Model-driven structural seismic response reconstruction and parameter identification based on machine learning

Pan Liu

doi:10.1016/j.engstruct.2026.122890

Model-driven structural seismic response reconstruction and parameter identification based on machine learning

2026-05-05

0

PRE

AI

DOI：10.1016/j.engstruct.2026.122890

Original

Original request for help

Save

Abstract

En 中文

• A unified framework for seismic response reconstruction is proposed and validated. • Adaptive denoising is proposed to improve measured acceleration data quality. • Heuristic optimization efficiency is significantly enhanced with surrogate models. • Transfer learning is employed to improve accuracy without sacrificing efficiency.

Keywords:

seismic response reconstruction

adaptive denoising

surrogate models

transfer learning

parameter identification

Model-driven structural seismic response reconstruction and parameter identification based on machine learning

Abstract

Journal

Organization

Cited Papers