Prediction of temperature of tubular truss under fire using artificial neural networks

A three-layer Back-Propagation neural network has been developed to predict the limiting temperature of steel planar tubular truss under fire. The input parameters of the network model include the diameter ratio (beta), the wall thickness ratio (tau), the diameter-thickness ratio (gamma) and the load ratio. The output parameters include the limiting temperature. In this paper, the training and testing samples of the neural network were obtained by using the finite element software ABAQUS. 105 sets of data were used to train the Back-Propagation neural network; 15 sets of data were used to test and validate the BP network. In the process of training the Back-Propagation network, the Levenberg-Marquardt Back-Bropagation algorithm was adopted. The 'tansig' function was adopted in the hidden layer, and the 'purelin' function was adopted in the output layer. The results obtained by analyzing show that the prediction of the limiting temperature using the Back-Propagation network model is accurate and effective. (c) 2013 Elsevier Ltd. All rights reserved.