Conveyor belts are the most widespread means of transportation for large quantities of materials in the mining sector. Therefore, autonomous methods that can help human beings to perform the inspection of the belt conveyor system is a major concern for companies. In this context, we present in this work a novel and automatic visual detector that recognizes dirt buildup on the structures of conveyor belts, which is one of the tasks of the maintenance inspectors. This visual detector can be embedded as sensors in autonomous robots for the inspection activity. The proposed system involves training a convolutional neural network from RGB images. The use of the transfer learning technique, i.e., retraining consolidated networks for image classification with our collected images has shown very effective. Two different approaches for transfer learning have been analyzed. The best one presented an average accuracy of 0.8975 with an F-1 Score of 0.8773 for the dirt recognition. A field validation experiment served to evaluate the performance of the proposed system in a real time classification task.
In the mining sector, conveyor belts are the most widespread means of transportation for large quantities of materials. Mining sites usually contain thousands of bearings, which make the inspection task complex. One aims with this work to perform a research in the field of artificial intelligence in order to automate and to facilitate the inspection in conveyor belts. The proposed methodology involves training a pattern detector through Convolutional Neural Networks (CNN) from RGB images that will be collected by an autonomous robot. As an initial application, one seeks to develop a classifier capable of identifying the clutter of dirt in the structures, which is one of the tasks of the maintenance teams. To analyze the problem, we chose the use of the transfer learning technique, using networks consolidated in the classification of images and retrained with the images collected. Accuracy in test data ranged from 81.81% to 95.45%. A full description of the methodology employed and the results obtained is presented in the article. Resumo: No setor da mineração os transportadores de correia constituem o meio mais difundido de transporte para grandes quantidades de materiais. Os locais de mineração geralmente contêm milhares de rolamentos, que tornam complexa a tarefa de inspeção. Se objetiva com este trabalho realizar uma pesquisa no campo da inteligência artificial de forma a automatizar e facilitar a inspeção em transportadores de correia. A metodologia proposta envolve treinar um classificador de padrões por meio de Redes Neurais Convolucionais (RNC) a partir de imagens RGB que serão coletadas por um robô autônomo. Como aplicação inicial, busca-se desenvolver um classificador capaz de identificar a aglomeração de sujeira nas estruturas, queé uma entre as tarefas das equipes de manutenção. Para análise do problema, optou-se pelo uso da técnica de transferência de conhecimento, usando redes consolidadas na classificação de imagens e re-treinadas com as imagens coletadas. A acurácia nos dados de teste variou entre 81.81% e 95.45%. Uma descrição completa da metodologia empregada e dos resultados obtidosé apresentada no artigo.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.