What question did this study set out to answer?

This study aims to create an effective framework for diagnosing faults in induction motors used in electric vehicles.

July 23, 2026Proceedings of the Institution of Mechanical Engineers Part K Journal of Multi-body Dynamics0 citations

Robust Fault Diagnosis of Electric Vehicle Induction Motors Using Advanced Deep Learning Techniques

Robust fault diagnosis of electric vehicle induction motors via Gramian angular field encoding and metaheuristic-optimized deep transfer learning

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates fault diagnosis in electric vehicle motors, suggesting improved safety and efficiency.

This study aims to create an effective framework for diagnosing faults in induction motors used in electric vehicles.
Developed a diagnostic pipeline using Gramian angular field encoding to create 2D representations of signals.
Evaluated five pretrained convolutional neural network architectures with a transfer learning strategy.
Integrated Coati optimization algorithm for improving feature selection and weighting.
DenseNet169–Coati model achieved 97.22% accuracy and 97.62% precision.
Macro area under the curve of 98.80% demonstrates high classification performance.
Gradient-weighted class activation mapping confirmed model focus on important signal regions.

ÖZÜPAK et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

July 23, 2026Proceedings of the Institution of Mechanical Engineers Part K Journal of Multi-body Dynamics0 citations

Robust fault diagnosis of electric vehicle induction motors via Gramian angular field encoding and metaheuristic-optimized deep transfer learning

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates fault diagnosis in electric vehicle motors, suggesting improved safety and efficiency.

This study aims to create an effective framework for diagnosing faults in induction motors used in electric vehicles.
Developed a diagnostic pipeline using Gramian angular field encoding to create 2D representations of signals.
Evaluated five pretrained convolutional neural network architectures with a transfer learning strategy.
Integrated Coati optimization algorithm for improving feature selection and weighting.
DenseNet169–Coati model achieved 97.22% accuracy and 97.62% precision.
Macro area under the curve of 98.80% demonstrates high classification performance.
Gradient-weighted class activation mapping confirmed model focus on important signal regions.

ÖZÜPAK et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark