Quality assessment of porous CFRP specimens using X-ray Computed Tomography data and Artificial Neural Networks

Abstract Despite their extensive use and the quality amelioration, CFRPs remain susceptible to a variety of manufacturing defects such as the pores. Predictive tools capable of correlating the mechanical properties of CFRP parts with the characteristics of defects as derived from NDT techniques or with the manufacturing parameters could serve as an effective tool for the quality control of CFRP structural parts. The present work contributes towards the development of effective quality control tools for composite materials. Within this context, the characteristics of pores, as evaluated by X-ray Computed Tomography (CT), are correlated with the matrix-dominated mechanical properties of unidirectional porous CFRP specimens using an Artificial Neural Network (ANN). The ANN model has been trained by using a multi-scale numerical model. For the training of the ANN, 30 porosity scenarios have been created and given as input to the numerical model. The predictions of the ANN agree very well with results obtained from mechanical tests. Moving one step forward, a second ANN has been developed to correlate the autoclave pressure directly with the mechanical properties of the CFRP specimens. The validity of this ANN depends on the accuracy of the relation between the autoclave pressure and the characteristics of the pores.