Journal of Soft Computing in Civil Engineering
https://www.jsoftcivil.com/
Journal of Soft Computing in Civil Engineeringendaily1Mon, 01 Apr 2024 00:00:00 +0430Mon, 01 Apr 2024 00:00:00 +0430Predictive Equations for Estimation of the Slump of Concrete Using GEP and MARS Methods
https://www.jsoftcivil.com/article_175577.html
This paper developed two robust data-driven models, namely gene expression programming (GEP) and multivariate adaptive regression splines (MARS), for the estimation of the slump of concrete (SL). The main feature of the proposed data-driven methods is to provide explicit mathematical equations for estimating SL. The experimental data set contains five input variables, including the water-cement ratio (W/C), water (W), cement (C), river sand (Sa), and Bida Natural Gravel (BNG) used for the estimation of SL. Three common statistical indices, such as the correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE), were used to evaluate the accuracy of the derived equations. The statistical indices revealed that the GEP formula (R=0.976, RMSE=19.143, and MAE=15.113) was more accurate than the MARS equation (R=0.962, RMSE=23.748, and MAE=16.795). However, the application of MARS, due to its simple regression equation for estimating SL, is more convenient for practical purposes than the complex formulation of GEP.Implementation of Soft Computing Techniques in Forecasting Compressive Strength and Permeability of Pervious Concrete Blended with Ground Granulated Blast-furnace Slag
https://www.jsoftcivil.com/article_172918.html
Urban expansion and infrastructure development have exacerbated environmental issues by creating impermeable layers on the earth's surface, resulting in flash floods and reduced groundwater levels. These problems can be alleviated by using pervious concrete to enhance pavement drainage capacities. However, pervious concrete has limited applications due to its lower strength properties, which are attributed to its mix proportions featuring minimal fine aggregate quantities and an open-graded mix. This study examines the impact of incorporating Ground Granulated Blast-furnace Slag (GGBS) as a supplementary cementitious material in pervious concrete on its strength, drainage capabilities, and water absorption. Further, Artificial Neural Networks (ANN) were used to predict the mechanical and permeability properties of pervious concrete mixes with varying GGBS proportions. The study's results indicate that using GGBS as a 35% partial cement replacement with 10 mm aggregates significantly increases compressive and flexural strength by 28% and 20%, respectively. While permeability values were slightly reduced, they remained within acceptable limits for drainage properties. The developed ANN models outperformed the traditional MLR model, serving as a viable substitute logical tool for forecasting strength as well as permeability. Ultimately, adding GGBS to pervious concrete not only enhances strength but also contributes to environmentally friendly construction practices.Developing Soft-Computing Models for Simulating the Maximum Moment of Circular Reinforced Concrete Columns
https://www.jsoftcivil.com/article_175576.html
There has been a significant rise in research using soft-computing techniques to predict critical structural engineering parameters. A variety of models have been designed and implemented to predict crucial elements such as the load-bearing capacity and the mode of failure in reinforced concrete columns. These advancements have made significant contributions to the field of structural engineering, aiding in more accurate and reliable design processes. Despite this progress, a noticeable gap remains in literature. There's a notable lack of comprehensive studies that evaluate and compare the capabilities of various machine learning models in predicting the maximum moment capacity of circular reinforced concrete columns. The present study addresses a gap in the literature by examining and comparing the capabilities of various machine learning models in predicting the ultimate moment capacity of spiral reinforced concrete columns. The main models explored include AdaBoost, Gradient Boosting, and Extreme Gradient Boosting. The R2 value for Histogram-Based Gradient Boosting, Random Forest, and Extremely Randomized Trees models demonstrated high accuracy for testing data at 0.95, 0.96, and 0.95, respectively, indicating their robust performance. Furthermore, the Mean Absolute Error of Gradient Boosting and Extremely Randomized Trees on testing data was the lowest at 36.81 and 35.88 respectively, indicating their precision. This comparative analysis presents a benchmark for understanding the strengths and limitations of each method. These machine learning models have shown the potential to significantly outperform empirical formulations currently used in practice, offering a pathway to more reliable predictions of the ultimate moment capacity of spiral RC columns.Estimation and Optimization of the Hydrostatic Height of Waterway Embankment Using Taguchi-Based Honey Badger Algorithm
https://www.jsoftcivil.com/article_172923.html
The geometric design of a waterway embankment depends on several factors like soil and subsoil properties, loading conditions, geometric constraints, climate &amp; weather conditions, etc. Surface wind velocity (V) and fetch length (F) are two control factors that help to determine the wave height (H) utilizing the Taguchi Factorial design method. A non-linear equation was generated by integrating optimized H with the upstream water pressure (P). In the JAVA environment, a pseudo-code was created to solve the non-linear equation and determine the resulting hydrostatic height ( ) and crest width (b). The calculated &nbsp;and b were validated utilizing the Honey-Badger algorithm by initializing all the control factors along with P. The outcomes from the experimental analysis of Taguchi showcase that lower control factors helped to obtain the maximum &nbsp;along with b for the embankment. As per Analysis of Variance (ANOVA), maximum V was found to be the most significant control factor influencing the determination of H, &nbsp;and b of the earthen embankment. The regression squared (R2) value from the Design of Experiment (DoE) of the Taguchi method was found to be 99.21% which shows that the observed data were well fitted to the developed model for evaluating the contribution of Signal to Noise (S/N) ratio and verify the validity of optimal factor settings through confirmation experiments. The confirmatory test was piloted to check the similarity index between the two methods and the outcomes were found to be nearly similar with an error of 2.62%.