Search papers, labs, and topics across Lattice.
This paper introduces an end-to-end computational framework that integrates sparsified physics-augmented neural networks with finite-element-based topology optimization to tackle the challenges of optimizing spatial material distribution in multimaterial 3D printing. By utilizing closed-form, composition-aware hyperelastic constitutive laws derived from experimental data, the framework enables efficient symbolic differentiation and overcomes traditional bottlenecks associated with neural network models. Applied to soft robotic gripper designs, the method achieves continuous optimization of both material composition and macroscopic topology, demonstrating significant advancements in the design process for functionally graded components.
Continuous optimization of material composition and topology in 3D printing could revolutionize the design of soft robotics, enhancing performance and efficiency.
Multimaterial 3D printing enables the fabrication of functionally graded components, but optimizing their spatial material distribution alongside structural topology remains a formidable challenge due to high-dimensional design spaces and complex constitutive modeling. This paper presents an end-to-end computational framework integrating sparsified physics-augmented neural networks with finite-element-based topology optimization. By extracting closed-form, composition-aware hyperelastic constitutive laws from experimental data, this approach facilitates exact symbolic differentiation via the adjoint state method implemented with FEniCSx, efficiently circumventing the bottlenecks of applying neural network constitutive models. This pipeline is deployed on soft robotic gripper applications, demonstrating continuous composition optimization for highly anisotropic contact responses, and the concurrent optimization of macroscopic topology and material distribution under non-failure stretch constraints. This methodology could replace laborious empirical prototyping, establishing interpretable machine-learning models as practical, robust design primitives for advanced multimaterial additive manufacturing.
