© 2026 SOME RIGHTS RESERVED
The content of this web site is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.0 Germany License.
Journal of Railway Science and Engineering, 23(3), 1442–1454p. (2026) DOI:10.19713/j.cnki.43-1423/u.T20250784
To address the challenge of determining the modal frequency range in existing bridge modal parameter identification methods based on the Fast Bayesian Fast Fourier Transform (FBFFT), an improved FBFFT method (Fast Bayesian Fast Fourier Transform combined with Real-Time DEtection TRansformer v2, RT-FBFFT) is proposed to enable automated modal parameter identification without human intervention. First, acceleration data collected every 10 minutes from the bridge are converted into Power Spectral Density (PSD) and Recurrence Plot (RP). A dataset containing 743 labeled samples is constructed to train the RT-DETRv2 (Real-Time Detection Transformer v2) object detection model. Then, the RT-FBFFT method is developed by integrating the trained RTDETRv2 model into the original FBFFT framework, enabling automatic segmentation of the modal frequency range and completing fully automatic modal parameter identification. Finally, the proposed RT-FBFFT method is applied to both a 6-degree-of-freedom mass-stiffness-damping model and an extra-large-span railway cablestayed bridge for modal parameter identification. Comparative evaluations are conducted on the detection accuracy of each object detection model, the efficiency of various modal identification methods, and the robustness of the proposed model under different environmental conditions. The results demonstrate that the RTDETRv2 model achieves high detection accuracy. The proposed RT-FBFFT model outperforms traditional methods in both accuracy and efficiency, while eliminating the need for manual intervention. The model also exhibits strong robustness, maintaining high recognition accuracy even under high-noise conditions. By integrating the RT-FBFFT model with the Interquartile Range (IQR) method, automatic tracking of modal parameters becomes feasible. This method applies to bridges with varying stiffness and sensor configurations, laying a foundation for early warning strategies based on dynamic performance indicators.
back
© 2026 SOME RIGHTS RESERVED
The content of this web site is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.0 Germany License.
Please note: The abstracts of the bibliography database may underly other copyrights.
Ihr Browser versucht gerade eine Seite aus dem sogenannten Internet auszudrucken. Das Internet ist ein weltweites Netzwerk von Computern, das den Menschen ganz neue Möglichkeiten der Kommunikation bietet.
Da Politiker im Regelfall von neuen Dingen nichts verstehen, halten wir es für notwendig, sie davor zu schützen. Dies ist im beidseitigen Interesse, da unnötige Angstzustände bei Ihnen verhindert werden, ebenso wie es uns vor profilierungs- und machtsüchtigen Politikern schützt.
Sollten Sie der Meinung sein, dass Sie diese Internetseite dennoch sehen sollten, so können Sie jederzeit durch normalen Gebrauch eines Internetbrowsers darauf zugreifen. Dazu sind aber minimale Computerkenntnisse erforderlich. Sollten Sie diese nicht haben, vergessen Sie einfach dieses Internet und lassen uns in Ruhe.
Die Umgehung dieser Ausdrucksperre ist nach §95a UrhG verboten.
Mehr Informationen unter www.politiker-stopp.de.