Forecasting maximum formwork pressure for self-compacting concrete using ARX-Laguerre machine learning model
Forecasting the maximum pressure exerted by cast-in-place self-compacting concrete (SCC) is a major concern for formwork designers, researchers, and site engineers to accurately design the bearing capacity of the formwork and control the casting rate for safe and fast construction. This article aims...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-04-01
|
Series: | Developments in the Built Environment |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666165924000905 |
_version_ | 1797244870124896256 |
---|---|
author | Taoufik Najeh Yaser Gamil Jonny Nilimaa |
author_facet | Taoufik Najeh Yaser Gamil Jonny Nilimaa |
author_sort | Taoufik Najeh |
collection | DOAJ |
description | Forecasting the maximum pressure exerted by cast-in-place self-compacting concrete (SCC) is a major concern for formwork designers, researchers, and site engineers to accurately design the bearing capacity of the formwork and control the casting rate for safe and fast construction. This article aims to utilize the ARX-Laguerre model, which is a data-driven model to forecast the maximum form pressure. A laboratory instrumented setup was used to cast a 2-m column using SCC made with two different types of cement. A pressure system consisting of four sensors was used to document the pressure during casting. The data were sent to the cloud at every 1-min interval for real-time monitoring. The data were used to develop the model. The results demonstrated that forecasting with the ARX-Laguerre model is highly accurate. The model can forecast the maximum pressure exerted by SCC with less complexity. The model performance was also found to be consistent with insignificant differences between actual experimental results and predicted results. With a recursive and straightforward representation, the resulting model, known as the ARX-Laguerre model, ensures the parameter number reduction. Providing fast prediction of the maximum pressure. The model enables formwork designers to forecast the form pressure to design safe formwork and also helps to control the casting rate when SCC is used. |
first_indexed | 2024-04-24T19:17:52Z |
format | Article |
id | doaj.art-d2f133d27e904a949d9e75909a6d9559 |
institution | Directory Open Access Journal |
issn | 2666-1659 |
language | English |
last_indexed | 2024-04-24T19:17:52Z |
publishDate | 2024-04-01 |
publisher | Elsevier |
record_format | Article |
series | Developments in the Built Environment |
spelling | doaj.art-d2f133d27e904a949d9e75909a6d95592024-03-26T04:27:48ZengElsevierDevelopments in the Built Environment2666-16592024-04-0118100409Forecasting maximum formwork pressure for self-compacting concrete using ARX-Laguerre machine learning modelTaoufik Najeh0Yaser Gamil1Jonny Nilimaa2Operation, Maintenance, and Acoustics, Department of Civil, Environmental and Natural Resources Engineering, Lulea University of Technology, Sweden; Corresponding author.Department of Civil, Environmental and Natural Resources Engineering, Luleå University of Technology, SE-97187, Luleå, Sweden; Department of Civil Engineering, School of Engineering, Monash University Malaysia, Jalan Lagoon Selatan, 47500 Bandar Sunway, Selangor, Malaysia; Corresponding author.Department of Civil, Environmental and Natural Resources Engineering, Luleå University of Technology, SE-97187, Luleå, SwedenForecasting the maximum pressure exerted by cast-in-place self-compacting concrete (SCC) is a major concern for formwork designers, researchers, and site engineers to accurately design the bearing capacity of the formwork and control the casting rate for safe and fast construction. This article aims to utilize the ARX-Laguerre model, which is a data-driven model to forecast the maximum form pressure. A laboratory instrumented setup was used to cast a 2-m column using SCC made with two different types of cement. A pressure system consisting of four sensors was used to document the pressure during casting. The data were sent to the cloud at every 1-min interval for real-time monitoring. The data were used to develop the model. The results demonstrated that forecasting with the ARX-Laguerre model is highly accurate. The model can forecast the maximum pressure exerted by SCC with less complexity. The model performance was also found to be consistent with insignificant differences between actual experimental results and predicted results. With a recursive and straightforward representation, the resulting model, known as the ARX-Laguerre model, ensures the parameter number reduction. Providing fast prediction of the maximum pressure. The model enables formwork designers to forecast the form pressure to design safe formwork and also helps to control the casting rate when SCC is used.http://www.sciencedirect.com/science/article/pii/S2666165924000905FormworkPressureMaximumSCCCasting rateCement types |
spellingShingle | Taoufik Najeh Yaser Gamil Jonny Nilimaa Forecasting maximum formwork pressure for self-compacting concrete using ARX-Laguerre machine learning model Developments in the Built Environment Formwork Pressure Maximum SCC Casting rate Cement types |
title | Forecasting maximum formwork pressure for self-compacting concrete using ARX-Laguerre machine learning model |
title_full | Forecasting maximum formwork pressure for self-compacting concrete using ARX-Laguerre machine learning model |
title_fullStr | Forecasting maximum formwork pressure for self-compacting concrete using ARX-Laguerre machine learning model |
title_full_unstemmed | Forecasting maximum formwork pressure for self-compacting concrete using ARX-Laguerre machine learning model |
title_short | Forecasting maximum formwork pressure for self-compacting concrete using ARX-Laguerre machine learning model |
title_sort | forecasting maximum formwork pressure for self compacting concrete using arx laguerre machine learning model |
topic | Formwork Pressure Maximum SCC Casting rate Cement types |
url | http://www.sciencedirect.com/science/article/pii/S2666165924000905 |
work_keys_str_mv | AT taoufiknajeh forecastingmaximumformworkpressureforselfcompactingconcreteusingarxlaguerremachinelearningmodel AT yasergamil forecastingmaximumformworkpressureforselfcompactingconcreteusingarxlaguerremachinelearningmodel AT jonnynilimaa forecastingmaximumformworkpressureforselfcompactingconcreteusingarxlaguerremachinelearningmodel |