Automating equipment productivity measurement using deep learning

Elham Mahamedi; Kay Rogage; Omar Doukari; Mohamad Kassem

doi:10.35490/EC3.2021.153

Automating equipment productivity measurement using deep learning

Elham Mahamedi, Kay Rogage, Omar Doukari, Mohamad Kassem

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

25 Downloads (Pure)

Abstract

Measuring the productivity of earth moving equipment help to identify their inefficiencies and improve their performance; however, measurement processes are time and resource intensive. Current literature has foccussed on automating equipment activity capture but still lack adequate approaches for measurement of equipment productivity rates. Our contribution is to present a methodology for automating equipment productivity measurement using kinematic and noise data collected through smartphone sensors from within equipment and deep learning algorithms for recognizing equipment states. The testing of the proposed method in a real world case study demonstrated very high accuracy of 99.78% in measuring productivity of an excavator.

Original language	English
Title of host publication	Proceedings of the 2021 European Conference on Computing in Construction
Editors	James O'Donnell, Daniel Hall, Dragana Nikolic, Athanasios Chassiakos
Publisher	University College Dublin
Pages	140-147
Number of pages	8
Volume	2
ISBN (Electronic)	9783907234549
DOIs	https://doi.org/10.35490/EC3.2021.153
Publication status	Published - 26 Jul 2021
Event	2021 European Conference of Computing in Construction (2021 EC³) - Online Conference, Rhodes, Greece Duration: 19 Jul 2021 → 28 Jul 2021 https://ec-3.org/conference2021/

Publication series

Name	Computing in Construction
Publisher	University College Dublin

Conference

Conference	2021 European Conference of Computing in Construction (2021 EC³)
Abbreviated title	2021 EC3
Country/Territory	Greece
City	Rhodes
Period	19/07/21 → 28/07/21
Internet address	https://ec-3.org/conference2021/

Access to Document

10.35490/EC3.2021.153

Contribution_153_finalFinal published version, 477 KB

Cite this

Mahamedi, E., Rogage, K., Doukari, O., & Kassem, M. (2021). Automating equipment productivity measurement using deep learning. In J. O'Donnell, D. Hall, D. Nikolic, & A. Chassiakos (Eds.), Proceedings of the 2021 European Conference on Computing in Construction (Vol. 2, pp. 140-147). (Computing in Construction). University College Dublin. https://doi.org/10.35490/EC3.2021.153

@inproceedings{c2f1465462124f82b2263af33cea7819,

title = "Automating equipment productivity measurement using deep learning",

abstract = "Measuring the productivity of earth moving equipment help to identify their inefficiencies and improve their performance; however, measurement processes are time and resource intensive. Current literature has foccussed on automating equipment activity capture but still lack adequate approaches for measurement of equipment productivity rates. Our contribution is to present a methodology for automating equipment productivity measurement using kinematic and noise data collected through smartphone sensors from within equipment and deep learning algorithms for recognizing equipment states. The testing of the proposed method in a real world case study demonstrated very high accuracy of 99.78% in measuring productivity of an excavator.",

keywords = "Excavators, Productivity, IMU, Machine Learning",

author = "Elham Mahamedi and Kay Rogage and Omar Doukari and Mohamad Kassem",

year = "2021",

month = jul,

day = "26",

doi = "10.35490/EC3.2021.153",

language = "English",

volume = "2",

series = "Computing in Construction",

publisher = "University College Dublin",

pages = "140--147",

editor = "James O'Donnell and Daniel Hall and Dragana Nikolic and Athanasios Chassiakos",

booktitle = "Proceedings of the 2021 European Conference on Computing in Construction",

address = "Ireland",

note = "2021 European Conference of Computing in Construction (2021 EC³), 2021 EC3 ; Conference date: 19-07-2021 Through 28-07-2021",

url = "https://ec-3.org/conference2021/",

}

Mahamedi, E, Rogage, K , Doukari, O & Kassem, M 2021, Automating equipment productivity measurement using deep learning. in J O'Donnell, D Hall, D Nikolic & A Chassiakos (eds), Proceedings of the 2021 European Conference on Computing in Construction. vol. 2, Computing in Construction, University College Dublin, pp. 140-147, 2021 European Conference of Computing in Construction (2021 EC³), Rhodes, Greece, 19/07/21. https://doi.org/10.35490/EC3.2021.153

Automating equipment productivity measurement using deep learning. / Mahamedi, Elham; Rogage, Kay ; Doukari, Omar et al.

Proceedings of the 2021 European Conference on Computing in Construction. ed. / James O'Donnell; Daniel Hall; Dragana Nikolic; Athanasios Chassiakos. Vol. 2 University College Dublin, 2021. p. 140-147 (Computing in Construction).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Automating equipment productivity measurement using deep learning

AU - Mahamedi, Elham

AU - Rogage, Kay

AU - Doukari, Omar

AU - Kassem, Mohamad

PY - 2021/7/26

Y1 - 2021/7/26

N2 - Measuring the productivity of earth moving equipment help to identify their inefficiencies and improve their performance; however, measurement processes are time and resource intensive. Current literature has foccussed on automating equipment activity capture but still lack adequate approaches for measurement of equipment productivity rates. Our contribution is to present a methodology for automating equipment productivity measurement using kinematic and noise data collected through smartphone sensors from within equipment and deep learning algorithms for recognizing equipment states. The testing of the proposed method in a real world case study demonstrated very high accuracy of 99.78% in measuring productivity of an excavator.

AB - Measuring the productivity of earth moving equipment help to identify their inefficiencies and improve their performance; however, measurement processes are time and resource intensive. Current literature has foccussed on automating equipment activity capture but still lack adequate approaches for measurement of equipment productivity rates. Our contribution is to present a methodology for automating equipment productivity measurement using kinematic and noise data collected through smartphone sensors from within equipment and deep learning algorithms for recognizing equipment states. The testing of the proposed method in a real world case study demonstrated very high accuracy of 99.78% in measuring productivity of an excavator.

KW - Excavators

KW - Productivity

KW - IMU

KW - Machine Learning

U2 - 10.35490/EC3.2021.153

DO - 10.35490/EC3.2021.153

M3 - Conference contribution

VL - 2

T3 - Computing in Construction

SP - 140

EP - 147

BT - Proceedings of the 2021 European Conference on Computing in Construction

A2 - O'Donnell, James

A2 - Hall, Daniel

A2 - Nikolic, Dragana

A2 - Chassiakos, Athanasios

PB - University College Dublin

T2 - 2021 European Conference of Computing in Construction (2021 EC³)

Y2 - 19 July 2021 through 28 July 2021

ER -

Automating equipment productivity measurement using deep learning

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this