Design of a short tensile coupon for fiber reinforced plastic using artificial neural networks

Abstract

The measurement of the mechanical properties of Fibre Reinforced Plastic (FRP) material is necessary for numerical structural analysis and design. The mechanical properties of the FRP materials may be determined by specific coupon test methods or by analytical calculation. However, pultruded or moulded FRP components may not possess the dimensions to permit the extraction of standard length coupons. The shape of the short tensile coupon has been established to circumvent this limitation using a Finite Element (FE) representation and Artificial Neural Network (ANN) including the effect of gripping length, coupon shape, width, length and thickness. The FE results have been used for the learning and testing sets of the ANN. The Multi-Layer Perceptron (MLP) has been employed in the modelling of the ANN. The MLP model has been trained using the Scaled Conjugate Gradient Algorithm (SCGA) and tested. The ANN results show that the correlation between targets and outputs are consistent.