Real-time vision-based multiple object tracking of a production process: industrial digital twin case study

Robert Ward; Payam Soulatiantork; Shaun Finneran; Ruby Hughes; Ashutosh Tiwari

doi:10.1177/09544054211002464

Real-time vision-based multiple object tracking of a production process: industrial digital twin case study

Robert Ward^*
, Payam Soulatiantork
, Shaun Finneran
, Ruby Hughes
, Ashutosh Tiwari

^*Corresponding author for this work

National Manufacturing Institute Scotland

Research output: Contribution to journal › Article › peer-review

36 Citations (Scopus)

24 Downloads (Pure)

Abstract

The adoption of Industry 4.0 technologies within the manufacturing and process industries is widely accepted to have benefits for production cycles, increase system flexibility and give production managers more options on the production line through reconfigurable systems. A key enabler in Industry 4.0 technology is the rise in Cyber-Physical Systems (CPS) and Digital Twins (DTs). Both technologies connect the physical to the cyber world in order to generate smart manufacturing capabilities. State of the art research accurately describes the frameworks, challenges and advantages surrounding these technologies but fails to deliver on testbeds and case studies that can be used for development and validation. This research demonstrates a novel proof of concept Industry 4.0 production system which lays the foundations for future research in DT technologies, process optimisation and manufacturing data analytics. Using a connected system of commercial off-the-shelf cameras to retrofit a standard programmable logic controlled production process, a digital simulation is updated in real time to create the DT. The system can identify and accurately track the product through the production cycle whilst updating the DT in real-time. The implemented system is a lightweight, low cost, customable and scalable design solution which provides a testbed for practical Industry 4.0 research both for academic and industrial research purposes.

Original language	English
Pages (from-to)	1861-1872
Number of pages	12
Journal	Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture
Volume	235
Issue number	11
Early online date	12 Mar 2021
DOIs	https://doi.org/10.1177/09544054211002464
Publication status	Published - 30 Sept 2021

Funding

This project was a collaboration between the Department of Automatic Control and Systems Engineering and the Manufacturing Intelligence Department at the Advanced Manufacturing Research Centre, University of Sheffield. We would like to thank Dr Jamie Smith for his support with Tecnomatix. We would also like to thank Mike Smart, Joe Bell and Adam Jarmin from Inspec Solutions for their technical support throughout this project. The authors also acknowledge the support of the Royal Academy of Engineering under the Research Chairs and Senior Research Fellowships scheme (RCSRF1718/5/41). Professor Ashutosh Tiwari is Airbus/RAEng Research Chair in Digitisation for Manufacturing at the University of Sheffield. The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by the Higher Education Innovation Funding at the University of Sheffield Knowledge Exchange. Grant No. X/013194. The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by the Higher Education Innovation Funding at the University of Sheffield Knowledge Exchange. Grant No. X/013194. This project was a collaboration between the Department of Automatic Control and Systems Engineering and the Manufacturing Intelligence Department at the Advanced Manufacturing Research Centre, University of Sheffield. We would like to thank Dr Jamie Smith for his support with Tecnomatix. We would also like to thank Mike Smart, Joe Bell and Adam Jarmin from Inspec Solutions for their technical support throughout this project. The authors also acknowledge the support of the Royal Academy of Engineering under the Research Chairs and Senior Research Fellowships scheme (RCSRF1718/5/41). Professor Ashutosh Tiwari is Airbus/RAEng Research Chair in Digitisation for Manufacturing at the University of Sheffield.

Keywords

cyber-physical production systems
digital twin
industry 4.0
multiple object tracking
real time vision tracking
smart manufacturing

Access to Document

10.1177/09544054211002464

Ward-etal-IMEB-JEM-2021-Real-time-vision-based-muliple-objectFinal published version, 6.62 MBLicence: CC BY 4.0

