Multi-Objective Prediction of the Mechanical Properties and Environmental Impact Appraisals of Self-Healing Concrete for Sustainable Structures

Abstract

As the most commonly used construction material, concrete produces extreme amounts of carbon dioxide (CO2) yearly. For this resulting environmental impact on our planet, supplementary materials are being studied daily for their potentials to replace concrete constituents responsible for the environmental damage caused by the use of concrete. Therefore, the production of bio-concrete has been studied by utilizing the environmental and structural benefit of the bacteria, Bacillus subtilis, in concrete. This bio-concrete is known as self-healing concrete (SHC) due to its potential to trigger biochemical processes which heal cracks, reduce porosity, and improve strength of concrete throughout its life span. In this research paper, the life cycle assessment (LCA) based on the environmental impact indices of global warming potential, terrestrial acidification, terrestrial eco-toxicity, freshwater eco-toxicity, marine eco-toxicity, human carcinogenic toxicity, and human non-carcinogenic toxicity of SHC produced with Bacillus subtilis has been evaluated. Secondly, predictive models for the mechanical properties of the concrete, which included compressive (Fc), splitting tensile (Ft), and flexural (Ff) strengths and slump (S), have been studied by using artificial intelligence techniques. The results of the LCA conducted on the multiple data of Bacillus subtilis-based SHC mixes show that the global warming potential of SHC-350 mix (350 kg cement mix) is 18% less pollutant than self-healing geopolymer concrete referred to in the literature study. The more impactful mix in the present study has about 6% more CO2 emissions. In the terrestrial acidification index, the present study shows a 69–75% reduction compared to the literature. The results of the predictive models show that ANN outclassed GEP and EPR in the prediction of Fc, Ft, Ff, and S with minimal error and overall performance.

Evaluating the Compressive Strength of Recycled Aggregate Concrete Using Novel Artificial Neural Network

“…Recently, Artificial intelligence techniques have proven to be effective in providing end users with fairly accurate insights on concrete mechanical properties [48]. Therefore, predictive models based on artificial intelligence methods have been used to predict compressive strength of (RAC) and the effect of mix proportions on its behavior [48,[49][50][51][52][53][54]. In this research paper, a sigmoid activation function has been employed in the intelligent abilities of the ANN to predict the fc of a multiple database for a recycled aggregate concrete (RAC) and propose a closed-form equation for the studied concrete property.…”

Research on the Mechanical and Physical Properties of Basalt Fiber-Reinforced Pervious Concrete

“…Nowadays, various types of concrete gradually appear with the development of the economy, such as pervious concrete, fiber-reinforced concrete, and self-healing concrete [ 1 , 2 , 3 , 4 ]. Among these new types of concrete, pervious concrete has gradually become a research hotspot.…”

Application of Soft-Computing Methods to Evaluate the Compressive Strength of Self-Compacting Concrete

“…In recent decades, machine learning (ML) approaches have emerged as an appealing modelling tool appropriate to a broad array of scientific fields, including materials engineering [ 22 , 23 , 24 , 25 , 26 , 27 ]. These data sets can be used to build an appropriate surrogate model for predetermined model parameters, hence eliminating the need for costly and time-consuming trials [ 28 ].…”