Physics-Informed Neural Networks for Programmable Origami Metamaterials with Controlled Deployment

2025-08-19

AI Summary

Controllable deployment of origami metamaterials faces challenges including nonlinear mechanical complexity, difficulty in regulating multistability, and stringent accuracy requirements for deployment forces. This work proposes a training-data-free physics-informed neural network (PINN) framework that intrinsically embeds the mechanical equilibrium equations of conical Kresling origami into the network architecture, enabling forward prediction of energy landscapes and inverse design of multistable configurations. The method supports full-programmability of the entire energy curve, enabling precise control over stable-state heights and energy barriers; it further extends to hierarchical assembled structures, facilitating layer-by-layer programmable deployment sequencing. Validated via finite-element simulations and physical prototypes, the approach successfully reproduces prescribed deployment sequences and barrier ratios with <5% error. To the best of our knowledge, this is the first demonstration of data-free, mechanism-driven programmable deployment design for origami metamaterials.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Search and Optimization: Metareasoning and Metaheuristics
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Origami-inspired structures provide unprecedented opportunities for creating lightweight, deployable systems with programmable mechanical responses. However, their design remains challenging due to complex nonlinear mechanics, multistability, and the need for precise control of deployment forces. Here, we present a physics-informed neural network (PINN) framework for both forward prediction and inverse design of conical Kresling origami (CKO) without requiring pre-collected training data. By embedding mechanical equilibrium equations directly into the learning process, the model predicts complete energy landscapes with high accuracy while minimizing non-physical artifacts. The inverse design routine specifies both target stable-state heights and separating energy barriers, enabling freeform programming of the entire energy curve. This capability is extended to hierarchical CKO assemblies, where sequential layer-by-layer deployment is achieved through programmed barrier magnitudes. Finite element simulations and experiments on physical prototypes validate the designed deployment sequences and barrier ratios, confirming the robustness of the approach. This work establishes a versatile, data-free route for programming complex mechanical energy landscapes in origami-inspired metamaterials, offering broad potential for deployable aerospace systems, morphing structures, and soft robotic actuators.

Problem

• Predicting energy landscapes of origami structures accurately
• Designing programmable deployment sequences without pre-collected data
• Controlling nonlinear mechanics and multistability in metamaterials

Innovation

• Physics-informed neural network for origami design
• Embedding equilibrium equations into learning process
• Inverse design of energy landscapes without data