A novel boundary integrated neural networks for in plane fracture mechanics analysis of elastic and piezoelectric materials

2025-02-28

AI Summary

This work addresses the challenge of accurately and efficiently modeling crack-tip singular fields in in-plane fracture problems of elastic and piezoelectric materials. We propose Boundary-Integrated Neural Networks (BINNs), which tightly couple boundary integral equations with physics-informed neural networks. A key innovation is the introduction of Specialized Crack-Tip Neural Networks (SPNNs) that explicitly embed asymptotic singularity priors—supporting variable-order singularities to accommodate diverse crack geometries. By leveraging boundary dimensionality reduction and designing an asymptotic-field-constrained loss function, BINNs achieve high-accuracy prediction of stress intensity factors (SIFs) on coarse meshes, with errors below 1.2%. The method significantly outperforms conventional finite element and boundary element methods in computational efficiency while demonstrating strong robustness and generalization capability across heterogeneous material systems and crack configurations.

Technology Category

Cognitive Modeling & Cognitive Systems: Neural Spike CodingMachine Learning: Deep Neural Architectures and Foundation ModelsIntelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsSystems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applicationsSocial Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

In this study, we propose a novel approach, termed boundary integrated neural networks (BINNs), for analyzing in-plane crack problems within the framework of linear elastic fracture mechanics. The proposed approach integrates artificial neural networks (ANNs) with classical boundary integral equations (BIEs), enabling an efficient and accurate evaluation of partial differential equations (PDEs) associated with fracture mechanics. Additionally, novel special ANN-based crack-tip elements, the Special crack-tip Neural Networks(SPNNs) are developed to improve the modeling of displacement and stress fields in regions near crack tips. These specialized elements integrate the asymptotic characteristics of fracture mechanics into the neural network framework, ensuring enhanced accuracy in capturing the intricate singularities and steep gradients near the crack tips. Compared to conventional simulation tools in fracture mechanics, the present method offers several distinct advantages. First, by embedding higher-order fracture mechanics principles into the neural networks, the method achieves a more accurate and reliable representation of the near-tip fields, even when using relatively large crack-tip elements. Second, the SPNNs, which incorporates information about varying near-tip singularity orders, improve the method's versatility in solving problems involving complex and diverse crack-tips geometries. Moreover, the method demonstrates excellent computational efficiency due to the dimensionality reduction achieved by employing BIEs. Numerical experiments confirm that the proposed framework serves as a reliable, robust, and accurate tool for addressing fracture mechanics problems, offering substantial advantages over conventional numerical approaches.

Problem

• Develops boundary integrated neural networks for fracture mechanics analysis.
• Improves accuracy in modeling near-crack-tip stress and displacement fields.
• Enhances computational efficiency using boundary integral equations.

Innovation

• Integrates neural networks with boundary integral equations
• Develops special ANN-based crack-tip elements
• Enhances accuracy in modeling near-tip fields