Constructability-based multi-objective optimization with machine learning-enhanced meta-heuristics for reinforcing bar design in rectangular concrete columns

“

I wanted to make a strong statement here, (first) with a thorough literature review to prove that asymmetrical configurations of reinforcement can ensure acceptable structural efficiency and ductility levels, even under seismic loads. (Second), by proving that with constructability metrics, specifically focused on rebar, quite practical designs can be generated, and still obtaining, at the same time, huge amounts of material savings, in comparison to symmetrical designs. The latter, through multi-objective optimization methods. And (third), that such optimum designs could be generated in seconds, with Machine Learning and Deep Learning models as enhancement for meta-heuristic optimization methods (surrogate multi-objective optimization), with quite acceptable convergence.

”