Soft computing techniques for predicting the properties of raw rice husk concrete bricks using regression-based machine learning approaches

Abstract

In this study, the replacement of raw rice husk, fly ash, and hydrated lime for fine aggregate and cement was evaluated in making raw rice husk-concrete brick. This study optimizes compressive strength, water absorption, and dry density of concrete brick containing recycled aggregates via Response Surface Methodology. The optimized model's accuracy is validated through Artificial Neural Network and Multiple Linear Regression. The Artificial Neural Network model captured the 100 data's variability from RSM optimization as indicated by the high R threshold- (R > 0.9997), (R > 0.99993), (R > 0.99997). Multiple Linear Regression model captured the data's variability the decent R2 threshold confirming- (R2 > 0.9855), (R2 > 0.9768), (R2 > 0.9155). The raw rice husk-concrete brick 28-day compressive strength, water absorption, and density prediction were more accurate when using Response Surface Methodology and Artificial Neural Network compared to Multiple Linear Regression. Lower MAE and RMSE, coupled with higher R2 values, unequivocally indicate the model's superior performance. Additionally, employing sensitivity analysis, the influence of the six input parameters on outcomes was assessed. Machine learning aids efficient prediction of concrete's mechanical properties, conserving time, labor, and resources in civil engineering.

Effects of aggregate sizes on the performance of laterized concrete

“…This analysis aims to uncover trends, relationships, and variations within the data, offering valuable understandings into the performance of the material 75 . The objective of this analysis is to reveal patterns, associations, and fluctuations present in the data, Statistical analysis helps researchers draw meaningful conclusions from experimental data, providing insights into the effects of different factors such as mixture proportions, slump and aggregate sizes on the mechanical strength behavior of laterized concrete and supporting evidence-based decision-making in construction and engineering projects 76 , 77 . The derived experimental results from the mechanical properties evaluation exercise of the laterized concrete with varying sizes of coarse aggregates were tabulated for analysis purposes as presented in Table 5 .…”

Machine learning optimization of bio-sandcrete brick modelling using response surface methodology

“…The preference for a quadratic model within response surface methodology (RSM) is driven by its ability to capture nonlinearity, curvature, and intricate variable interactions, enhancing accuracy in system representation. This selection is critical for precise optimization and prediction 25 . where Y is the predicted response function; β 0 is the intercept; β 1 and β 2 are linear effect coefficients; β 11 and β 22 are quadratic effect coefficients; and β 12 is the interaction effect coefficient.…”

A study on waste PCB fibres reinforced concrete with and without silica fume made from electronic waste

“…All the samples were demolded the next day and cured in water for a period of 28 days. These samples were tested for compression strength, split tension strength, and flexural strength following BIS 1199-1959 standards 37 , 38 .…”