Artificial neural network for technical feasibility prediction of seismic retrofitting in existing RC structures

The seismic analysis of reinforced concrete (RC) structures generally requires significant computational effort, which can be challenging or at least time-consuming also for the modern computing systems. Particularly, huge effort is required running optimisation procedures intended selecting “best” retrofitting solution among wide set technical feasible ones. Therefore, this paper proposes use Machine Learning instead mechanistic analyses executed as part an procedure RC existing recently proposed by authors. Specifically, Artificial Neural Network trained and employed a possible substitute finite element rapid accurate assessment relevant performance exhibited enhanced configurations building typology. obtained results demonstrate effectiveness artificial neural network model to approximate in considering several structural configurations. methodology used speed-up search viable strengthening configuration within whole parametric field relevance, subsequently refined using more detailed computationally expensive FE methods.