Prediction of Concrete Compressive Strength Using a Back-Propagation Neural Network Optimized by a Genetic Algorithm and Response Surface Analysis Considering the Appearance of Aggregates and Curing Conditions

Abstract

In the present research, the authors have attempted to examine the compressive strength of conventional concrete, which is made using different aggregate sizes and geometries considering various curing temperatures. To this end, different aggregate geometries (rounded and angular) were utilized in various aggregate sizes (10, 20, and 30 mm) to prepare 108 rectangular cubic specimens. Then, the curing process was carried out in the vicinity of wind at different temperatures (5 °C < T < 30 °C). Next, the static compression experiments were performed on 28-day concrete specimens. Additionally, each test was repeated three times to check the repeatability of the results. Finally, the mean results were reported as the strength of concrete specimens. Response Surface Analysis (RSA) was utilized to determine the interaction effects of different parameters including the appearance of aggregates (shape and size) and curing temperature on the concrete strength. Afterwards, the optimum values of parameters were reported based on the RSA results to achieve maximum compressive strength. Moreover, to estimate concrete strength, a back-propagation neural network (OBPNN) optimized by a genetic algorithm (GA) was used. The findings of this study indicated that the developed neural network approach is greatly consistent with the experimental ones. Additionally, the compressive strength of concrete can be significantly increased (about 30%) by controlling the curing temperature in the range of 5–15 °C.

The Prediction of Compressive Strength and Compressive Stress–Strain of Basalt Fiber Reinforced High-Performance Concrete Using Classical Programming and Logistic Map Algorithm

“…The Coefficient of Determination (R2) was applied to find the Algorithm validation and accuracy in this study. Furthermore, the Mean Absolute Errors (MAE) and the Root-Mean-Square Deviation Error (RMSE) are two common types of validation methods to find the reliability of the Algorithm prediction [ 26 ]. The MAE equation is equal to the sum of the numerical differences of the values of the community set divided by whole numbers (Equation (9)).…”

“…The , , and are the actual, predicted, and mean values of the each community set, respectively, and is the number of whole sets. The Mean Absolute Errors (MAE)equation is defined as (Equation (9)) [ 26 ]: …”

“…According to their prediction results, the FL and ANNs methods are acceptable for comparing the experimental results. Reza Kashyzadeh et al [ 26 ] also used the Data Mining method to determine the compressive strength of concrete, considering the shape and size of the dry aggregate. They developed an algorithm to find the compressive strength of ordinary concrete through the Data Mining of the dry temperature and aggregate shapes.…”

Influence of Meso-Scale Pore Structure on Mechanical Behavior of Concrete under Uniaxial Compression Based on Parametric Modeling

“…Liu Huawei [16] applied 3D-printing technology to the study of concrete pore structure. In experimental research, many scholars [17][18][19][20] have tried a variety of innovative experimental methods and research methods. The research based on the experimental method proves that the use of total porosity to characterize the influence of meso-scale pore structure on the mechanical behavior of concrete is unscientific, and the influence of pore size and sub-porosity of pores in different pore size ranges cannot be ignored.…”

The Effect of Current and Time on Nut Spot Welding Process Towards Torque Test in Export Crate Construction

“…The results of the Taguchi sensitivity analysis showed that the parameters of electric current (22%) and welding time (17%) were the most effective factors on the diameter of the nugget. Furthermore, Multiple Regression Technique (MRT) is used to present a new equation to calculate the point diameter through the parameter process (Reza Kashyzadeh et al, 2022).…”