This study considers the use of artificial neural networks (NN) to predict the ultimate resistance of plate girders subjected to patch loading. The elastoplastic behaviour of web panels of plate girders under patch load is quite complex. This leads to significant errors in various design formulae. The training and testing patterns of the proposed neural network system are based on well established experimental results taken from literature. The trained NN results are compared with the experimental results and proposed formulae and are found to be considerably more accurate. The proposed neural network system presents a maximum error lower than 11%, while existing design formulae errors are over 20%.

Keywords