Statistical modelling of coating layer thickness distributions: Influence of overspray on coating quality

Self-Attention-Augmented Generative Adversarial Networks for Data-Driven Modeling of Nanoscale Coating Manufacturing

Nanoscale coating manufacturing (NCM) process modeling is an important way to monitor and modulate coating quality. The multivariable prediction of coated film and the data augmentation of the NCM process are two common issues in smart factories. However, there has not been an artificial intelligence model to solve these two problems simultaneously. Focusing on the two problems, a novel auxiliary regression using a self-attention-augmented generative adversarial network (AR-SAGAN) is proposed in this paper. This model deals with the problem of NCM process modeling with three steps. First, the AR-SAGAN structure was established and composed of a generator, feature extractor, discriminator, and regressor. Second, the nanoscale coating quality was estimated by putting online control parameters into the feature extractor and regressor. Third, the control parameters in the recipes were generated using preset parameters and target quality. Finally, the proposed method was verified by the experiments of a solar cell antireflection coating dataset, the results of which showed that our method performs excellently for both multivariable quality prediction and data augmentation. The mean squared error of the predicted thickness was about 1.6~2.1 nm, which is lower than other traditional methods.

Modeling the coating layer thickness in a pharmaceutical coating process

Although mechanistic numerical simulations can offer great insights into a process, they are limited with respect to resolved process time. While statistical models provide long-term predictability, determining the underlying probability distributions is often challenging. In this work, detailed CFD-DEM simulations of a pharmaceutical Wurster coating process for microspheres are used to evaluate the input parameters for a novel Monte-Carlo simulation approach. The combined strengths of both modeling approaches make it possible to predict the coating mass and thickness distributions over the entire process time. It was observed that smaller beads receive a thicker coating layer since they pass the spray zone closer to the nozzle. Moreover, it was established that, in contrast to the airflow rate, the spray rate has a great impact on the inter-particle coating variability. A stochastic model was developed to investigate the relative contribution of coating layer variability and fill weight variability to the product non-uniformity in a capsule filling process of Multiple Unit Pellet Systems (MUPS).

Novel Synthesis of Core-Shell Biomaterials from Polymeric Filaments with a Bioceramic Coating for Biomedical Applications

Bone tissue engineering is constantly in need of new material development with improved biocompatibility or mechanical features closer to those of natural bone. Other important factors are the sustainability, cost, and origin of the natural precursors involved in the technological process. This study focused on two widely used polymers in tissue engineering, namely polylactic acid (PLA) and thermoplastic polyurethane (TPU), as well as bovine-bone-derived hydroxyapatite (HA) for the manufacturing of core-shell structures. In order to embed the ceramic particles on the polymeric filaments surface, the materials were introduced in an electrical oven at various temperatures and exposure times and under various pressing forces. The obtained core-shell structures were characterized in terms of morphology and composition, and a pull-out test was used to demonstrate the particles adhesion on the polymeric filaments structure. Thermal properties (modulated temperature and exposure time) and the pressing force’s influence upon HA particles’ insertion degree were evaluated. More to the point, the form variation factor and the mass variation led to the optimal technological parameters for the synthesis of core-shell materials for prospect additive manufacturing and regenerative medicine applications.