Technical gazette, Vol. 31 No. 3, 2024.
Original scientific paper
https://doi.org/10.17559/TV-20240104001243
Research on Damage Detection of Civil Structures Based on Machine Learning of Multiple Vegetation Index Time Series
Jianling Tan
; School of Water Conservancy Engineering, Yellow River Conservancy Technical Institute， Kaifeng, 475004, China
*
Xuejing Zhang
; School of Water Conservancy Engineering, Yellow River Conservancy Technical Institute， Kaifeng, 475004, China
Dan Li
; School of Civil Engineering and Transportation Engineering, Yellow River Conservancy Technical Institute, Kaifeng, 475004, China
Hanzheng Sun
; School of Civil Engineering and Transportation Engineering, Yellow River Conservancy Technical Institute, Kaifeng, 475004, China
* Corresponding author.
Abstract
On the basis of analyzing the natural frequency of the structure, the identification quantity of each process is constructed with modal parameters and input into the machine learning as characteristic parameters to realize the damage identification. By extracting the median curve of vegetation index time series after 5G filtering in the damaged area of typical civil structures, and comparing it with the actual growth curve of crops in the area, the vegetation index time series monitoring model was constructed, and 10 was selected as the best threshold. The accuracy of the result is verified, and the iteration time is 0.18 hours. A damage detection method based on machine learning is proposed. Good prediction results are obtained for three common surface damage of concrete cracks, spalling and exposed steel bars, which verify the ability of this method to accurately identify and detect structural surface damage at pixel level.
Keywords
civil structure damage detection; machine learning; multiple vegetation index time series; structural damage identification
Hrčak ID:
316375
URI
Publication date:
23.4.2024.
Visits: 611 *