Optimization of Reinforced Concrete Shear Wall by Machine Learning

In the existing work, cost optimization for an R/C structure system was performed by using machine learning. In fetch optimization, the aspects of the shear wall were contemplated as design variables, and the objective was to find the optimal shear wall aspects that keep down the overall cost of the material. The limitations of the structural inflation problem are designed according to the exigencies of the R/C spec stipulation named “IS 456:2000”, IS 13920:1993, and INDIAS Seismic Code, which came into force as IS 1893:1975. Support elements are typically based on the designer's technical knowledge, experience, and intuition. In empirical design implementations, the eventual aspects are usually chosen as one of the bulk appropriate among numerous standard-compliant design choices. Though solely these blueprint alternatives may not be cheap, and the cheapest blueprint could only be apportioned through a more laborious optimization process. An application of the software is also being developed to determine the optimum shear wall dimensions for designing structural systems at a minimal cost. The recommended algorithm trivializes structural costs, including concrete and reinforcement costs, where fetch associated with transport, labor, and shuttering prices are excluded. An 18-story shear wall system in Sikkim, INDIA is a numerical example.