Fastener identification and assembly verification via machine vision
ISSN: 0144-5154
Article publication date: 14 December 2017
Issue publication date: 23 January 2018
Abstract
Purpose
The study aims to evaluate the capability of a machine vision camera and software to recognize fasteners for the purpose of assembly verification. This will enable the current assembly verification system to associate torque verfication with a specific fastener.
Design/methodology/approach
A small camera is installed at the head of a tool near the socket. The camera is used to capture images surrounding the fastener, and feeding them into machine vision recognition software. By recognizing unique features around the fastener, the fastener can be uniquely identified and therefore verified to be assembled. Additional filtering and multiple frame recognition will improve the reliability of the recognition.
Findings
The machine vision technology is found to be adequately reliable in identifying fasteners after tuning key threshold parameters and requiring multiple positively recognized frames. The time to verify can be kept around a fraction of a second to prevent impacting assembly speed.
Research limitations/implications
This experiment was run under simulated assembly line lighting conditions. It also does not explore industrial remote head industrial camera hardware.
Practical implications
By using a remote-mounted camera in combination with electric tools, a reliable assembly verification system can be used to eliminate torque check processes of critical fasteners, thereby reducing the cost of assembly.
Originality/value
Currently, assembly verification is done only using the torque values. In automated assembly line, each process might involve fastening multiple fasteners. Using this system, a new level of assembly verification is achieved by recording the assembled fastener and its associated torque.
Keywords
Acknowledgements
The authors would like to acknowledge the financial support by Honda of America Manufacturing for this project, and Stanley Tools and Center for Occupational Health in Automotive Manufacturing for the facility.
Citation
Rusli, L. and Luscher, A. (2018), "Fastener identification and assembly verification via machine vision", Assembly Automation, Vol. 38 No. 1, pp. 1-9. https://doi.org/10.1108/AA-08-2016-093
Publisher
:Emerald Publishing Limited
Copyright © 2018, Emerald Publishing Limited