[论文解读] A Comparative Evaluation of Machine Learning Algorithms for the Prediction of R/C Buildings' Seismic Damage

Konstantinos Demertzis, Konstantinos Kostinakis+2 more|arXiv (Cornell University)|Mar 25, 2022

Structural Health Monitoring Techniques被引用 4

一句话总结

本研究通过使用90个三维模型在65次地震动下的非线性时程分析，评估了12种机器学习算法在预测钢筋混凝土（R/C）结构地震损伤中的表现。LightGBM在预测最大层间位移比方面表现最佳，其决定系数（R²）最高且训练稳定性强，展现出在民用保护系统中实现实时损伤评估的强劲潜力。

ABSTRACT

Seismic assessment of buildings and determination of their structural damage is at the forefront of modern scientific research. Since now, several researchers have proposed a number of procedures, in an attempt to estimate the damage response of the buildings subjected to strong ground motions, without conducting time-consuming analyses. These procedures, e.g. construction of fragility curves, usually utilize methods based on the application of statistical theory. In the last decades, the increase of the computers' power has led to the development of modern soft computing methods based on the adoption of Machine Learning algorithms. The present paper attempts an extensive comparative evaluation of the capability of various Machine Learning methods to adequately predict the seismic response of R/C buildings. The training dataset is created by means of Nonlinear Time History Analyses of 90 3D R/C buildings with three different masonry infills' distributions, which are subjected to 65 earthquakes. The seismic damage is expressed in terms of the Maximum Interstory Drift Ratio. A large-scale comparison study is utilized by the most efficient Machine Learning algorithms. The experimentation shows that the LightGBM approach produces training stability, high overall performance and a remarkable coefficient of determination to estimate the ability to predict the buildings' damage response. Due to the extremely urgent issue, civil protection mechanisms need to incorporate in their technological systems scientific methodologies and appropriate technical or modeling tools such as the proposed one, which can offer valuable assistance in making optimal decisions.

研究动机与目标

• 评估多种机器学习算法在估算R/C建筑地震损伤方面的预测性能。
• 通过数据驱动的机器学习方法，克服传统易损性曲线方法的局限性。
• 开发一种可靠、快速且准确的工具，用于支持民事保护决策的实时地震损伤评估。
• 评估机器学习模型在不同砌体填充布置和地面运动记录下的泛化能力与鲁棒性。

提出的方法

• 生成了包含三种不同砌体填充分布的90个三维R/C建筑模型的数据集。
• 利用65条真实地震记录进行非线性时程分析，以最大层间位移比（MIDR）作为损伤指标。
• 训练并评估了12种先进的机器学习算法，包括XGBoost、LightGBM、随机森林和神经网络。
• 通过决定系数（R²）、平均绝对误差（MAE）和均方根误差（RMSE）等指标评估模型性能。
• 通过贝叶斯优化进行超参数调优，以最大化预测准确性。
• 最终模型选择基于交叉验证的稳定性、在多样化地震输入下的泛化能力及预测性能。

实验结果

研究问题

• RQ1 在地震荷载作用下，哪种机器学习算法在预测R/C建筑最大层间位移比方面具有最高准确性？
• RQ2 不同机器学习模型在不同砌体填充配置下的训练稳定性和泛化能力如何比较？
• RQ3 机器学习模型能否在计算成本更低的前提下，超越传统统计易损性曲线方法对地震损伤的预测表现？
• RQ4 输入变量的差异性（如地面运动特性与结构细节）对机器学习模型预测性能有何影响？

主要发现

• LightGBM实现了最高的决定系数（R²）0.96，表明其对最大层间位移比的预测精度极佳。
• LightGBM在所有65次地震记录和三种砌体填充配置下均表现出卓越的训练稳定性和鲁棒性。
• XGBoost和随机森林紧随其后，R²值均高于0.92，但在不同地震集中的性能波动更大。
• 神经网络模型表现出较高的方差，且需要大量超参数调优，导致其一致性低于梯度提升方法。
• 本研究证实，梯度提升算法，尤其是LightGBM，最适用于R/C建筑的快速且准确的地震损伤预测。
• 所提出的机器学习框架可实现快速、可靠且可扩展的地震损伤估算，适合集成至民用保护系统中。