Intelligent composite structures with self-aware functions are preferable for future aircrafts. The real-time location of damaged areas of composites is a key step. In this study, deep transfer learning was used to achieve the real-time location of damaged areas. The sensor network obtained acoustic emission signals from different damaged areas of the aluminum alloy plate. The acoustic emission time-domain signal is transformed into the input image by continuous wavelet transform. The convolutional neural network-based model automatically localized the damaged area by extracting features from the input image. A small amount of composite acoustic emission data was used to fine-tune some network parameters of the basic model through transfer learning. This enabled the model to classify the damaged area of composites. The accuracy of the transfer learning model trained with 900 samples is 96.38%, which is comparable to the accuracy of the model trained directly with 1800 samples; the training time of the former is only 17.68% of that of the latter. The proposed method can be easily adapted to new composite structures using transfer learning and a small dataset, providing a new idea for structural health monitoring.
26 July 2023 in International Journal of Impact Engineering
In this work, the mechanical behavior and energy absorption characteristics of flexible fabric under hypervelocity impact (HVI) were investigated. Basalt fabric, ultra-high molecular weight polyethylene (UHMWPE) fabric, and aluminum alloy (Al) plate were chosen to be the sample materials for their excellent mechanical properties and applicative prospect in spacecraft shielding. HVI experiments had been conducted with the help of a two-stage light-gas gun facility, wherein Al projectile with 3.97 mm diameter was launched at velocities in the range 4.1~4.3 km/s. Impact conditions and areal density were kept constant for all targets. The microstructural damage morphology of fiber post-impact was characterized using a scanning electron microscope (SEM). Analysis results show that a brittle fracture occurred for Basalt fiber during HVI. On the contrary, the ductile fractures with large-scale plastic deformation and apparent thermal softening/melting of the material had happened on the UHMWPE fiber when subjected to a projectile impact. According to the HVI shielding performance and microstructural damage analysis results, it can be inferred that ductile fractures and thermal softening/melting of the material were the prevailing energy absorption behaviors of UHMWPE fabric, which leads to absorbing more impact energy than Basalt fabric and eventually, contributes the superior shielding performance.
20 January 2024 in Microgravity Science and Technology