Bridging Simulation and Experiment: A Self-Supervised Domain Adaptation Framework for Concrete Damage Classification

TL;DR

This paper introduces a self-supervised domain adaptation framework that combines virtual testing, domain adversarial training, and self-supervised learning to improve concrete damage classification from ultrasonic signals, reducing reliance on labeled experimental data.

Contribution

The study develops a novel framework integrating advanced virtual testing and domain adaptation techniques for accurate concrete damage classification with minimal labeled experimental data.

Findings

Achieved an accuracy of 0.7762 and macro F1 score of 0.7713.

Outperformed baseline and six domain adaptation methods.

Demonstrated robustness and low additional computational cost.

Abstract

Reliable assessment of concrete degradation is critical for ensuring structural safety and longevity of engineering structures. This study proposes a self-supervised domain adaptation framework for robust concrete damage classification using coda wave signals. To support this framework, an advanced virtual testing platform is developed, combining multiscale modeling of concrete degradation with ultrasonic wave propagation simulations. This setup enables the generation of large-scale labeled synthetic data under controlled conditions, reducing the dependency on costly and time-consuming experimental labeling. However, neural networks trained solely on synthetic data often suffer from degraded performance when applied to experimental data due to domain shifts. To bridge this domain gap, the proposed framework integrates domain adversarial training, minimum class confusion loss, and the Bootstrap Your Own Latent (BYOL) strategy. These components work jointly to facilitate effective knowledge transfer from the labeled simulation domain to the unlabeled experimental domain, achieving accurate and reliable damage classification in concrete. Extensive experiments demonstrate that the proposed method achieves notable performance improvements, reaching an accuracy of 0.7762 and a macro F1 score of 0.7713, outperforming both the plain 1D CNN baseline and six representative domain adaptation techniques. Moreover, the method exhibits high robustness across training runs and introduces only minimal additional computational cost. These findings highlight the practical potential of the proposed simulation-driven and label-efficient framework for real-world applications in structural health monitoring.