Computer Vision as Key to an Automated Concrete Production Control

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autoren

Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des SammelwerksProceedings of the 41st International Symposium on Automation and Robotics in Construction
Herausgeber/-innenVicente Gonzalez-Moret, Jiansong Zhang, Borja García de Soto, Ioannis Brilakis
ErscheinungsortLille, France
Seiten26-33
Seitenumfang8
ISBN (elektronisch)9780645832211
PublikationsstatusVeröffentlicht - 1 Juni 2024

Publikationsreihe

NameProceedings of the International Symposium on Automation and Robotics in Construction
ISSN (elektronisch)2413-5844

Abstract

The need to reduce CO 2 emissions from concrete leads to increasingly complex mix designs involving e.g. CO 2 reduced cements, recycled materials, and various chemical additives. This complexity results in a larger sensitivity of the concrete to unpredictable fluctuations in both, the base material properties and in boundary conditions such as temperature and humidity during the production process. Digital sensor systems and quality control schemes are considered as key to counteract this problem by enabling an automated production control. As contribution towards this goal, this paper investigates the research question whether Computer Vision can be used for the predictive characterisation of raw materials (here: of concrete aggregates) and of the fresh concrete quality during the mixing process. In particular, we propose the usage of imaging sensors for the observation of both, aggregate material and the flow behaviour of fresh concrete during the mixing process, and present deep learning methods for the prediction of granulometric and rheological properties from the image observations, respectively. Incorporating such systems into the concrete production process enables the facilitation of a digital control loop for ready-mixed concrete production by allowing an in-line reaction to raw material fluctuations and to deviations of the concrete from the target properties.

ASJC Scopus Sachgebiete

Zitieren

Computer Vision as Key to an Automated Concrete Production Control. / Coenen, Max; Meyer, Maximilian; Beyer, Dries et al.
Proceedings of the 41st International Symposium on Automation and Robotics in Construction. Hrsg. / Vicente Gonzalez-Moret; Jiansong Zhang; Borja García de Soto; Ioannis Brilakis. Lille, France, 2024. S. 26-33 (Proceedings of the International Symposium on Automation and Robotics in Construction).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Coenen, M, Meyer, M, Beyer, D, Heipke, C & Haist, M 2024, Computer Vision as Key to an Automated Concrete Production Control. in V Gonzalez-Moret, J Zhang, B García de Soto & I Brilakis (Hrsg.), Proceedings of the 41st International Symposium on Automation and Robotics in Construction. Proceedings of the International Symposium on Automation and Robotics in Construction, Lille, France, S. 26-33. https://doi.org/10.22260/ISARC2024/0005
Coenen, M., Meyer, M., Beyer, D., Heipke, C., & Haist, M. (2024). Computer Vision as Key to an Automated Concrete Production Control. In V. Gonzalez-Moret, J. Zhang, B. García de Soto, & I. Brilakis (Hrsg.), Proceedings of the 41st International Symposium on Automation and Robotics in Construction (S. 26-33). (Proceedings of the International Symposium on Automation and Robotics in Construction).. https://doi.org/10.22260/ISARC2024/0005
Coenen M, Meyer M, Beyer D, Heipke C, Haist M. Computer Vision as Key to an Automated Concrete Production Control. in Gonzalez-Moret V, Zhang J, García de Soto B, Brilakis I, Hrsg., Proceedings of the 41st International Symposium on Automation and Robotics in Construction. Lille, France. 2024. S. 26-33. (Proceedings of the International Symposium on Automation and Robotics in Construction). doi: 10.22260/ISARC2024/0005
Coenen, Max ; Meyer, Maximilian ; Beyer, Dries et al. / Computer Vision as Key to an Automated Concrete Production Control. Proceedings of the 41st International Symposium on Automation and Robotics in Construction. Hrsg. / Vicente Gonzalez-Moret ; Jiansong Zhang ; Borja García de Soto ; Ioannis Brilakis. Lille, France, 2024. S. 26-33 (Proceedings of the International Symposium on Automation and Robotics in Construction).
Download
@inproceedings{83bd572bc2ce457488aab3dbd49c23a3,
title = "Computer Vision as Key to an Automated Concrete Production Control",
abstract = "The need to reduce CO 2 emissions from concrete leads to increasingly complex mix designs involving e.g. CO 2 reduced cements, recycled materials, and various chemical additives. This complexity results in a larger sensitivity of the concrete to unpredictable fluctuations in both, the base material properties and in boundary conditions such as temperature and humidity during the production process. Digital sensor systems and quality control schemes are considered as key to counteract this problem by enabling an automated production control. As contribution towards this goal, this paper investigates the research question whether Computer Vision can be used for the predictive characterisation of raw materials (here: of concrete aggregates) and of the fresh concrete quality during the mixing process. In particular, we propose the usage of imaging sensors for the observation of both, aggregate material and the flow behaviour of fresh concrete during the mixing process, and present deep learning methods for the prediction of granulometric and rheological properties from the image observations, respectively. Incorporating such systems into the concrete production process enables the facilitation of a digital control loop for ready-mixed concrete production by allowing an in-line reaction to raw material fluctuations and to deviations of the concrete from the target properties.",
keywords = "CNN, Computer Vision, Concrete 4.0, Deep Learning, ViT, image-based granulometry, image-based rheology",
author = "Max Coenen and Maximilian Meyer and Dries Beyer and Christian Heipke and Michael Haist",
note = "Publisher Copyright: {\textcopyright} 2024 ISARC. All Rights Reserved.",
year = "2024",
month = jun,
day = "1",
doi = "10.22260/ISARC2024/0005",
language = "English",
isbn = "978-0-6458322-1-1",
series = "Proceedings of the International Symposium on Automation and Robotics in Construction",
pages = "26--33",
editor = "Vicente Gonzalez-Moret and Jiansong Zhang and {Garc{\'i}a de Soto}, Borja and Ioannis Brilakis",
booktitle = "Proceedings of the 41st International Symposium on Automation and Robotics in Construction",

