Intelligent enhancement and identification of pipeline hyperbolic signal in 3D ground penetrating radar data

Concealed pipeline maintenance in aging residential areas faces a key challenge of discrepancies between existing data and reality. Ground-penetrating radar with dense, high-speed 3D monitoring capabilities can provide massive data, but effective analysis is difficult due to the presence of irrelevant information. To accurately extract target information, this paper first proposes a 3D data array block concept, which enhances the feature relevance of target data blocks while expanding the data volume. An energy density window method is also proposed to enhance horizontal cross-sectional pipeline signals. Furthermore, a model named PR3DCNN for pipeline recognition is developed based on 3D convolutional neural networks and residual modules. Experimental results demonstrate that PR3DCNN has a classification accuracy of 0.871 for pipelines. After strengthening with 3D data array blocks and the energy density window, the PR-EDW-B model achieves an accuracy of 0.900, and can also classify the pipeline material and calculate its orientation.