Univariate Conditional Variational Autoencoder for Morphogenic Patterns Design in Frontal Polymerization-Based Manufacturing

TL;DR

This paper introduces a univariate conditional variational autoencoder (UcVAE) for inverse design in frontal polymerization, enabling the generation of process conditions that produce specific hierarchical patterns in polymeric materials.

Contribution

The work presents a novel UcVAE model that simplifies the encoding process, reduces training complexity, and effectively generates process conditions for desired patterns in FP-based manufacturing.

Findings

UcVAE achieves comparable performance to cVAE with fewer parameters.

The model can generate multiple process solutions for a given pattern.

Training time is significantly reduced compared to traditional cVAE.

Abstract

Under some initial and boundary conditions, the rapid reaction-thermal diffusion process taking place during frontal polymerization (FP) destabilizes the planar mode of front propagation, leading to spatially varying, complex hierarchical patterns in thermoset polymeric materials. Although modern reaction-diffusion models can predict the patterns resulting from unstable FP, the inverse design of patterns, which aims to retrieve process conditions that produce a desired pattern, remains an open challenge due to the non-unique and non-intuitive mapping between process conditions and manufactured patterns. In this work, we propose a probabilistic generative model named univariate conditional variational autoencoder (UcVAE) for the inverse design of hierarchical patterns in FP-based manufacturing. Unlike the cVAE, which encodes both the design space and the design target, the UcVAE encodes only the design space. In the encoder of the UcVAE, the number of training parameters is significantly reduced compared to the cVAE, resulting in a shorter training time while maintaining comparable performance. Given desired pattern images, the trained UcVAE can generate multiple process condition solutions that produce high-fidelity hierarchical patterns.