This article presents a method that enables a finite element (FE) model to remesh itself for updating the geometric changes caused by structural damages, using computer vision (CV) techniques and geometric analyses. Currently, there is no mature automatic approach to utilize the information of structural damage detection (SDD) for structural state awareness. Thus, the purpose of this study is to automate the pipeline from the accomplishment of SDD to numerical analyses for fast structural capacity evaluation. CV techniques are used to determine the shapes and dimensions of both structural components and damages. Geometric analyses are used to develop the algorithms for automatically deleting, generating, and splitting the elements of FE models for updating the geometric changes. Experiments are performed on a plate and a C-shaped steel crossbeam of a bridge to demonstrate the effectiveness of the proposed method and algorithms.

中文翻译：

---

用于更新有限元模型几何的基于计算机视觉的差分重新网格划分

本文提出了一种方法，该方法使有限元 (FE) 模型能够使用计算机视觉 (CV) 技术和几何分析重新划分自身，以更新由结构损坏引起的几何变化。目前，还没有成熟的自动方法来利用结构损伤检测（SDD）的信息进行结构状态感知。因此，本研究的目的是使从 SDD 的完成到快速结构容量评估的数值分析的管道自动化。CV 技术用于确定结构部件和损坏的形状和尺寸。几何分析用于开发自动删除、生成和拆分有限元模型元素以更新几何变化的算法。