Data-Driven Bridge Weigh-in-Motion

Kawakatsu, Takaya; Aihara, Kenro; Takasu, Atsuhiro; Nagayama, Tomonori; Adachi, Jiro

doi:10.1109/jsen.2023.3283849

Cited by 3 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MiniRocket achieves the best performance for both vehicle sets. For all vehicles, it achieves an R 2 of 0.94 and an MAE of 0.76 m/s, which is slightly better than the 0.86 m/s of Kawakatsu et al [23]. All featurebased methods have comparable results for R 2 and are less effective than MiniRocket.…”

Section: Speedmentioning

confidence: 76%

“…GB has the best R 2 for trucks and is slightly worse than MiniRocket in MSE and MAE. MiniRocket, with an MAE of 1.02 m/s is still only 0.16 m/s worse than Kawakatsu et al [23]. However, they evaluate more data, making their results more robust.…”

Section: Speedmentioning

confidence: 88%

“…They also increase the sequence length of the input data to 20 s. For a 74 m-long steel bridge, they achieve an MAE of 0.92 m/s for speed, and an 0.354 m for axle spacing. The effects of more than one sensor are investigated in [23]. Eleven sensors are used to input different CNN architectures for several bridges, further improving the previous results.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning and Signal Processing for Bridge Traffic Classification with Radar Displacement Time-Series Data

Arnold,

Keller

2024

Infrastructures

View full text Add to dashboard Cite

This paper introduces a novel nothing-on-road (NOR) bridge weigh-in-motion (BWIM) approach with deep learning (DL) and non-invasive ground-based radar (GBR) time-series data. BWIMs allow site-specific structural health monitoring (SHM) but are usually difficult to attach and maintain. GBR measures the bridge deflection contactless. In this study, GBR and an unmanned aerial vehicle (UAV) monitor a two-span bridge in Germany to gather ground-truth data. Based on the UAV data, we determine vehicle type, lane, locus, speed, axle count, and axle spacing for single-presence vehicle crossings. Since displacement is a global response, using peak detection like conventional strain-based BWIMs is challenging. Therefore, we investigate data-driven machine learning approaches to extract the vehicle configurations directly from the displacement data. Despite a small and imbalanced real-world dataset, the proposed approaches classify, e.g., the axle count for trucks with a balanced accuracy of 76.7% satisfyingly. Additionally, we demonstrate that, for the selected bridge, high-frequency vibrations can coincide with axles crossing the junction between the street and the bridge. We evaluate whether filtering approaches via bandpass filtering or wavelet transform can be exploited for axle count and axle spacing identification. Overall, we can show that GBR is a serious contender for BWIM systems.

show abstract

Section: Speedmentioning

confidence: 76%

Section: Speedmentioning

confidence: 88%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation