Seismic Performance Prediction Using MATLAB and ETABS

A student-laptop study that predicts how reinforced-concrete moment-frame buildings perform in an earthquake - peak storey drift, floor acceleration, roof and residual drift and the performance level (Operational, Immediate Occupancy, Life Safety, Collapse Prevention, Collapse). 406 synthetic IS 1893:2016-designed buildings (2-12 storeys, zones II-V, soils I-III) are modelled with a 2-D frame FE model and calibrated storey springs, shaken by 133 synthetic ground motions in 18,324 nonlinear time-history analyses (NLTHA), and an ML surrogate (LightGBM) trained on that database predicts the drift of unseen buildings under unseen earthquakes with test R2 0.975 (log scale) in about 0.1 s. It also gives fragility curves, an IS 1893 drift check against the nonlinear response, and a web app that can confirm any prediction with an exact NLTHA. Honest scope: MATLAB and ETABS are NOT installed on the build computer - the MATLAB .m files, the ETABS .e2k models and the ETABS OAPI scripts were written but NOT run; all numbers come from the Python solvers. The ground motions are synthetic (stochastic model; PEER NGA-West2 needs a login) and the buildings are synthetic.

Category: Civil Engineering / Structural Engineering / Earthquake Engineering / Performance-Based Seismic Design / Machine Learning / MATLAB and ETABS (scripts) with Python

Civil Engineering Project C04 from ProTechSC Academy, with graphical abstract, video demonstration and project guidance.