The method for modeling cyclic stress-strain-curve scatter for an arbitrary selection of the influencing factors using a hybrid neural network is presented. In an example of the measured data it is clear that the suggested method is suitable for describing cyclic stress-strain curves. The main advantage of a hybrid neural network is the neural network's ability to precisely describe the influence of various factors, and their combinations, based on the form and scatter of the cyclic stress-strain-curve families. We will use this method to define needed rheological models in research project.
COBISS.SI-ID: 10954267
Because of the randomness of the environment the shape of measured load spectra can vary considerably and therefore simple distribution functions are frequently not sufficient for their modelling. Thus mixed distribution functions have to be used. The scope of the paper is to investigate the load spectra growth for actual operating conditions and to investigate the modelling and extrapolation of load spectra with algorithm for mixed distribution estimation, REBMIX. In research project a part of load spectra modeled with REBMIX algorithm will be used.
COBISS.SI-ID: 11155483