Data-Driven Structural Health Monitoring of Short Carbon Fiber-Reinforced Polymer Composites via Multiphysics Phase-Field Simulation

2026-05-24

AI Summary

This study addresses the challenge of simultaneously capturing the anisotropy, rate-dependent fracture behavior, and piezoresistive damage sensing in short carbon fiber–reinforced polymer composites. The authors propose a large-deformation multiphysics phase-field framework that unifies viscoelastic–viscoplastic constitutive modeling, anisotropic crack resistance, and a piezoresistive conduction model, with the fiber orientation tensor coherently characterizing fiber alignment, crack propagation resistance, and electrical conduction pathways. By integrating eight-electrode electrical impedance tomography with a feedforward neural network, the method enables, for the first time, real-time damage inversion without mechanical sensors. Validated on unseen microstructures, the approach achieves R² values of 0.99 in predicting normalized crack length and mechanical compliance, demonstrating exceptional generalization capability and computational efficiency.

Abstract

Short carbon fiber-reinforced polymer (SCFRP) composites exploit the intrinsic conductivity of the carbon fiber network for self-sensing, yet no predictive model couples their anisotropic, rate-dependent fracture to piezoresistive damage identification. This work presents a finite deformation multiphysics phase-field framework coupling a viscoelastic-viscoplastic constitutive model, an anisotropic crack resistance formulation, and a piezoresistive conductivity model. The three sub-problems are unified through the second-order fiber orientation tensor, which simultaneously defines fiber family directions, crack resistance anisotropy, and principal conduction paths of the carbon fiber network. A damage-coupled conductivity tensor captures both strain-driven geometric-kinematic resistance changes and irreversible network severance driven by the phase-field variable. The framework is coupled to an eight-electrode electrical impedance tomography configuration, and the normalized inter-electrode conductance ratios serve as inputs to a feedforward artificial neural network that infers normalized crack length and mechanical compliance without mechanical sensing. The network achieves R2 = 0.99 on held-out configurations, confirming generalization across the microstructure space. The framework establishes a physics-based, computationally efficient route for real-time structural health monitoring and inverse damage assessment in SCFRP composites.

Problem

• structural health monitoring
• short carbon fiber-reinforced polymer composites
• piezoresistive damage identification
• anisotropic fracture
• multiphysics modeling

Innovation

• multiphysics phase-field
• piezoresistive damage sensing
• anisotropic fracture
• electrical impedance tomography
• data-driven structural health monitoring