Probabilistic seismic design method for high-rise self-centering friction-viscous braced steel moment-resisting frames using the XGBoost-GA algorithm

IF 5.7 1区工程技术 Q1 ENGINEERING, CIVIL

Thin-Walled Structures Pub Date : 2025-05-22 DOI:10.1016/j.tws.2025.113394

Ruizhao Zhu , Tong Guo , Shuling Hu , Tao Wang , Yu Xia , Solomon Tesfamariam

{"title":"Probabilistic seismic design method for high-rise self-centering friction-viscous braced steel moment-resisting frames using the XGBoost-GA algorithm","authors":"Ruizhao Zhu , Tong Guo , Shuling Hu , Tao Wang , Yu Xia , Solomon Tesfamariam","doi":"10.1016/j.tws.2025.113394","DOIUrl":null,"url":null,"abstract":"<div><div>The self-centering friction-viscous device (SC-FVD) is a novel high-performance resilience system reducing the structural peak inter-story drift ratio (PISDR), residual inter-story drift ratio (RISDR), and peak floor acceleration (PFA). This study proposes a design method for high-rise SC-FVD braced steel moment-resisting frames (MRFs) based on the machine learning algorithm, with the performance objectives of the probability of exceeding PISDR, RISDR, and PFA. First, an equivalent multi-degree-of-freedom shear model is established, and a lateral load distribution model is established based on the XGBoost algorithm using hyperparameters optimized by the genetic algorithm (XGBoost-GA algorithm). The probability distribution models of peak inter-story displacement (PISD), residual inter-story displacement (RISD), and PFA ratios are then established, and the influence of design parameters on the probabilistic PISD, RISD, and PFA ratios is studied. Subsequently, a prediction model for the mean and variance of PISD, RISD, and PFA ratios is established using the XGBoost-GA algorithm. Finally, the design method with the probability of exceeding PISDR, RISDR, and PFA as performance objectives is proposed and validated through different height structures with different probability objectives. The results indicate that the revised Eurocode lateral load distribution model results in a more uniform PISDR distribution than the revised ASCE, unrevised Eurocode, and unrevised ASCE lateral load distribution models. The prediction models for the revised Eurocode load distribution model, as well as the mean and variance of the PISD, RISD, and PFA ratios, based on the XGBoost-GA algorithm, are highly accurate, with a determination coefficient of mostly above 0.99. The actual performance of the designed structure is close to the predicted probability performance, with the probability error falling within 10 %, confirming the effectiveness of the design method.</div></div>","PeriodicalId":49435,"journal":{"name":"Thin-Walled Structures","volume":"215 ","pages":"Article 113394"},"PeriodicalIF":5.7000,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Thin-Walled Structures","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0263823125004872","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}

引用次数: 0

Abstract

The self-centering friction-viscous device (SC-FVD) is a novel high-performance resilience system reducing the structural peak inter-story drift ratio (PISDR), residual inter-story drift ratio (RISDR), and peak floor acceleration (PFA). This study proposes a design method for high-rise SC-FVD braced steel moment-resisting frames (MRFs) based on the machine learning algorithm, with the performance objectives of the probability of exceeding PISDR, RISDR, and PFA. First, an equivalent multi-degree-of-freedom shear model is established, and a lateral load distribution model is established based on the XGBoost algorithm using hyperparameters optimized by the genetic algorithm (XGBoost-GA algorithm). The probability distribution models of peak inter-story displacement (PISD), residual inter-story displacement (RISD), and PFA ratios are then established, and the influence of design parameters on the probabilistic PISD, RISD, and PFA ratios is studied. Subsequently, a prediction model for the mean and variance of PISD, RISD, and PFA ratios is established using the XGBoost-GA algorithm. Finally, the design method with the probability of exceeding PISDR, RISDR, and PFA as performance objectives is proposed and validated through different height structures with different probability objectives. The results indicate that the revised Eurocode lateral load distribution model results in a more uniform PISDR distribution than the revised ASCE, unrevised Eurocode, and unrevised ASCE lateral load distribution models. The prediction models for the revised Eurocode load distribution model, as well as the mean and variance of the PISD, RISD, and PFA ratios, based on the XGBoost-GA algorithm, are highly accurate, with a determination coefficient of mostly above 0.99. The actual performance of the designed structure is close to the predicted probability performance, with the probability error falling within 10 %, confirming the effectiveness of the design method.

查看原文本刊更多论文

基于XGBoost-GA算法的高层自定心摩擦-粘性支撑钢抗矩框架概率抗震设计方法

自定心摩擦粘滞装置（SC-FVD）是一种新型的高性能回弹系统，可降低结构峰值层间漂移比（PISDR）、剩余层间漂移比（RISDR）和峰值层加速度（PFA）。本研究提出了一种基于机器学习算法的高层SC-FVD支撑钢抗弯矩框架（MRFs）设计方法，性能目标为超过PISDR、RISDR和PFA的概率。首先，建立了等效多自由度剪切模型，并利用遗传算法优化的超参数（XGBoost- ga算法）建立了基于XGBoost算法的横向荷载分布模型。建立了峰值层间位移（PISD）、剩余层间位移（RISD）和PFA比的概率分布模型，研究了设计参数对概率层间位移（PISD）、剩余层间位移（RISD）和PFA比的影响。随后，利用XGBoost-GA算法建立了PISD、RISD和PFA比率的均值和方差预测模型。最后，提出了以超过PISDR、RISDR和PFA概率为性能目标的设计方法，并通过具有不同概率目标的不同高度结构进行了验证。结果表明，修正后的欧洲规范横向荷载分布模型比修正后的ASCE、未修正的欧洲规范和未修正的ASCE横向荷载分布模型得到更均匀的PISDR分布。修正后的Eurocode负荷分布模型的预测模型，以及基于XGBoost-GA算法的PISD、RISD和PFA比率的均值和方差具有较高的准确性，其决定系数大多在0.99以上。设计结构的实际性能与预测概率性能接近，概率误差在10%以内，验证了设计方法的有效性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Thin-Walled Structures 工程技术-工程：土木

CiteScore

9.60

自引率

20.30%

发文量

801

审稿时长

66 days

期刊介绍： Thin-walled structures comprises an important and growing proportion of engineering construction with areas of application becoming increasingly diverse, ranging from aircraft, bridges, ships and oil rigs to storage vessels, industrial buildings and warehouses. Many factors, including cost and weight economy, new materials and processes and the growth of powerful methods of analysis have contributed to this growth, and led to the need for a journal which concentrates specifically on structures in which problems arise due to the thinness of the walls. This field includes cold– formed sections, plate and shell structures, reinforced plastics structures and aluminium structures, and is of importance in many branches of engineering. The primary criterion for consideration of papers in Thin–Walled Structures is that they must be concerned with thin–walled structures or the basic problems inherent in thin–walled structures. Provided this criterion is satisfied no restriction is placed on the type of construction, material or field of application. Papers on theory, experiment, design, etc., are published and it is expected that many papers will contain aspects of all three.