Modelling of forming limit diagram of perforated commercial pure aluminium sheets using artificial neural network

Abstract

In perforated sheet metal industries, the ability to predict and avoid failures, such as necking, fracture and wrinkling are of great importance. It is important to work within the safe strain region to avoid these failures. The forming limit diagram (FLD) is the most appropriate tool to obtain the safe strain region for every perforated sheet metal in different strain conditions and ratio. Forming limit diagram of perforated sheet metal can be affected by its geometrical features. In this paper, the geometrical features of perforated commercial pure aluminium sheet are correlated with its forming limit diagram. A model based on an artificial neural network (ANN) is introduced to reveal the forming limit diagram of perforated sheet with different geometrical features. This model is a feed forward back propagation neural network (BPNN) with a set of geometrical variables as its inputs and the safe strains as its output. After using experimental data to train and test it, the model was applied to new data for prediction of forming limit diagram.