[论文] A Multi-Fidelity Convolutional Autoencoder-Transfer Learning Framework...

论文概要

研究领域: ML 作者: Santosh Kapuria, Abhishek 发布时间: 2026-06-25 arXiv: 2606.27304

中文摘要

基于导波的结构健康监测（GWSHM）利用机载换能器为工程结构的早期损伤诊断提供了巨大潜力。然而，深度学习模型的实际部署常因标记实验数据有限和生成大规模高保真仿真数据集的高计算成本而受阻。本研究提出一种多保真迁移学习框架，将轻量级物理仿真、基于卷积自编码器（CAE）的深度特征学习、前馈神经网络和有限实验测量相结合，用于压电换能器 instrumented 的板状结构中的精确损伤定位和定量化。采用计算高效的一维时域谱元模型生成大规模合成数据集进行预训练，而迁移学习仅使用少量标记数据即可将模型适配到实验领域。基于 CAE 的迁移学习框架在损伤定位精度上显著优于其基于 CNN 的对应方法。模型在损伤定位上实现超过 0.93、在损伤定量化上超过 0.99 的 R2 分数。其泛化能力在未见数据上得到验证，对预训练或微调期间未表征的损伤场景仍保持高预测精度。结果确立了所提框架作为真实 GWSHM 应用中准确、计算高效且实际可行的解决方案。

原文摘要

Guided wave-based structural health monitoring (GWSHM) with onboard transducers offers significant potential for the early diagnosis of damage in engineering structures. However, the practical deployment of deep learning models is often hindered by the limited availability of labelled experimental data and the high computational cost of generating large-scale high-fidelity simulation datasets. This study presents a multifidelity transfer learning framework that integrates lightweight physics-based simulations, convolutional autoencoder (CAE)-based deep feature learning, a feed-forward neural network, and limited experimental measurements for accurate damage localisation and sizing in plate-like structures instrumented with piezoelectric transducers. A computationally efficient one-dimensio...

--- *自动采集于 2026-06-28*

#论文 #arXiv #ML #小凯