A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Prediction model for compressive strength of rice husk ash blended sandcrete blocks using a machine learning models
https://orcid.org/http://orcid.org/0000-0001-8570-0580
Sandcrete blocks are popular for construction but their production relies on cement, which is a major contributor to greenhouse gases. Rice husk ash (RHA), a waste product, can partially replace cement in sandcrete blocks. This study uses machine learning (ML) to predict the compressive strength of these blocks, which is influenced by factors such as the ratio of fine aggregate to binder, RHA to binder ratio, water-to-binder ratio, and curing time. The data were collected from published literature on factors affecting compressive strength from various sources and analyzed 795 observations. The analysis showed that strength increases with longer curing but decreases with higher ratios of aggregate-to-binder, RHA-to-binder, and water-to-binder. The data were divided for training and testing ML models. Five algorithms were investigated, and the eXtreme Gradient Boosting (XGB) model emerged as the best for predicting compressive strength. The XGB model strongly correlated with predicted and measured strength, with an R2 value of 0.94 for training data and 0.89 for testing data. It also displayed lower error metrics compared to other models. XGB's success is due to its ability to handle complex relationships and prevent overfitting. This study highlights the potential of ML for predicting the strength of RHA-blended sandcrete blocks.
Prediction model for compressive strength of rice husk ash blended sandcrete blocks using a machine learning models
https://orcid.org/http://orcid.org/0000-0001-8570-0580
Sandcrete blocks are popular for construction but their production relies on cement, which is a major contributor to greenhouse gases. Rice husk ash (RHA), a waste product, can partially replace cement in sandcrete blocks. This study uses machine learning (ML) to predict the compressive strength of these blocks, which is influenced by factors such as the ratio of fine aggregate to binder, RHA to binder ratio, water-to-binder ratio, and curing time. The data were collected from published literature on factors affecting compressive strength from various sources and analyzed 795 observations. The analysis showed that strength increases with longer curing but decreases with higher ratios of aggregate-to-binder, RHA-to-binder, and water-to-binder. The data were divided for training and testing ML models. Five algorithms were investigated, and the eXtreme Gradient Boosting (XGB) model emerged as the best for predicting compressive strength. The XGB model strongly correlated with predicted and measured strength, with an R2 value of 0.94 for training data and 0.89 for testing data. It also displayed lower error metrics compared to other models. XGB's success is due to its ability to handle complex relationships and prevent overfitting. This study highlights the potential of ML for predicting the strength of RHA-blended sandcrete blocks.
Prediction model for compressive strength of rice husk ash blended sandcrete blocks using a machine learning models
https://orcid.org/http://orcid.org/0000-0001-8570-0580
Sandcrete blocks are popular for construction but their production relies on cement, which is a major contributor to greenhouse gases. Rice husk ash (RHA), a waste product, can partially replace cement in sandcrete blocks. This study uses machine learning (ML) to predict the compressive strength of these blocks, which is influenced by factors such as the ratio of fine aggregate to binder, RHA to binder ratio, water-to-binder ratio, and curing time. The data were collected from published literature on factors affecting compressive strength from various sources and analyzed 795 observations. The analysis showed that strength increases with longer curing but decreases with higher ratios of aggregate-to-binder, RHA-to-binder, and water-to-binder. The data were divided for training and testing ML models. Five algorithms were investigated, and the eXtreme Gradient Boosting (XGB) model emerged as the best for predicting compressive strength. The XGB model strongly correlated with predicted and measured strength, with an R2 value of 0.94 for training data and 0.89 for testing data. It also displayed lower error metrics compared to other models. XGB's success is due to its ability to handle complex relationships and prevent overfitting. This study highlights the potential of ML for predicting the strength of RHA-blended sandcrete blocks.
Prediction model for compressive strength of rice husk ash blended sandcrete blocks using a machine learning models
Asian J Civ Eng
Sathiparan, Navaratnarajah (author)
Asian Journal of Civil Engineering ; 25 ; 4745-4758
2024-09-01
14 pages
Article (Journal)
Electronic Resource
English
Some engineering properties of sandcrete blocks containing rice husk ash
| Online Contents | 1993
Some engineering properties of sandcrete blocks containing rice husk ash
| British Library Online Contents | 1993
Some engineering properties of sandcrete blocks containing rice husk ash
| Elsevier | 1993
Use of rice husk ash in sandcrete blocks for masonry units
| Online Contents | 1987