ARTIFICIAL NEURAL NETWORKS IN PREDICTION OF MECHANICAL-BEHAVIOR OF CONCRETE AT HIGH-TEMPERATURE

The behavior of concrete structures that are exposed to extreme thermo -mechanical loading is an issue of great importance in nuclear enginee ring. The mechanical behavior of concrete at high temperature is non-l inear. The properties that regulate its response are highly temperatur e dependent and extremely complex. In addition, the constituent materi als, e.g. aggregates, influence the response significantly. Attempts h ave been made to trace the stress-strain curve through mathematical mo dels and rheological models. However, it has been difficult to include all the contributing factors in the mathematical model. This paper ex amines a new programming paradigm, artificial neural networks, for the problem. Implementing a feedforward network and backpropagation algor ithm the stress-strain relationship of the material is captured. The n eural networks for the prediction of uniaxial behavior of concrete at high temperature has been presented here. The results of the present i nvestigation are very encouraging. (C) 1997 Elsevier Science S.A.