Within a structural health monitoring (SHM) framework, we propose a simulation-based classification strategy to move towards online damage localization. The procedure combines parametric Model Order Reduction (MOR) techniques and Fully Convolutional Networks (FCNs) to analyze raw vibration measurements recorded on the monitored structure. First, a dataset of possible structural responses under varying operational conditions is built through a physics-based model, allowing for a finite set of predefined damage scenarios. Then, the dataset is used for the offline training of the FCN. Because of the extremely large number of model evaluations required by the dataset construction, MOR techniques are employed to reduce the computational burden. The trained classifier is shown to be able to map unseen vibrational recordings, e.g. collected on-the-fly from sensors placed on the structure, to the actual damage state, thus providing information concerning the presence and also the location of damage. The proposed strategy has been validated by means of two case studies, concerning a 2D portal frame and a 3D portal frame railway bridge; MOR techniques have allowed us to respectively speed up the analyses about 30 and 420 times. For both the case studies, after training the classifier has attained an accuracy larger than $85\%$.

在结构健康监测 (SHM) 框架内，我们提出了一种基于模拟的分类策略，以实现在线损伤定位。该程序结合了参数模型降阶 (MOR) 技术和全卷积网络 (FCN) 来分析记录在受监控结构上的原始振动测量值。首先，在不同操作条件下可能的结构响应数据集是通过基于物理的模型构建的，允许有限的一组预定义损坏场景。然后，该数据集用于 FCN 的离线训练。由于数据集构建需要大量的模型评估，因此采用 MOR 技术来减少计算负担。训练有素的分类器能够映射看不见的振动记录，例如，从放置在结构上的传感器实时收集到实际损坏状态，从而提供有关损坏存在和位置的信息。所提出的策略已通过两个案例研究得到验证，涉及 2D 门式框架和 3D 门式框架铁路桥；MOR 技术使我们能够分别将分析速度提高约 30 倍和 420 倍。对于这两个案例研究，在训练分类器后，分类器的准确度大于$85\%$.