Cite this

@article{19a39295416a4f32909b96d6d9ab4dc3,

title = "Real-time vision-based multiple object tracking of a production process: industrial digital twin case study",

abstract = "The adoption of Industry 4.0 technologies within the manufacturing and process industries is widely accepted to have benefits for production cycles, increase system flexibility and give production managers more options on the production line through reconfigurable systems. A key enabler in Industry 4.0 technology is the rise in Cyber-Physical Systems (CPS) and Digital Twins (DTs). Both technologies connect the physical to the cyber world in order to generate smart manufacturing capabilities. State of the art research accurately describes the frameworks, challenges and advantages surrounding these technologies but fails to deliver on testbeds and case studies that can be used for development and validation. This research demonstrates a novel proof of concept Industry 4.0 production system which lays the foundations for future research in DT technologies, process optimisation and manufacturing data analytics. Using a connected system of commercial off-the-shelf cameras to retrofit a standard programmable logic controlled production process, a digital simulation is updated in real time to create the DT. The system can identify and accurately track the product through the production cycle whilst updating the DT in real-time. The implemented system is a lightweight, low cost, customable and scalable design solution which provides a testbed for practical Industry 4.0 research both for academic and industrial research purposes.",

keywords = "cyber-physical production systems, digital twin, industry 4.0, multiple object tracking, real time vision tracking, smart manufacturing",

author = "Robert Ward and Payam Soulatiantork and Shaun Finneran and Ruby Hughes and Ashutosh Tiwari",

year = "2021",

month = sep,

day = "30",

doi = "10.1177/09544054211002464",

language = "English",

volume = "235",

pages = "1861--1872",

journal = "Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture",

issn = "0954-4054",

publisher = "SAGE Publications Inc.",

number = "11",

}

Real-time vision-based multiple object tracking of a production process: industrial digital twin case study. / Ward, Robert; Soulatiantork, Payam; Finneran, Shaun et al.
In: Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, Vol. 235, No. 11, 30.09.2021, p. 1861-1872.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - Real-time vision-based multiple object tracking of a production process

T2 - industrial digital twin case study

AU - Ward, Robert

AU - Soulatiantork, Payam

AU - Finneran, Shaun

AU - Hughes, Ruby

AU - Tiwari, Ashutosh

PY - 2021/9/30

Y1 - 2021/9/30

N2 - The adoption of Industry 4.0 technologies within the manufacturing and process industries is widely accepted to have benefits for production cycles, increase system flexibility and give production managers more options on the production line through reconfigurable systems. A key enabler in Industry 4.0 technology is the rise in Cyber-Physical Systems (CPS) and Digital Twins (DTs). Both technologies connect the physical to the cyber world in order to generate smart manufacturing capabilities. State of the art research accurately describes the frameworks, challenges and advantages surrounding these technologies but fails to deliver on testbeds and case studies that can be used for development and validation. This research demonstrates a novel proof of concept Industry 4.0 production system which lays the foundations for future research in DT technologies, process optimisation and manufacturing data analytics. Using a connected system of commercial off-the-shelf cameras to retrofit a standard programmable logic controlled production process, a digital simulation is updated in real time to create the DT. The system can identify and accurately track the product through the production cycle whilst updating the DT in real-time. The implemented system is a lightweight, low cost, customable and scalable design solution which provides a testbed for practical Industry 4.0 research both for academic and industrial research purposes.

AB - The adoption of Industry 4.0 technologies within the manufacturing and process industries is widely accepted to have benefits for production cycles, increase system flexibility and give production managers more options on the production line through reconfigurable systems. A key enabler in Industry 4.0 technology is the rise in Cyber-Physical Systems (CPS) and Digital Twins (DTs). Both technologies connect the physical to the cyber world in order to generate smart manufacturing capabilities. State of the art research accurately describes the frameworks, challenges and advantages surrounding these technologies but fails to deliver on testbeds and case studies that can be used for development and validation. This research demonstrates a novel proof of concept Industry 4.0 production system which lays the foundations for future research in DT technologies, process optimisation and manufacturing data analytics. Using a connected system of commercial off-the-shelf cameras to retrofit a standard programmable logic controlled production process, a digital simulation is updated in real time to create the DT. The system can identify and accurately track the product through the production cycle whilst updating the DT in real-time. The implemented system is a lightweight, low cost, customable and scalable design solution which provides a testbed for practical Industry 4.0 research both for academic and industrial research purposes.

KW - cyber-physical production systems

KW - digital twin

KW - industry 4.0

KW - multiple object tracking

KW - real time vision tracking

KW - smart manufacturing

U2 - 10.1177/09544054211002464

DO - 10.1177/09544054211002464

M3 - Article

AN - SCOPUS:85102694382

SN - 0954-4054

VL - 235

SP - 1861

EP - 1872

JO - Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture

JF - Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture

IS - 11

ER -

Real-time vision-based multiple object tracking of a production process: industrial digital twin case study

Abstract

Funding

Keywords

Access to Document

Fingerprint

Cite this