An advanced resin reaction modeling using data-driven and digital twin techniques
Abstract
Elium® resin is nowadays actively investigated to leverage its recycling ability. Thus, multiple polymerization modeling are developed and used. In this work, we investigate the polymerization of Elium®/Carbon fiber composite in a cylindrical deposition, followed by an in-oven heating. The model parameters are optimized using an active-set algorithm to match the experimental heating profiles. Moreover, the simulation efforts are coupled to an artificial intelligence modeling of the discrepancies. For instance, a surrogate model using convolution recurrent neural network is trained to reproduce the error of the simulation. Later, a digital twin of the process is built by coupling the simulation and the machine learning algorithm. The obtained results show a good match of the experimental results even on the testing sets, never used during the training of the surrogate model. Finally, the digital twin results are post-processes to investigate the resin polymerization through the thickness of the part.