Acoustic signal based fault detection on belt conveyor idlers using machine learning

[Display omitted] •A fault diagnosis approach for belt conveyor idlers based on machine learning.•MFCCs of sound signal are extracted as features.•A Gradient Boost Decision Tree model is developed.•High accuracy of fault diagnosis is achieved by using MFCCs & GBDT. Belt conveyor systems are wide...

Full description

Saved in:
Bibliographic Details
Published inAdvanced powder technology : the international journal of the Society of Powder Technology, Japan Vol. 31; no. 7; pp. 2689 - 2698
Main Authors Liu, Xiangwei, Pei, Deli, Lodewijks, Gabriel, Zhao, Zhangyan, Mei, Jie
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.07.2020
Subjects
Acoustic
Belt conveyor
Decision tree
Idler
Machine learning
MFCC
Belt conveyor
Acoustic
Idler
Decision tree
MFCC
Machine learning
Online AccessGet full text

Cover

More Information
Summary:[Display omitted] •A fault diagnosis approach for belt conveyor idlers based on machine learning.•MFCCs of sound signal are extracted as features.•A Gradient Boost Decision Tree model is developed.•High accuracy of fault diagnosis is achieved by using MFCCs & GBDT. Belt conveyor systems are widely utilized in transportation applications. This research aims to achieve fault detection on belt conveyor idlers with an acoustic signal based method. The presented novel method uses Mel Frequency Cepstrum Coefficients and Gradient Boost Decision Tree for feature extraction and classification. Thirteen Mel Frequency Cepstrum Coefficients are extracted from acquired sound signal as features. A Gradient Boost Decision Tree model is developed and trained. After training, the model is applied to a testing dataset. Results show that the trained model can achieve diagnosis accuracy of 94.53%, as well as recall rate up to 99.7%. This study verifies the proposed method for acoustic signal based fault detection of belt conveyor idlers.
ISSN:0921-8831
1568-5527
DOI:10.1016/j.apt.2020.04.034