Skip to main navigation Skip to search Skip to main content

FFformer: A Transformer Architecture for Structural Natural Frequency Estimation from Video Data

  • Yunfan Yang
  • , Rongfeng Deng*
  • , Lin Li
  • , Jianhua Liu
  • *Corresponding author for this work
  • Beijing Institute of Technology
  • Beijing Institute of Technology (Zhuhai)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

To address frequency feature extraction in vibrating structures, this study developed a computer vision-based Transformer architecture incorporating temporal feature learning, designed to acquire modal information from structural vibration sequences and precisely extract frequency-domain characteristics. The proposed framework initially employed optical flow method to capture vibration displacement sequences from video recordings. Subsequently, the frequency-enhanced Transformer processed these temporal signals through seasonal-trend decomposition, followed by spectral analysis of the decomposed vibration components to identify natural frequencies. The architecture integrates specialized frequency feature extraction modules with an attention mechanism that prioritizes spectral characteristics in vibration signals. Operating directly on raw vibration videos as input, the system successfully predicted modal frequencies with high precision. Furthermore, defect simulation experiments demonstrated the learned representations' strong generalization capability across novel vibrating structures. Experimental validation revealed superior performance in both prediction accuracy (95%) and robustness, significantly outperforming conventional frequency analysis methods.

Original languageEnglish
Title of host publication2025 7th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages207-212
Number of pages6
ISBN (Electronic)9798331570170
DOIs
Publication statusPublished - 2025
Externally publishedYes
Event2025 7th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2025 - Xi'an, China
Duration: 28 Nov 2025 → 30 Nov 2025

Publication series

Name2025 7th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2025

Conference

Conference2025 7th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2025
Country/TerritoryChina
CityXi'an
Period28/11/25 → 30/11/25

Keywords

  • Computer vision
  • Frequency-domain feature extraction
  • Modal analysis
  • Optical flow
  • Transformer architecture

Fingerprint

Dive into the research topics of 'FFformer: A Transformer Architecture for Structural Natural Frequency Estimation from Video Data'. Together they form a unique fingerprint.

Cite this