Cost Effective Polyethylene Terephthalate (PET) Object Orientation Detection System

Jeanes, Gareth (2018) Cost Effective Polyethylene Terephthalate (PET) Object Orientation Detection System. [USQ Project]


The push of industry 4.0 which is the convergence of all Internet of Things (IoT) devices to streamline businesses for spoilage reduction; increased overall equipment effectiveness (OEE) and ultimately increase productivity and profits is now a reality. These objectives are being met with the use of smart sensors and machine automation.

Currently, there are specific applications that are hard to sense and intervention is required by human operators. This additional intervention increases the operators cognitive load. This project looks into the viability and feasibility of using smart sensors for the manufacturing industry.

The project investigates different options in sensing technologies and determines a suitable sensing system. The object orientation system is to be used in the beverage industry, primarily the polyethylene terephthalate (PET) construction. The object orientation detection system is used in conjunction with a graphical user interface (GUI) to determine if a bottle has fallen over on a consolidation conveyor belt. The algorithms of the stereo vision system work with standard o↵ the shelf webcams and are tested using MATLAB and on-site real world machine tests.

MATLAB scripts were written to calibrate and process the stereo images. Image conversions; disparity mapping and thresholding was used to determine if the field of view (FOV) of the conveyor was in a healthy or unhealthy state.

The outcome of the on-site testing was a successful detection of incorrectly orientated bottles that spanned across approximately 5 minutes of real time running of 600ml water bottles in production. The final outcome of the trials was that it is viable to use stereo vision as a smart sensor to detect incorrectly orientated bottles at the cost of only 2 cameras.

Statistics for USQ ePrint 40733
Statistics for this ePrint Item
Item Type: USQ Project
Item Status: Live Archive
Faculty/School / Institute/Centre: Historic - Faculty of Health, Engineering and Sciences - School of Mechanical and Electrical Engineering (1 Jul 2013 - 31 Dec 2021)
Supervisors: Leis, John
Qualification: Bachelor of Engineering (Electrical and Electronic)
Date Deposited: 01 Sep 2022 22:11
Last Modified: 29 Jun 2023 01:45
Uncontrolled Keywords: sensing technologies; polyethylene terephthalate (PET); construction; graphical user interface (GUI)

Actions (login required)

View Item Archive Repository Staff Only