A new fault detection method of conveyer belt based on machine vision

Bingxia Shen; Muyan Ma

doi:10.1117/12.888358

26 May 2011 A new fault detection method of conveyer belt based on machine vision

Bingxia Shen, Muyan Ma

Proceedings Volume 7997, Fourth International Seminar on Modern Cutting and Measurement Engineering; 79972L (2011) https://doi.org/10.1117/12.888358
Event: Fourth International Seminar on Modern Cutting and Measuring Engineering, 2010, Beijing, China

Abstract

A new fault detection and measurement method of conveyer belt based on machine vision is proposed. The conveyer belt used in coal mine transportation usually goes two kinds of faults: joint's elongation and local rust. Under this engineering background, the system focuses on detecting the state of conveyer belt and measuring the fault size. This paper brings forward a modified BP neural network to detect and classify different faults. The new BP algorithm's detecting speed is rapid, and the correct recognition rate of the joint and erosion has a great improvement. The measurements of joint's length and erosion's area are realized on the machine vision platform which built by LabVIEW IMAQ Vision module. And the measurements have a high accuracy. The results demonstrate that the new method is effective and efficiency.

Citation Download Citation

Bingxia Shen and Muyan Ma "A new fault detection method of conveyer belt based on machine vision", Proc. SPIE 7997, Fourth International Seminar on Modern Cutting and Measurement Engineering, 79972L (26 May 2011); https://doi.org/10.1117/12.888358

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available