Machine Learning for Extracting Features of Approximate Optimal Brace Locations for Steel Frames

A method is presented for extracting features of approximate optimal brace types and locations large-scale steel building frames. The frame subjected to static seismic loads, the maximum stress in members minimized under constraints on number braces each story interstory drift angle. new formulation important from machine learning results using a support vector with radial basis function kernel. nonlinear programming problem be solved finding values components matrix condensing those small-scale so that can extracted frame. It shown numerical examples 24-story are successfully 12-story