Investigation of framed shearwall behaviour with neural networks

Abstract

To date, concrete structure modelling has involved the development of mathematical models of concrete structure behaviour derived from human observation of and reasoning with, experimental data. An alternative, discussed in this Paper, is to use a computation and knowledge representation paradigm, called neural networks, developed by researchers in connectionism (a sub-jeld of artificial intelligence) to model concrete structure behaviour. m e main benefits in using a neural-network approach are that all behaviour can be represented within a unified environment of a neural network and the network is built directly from experimental data using the self-organizing capabilities of the neural network, i.e. the network is presented with the experimental data and learns the relationships between stresses and strains. Such a strategy has important implications for modelling the behaviour of modern, complex concrete structures. In this Paper, the behaviour of reinforced concrete framed shearwalls is modelled with a back-propagation neural network. Preliminary results of the use of networks to model concrete structure look promising.