Machine-Guided Discovery of Acrylate Photopolymer Compositions.

Additive manufacturing (AM) can be advanced by the diverse characteristics offered by thermoplastic and thermoset polymers and the further benefits of copolymerization. However, the availability of suitable polymeric materials for AM is limited and may not always be ideal for specific applications. Additionally, the extensive number of potential monomers and their combinations make experimental determination of resin compositions extremely time-consuming and costly. To overcome these challenges, we develop an active learning (AL) approach to effectively choose compositions in a ternary monomer space ranging from rigid to elastomeric. Our AL algorithm dynamically suggests monomer composition ratios for the subsequent round of testing, allowing us to efficiently build a robust machine learning (ML) model capable of predicting polymer properties, including Young's modulus, peak stress, ultimate strain, and Shore A hardness based on composition while minimizing the number of experiments. As a demonstration of the effectiveness of our approach, we use the ML model to drive material selection for a specific property, namely, Young's modulus. The results indicate that the ML model can be used to select material compositions within at least 10% of a targeted value of Young's modulus. We then use the materials designed by the ML model to 3D print a multimaterial "hand" with soft "skin" and rigid "bones". This work presents a promising tool for enabling informed AM material selection tailored to user specifications and accelerating material discovery using a limited monomer space.

Machine learning-enabled forward prediction and inverse design of 4D-printed active plates.

Shape transformations of active composites (ACs) depend on the spatial distribution of constituent materials. Voxel-level complex material distributions can be encoded by 3D printing, offering enormous freedom for possible shape-change 4D-printed ACs. However, efficiently designing the material distribution to achieve desired 3D shape changes is significantly challenging yet greatly needed. Here, we present an approach that combines machine learning (ML) with both gradient-descent (GD) and evolutionary algorithm (EA) to design AC plates with 3D shape changes. A residual network ML model is developed for the forward shape prediction. A global-subdomain design strategy with ML-GD and ML-EA is then used for the inverse material-distribution design. For a variety of numerically generated target shapes, both ML-GD and ML-EA demonstrate high efficiency. By further combining ML-EA with a normal distance-based loss function, optimized designs are achieved for multiple irregular target shapes. Our approach thus provides a highly efficient tool for the design of 4D-printed active composites.