Predicting the uniaxial compressive strength of oil palm shell lightweight aggregate concrete using artificial intelligence‐based algorithms

Self Cite

Obtaining a trustworthy approach to forecast the chloride penetration into self-compacting concrete via rapid test may lead to frugality in cost, time, and energy to provide a durable mix design. Different single and hybrid regression methods are developed to predict the results of rapid chloride penetration tests in the present study. Cement content, fly ash, and silica fume replacement percent with cement, temperature and fine and coarse aggregates are considered as input variables. All predicted values using expanded models have a good agreement with experimentally measured results. Evaluating the accuracy and precision of single and hybrid optimized models by five statistical performance criteria (R 2 , root mean square error, mean absolute error, mean absolute percentage error, and performance index) illustrates that the hybrid support vector regression with optimization algorithm is a high-accurate promising model for predicting the results of a rapid chloride penetration test.

Section: Introductionmentioning

confidence: 99%

Retracted: A comparative study on predicting the rapid chloride permeability of self‐compacting concrete using meta‐heuristic algorithm and artificial intelligence techniques

Jia

Zhao

Esmaeili‐Falak

2022

Self Cite

“…Predicting methods are used for predicting the mechanical properties, constitutive modeling, and the behavior of the materials more than ever 17 . In addition to predicting the behavior and physical and mechanical properties of RAC, optimization of parametric studies has recently been considered in some studies 14,15,25,26,28,37,41,46,61,64 …”

Section: Introductionmentioning

confidence: 99%

Retracted: Predicting the compressive strength of modified recycled aggregate concrete

Yang

Feng

Esmaeili‐Falak

2022

Self Cite

Reuse and recycling of construction wastes effectively prevent further destruction of the environment and nature due to the construction industry. One of the conventional methods is the reapplication of recycled aggregates (RAs) in concrete mix design and construction. Compressive strength (CS) is a considerable representation of the mechanical properties of recycled aggregate concrete (RAC). The present study is divided into two parts of experimental and predicting. In the laboratory studies phase, RA was used with 100% replacement. Due to the proven defects in RAC, glass fibers and silica fume (variables) have been used to compensate for these defects. Different mixing designs were used to construct concrete samples, and then the CS of each specimen was measured in the laboratory. Afterward, these data were used as training and testing in various conventional, ensembled and hybrid models as the tree-based learning algorithms, rules, Lazy-learning Algorithms, Functions, and Meta classifiers. Considering the applied performance statistical criteria (R 2 , root mean squared error, mean absolute error, and mean absolute percentage error), all models have provided excellent and acceptable results, which the precision of the multilayer perceptron single model and additive regression-random Forest hybrid model have the best agreement with measured values of CS of RAC.

“…Every single particle in the search space has a velocity, which is dynamically adjusted by searching for the best position of the particle in the solution space. 60 The PSO algorithm can be expressed as follows 44 :…”

Section: Pso-annmentioning

confidence: 99%

Prediction and uncertainty quantification of compressive strength of high‐strength concrete using optimized machine learning algorithms

Han

Liu

2022

Compressive strength is considered to be one of the most important mechanical properties of high-strength concrete (HSC). In this study, three machine learning models, ELM, PSO-ANN, and GS-SVR were employed to predict the compressive strength of HSC using 681 data records. The five ingredients and the compressive strength of HSC were regarded as input variable features and output target, respectively. Results indicated that the GS-SVR model showed the best performance in forecasting with the R of 0.992, MAPE of 0.016, RMSE of 1.241, MAE of 0.842, and RRMSE of 0.024, which could be an alternative candidate for strength prediction. Additionally, a sensitivity analysis was performed within the GS-SVR model to achieve an in-depth examination of the effect of each single input variable on the compressive strength. The sensitivity of input variables demonstrated that the water is the most sensitive parameter to the compressive strength of HSC, while the superplasticizer is less sensitive.