (2) For the first time, four direct Multiclass Support Vector Machines (M-SVM) were introduced on the Generic Model basis; each one received the KSOM outputs. (3) Dempster–Shafer fusion was applied to the nine membership probabilities returned by the four M-SVM, to improve the accuracy and to support decision making. (4) An output post-processing approach was suggested to overcome the contradictory evidence problem. The achieved AUROC and sensitivity average percentages of 98.78–95.19% (p-value < 0.001), respectively, highlight the remarkable proposed system performance, bringing a new insight to DGA analysis.

show abstract

Section: Study Motivations and Innovationsmentioning

confidence: 99%

Using Generic Direct M-SVM Model Improved by Kohonen Map and Dempster–Shafer Theory to Enhance Power Transformers Diagnostic

Hendel,

Meghnefi,

Senoussaoui

et al. 2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…Como técnica de aprendizaje supervisado, la clasificación es una herramienta estadística, que a través de un conjunto de datos de entrenamiento permite definir reglas de clasificación para establecer covariables y etiquetas de clase. Las reglas de clasificación se utilizan para la predicación de clase de nuevos objetos cuyas covariables están disponibles (Hua et al, 2022). Son diversas las estrategias de clasificación y los desafíos crecen exponencialmente, no hay una técnica que sea la mejor, cada clasificador presenta un número considerable de ventajas y desventajas.…”

Section: Multiclaseunclassified

Clasificación de la ocupación espectral para la toma de decisiones en redes inalámbricas cognitivas implementando extracción de características y aprendizaje automático

2022

View full text Add to dashboard Cite

La radio cognitiva (CR) es una tecnología que busca maximizar el uso de los recursos de frecuencia al permitir que los usuarios sin licencia accedan a las bandas de espectro de forma oportunista. Se analiza el proceso de toma de decisiones a través de la clasificación de tres niveles de tráfico. Para evaluar el proceso, se utilizan tres métricas de costo y una de beneficio. Los resultados muestran que el clasificador que utiliza máquinas de soporte vectorial presenta el mejor desempeño, seguido por KnNC (K-nearest Neighbor Classifier) y DAC (Discriminan Analysis Classifier). El desempeño más bajo, con los indicadores de desempeño más deficiente, lo obtiene BDT (Binary Decision Tree). Se concluye que la CR ofrece un conjunto de soluciones al hacer que el espectro se use de manera dinámica.

show abstract

“…The oil-immersed transformer continues to play a crucial role in modern power systems due to its exceptional reliability, convenient maintenance, extensive application range, and high level of overvoltage protection. − Transformer oil, an indispensable component of the oil-immersed transformer, serves critical functions in insulation, heat dissipation, mechanical support, and protection. These functions are of paramount importance in ensuring normal operation and prolonged service life of the transformer.…”

Section: Introductionmentioning

confidence: 99%

Adsorption Properties of Dissolved Gas Molecules in Transformer Oil on the ReSe₂ Monolayer: A DFT Study

Yang,

Hu,

Zhang

et al. 2024

Langmuir

View full text Add to dashboard Cite

Based on density functional theory, the adsorption behavior of seven typical dissolved gas molecules (CO, CO 2 , H 2 , CH 4 , C 2 H 2 , C 2 H 4 , and C 2 H 6 ) and H 2 O molecule on the ReSe 2 monolayer was systematically investigated. The interactions between the ReSe 2 monolayer and eight gas molecules were investigated by calculating the adsorption energies, charge transfer, density of states (DOS), and deformation charge density (DCD) for eight different adsorption systems. The gas sensitivity of the ReSe 2 monolayer toward these gases was studied using frontier molecular orbital theory and work function analysis. The results demonstrate that compared to other gas molecules, the ReSe 2 monolayer exhibits a stronger interaction with CO with an adsorption energy of −1.49 eV. It also displays excellent sensitivity and selectivity toward CO making it a promising candidate for CO gas sensing applications. We aspire that this research will offer theoretical guidance for the development of ReSe 2 -based gas sensors and contribute to state monitoring technology in oil-immersed power equipment.

show abstract

A fault diagnostic method for oil-immersed transformer based on multiple probabilistic output algorithms and improved DS evidence theory

Cited by 31 publications

References 27 publications

Using Generic Direct M-SVM Model Improved by Kohonen Map and Dempster–Shafer Theory to Enhance Power Transformers Diagnostic

Using Generic Direct M-SVM Model Improved by Kohonen Map and Dempster–Shafer Theory to Enhance Power Transformers Diagnostic

Clasificación de la ocupación espectral para la toma de decisiones en redes inalámbricas cognitivas implementando extracción de características y aprendizaje automático

Adsorption Properties of Dissolved Gas Molecules in Transformer Oil on the ReSe₂ Monolayer: A DFT Study

Contact Info

Product

Resources

About

A fault diagnostic method for oil-immersed transformer based on multiple probabilistic output algorithms and improved DS evidence theory

Cited by 31 publications

References 27 publications

Using Generic Direct M-SVM Model Improved by Kohonen Map and Dempster–Shafer Theory to Enhance Power Transformers Diagnostic

Using Generic Direct M-SVM Model Improved by Kohonen Map and Dempster–Shafer Theory to Enhance Power Transformers Diagnostic

Clasificación de la ocupación espectral para la toma de decisiones en redes inalámbricas cognitivas implementando extracción de características y aprendizaje automático

Adsorption Properties of Dissolved Gas Molecules in Transformer Oil on the ReSe2 Monolayer: A DFT Study

Contact Info

Product

Resources

About

Adsorption Properties of Dissolved Gas Molecules in Transformer Oil on the ReSe₂ Monolayer: A DFT Study