Prediction of influences of size and locations of delamination on dynamic characteristics of laminated composite plate using particle swarm optimization and artificial neural network

Abstract In laminated composite structures, delamination is one of the most common defects. The delamination affects the vibration characteristics of laminates, and thus these indicators can be used to detect the potentially catastrophic failures and measures the health characteristics of laminates. In this study, particle swarm optimization (PSO) and artificial neural network (ANN) are used to optimize and predict the influences of location and size of delamination on the dynamic behavior of composite plates. The classical laminated plate theory adopted principle equation based on the dynamic characteristics of composite laminate has expressed through the finite element method. The delamination behavior of laminate composite plate is modeled by considering delamination at several interfaces with variable sizes and locations. PSO methodology is recommended to optimize the decrease in natural frequency due to the delamination with varying weight fractions under completely clamped edge boundary conditions. Further, an ANN algorithm is proposed for predicting the dynamic responses of the composite plate by considering unknown ranges of parameters such as weight fraction, ply configuration, and different delamination locations.