To make sure the wide applications of ground-penetrating radar(GPR)to railway roadbed inspection
an efficient method for recognizing different signal types gets necessary to overcome the low efficiency and subjectivity of the conventional artificial interpretation. Taking actual GPR data from Datong-Zhungeer railway as the example and analyzing the signals in time-domain and frequency-domain by short-time Fourier transform(STFT)
an appropriate window function with suitable type and length is deduced to obtain a set of time-frequency patterns for classification. The energy distributions in different depths of the patterns coincide with the corresponding ground truth. The classification
which focuses on the sample collection from samples of different signal types
is performed to investigate the clustering result by a selected planar eigenvectors. Compared with the conventional methods
such as the target recognition methods based on Welch algorithm or local energy analysis in time domain
the advantages of STFT for GPR data interpretation are demonstrated.
LI Janxun, ZHENG Junting. Automatic target recognition for ultra-wideband ground-penetrating radar [J]. Chinese Journal of Radio Science, 2007, 20(4): 535-540.
XIE Yongyong, LIAO Hongjian, ZAN Yuewen. Two dimensional forward simulation of railway roadbed disease based on ground penetrating radar technique [J]. Journal of Zhejiang University: Engineering Science, 2005, 44(10): 1907-1911.
昝月稳,章锡元,张安学.铁路路基检查车的研究[J].铁道工程学报, 2007(9): 17-21.
ZAN Yuewen, ZHANG Xiyuan, ZHANG Anxue. Research on railway subgrade inspection car [J]. Journal of Railway Engineering Society, 2007(9): 17-21.
CLARK M, GORDON M, FORDE M C. Issues over high-speed non-invasive monitoring of railway track bed [J]. NDT E International, 2004, 37(2): 131-139.
SILVAST M, LEVOMAKI M, NURMIKOLU A, et al. NDT techniques in railway structure analysis [C/OL]∥Proceedings of the 7th World Congress on Railway Research, Montreal, Canada, June 4-8, 2006. [2011-05-01]. http:∥dspace.cc.tut.fi/dpub/handle/123456789/12987.
ZHANG Yongshan, ZHANG Dan. Ground penetrating radar signal echo analysis of non-stationarity [J]. Electronic Test, 2011(8): 26-28.
AL-QADI I L, LAHOUAR S. Data analysis techniques for GPR used for assessing railroad ballast in high radio-frequency environment [J]. Materials Evaluation Journal, 2010, 63(9): 921-925.
AL-QADI I L, XIE Wei, JONES D L, et al. Development of a time-frequency approach to quantify railroad ballast fouling condition using ultra-wide band ground-penetrating radar data [J]. International Journal of Pavement Engineering, 2010, 11(4): 269-279.
FAN Xinhai, AN Gang, QIU Mianhao. A method of target recognition based on Welch arithmetic [J]. Journal of Test and Measurement Technology, 2001, 15(1): 26-31.
LIAO Lijian, YANG Xin'an, DING Chunlin. Technique for automatic interpretation of GPR images of railroad subgrades [J]. China Civil Engineering Journal, 2009, 42(6): 102-108.