Hybrid CNN-BYOL Approach for Fault Detection in Induction Motors Using Thermal Images

2025-10-08

AI Summary

Addressing the challenges of early fault detection in induction motors and poor model generalizability due to scarce thermal imaging data, this paper proposes an end-to-end thermal image diagnosis method integrating BYOL-based self-supervised learning with a lightweight CNN. We innovatively design BYOL-IMNet—a four-module specialized network built upon mainstream backbones (e.g., ResNet-50)—and incorporate the Bootstrap Your Own Latent (BYOL) framework to enable label-free self-supervised pretraining on thermal images, substantially enhancing feature discriminability under low-data regimes. Evaluated on a standardized thermal image dataset, the model achieves a test accuracy of 99.89% with only 5.7 ms inference time per image, outperforming existing state-of-the-art methods in both accuracy and efficiency. This work establishes a new paradigm for motor overheating预警 and energy-efficiency optimization—characterized by high robustness, ultra-low latency, and strong generalization with limited labeled data.

Technology Category

• Machine Learning: Unsupervised & Self-Supervised Learning
• Computer Vision: Representation Learning for Vision
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Induction motors (IMs) are indispensable in industrial and daily life, but they are susceptible to various faults that can lead to overheating, wasted energy consumption, and service failure. Early detection of faults is essential to protect the motor and prolong its lifespan. This paper presents a hybrid method that integrates BYOL with CNNs for classifying thermal images of induction motors for fault detection. The thermal dataset used in this work includes different operating states of the motor, such as normal operation, overload, and faults. We employed multiple deep learning (DL) models for the BYOL technique, ranging from popular architectures such as ResNet-50, DenseNet-121, DenseNet-169, EfficientNetB0, VGG16, and MobileNetV2. Additionally, we introduced a new high-performance yet lightweight CNN model named BYOL-IMNet, which comprises four custom-designed blocks tailored for fault classification in thermal images. Our experimental results demonstrate that the proposed BYOL-IMNet achieves 99.89% test accuracy and an inference time of 5.7 ms per image, outperforming state-of-the-art models. This study highlights the promising performance of the CNN-BYOL hybrid method in enhancing accuracy for detecting faults in induction motors, offering a robust methodology for online monitoring in industrial settings.

Problem

• Detecting induction motor faults using thermal image classification
• Developing hybrid CNN-BYOL method for early fault identification
• Creating lightweight BYOL-IMNet model for industrial monitoring applications

Innovation

• Hybrid CNN-BYOL method for thermal image classification
• Introduces lightweight BYOL-IMNet with four custom blocks
• Achieves high accuracy with fast inference for monitoring