Machine-Learning Based Prediction Model for Identifying Torsion-Induced Seismic Response Amplification in Plan-Asymmetric Buildings

Aug 4, 2026

Upload by Oliver

Torsion-induced seismic response amplification poses major challenges in the structural design of plan-asymmetric buildings. Code-based seismic design methods relying on elastic analyses cannot capture torsional risks that intensify after yielding, where nonlinear dynamic assessment becomes impractical for routine engineering. This work proposes a machine-learning approach to rapidly identify the “hump” in drift demand ratio once yield is exceeded. Parametric nonlinear studies of single-storey wall systems support three hump categories and enable preliminary-stage risk-aware optimization.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Abstract

Introduction

Torsion effects in plan-asymmetric buildings

Limitations of code-based elastic procedures

Drift demand ratio hump in post-yield response

University of Dundee Machine-Learning Based Prediction Model for Identifying Torsion-Induced Seismic Response Amplification in Plan-Asymmetric Buildings Hu, Yao; Lumantarna, Elisa; Lam, Nelson; Tsang, Hing Ho Published in: Proceedings of the 26th Australasian Conference on the Mechanics of Structures and Materials-ACMSM26 DOI: 10. 1007/978-981-97-3397-2_51 Publication date: 2024 Document Version Peer reviewed version Link to publication in Discovery Research Portal Citation for published version (APA): Hu, Y. , Lumantarna, E. , Lam, N. , & Tsang, H. H. (2024) . Machine-Learning Based Prediction Model for Identifying Torsion-Induced Seismic Response Amplification in Plan-Asymmetric Buildings. In N. Chouw, & C. Zhang (Eds. ), Proceedings of the 26th Australasian Conference on the Mechanics of Structures and MaterialsACMSM26: ACMSM26, 3–6 December 2023, Auckland, New Zealand (1 ed. , pp. 593-604) . (Lecture Notes in Civil Engineering; Vol. 513 LNCE) . Springer Singapore. [https://doi.org/10.1007/978-981-97-3397-2_51](https://doi.org/10.1007/978-981-97-3397-2_51) General rights Copyright and moral rights for the publications made accessible in Discovery Research Portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. Take down policy If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim. Download date: 03. Aug. 2026 Machine-learning based Prediction Model for Identifying Torsion-induced Seismic Response Amplification in Plan-asymmetric Buildings Yao Hu1,*, Elisa Lumantarna1, Nelson Lam1, and Hing-Ho Tsang2 1 Department of Infrastructure Engineering, The University of Melbourne, Melbourne, Australia; 2 School of Engineering, Swinburne University of Technology, Melbourne, Australia; [Emails](Emails: yaoh4@student.unimelb.edu.au)[:](Emails: yaoh4@student.unimelb.edu.au)[ yaoh4@student.unimelb.edu.au](Emails: yaoh4@student.unimelb.edu.au), [elu@unimelb.edu.au](elu@unimelb.edu.au), [ntkl@unimelb.edu.au](ntkl@unimelb.edu.au), [htsang@swin.edu.au](htsang@swin.edu.au) Abstract. Torsion-induced seismic response amplification in plan-asymmetric buildings is of major concern in structural design. Code-based seismic design procedures based on elastic analyses do not address potential seismic risks that are aggravated by torsional actions. Implementing rigorous nonlinear dynamic analysis to guide the design of buildings featuring plan asymmetry is costly and not practical for day-to-day structural engineering practices. This paper presents a machine learning based methodology to identify a building that may experience the stepped increase in the drift demand ratio (i.e. hump) when the yield limit of the lateral load-resisting elements has been exceeded. Parametric studies based on nonlinear dynamic analysis of single-storey buildings with structural walls in varying number, size and position were undertaken to examine the effect of system parameters on hump that may occur in the post yield conditions. Buildings were divided into three categories including no hump, slight hump and large hump by assessing the increase in the inelastic drift demand ratio in comparison to the elastic drift demand ratio. Machine learning based prediction models have been developed to achieve a rapid identification of hump in a building based on dynamic analysis results of various singlestorey buildings. The models can be an effective tool for optimising the design of plan asymmetric buildings by identifying the potential seismic risks posed by torsional action at the preliminary design stage. Keywords: seismic response amplification, machine learning, nonlinear dynamic analysis, drift demand ratio, torsional behaviour 1 INTRODUCTION Buildings featuring plan as

FAQs

Why do plan-asymmetric buildings require attention to torsion-induced seismic response amplification?

They experience additional seismic demand from torsion compared with symmetric configurations, which can amplify earthquake damage risk.

What limitation does this paper address in code-based seismic design?

Elastic-analysis-based code procedures may miss torsional risks that become more severe in the inelastic post-yield range.

How does the proposed machine-learning method identify the “hump” in drift demand ratio?

It uses results from nonlinear dynamic analyses of single-storey wall systems and classifies buildings into no-hump, slight-hump, or large-hump categories to enable rapid prediction.

Aug 4, 2026

Upload by Oliver