Fault detection in induction machines using learning models and fourier spectrum image analysis

Induction motors are essential components in industry due to their efficiency and cost-effectiveness. This study presents an innovative methodology for automatic fault detection by analyzing images generated from the Fourier spectra of current signals using deep learning techniques. A new preprocess...

ver descrição completa

Detalhes bibliográficos
Autores: Barrera Llanga, Kevin Iván|||0000-0002-1072-6142, Burriel Valencia, Jordi, Sapena Bañó, Ángel, Martínez Román, Javier
Formato: artículo
Fecha de publicación:2025
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/457125
Acesso em linha:https://hdl.handle.net/2117/457125
https://dx.doi.org/10.3390/s25020471
Access Level:acceso abierto
Palavra-chave:Fault diagnosis
Induction motors
Spectral images
Deep learning
Explainability
Predictive maintenance
Àrees temàtiques de la UPC::Enginyeria mecànica::Motors
Descrição
Resumo:Induction motors are essential components in industry due to their efficiency and cost-effectiveness. This study presents an innovative methodology for automatic fault detection by analyzing images generated from the Fourier spectra of current signals using deep learning techniques. A new preprocessing technique incorporating a distinctive background to enhance spectral feature learning is proposed, enabling the detection of four types of faults: healthy motor coupled to a generator with a broken bar (HGB), broken rotor bar (BRB), race bearing fault (RBF), and bearing ball fault (BBF). The dataset was generated from three-phase signals of an induction motor controlled by a Direct Torque Controller under various operating conditions (20–1500 rpm with 0–100% load), resulting in 4251 images. The model, based on a Visual Geometry Group (VGG) architecture with 19 layers, achieved an overall accuracy of 98%, with specific accuracies of 99% for RAF, 100% for BRB, 100% for RBF, and 95% for BBF. A new model interpretability was assessed using explainability techniques, which allowed for the identification of specific learning patterns. This analysis introduces a new approach by demonstrating how different convolutional blocks capture particular features: the first convolutional block captures signal shape, while the second identifies background features. Additionally, distinct convolutional layers were associated with each fault type: layer 9 for RAF, layer 13 for BRB, layer 16 for RBF, and layer 14 for BBF. This methodology offers a scalable solution for predictive maintenance in induction motors, effectively combining signal processing, computer vision, and explainability techniques.