A Subsystem-Aware Graph Autoencoder with uncertainty guided learning framework for explainable power transformer health classification and health-index estimation

This paper presents a Subsystem-Aware Graph Autoencoder uncertainty guided learning (SA-GAE (ug)) framework for explainable power transformer health assessment. The framework is developed to address the limitation of conventional autoencoder-based health-classification models, which compress condition-monitoring variables as ordinary tabular features without explicitly representing the physical relationships among transformer subsystems. In the proposed approach, assessment data from 405 power transformers described by 31 condition-based monitoring (CBM) parameters are first grouped into diagnostic subsystems, including dissolved gas analysis, oil quality, internal components, insulation/impurity, bushing, on-load tap changer and operating factors. These variables are then formulated as nodes in a subsystem-aware diagnostic graph, while subsystem membership, statistical correlation and physical degradation relationships define the graph edges. A graph autoencoder is used to extract compact latent health embeddings, which are then passed into uncertainty-guided multi-task learning heads for simultaneous estimation of transformer health class, continuous health index, confidence level and subsystem-level risk drivers. The proposed framework is compared with direct machine-learning classifiers, conventional MLPA-autoencoder baselines, graph convolutional networks and graph attention networks. The proposed model achieved a mean accuracy of 95.2% (95% CI: 94.8–95.6%), macro-F1 of 0.960 (95% CI: 0.956–0.964) and poor-class recall of 0.940 (95% CI: 0.930–0.950). This indicated improved class discrimination and reduced missed detection of poor-condition transformers. The framework therefore demonstrates strong internal performance and potential as an interpretable, maintenance-oriented decision-support approach for transformer asset management.

Authors

Institutions

Publication Details

Journal
Energy Informatics
Published
2026-11-18
DOI
https://doi.org/10.1186/s42162-026-00705-x
Primary Topic
Power Transformer Diagnostics and Insulation
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Subsystem-Aware Graph Autoencoder with uncertainty guided learning framework for explainable power transformer health classification and health-index estimation

Kayenga Tendo Joshua, Athur Mugumya, Jeffy Briton Ssemuddu, Andrew Ndawula et al.
Energy Informatics
Power Transformer Diagnostics and Insulation
article

A Subsystem-Aware Graph Autoencoder with uncertainty guided learning framework for explainable power transformer health classification and health-index estimation

Kayenga Tendo Joshua, Athur Mugumya, Jeffy Briton Ssemuddu, Andrew Ndawula, Alfred Ochieng
article en

Abstract

This paper presents a Subsystem-Aware Graph Autoencoder uncertainty guided learning (SA-GAE (ug)) framework for explainable power transformer health assessment. The framework is developed to address the limitation of conventional autoencoder-based health-classification models, which compress condition-monitoring variables as ordinary tabular features without explicitly representing the physical relationships among transformer subsystems. In the proposed approach, assessment data from 405 power transformers described by 31 condition-based monitoring (CBM) parameters are first grouped into diagnostic subsystems, including dissolved gas analysis, oil quality, internal components, insulation/impurity, bushing, on-load tap changer and operating factors. These variables are then formulated as nodes in a subsystem-aware diagnostic graph, while subsystem membership, statistical correlation and physical degradation relationships define the graph edges. A graph autoencoder is used to extract compact latent health embeddings, which are then passed into uncertainty-guided multi-task learning heads for simultaneous estimation of transformer health class, continuous health index, confidence level and subsystem-level risk drivers. The proposed framework is compared with direct machine-learning classifiers, conventional MLPA-autoencoder baselines, graph convolutional networks and graph attention networks. The proposed model achieved a mean accuracy of 95.2% (95% CI: 94.8–95.6%), macro-F1 of 0.960 (95% CI: 0.956–0.964) and poor-class recall of 0.940 (95% CI: 0.930–0.950). This indicated improved class discrimination and reduced missed detection of poor-condition transformers. The framework therefore demonstrates strong internal performance and potential as an interpretable, maintenance-oriented decision-support approach for transformer asset management.

Energy Informatics
Mbarara University of Science and Technology (UG), Makerere University (UG)
Affordable and clean energy, Industry, innovation and infrastructure
Power Transformer Diagnostics and Insulation
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon