This paper presents a novel method for estimating the seismic peak interstory drift ratio (IDR) in reinforced concrete (RC) columns after an earthquake using surface crack image analysis. The quantitative representation of the complexity and irregularity of crack images in damaged RC columns is obtained through the consideration of the generalized fractal dimensions. The authors have compiled a comprehensive database consisting of 445 crack maps obtained from cyclic experiments conducted on 110 rectangular RC column specimens exhibiting double-curvature deformation mode. This database is utilized by the authors to develop and validate the proposed procedure. The research database contains a wide range of structural and geometric features. Five closed-form equations are developed with the objective of estimating the peak IDR experienced by the RC columns during a seismic event. The predictive equations are derived through the utilization of symbolic regression technique, with the input parameters varying according to the availability of columns characteristic parameters. Results reveal that generalized fractal dimensions, especially D₋₁, are strong vision-based indicator of damage in RC columns having correlation coefficients with IDR ranging from 0.82 to 0.92 across the considered plans. The seismic peak IDR obtained through the empirical equations can serve as the input engineering demand parameter (EDP) in the seismic loss estimation frameworks. This allows for the determination of the probability of exceeding damage states for structural and nonstructural components of concrete buildings. Finally, the practical implementation of the methodology is examined by its application to an actual case of a damaged column during the Kermanshah earthquake of magnitude 7.3 that occurred in 2017.

中文翻译：

---

基于机器视觉的钢筋混凝土柱地震诱发位移比自动化量化

本文提出了一种利用表面裂纹图像分析来估计地震后钢筋混凝土 (RC) 柱的地震峰值层间位移比 (IDR) 的新方法。通过考虑广义分形维数，获得了受损钢筋混凝土柱裂纹图像的复杂性和不规则性的定量表示。作者编制了一个综合数据库，其中包含 445 个裂纹图，这些裂纹图是通过对 110 个具有双曲率变形模式的矩形 RC 柱样本进行循环实验而获得的。作者利用该数据库来开发和验证所提出的程序。研究数据库包含广泛的结构和几何特征。开发了五个封闭式方程，目的是估计地震事件期间 RC 柱所经历的峰值 IDR。预测方程是通过利用符号回归技术得出的，输入参数根据列特征参数的可用性而变化。结果表明，广义分形维数，尤其是D _-1，是基于视觉的 RC 柱损坏的强有力的指标，在​​所考虑的计划中与 IDR 的相关系数在 0.82 到 0.92 之间。通过经验方程获得的地震峰值IDR可以作为地震损失估计框架中的输入工程需求参数（EDP）。这可以确定混凝土建筑物的结构和非结构部件超出损坏状态的概率。最后，通过将其应用于 2017 年发生的 7.3 级克尔曼沙赫地震中受损柱的实际案例来检验该方法的实际实施情况。