Biology-inspired algorithms represent a set of various techniques which can be used e.g. in the case of high-nonlinear approximation tasks. In the presented research, this kind of algorithms was utilized to approximate the experimental flow curve dataset of the micro-alloyed manganese-vanadium steel. Two methodically different representatives, namely a genetic algorithm optimization and an artificial neural network approach, were applied for this purpose. In the first case, a genetic-algorithm-optimization technique was used to calculate the material constants of two flow stress models. These models were then applied to describe the flow curves of the examined steel. In the second case, an artificial neural network was assembled, adapted and used to deal with the flow curve approximation issue. Graphical results have showed a high accuracy with respect to both approximation methods. Nevertheless, the following statistical evaluation has revealed a much higher fit in the case of the proposed neural network approach.Keywords: Hot flow curve approximation, genetic algorithm, artificial neural network
© This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.