Designing and manufacturing for concrete structure with construction waste analysis using big data and artificial intelligence

Most widely utilized material in building sector, concrete is recognised as a pollutant to the environment and presents significant obstacles to sustainability in terms of energy use, greenhouse gas emissions, and resource depletion. Therefore, to increase the sustainability of concrete, efforts must be concentrated on reducing the material's negative environmental effects. this research proposes novel technique in computer aided system based concrete structure designing and manufacturing with their construction waste analysis using big data and machine learning model. The aim is to develop concrete structure design based on big data in manufacturing and their waste reduction is carried out using linear stochastic regression based Gaussian gradient vector machine. The sustainability index declines as cement as well as super-plasticizer content are increased in mixture design. Following design of sixteen sustainable mixture proportions, the most inexpensive, environmentally friendly, sustainable, least material-intensive mixtures are compared and presented according to their sustainability indices. The experimental analysis has been carried out in terms of computational cost, design efficiency, training accuracy, reliability, precision. According to the experimental findings, as the ratio of plastic aggregate increases, densities reduce by around 10% and workability rises by approximately 60%. As plastic substitution increases, compressive strength and split tensile strength drop by 14% and 34%.