Eventos Anais de eventos
DINAME 2023
XIX International Symposium on Dynamic Problems of Mechanics
Machine Learning Based Fault Detection on Belt Conveyor Idlers
Submission Author:
João Lucas Lobato Soares , PA , Brazil
Co-Authors:
João Lucas Lobato Soares, Thiago Barroso Costa, Lis Silva de Moura, Walter dos Santos Sousa, Alexandre Mesquita, André Luiz Amarante Mesquita, Danilo Braga
Presenter: João Lucas Lobato Soares
doi://10.26678/ABCM.DINAME2023.DIN2023-0141
Abstract
Belt conveyors are used extensively in mining industry. Faults in their components can compromise the entire plant production. Machine learning-based techniques have been applied successfully for condition monitoring and fault diagnosis of industrial equipment. Therefore, in this paper a machine learning based method is presented for the diagnosis of faults in belt conveyor idlers. The method consists in applying wavelet transform to the measured vibration signals, extracting features from the processed signals and applying the Gradient Boosting method to classify the state of the idlers. Finally, with dimensionality reduction (PCA), the model achieved accuracy of 100% for two different failure modes.
Keywords
machine learning, GBDT, Wavelet packet, Belt conveyor idler, Fault Detection
