The utilization of recycled aggregates(RA)for concrete production has the potential to offer substantial environmental and economic advantages.However,RA concrete is plagued with considerable durability concerns,parti...The utilization of recycled aggregates(RA)for concrete production has the potential to offer substantial environmental and economic advantages.However,RA concrete is plagued with considerable durability concerns,particularly carbonation.To advance the application of RA concrete,the establishment of a reliable model for predicting the carbonation is needed.On the one hand,concrete carbonation is a long and slow process and thus consumes a lot of time and energy to monitor.On the other hand,carbonation is influenced by many factors and is hard to predict.Regarding this,this paper proposes the use of machine learning techniques to establish accurate prediction models for the carbonation depth(CD)of RA concrete.Three types of regression techniques and meta-heuristic algorithms were employed to provide more alternative predictive tools.It was found that the best prediction performance was obtained from extreme gradient boosting-multi-universe optimizer(XGB-MVO)with R^(2) value of 0.9949 and 0.9398 for training and testing sets,respectively.XGB-MVO was used for evaluating physical laws of carbonation and it was found that the developed XGB-MVO model could provide reasonable predictions when new data were investigated.It also showed better generalization capabilities when compared with different models in the literature.Overall,this paper emphasizes the need for sustainable solutions in the construction industry to reduce its environmental impact and contribute to sustainable and low-carbon economies.展开更多
The need to find a simple method for measuring soil aggregate porosity (φ) is justified by the growing interest of researchers in this important parameter of soil physical status. The aim of this study was to present...The need to find a simple method for measuring soil aggregate porosity (φ) is justified by the growing interest of researchers in this important parameter of soil physical status. The aim of this study was to present a simple method (AM) for estimating the total 0 of a single soil aggregate. In this case, soil aggregate 0 was calculated as the quotient between the pore volume, estimated from the weight of the aggregate saturated with ethanol, and the total volume (V T ) of aggregate, calculated from the particle density and dry aggregate weight. The V T estimated with AM was compared with the corresponding volume measured with the photogrammetry (PHM) technique using soil aggregates of 8–16 mm in diameter and collected from three different tillage systems: conventional tillage (CT), reduced tillage (RT), and no tillage (NT). Next, the AM was used to study the effects of the tillage system on soil aggregate φ. Although a strong relationship ( R 2 = 0.99, P < 0.000 1) between aggregate V T measured with PHM and that estimated with AM was obtained, AM tended to underestimate aggregate V T with an average deviation of 2.85%. This difference may be due to ethanol evaporation during the first 10 s before the ethanol-saturated aggregate was weighed. The use of AM to determine the effects of different tillage systems on aggregate φ showed that this method was sensitive to detect significant differences among the tillage treatments. The results showed that AM could be an accurate, simple, and inexpensive alternative to estimate φ of a single soil aggregate.展开更多
基金the funding supported by China Scholarship Council(Nos.202008440524 and 202006370006)partially supported by the Distinguished Youth Science Foundation of Hunan Province of China(No.2022JJ10073)+1 种基金the Innovation Driven Project of Central South University(No.2020CX040)Shenzhen Science and Technology Plan(No.JCYJ20190808123013260).
文摘The utilization of recycled aggregates(RA)for concrete production has the potential to offer substantial environmental and economic advantages.However,RA concrete is plagued with considerable durability concerns,particularly carbonation.To advance the application of RA concrete,the establishment of a reliable model for predicting the carbonation is needed.On the one hand,concrete carbonation is a long and slow process and thus consumes a lot of time and energy to monitor.On the other hand,carbonation is influenced by many factors and is hard to predict.Regarding this,this paper proposes the use of machine learning techniques to establish accurate prediction models for the carbonation depth(CD)of RA concrete.Three types of regression techniques and meta-heuristic algorithms were employed to provide more alternative predictive tools.It was found that the best prediction performance was obtained from extreme gradient boosting-multi-universe optimizer(XGB-MVO)with R^(2) value of 0.9949 and 0.9398 for training and testing sets,respectively.XGB-MVO was used for evaluating physical laws of carbonation and it was found that the developed XGB-MVO model could provide reasonable predictions when new data were investigated.It also showed better generalization capabilities when compared with different models in the literature.Overall,this paper emphasizes the need for sustainable solutions in the construction industry to reduce its environmental impact and contribute to sustainable and low-carbon economies.
基金supported by the Ministerio de Economía y Competitividad of Spain (No. AGL201022050-C03-02)
文摘The need to find a simple method for measuring soil aggregate porosity (φ) is justified by the growing interest of researchers in this important parameter of soil physical status. The aim of this study was to present a simple method (AM) for estimating the total 0 of a single soil aggregate. In this case, soil aggregate 0 was calculated as the quotient between the pore volume, estimated from the weight of the aggregate saturated with ethanol, and the total volume (V T ) of aggregate, calculated from the particle density and dry aggregate weight. The V T estimated with AM was compared with the corresponding volume measured with the photogrammetry (PHM) technique using soil aggregates of 8–16 mm in diameter and collected from three different tillage systems: conventional tillage (CT), reduced tillage (RT), and no tillage (NT). Next, the AM was used to study the effects of the tillage system on soil aggregate φ. Although a strong relationship ( R 2 = 0.99, P < 0.000 1) between aggregate V T measured with PHM and that estimated with AM was obtained, AM tended to underestimate aggregate V T with an average deviation of 2.85%. This difference may be due to ethanol evaporation during the first 10 s before the ethanol-saturated aggregate was weighed. The use of AM to determine the effects of different tillage systems on aggregate φ showed that this method was sensitive to detect significant differences among the tillage treatments. The results showed that AM could be an accurate, simple, and inexpensive alternative to estimate φ of a single soil aggregate.
