Machine Learning-based Optimum Reinforced Concrete Design for Progressive Collapse

This paper investigated progressive collapse analysis of three-dimensional (3D) reinforced concrete (RC) frames that are optimized for carrying structural loads by introducing a unique simultaneous multi-column removal load path using Machine Learning. The investigation includes formulating an integrated computational framework incorporates self-training machine learning algorithm. algorithm is used to train the largest models 3D RC containing more than 600 structures predict posterior based on trained priors. efficiency was shown conducting comprehensive study optimization and behavior considering seismic loading, alternative due collapse, second order (P–delta) effects. results show proposed ensures system solutions meet both integrity constructability requirements ACI Unified Facilities Criteria.