Recent developments in artificial neural networks (ANN) have opened up new possibilities in the domain of structural engineering. For inverse problems like structural identification of large civil engineering structures such as bridges and buildings where the in situ measured data are expected to be imprecise and often incomplete, the ANN holds greater promise. The detection of structural damage and identification of damaged element in a large complex structure is a challenging task indeed. This paper presents an application of multilayer perceptron in the damage detection of steel bridge structures. The issues relating to the design of network and learning paradigm are addressed and network architectures have been developed with reference to trussed bridge structures. The training patterns are generated for multiple damaged zones in a structure and performance of the networks with one and two hidden layers are examined. It has been observed that the performance of the network with two hidden layers was better than that of a single-layer architecture in general. The engineering importance of the whole exercise is demonstrated from the fact that measured input at only a few locations in the structure is needed in the identification process using the ANN.NOTATIONn number of input nodesm number of hidden nodesp number of output nodesi 1, nj 1, mk 1, p{X i } training input vector[W j i ] weights between input and hidden layer{out j } activation values for the hidden nodes[W k j ] weights between hidden and output layer{o k } activation values for the output nodes or output vector[ΔW k j ] error in weights between hidden and output nodesη learning parameter, here 0.9{t k } target output vectorα momentum parameter, here 0.7[Δ p W k j ] error [ΔW k j ] in previous pass[ΔW j i ] error in weights between input and hidden nodes[Δ p W j i ] error [ΔW j i ] in previous passP total number of samplesE average system errorθ j threshold or bias parameterθ 0 parameter for shape of the sigmoid function