}

Download

TY - GEN

T1 - Computer Vision as Key to an Automated Concrete Production Control

AU - Coenen, Max

AU - Meyer, Maximilian

AU - Beyer, Dries

AU - Heipke, Christian

AU - Haist, Michael

N1 - Publisher Copyright: © 2024 ISARC. All Rights Reserved.

PY - 2024/6/1

Y1 - 2024/6/1

N2 - The need to reduce CO 2 emissions from concrete leads to increasingly complex mix designs involving e.g. CO 2 reduced cements, recycled materials, and various chemical additives. This complexity results in a larger sensitivity of the concrete to unpredictable fluctuations in both, the base material properties and in boundary conditions such as temperature and humidity during the production process. Digital sensor systems and quality control schemes are considered as key to counteract this problem by enabling an automated production control. As contribution towards this goal, this paper investigates the research question whether Computer Vision can be used for the predictive characterisation of raw materials (here: of concrete aggregates) and of the fresh concrete quality during the mixing process. In particular, we propose the usage of imaging sensors for the observation of both, aggregate material and the flow behaviour of fresh concrete during the mixing process, and present deep learning methods for the prediction of granulometric and rheological properties from the image observations, respectively. Incorporating such systems into the concrete production process enables the facilitation of a digital control loop for ready-mixed concrete production by allowing an in-line reaction to raw material fluctuations and to deviations of the concrete from the target properties.

AB - The need to reduce CO 2 emissions from concrete leads to increasingly complex mix designs involving e.g. CO 2 reduced cements, recycled materials, and various chemical additives. This complexity results in a larger sensitivity of the concrete to unpredictable fluctuations in both, the base material properties and in boundary conditions such as temperature and humidity during the production process. Digital sensor systems and quality control schemes are considered as key to counteract this problem by enabling an automated production control. As contribution towards this goal, this paper investigates the research question whether Computer Vision can be used for the predictive characterisation of raw materials (here: of concrete aggregates) and of the fresh concrete quality during the mixing process. In particular, we propose the usage of imaging sensors for the observation of both, aggregate material and the flow behaviour of fresh concrete during the mixing process, and present deep learning methods for the prediction of granulometric and rheological properties from the image observations, respectively. Incorporating such systems into the concrete production process enables the facilitation of a digital control loop for ready-mixed concrete production by allowing an in-line reaction to raw material fluctuations and to deviations of the concrete from the target properties.

KW - CNN

KW - Computer Vision

KW - Concrete 4.0

KW - Deep Learning

KW - ViT

KW - image-based granulometry

KW - image-based rheology

UR - http://www.scopus.com/inward/record.url?scp=85199655931&partnerID=8YFLogxK

U2 - 10.22260/ISARC2024/0005

DO - 10.22260/ISARC2024/0005

M3 - Conference contribution

SN - 978-0-6458322-1-1

T3 - Proceedings of the International Symposium on Automation and Robotics in Construction

SP - 26

EP - 33

BT - Proceedings of the 41st International Symposium on Automation and Robotics in Construction

A2 - Gonzalez-Moret, Vicente

A2 - Zhang, Jiansong

A2 - García de Soto, Borja

A2 - Brilakis, Ioannis

CY - Lille, France

ER -

Von denselben Autoren