Evaluation of Interface Adhesion Strength of Unidirectional CFRP Using Numerical Material Test and Neural Network

When analyzing the fracture behavior of unidirectional carbon fiber-reinforced polymer (CFRP), it is important to consider interfacial strength between reinforcing fiber and base resin, resin. Therefore, adhesiveness material compatibility with sizing fibers are design parameters in development CFRPs. However, a quantitative method for estimating resin has not been established. In this study, we propose evaluate interface CFRPs by creating learning data through series numerical tests constructing neural network that outputs based on homogenization from results off-axis tensile tests. We adopt general feed forward whereby learned employing backpropagation method. The matrix predicted evaluated test demonstrate effectiveness system.