Width estimation of hidden cracks in tunnel lining based on time-frequency analysis of GPR data and back propagation neural network optimized by genetic algorithm

Hou, Lili; Zhang, Qian; Du, Yanliang

doi:10.1016/j.autcon.2024.105394

Cited by 13 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another methodology, reported in studies 41 , 42 , is lining detection by means of permittivity mapping of structures in the subsurface structures via specialized CNN, and deep neural network models. Also, time frequency domain and its features 43 have been used with neural network for tunnel lining. Yet another approach employing deep neural network architectures 44 has been used to acquire permittivity inversion of geometrical configurations of buried objects.…”

Section: Introductionmentioning

confidence: 99%

Variable data structures and customized deep learning surrogates for computationally efficient and reliable characterization of buried objects

Yurt,

Torpi,

Kizilay

et al. 2024

Sci Rep

View full text Add to dashboard Cite

In this study, in order to characterize the buried object via deep-learning-based surrogate modeling approach, 3-D full-wave electromagnetic simulations of a GPR model have been used. The task is to independently predict characteristic parameters of a buried object of diverse radii allocated at different positions (depth and lateral position) in various dispersive subsurface media. This study has analyzed variable data structures (raw B-scans, extracted features, consecutive A-scans) with respect to computational cost and accuracy of surrogates. The usage of raw B-scan data and the applications for processing steps on B-scan profiles in the context of object characterization incur high computational cost so it can be a challenging issue. The proposed surrogate model referred to as the deep regression network (DRN) is utilized for time frequency spectrogram (TFS) of consecutive A-scans. DRN is developed with the main aim being computationally efficient (about 13 times acceleration) compared to conventional network models using B-scan images (2D data). DRN with TFS is favorably benchmarked to the state-of-the-art regression techniques. The experimental results obtained for the proposed model and second-best model, CNN-1D show mean absolute and relative error rates of 3.6 mm, 11.8 mm and 4.7%, 11.6% respectively. For the sake of supplementary verification under realistic scenarios, it is also applied for scenarios involving noisy data. Furthermore, the proposed surrogate modeling approach is validated using measurement data, which is indicative of suitability of the approach to handle physical measurements as data sources.

show abstract