Get started
Work

Signal Separation of Simulated and Monitored Deflections Based on a Hybrid Bridge System Using the EEMD-GSA-LSSVM Approach

Year: 2025
Type: article
Abstract: Bridge health monitoring (BHM) technology serves as an effective tool in maintaining the bridge safety. However, due to the limited budgets for maintenance of short- and medium-span bridges, BHM cannot be covered widely, although short- and medium-span bridges occupy a large proportion of the global transportation networks. The original signals collected from BHM system are composed of multiple components and cannot be directly used to assess the bridge safety. It is thus important to decompose the monitored data collected from the economical BHM system installed at the short- and medium-span bridges to obtain the dynamic response signal caused by vehicle loads. In this study, photogrammetric photoelectric transducers were used to monitor the deflections of a 170-m span hybrid bridge with spread steel box girders. A signal separation technique based on ensemble empirical mode decomposition (EEMD), least squares support vector machine (LSSVM) and gravitational search algorithm (GSA), named EEMD-GSA-LSSVM, is presented. Simulated mixed signals from the finite element model are used to first examine the effectiveness of the mixed EEMD-GSA-LSSVM approach, and it has been demonstrated that the mixed approach is superior to individual algorithms in terms of signal separation. The proposed method is finally applied to the actual single-day and multi-day monitoring signals of the novel hybrid bridge in situ. Results showed that the mixed algorithm successfully separates temperature-related component and the noise signals from source signals, obtaining dynamic deflections induced only by vehicle loads.
DOI: 10.1061/jbenf2.beeng-7128
Language: English
Open Access status: green
OpenAlex ID: W4407155671
FWCI: 1.124
Cites: 74
Cited by: 3
Related to: 10