1. Fault diagnosis of belt conveyor idlers based on gradient boosting decision tree.
- Author
-
Soares, João L. L., Costa, Thiago B., Moura, Lis S., Sousa, Walter S., Mesquita, Alexandre L. A., Mesquita, André L. A., de Figueiredo, Jullyane M. S., and Braga, Danilo S.
- Subjects
CONVEYOR belts ,BELT conveyors ,DECISION trees ,CLASSIFICATION algorithms ,FAILURE mode & effects analysis ,BOOSTING algorithms ,FAULT diagnosis - Abstract
Maintenance planning and control should prioritize predictive techniques (e.g., vibration analysis on critical components such as belt conveyors and idlers) for addressing the low reliability of bulk transportation systems. The extensive length of the belt conveyor hampers manual inspections and machine learning based on vibration measurements becomes an effective method for fault diagnosis. Models that classify faults, such as Gradient Boosting Decision Tree (GBDT), offer flexible algorithms that optimize decision tree classification through gradient-based techniques for minimizing predictive function errors. However, in case of non-stationary and nonlinear vibration signals, traditional techniques like Fourier Transform can hinder vibration analysis. Methods such as Wavelet Packet Decomposition (WPD) have emerged as an alternative to improve defect detection by extracting energy from signal frequency bands. This paper proposes a combination of WPD and GBDT for feature extraction and classification, respectively, for diagnosing two different failure modes in laboratory belt conveyor idlers, namely, bearing faults and surface wear. GBDT hyperparameters were well-fitted from 21 boosting stages, corroborating the high flexibility of the classification algorithm applied for less robust datasets. Furthermore, GBDT models achieved diagnosis accuracies of 100% for bearing defects and 97.5% for surface wear, showing the effectiveness of the combination for fault identification. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF