Experimental and neural networks analysis on elevated-temperature mechanical properties of structural steels

Abstract

This study presents the possibility of using artificial neural network (ANN) for describing and predicting the high temperature mechanical behavior of structural steel. For this reason, a series of steady-state tensile tests were performed on two representative structural steels Q345B and Q460GJ in temperature range of 20 ℃ to 800 ℃, in the forms of steel bars with diameters of 8, 10 and 12 mm. The high-temperature mechanical properties were evaluated and compared, revealing the necessity of a general and reliable prediction model on the elevated-temperature mechanical properties of different structural steels. Furthermore, the experimental results could be well predicted by using the Ramberg-Osgood model only in a limited temperature range. Therefore, the application of back-propagation neuron network (BPNN) was proposed to predict the yield stress and ultimate stress. In order to model flow property, a long short-term memory recurrent neural network (LSTM-RNN) was first adopted in strength of mechanics. Two preprocessing methodologies including one-hot encoding and polynomial feature function were used in the models. The satisfactory agreements indicate that the trained BPNN and LSTM-RNN models are efficient and accurate in predicting the mechanical properties of structural steels.