发表机构
addressline= Sibley School of Mechanical; Aerospace Engineering, Cornell University , city= Ithaca , state= NY , country= USA; addressline= Department of Aerospace \& Mechanical Engineering, University of Southern California , city= Los Angeles , state= CA , country= USA; addressline= Department of Materials Science; Engineering, Technion - Israel Institute of Technology , city= Haifa , country= Israel; addressline= Pasteur Labs , city= Brooklyn , state= NY , country= USA（; ; ; ; ; ）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对多材料3D打印中优化空间材料分布与结构拓扑的难题，提出将稀疏物理增强神经网络与有限元拓扑优化集成的端到端框架，通过提取本构定律实现精确微分，应用于软机器人抓手，可取代经验原型制作，建立实用的机器学习设计模型。
AI 中文摘要
多材料3D打印能够制造功能梯度部件，但由于高维设计空间和复杂的本构建模，在优化其空间材料分布和结构拓扑方面仍然是一个巨大挑战。本文提出了一个端到端计算框架，将稀疏物理增强神经网络与基于有限元的拓扑优化相结合。通过从实验数据中提取封闭形式、成分感知的超弹性本构定律，该方法借助FEniCSx实现的伴随状态法促进精确符号微分，有效规避应用神经网络本构模型的瓶颈。该流程应用于软机器人抓手应用，展示了针对高度各向异性接触响应的连续成分优化，以及在非失效拉伸约束下宏观拓扑和材料分布的协同优化。这种方法可以取代费力的经验原型制作，将可解释的机器学习模型确立为先进多材料增材制造实用、稳健的设计原语。
英文摘要
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.
