Abstract
In traditional methods for modelling the behaviour of manufacturing processes by using artificial neural networks, design of optimal architecture of these networks needs many trials and errors. Sometimes it may not achieve the best architecture of networks because of the time-consuming and tedious procedure of these methods. In this paper, the failure behaviour of magnesium alloy sheet forming at warm temperature is modelled by using the adaptive neuro-fuzzy inference systems (ANFIS) network. In order to reduce the time of finding the best architecture of ANFIS network, an optimisation algorithm, imperialistic competitive algorithm, was used. By combining this optimisation algorithm with the ANFIS, the best architecture of ANFIS network can be proposed to model the accurate behaviour of the manufacturing process in the least time possible.