Prediction of carbonation depth for recycled aggregate concrete using ANN hybridized with swarm intelligence algorithms

Liu, Kaihua; Alam, M. Shahria; Zhu, Jiang; Zheng, Jiakai; Chi, Lin

doi:10.1016/j.conbuildmat.2021.124382

Cited by 64 publications

(39 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Soft computing algorithms have been extensively used in civil engineering fields, especially concrete made with recycled aggregates because of their effectiveness in computation processing 15–18 . For example, several researchers applied such methods in predicting triaxial compressive strength and MOE of frozen sand 19 and modeling the behavior of frozen soils 20 .…”

Section: Introductionmentioning

confidence: 99%

Retracted: Prediction of the elastic modulus of recycled aggregate concrete applying hybrid artificial intelligence and machine learning algorithms

Zhou

Afzal

2021

Structural Concrete

View full text Add to dashboard Cite

Recycled aggregates (RAGs) usage in concrete is surging, inspired by environmental and economic concerns. Regarding predicting various models designed the values of modulus of elasticity (MOE) of concrete with natural aggregates and, in conclusion, they would probably be unreliable when used to concrete with RAG. In the present study, two new gray wolf multi‐layer perceptron neural networks (GWMLP) and gray wolf support vector regression (GWSVR) algorithms were proposed to predict RAG concrete's elastic modulus. About 400 records were gathered from published articles to develop these models. The results show that among the GWMLP models with different hidden layers, GWM3L with three hidden layers could get the highest score (TRS) at 39. Simultaneously, in the testing phase, the GWSVR was the first‐rank model because of the lower RMSE (0.6381), MAE (0.1541), and a larger R2 (0.9707) compared with GWMLP models. Therefore, it can result that the GWSVR model could predict the elastic modulus of RAG concrete precisely even better than GWM3L, which is well over the accuracy of the developed models.

show abstract

Section: Introductionmentioning

confidence: 99%

Retracted: Prediction of the elastic modulus of recycled aggregate concrete applying hybrid artificial intelligence and machine learning algorithms

Zhou

Afzal

2021

Structural Concrete

View full text Add to dashboard Cite

show abstract

“…Inspired by the principle, the BAS algorithm simulates the goal hyperparameter as the food, rendering the ML models with the capability of automatically tuning [39]. As explained by Equation ( 7), the first step of BAS is to generate a random vector as the beetle antennae, where V indicates the direction and k represents the space dimensionality [40].…”

Section: Beetle Antennae Search (Bas)mentioning

confidence: 99%

“…BAS demonstrates benefits comprising easy implementation and convergence, yielding the capability of automatically tuning the hyperparameters [39]. The construction of the algorithm originated from the beetle foraging behavior, leading to the order movement of the group and the optimal hyperparameter combination [40,41].…”

Section: Introductionmentioning

confidence: 99%

Performance Prediction of Cement Stabilized Soil Incorporating Solid Waste and Propylene Fiber

Ding

Wang

et al. 2022

Materials

View full text Add to dashboard Cite

Cement stabilized soil (CSS) yields wide application as a routine cementitious material due to cost-effectiveness. However, the mechanical strength of CSS impedes development. This research assesses the feasible combined enhancement of unconfined compressive strength (UCS) and flexural strength (FS) of construction and demolition (C&D) waste, polypropylene fiber, and sodium sulfate. Moreover, machine learning (ML) techniques including Back Propagation Neural Network (BPNN) and Random Forest (FR) were applied to estimate UCS and FS based on the comprehensive dataset. The laboratory tests were conducted at 7-, 14-, and 28-day curing age, indicating the positive effect of cement, C&D waste, and sodium sulfate. The improvement caused by polypropylene fiber on FS was also evaluated from the 81 experimental results. In addition, the beetle antennae search (BAS) approach and 10-fold cross-validation were employed to automatically tune the hyperparameters, avoiding tedious effort. The consequent correlation coefficients (R) ranged from 0.9295 to 0.9717 for BPNN, and 0.9262 to 0.9877 for RF, respectively, indicating the accuracy and reliability of the prediction. K-Nearest Neighbor (KNN), logistic regression (LR), and multiple linear regression (MLR) were conducted to validate the BPNN and RF algorithms. Furthermore, box and Taylor diagrams proved the BAS-BPNN and BAS-RF as the best-performed model for UCS and FS prediction, respectively. The optimal mixture design was proposed as 30% cement, 20% C&D waste, 4% fiber, and 0.8% sodium sulfate based on the importance score for each variable.

show abstract

“…Note that existing ML-based studies focus mainly on forecasting the mechanical properties of RAC, while research on predicting the durability of RAC is scarce. An attempt is thus worthwhile in this regard, as recent studies [40,41] have shown the utility of ML methods for evaluating the durability of concrete.…”

Section: Introductionmentioning

confidence: 99%

Innovative modeling framework of chloride resistance of recycled aggregate concrete using ensemble-machine-learning methods

Liu

Zheng

Pacheco-Torgal

et al. 2022

Construction and Building Materials

View full text Add to dashboard Cite

Prediction of carbonation depth for recycled aggregate concrete using ANN hybridized with swarm intelligence algorithms

Cited by 64 publications

References 60 publications

Retracted: Prediction of the elastic modulus of recycled aggregate concrete applying hybrid artificial intelligence and machine learning algorithms

Retracted: Prediction of the elastic modulus of recycled aggregate concrete applying hybrid artificial intelligence and machine learning algorithms

Performance Prediction of Cement Stabilized Soil Incorporating Solid Waste and Propylene Fiber

Innovative modeling framework of chloride resistance of recycled aggregate concrete using ensemble-machine-learning methods

Contact Info

Product

Resources

About