Thermal Anomaly Detection in Belt Conveyor Idlers in the Mining Industry Through an Optimized Convolutional Neural Network Using an Amended Salp Swarm Algorithm

Effective condition monitoring (CM) in the mining industry is crucial for operational excellence, given the harsh environments, continuous operation, and high-value nature of assets. Traditional fault diagnosis methods like vibration analysis often prove inadequate due to signal noise, logistical challenges for sensor placement, and limitations in detecting subtle failures. This paper addresses these challenges by proposing an advanced contactless diagnostic system that integrates Infrared Thermography (IRT) with an optimized Convolutional Neural Network (CNN) for detecting machinery faults in mining operations. The core of the approach involves a customized ResNet-50 architecture, chosen for its inherent ability to extract hierarchical features directly from raw thermal image data, thereby circumventing the laborious and error-prone process of manual feature engineering. Recognizing the profound impact of hyperparameters on model performance, a novel optimization strategy is developed. This strategy utilizes an amended Salp Swarm Algorithm (SSA), which incorporates a Levy flight mutation strategy and improved position update mechanisms to enhance its exploration capabilities and prevent premature convergence, ensuring a thorough search of the complex hyperparameter space. The proposed methodology is rigorously evaluated using thermal images acquired from a heavy-duty belt conveyor system at the JARO S.A. mine. The optimized ResNet-50 model achieved a remarkable validation accuracy of 97.22%, demonstrating superior performance. Comparative analysis showed that our model significantly outperformed other state-of-the-art deep learning architectures, such as InceptionV3 and ResNet-18, as well as other metaheuristic optimization algorithms, yielding a 15.6% improvement over the basic SSA. This robust performance, combined with efficient convergence, underscores the model’s capacity for accurate and timely fault identification, paving the way for proactive maintenance, reduced downtime, and enhanced safety in demanding mining environments.