Transformer fault diagnosis using machine learning: a method combining SHAP feature selection and intelligent optimization of LGBM

Abstract This paper proposes a novel approach for transformer fault diagnosis. Initially, a high-dimensional feature set comprising 19 features related to five gas concentrations is constructed to reflect the gas-fault relationship. Subsequently, the Shapley Additive Explanations (SHAP) method is em...

Descrición completa

Detalles Bibliográficos

Principais autores:	Cheng Liu, Weiming Yang
Formato:	Artigo
Idioma:	Inglês
Publicado:	SpringerOpen 2025-04-01
Series:	Energy Informatics
Assuntos:	Transformer fault diagnosis Light gradient boosting machine Intelligent optimization algorithms Shapley additive explanations
Acceso en liña:	https://doi.org/10.1186/s42162-025-00519-3
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!