PNAS Nexus · 2024 · 11 citations · 47 references
Natural SciencesMaterials EngineeringMaterials ScienceComputational MechanicsMachine LearningOptimizationComposite Structure AnalysisDeep LearningMaterial ModelingOptimization For Machine LearningOptimization In MechanicsPartial Differential EquationsComputational Design ExplorationComputational Material DesignComputational Structural MechanicsInitializationOptimization AlgorithmsPhysics-informed ModelingPhysics-informed OptimizationPretraining
Numerical solutions to partial differential equations (PDEs) are instrumental for material structural design where extensive data screening is needed. However, traditional numerical methods demand significant computational resources, highlighting the need for innovative optimization algorithms to streamline design exploration. Direct gradient-based optimization algorithms, while effective, rely on design initialization and require complex, problem-specific sensitivity derivations. The advent of machine learning offers a promising alternative to handling large parameter spaces. To further mitigate data dependency, researchers have developed physics-informed neural networks (PINNs) to learn directly from PDEs. However, the intrinsic continuity requirement of PINNs restricts their application in structural mechanics problems, especially for composite materials. Our work addresses this discontinuity issue by substituting the PDE residual with a weak formulation in the physics-informed training process. The proposed approach is exemplified in modeling digital materials, which are mathematical representations of complex composites that possess extreme structural discontinuity. This article also introduces an interactive process that integrates physics-informed loss with design objectives, eliminating the need for pretrained surrogate models or analytical sensitivity derivations. The results demonstrate that our approach can preserve the physical accuracy in data-free material surrogate modeling but also accelerates the direct optimization process without model pretraining.
47
Maziar Raissi, Paris Perdikaris, George Em Karniadakis · Journal of Computational Physics · 2018 · 16.9K citations · Full text
Machine learning on big data: Opportunities and challenges
Lina Zhou, Shimei Pan, Jianwu Wang et al. · Neurocomputing · 2017 · 1.2K citations · Full text
Topology optimization of continuum structures: A review*
H. Eschenauer, Niels Olhoff · Applied Mechanics Reviews · 2001 · 1.1K citations