No abstract

No abstract

This paper investigates low-velocity impact response of Quasi Isotropic (QI) hybrid carbon/glass fiber reinforced polymer composites with alternate stacking sequences. Cross-ply woven carbon and glass fibers were used as reinforcing materials to fabricate sandwiched and interlayer hybrid composites. For comparison, the laminates containing only-carbon and only-glass fibers were also studied. Drop weight test was used to impact the samples. The images captured by a normal camera demonstrated that localized damages (delamination) existed within plies. The hybrid laminates had smaller load drops, smaller maximum deflection, and higher maximum load compared to the single fiber laminates. In addition, carbon outside interlayer hybrid laminate showed the highest maximum load and energy absorption, showing the significant dependence of the impact performance on hybridization and stacking sequence. It was concluded that a hybrid composite would help improve impact performance of laminated composites compared to non-hybrid composites if they are properly designed.

Nowadays, various machine learning (ML) approaches are widely used in different research areas. However, the need for a large training dataset has restricted the attractiveness of ML techniques for industrial applications, since the preparation of a large dataset is very costly and inefficient. To deal with this limitation, an efficient method is required to fill the gap between industry and research. For this purpose, in this study a transfer learning-based deep neural network (TL-DNN) model was developed to predict the mechanical properties of various graphene reinforced nanocomposites. In this respect, a hybrid multi-layer feedforward DNN was designed, containing one source network and one target network. The source DNN was trained to predict the mechanical properties of graphene/graphene oxide nanocomposites with various matrix types including Al, Cu, PMMA, Si3N4, Al2O3, etc. By transferring the acquired knowledge of the source DNN to the target DNN, the mechanical properties of another material (graphene/epoxy nanocomposite) were estimated with high accuracy level, even with limited number of data samples. It should be mentioned that the optimal values of the network hyperparameters were determined using genetic algorithm (GA), simulated annealing (SA) and particle swarm optimization (PSO) algorithms.

In this study, acoustic emission (AE) monitoring with a Fuzzy C-Means (FCM) clustering is developed to detect the delamination process during quasi-static 3-point bending test on glass/epoxy composite materials. The main fracture mode that should be emphasized and has an effect on the residual strength of composite materials is delamination. The 3-point bending test simulates thrust force due to drilling process without backup plate. In this work, two types of specimen at different layups, woven [0,90] s and unidirectional [0] s, leading to different levels of damage evolution, were studied. Using acoustic emission monitoring can help to detect these fracture mechanisms. The obtained AE signals were classified using FCM. Dependency percentage of damages in each class is different in two specimens. Three parameters (Peak Amplitude, Count, and Average Frequency) were used to validate the FCM based classification. The results show that there is a good agreement with the FCM classification and microscopic observation by SEM.