Data-Driven Modelling for Predicting Crystallization Kinetics in a Polyamide Matrix With Carbon Fibres
Please login to view abstract download link
High-performance applications, for which composite materials are generally conceived, require carefully engineered properties, making it necessary to consider the microstructural features, as they can impact the macroscopic behaviour of the material. Thanks to the advancements in computational capacity, detailed analysis of microstructure images is now possible with data-driven methods. In this work, the crystallinity degree and morphology of a polyamide matrix in the presence of carbon fibres were studied as they have an impact on the mechanical properties of the composite. An optical microscope equipped with a heating stage was employed to obtain high resolution images of the crystallization process, including nucleation and crystal growth rate. These images were then analysed using machine learning to predict the crystallization kinetics of a composite under different thermal profiles that reflect real manufacturing conditions.
