Show simple item record

dc.contributor.authorChauhan, Vedangen
dc.date2016-04-29 14:24:27.663
dc.date.accessioned2016-04-29T20:31:28Z
dc.date.available2016-04-29T20:31:28Z
dc.date.issued2016-04-29
dc.identifier.urihttp://hdl.handle.net/1974/14340
dc.descriptionThesis (Ph.D, Mechanical and Materials Engineering) -- Queen's University, 2016-04-29 14:24:27.663en
dc.description.abstractAutomated assembly machines operate continuously to achieve high production rates. Continuous operation increases the potential for faults, with subsequent machine downtime. Early fault detection can reduce the amount of downtime. Traditional fault detection methods check for deviations from fixed threshold limits with multiple mechanical, optical and proximity sensors. The goal of this thesis was to develop and validate a machine vision inspection (MVI) system to detect and classify multiple faults using a single camera as a sensor. An industrial automated O-ring assembly machine that places O-rings on to continuously moving plastic carriers at a rate of over 100 assemblies per minute was modified to serve as the test apparatus. An industrial CCD camera with LED panel lights for illumination was used to acquire videos of the machine’s operation. A Programmable Logic Controller (PLC) with a Human-Machine Interface (HMI) allowed for the generation of faults in a controlled fashion. Three MVI methods, based on from computer vision techniques available in the literature, were developed for this application. The methods used features extracted from the videos to classify the machine’s condition. The first method was based on Gaussian Mixture Models (GMMs), as originally used for real-time outdoor tracking of moving regions in image sequences. The second method used an optical flow approach which was originally used for motion estimation in a video. The third method was based on running average and morphological image processing, originally used for noise filtering in image sequences. In order to provide a single metric to quantify relative performance, a Machine Vision Performance Index (MVPI) was developed with five measures of performance: accuracy, processing time, speed of response, robustness against noise, and ease of implementation. On the basis of the calculated MVPI, it was concluded that the GMM-based method is the best of the three methods for this application. This thesis has two main contributions: 1) validation that MVI can be used to detect and classify multiple faults using a single camera and 2) documentation on how computer vision techniques can be applied to the problem of fault detection and classification in assembly machines.en
dc.language.isoengen
dc.relation.ispartofseriesCanadian thesesen
dc.rightsQueen's University's Thesis/Dissertation Non-Exclusive License for Deposit to QSpace and Library and Archives Canadaen
dc.rightsProQuest PhD and Master's Theses International Dissemination Agreementen
dc.rightsIntellectual Property Guidelines at Queen's Universityen
dc.rightsCopying and Preserving Your Thesisen
dc.rightsCreative Commons - Attribution - CC BYen
dc.rightsThis publication is made available by the authority of the copyright owner solely for the purpose of private study and research and may not be copied or reproduced except as permitted by the copyright laws without written authority from the copyright owner.en
dc.subjectMachine Visionen
dc.subjectAutomated Assembly Machineen
dc.subjectFault Detectionen
dc.titleFault Detection and Classification in Automated Assembly Machines Using Machine Visionen
dc.typethesisen
dc.description.degreePhDen
dc.contributor.supervisorSurgenor, Brian W.en
dc.contributor.departmentMechanical and Materials Engineeringen
dc.degree.grantorQueen's University at Kingstonen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record