Hybrid machine learning based scale bridging framework for permeability prediction of fibrous structures

2025-02-07

AI Summary

Accurate multiscale permeability prediction for fibrous textile structures suffers from prohibitive computational cost and limited accuracy. Method: This paper proposes a machine learning–driven cross-scale modeling framework. Its core innovations are: (1) a Scale-Bridging Method (SBM) that enables efficient mesoscale permeability prediction based on microscale segment-wise permeability assignments; and (2) a novel dual-scale hybrid solver integrating Physics-Informed Neural Networks (PINNs) with a CFD numerical solver to enhance robustness and generalization under small-data regimes. Results: Experiments show SBM achieves accuracy comparable to the fully-resolved model (FRM), with similar error magnitude, yet reduces runtime per instance to 45 minutes—270× faster than FRM—and avoids FRM’s >300 GB memory footprint. The PINN-CFD hybrid solver effectively mitigates generalization errors arising from data scarcity.

Technology Category

• Machine Learning: Scalability of ML Systems
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This study introduces a hybrid machine learning-based scale-bridging framework for predicting the permeability of fibrous textile structures. By addressing the computational challenges inherent to multiscale modeling, the proposed approach evaluates the efficiency and accuracy of different scale-bridging methodologies combining traditional surrogate models and even integrating physics-informed neural networks (PINNs) with numerical solvers, enabling accurate permeability predictions across micro- and mesoscales. Four methodologies were evaluated: Single Scale Method (SSM), Simple Upscaling Method (SUM), Scale-Bridging Method (SBM), and Fully Resolved Model (FRM). SSM, the simplest method, neglects microscale permeability and exhibited permeability values deviating by up to 150% of the FRM model, which was taken as ground truth at an equivalent lower fiber volume content. SUM improved predictions by considering uniform microscale permeability, yielding closer values under similar conditions, but still lacked structural variability. The SBM method, incorporating segment-based microscale permeability assignments, showed significant enhancements, achieving almost equivalent values while maintaining computational efficiency and modeling runtimes of ~45 minutes per simulation. In contrast, FRM, which provides the highest fidelity by fully resolving microscale and mesoscale geometries, required up to 270 times more computational time than SSM, with model files exceeding 300 GB. Additionally, a hybrid dual-scale solver incorporating PINNs has been developed and shows the potential to overcome generalization errors and the problem of data scarcity of the data-driven surrogate approaches. The hybrid framework advances permeability modelling by balancing computational cost and prediction reliability, laying the foundation for further applications in fibrous composite manufacturing.

Problem

• Predict permeability in fibrous textile structures.
• Address multiscale modeling computational challenges.
• Enhance accuracy with hybrid machine learning.

Innovation

• Hybrid machine learning framework
• Physics-informed neural networks
• Scale-bridging methodologies