Research On ADCN Method For Damage Detection Of Mining Conveyor Belt

Journal article (2021)

Authors

Dingran Qu Taiyuan University of Technology
Tiezhu Qiao Taiyuan University of Technology
Y. Pang Transport Engineering and Logistics - Mechanical, Maritime and Materials Engineering
Yi Yang Taiyuan University of Technology
Haitao Zhang Taiyuan University of Technology
Research Group
Transport Engineering and Logistics (Mechanical, Maritime and Materials Engineering) (TU Delft)
Copyright: © 2021 Dingran Qu, Tiezhu Qiao, Y. Pang, Yi Yang, Haitao Zhang
DOI
help_outline
https://doi.org/10.1109/JSEN.2020.3048057
Convolution Deep learning Sensors Feature extraction Neural networks Damage Mathematical model Conveyor belt Kernel ADCN Belts
More Info
expand_more

Published Date

2021

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical, Maritime and Materials Engineering

Department

Marine and Transport Technology

Research Group

Transport Engineering and Logistics

Abstract

Belt conveyor is considered as a momentous component of modern coal mining transportation system, and thus it is an essential task to diagnose and monitor the damage of belt in real time and accurately. Based on the deep learning algorithm, this present study proposes a method of conveyor belt damage detection based on ADCN (Adaptive Deep Convolutional Network). A deep convolution network with unique adaptability is built to extract the different scale features of visible light image of conveyor belt damage, and the target is classified and located in the form of anchor boxes. A data set with data diversity is collected according to the actual working conditions of the conveyor belt. After training and regression, the ADCN model can perfectly capture and classify the damaged target in the video of the conveyor running. Compared with the SVM based method, the method based on ADCN can better meet the real-time and reliability requirements of belt damage detection, and it has the positioning function which SVM does not have.

Files

09310211.pdf
(.pdf | 1.16 Mb)
09310211.pdf
(.pdf | 2.18 Mb)