Generative Adversarial Networks for geometric surfaces prediction in injection molding

TL;DR

This paper explores using GANs, specifically pix2pix, to predict the final geometry of injection-molded parts from thermographic images of hot parts, enabling better process control.

Contribution

It introduces a novel approach combining GANs with Discrete Modal Decomposition to analyze and predict surface geometries from limited thermographic data.

Findings

GANs can effectively translate thermography to geometry.

DMD provides a geometric analysis of surface predictions.

Prediction performance varies with image similarity metrics.

Abstract

Geometrical and appearance quality requirements set the limits of the current industrial performance in injection molding. To guarantee the product's quality, it is necessary to adjust the process settings in a closed loop. Those adjustments cannot rely on the final quality because a part takes days to be geometrically stable. Thus, the final part geometry must be predicted from measurements on hot parts. In this paper, we use recent success of Generative Adversarial Networks (GAN) with the pix2pix network architecture to predict the final part geometry, using only hot parts thermographic images, measured right after production. Our dataset is really small, and the GAN learns to translate thermography to geometry. We firstly study prediction performances using different image similarity comparison algorithms. Moreover, we introduce the innovative use of Discrete Modal Decomposition (DMD) to analyze network predictions. The DMD is a geometrical parameterization technique using a modal space projection to geometrically describe surfaces. We study GAN performances to retrieve geometrical parameterization of surfaces.