volume | PIER Journals

Abstract

Electromagnetic induction (EMI) is a crucial non-destructive testing (NDT) technique for reinforced concrete structures, particularly for detecting and evaluating rebar distribution. However, the presence of multiple factors - including electromagnetic coupling effects from dense rebar arrangements, nonlinear waveform distortion due to rebar height differences, and environmental interference - renders traditional feature extraction methods inadequate for accurately reconstructing the rebar distribution parameters within the concrete cover. To address these challenges, a Sliding Omni-Scale Attention Network (SOSANet) is proposed in this paper. Initially, adaptive sliding window segmentation processes variable-length signals, preventing information distortion from signal truncation or padding. Subsequently, a dual-scale OS-Block architecture is constructed, wherein local small-scale OS-Blocks perform multi-scale feature extraction on the signals within each window. Furthermore, a multi-head attention mechanism and a global large-scale OS-Block are employed to model cross-window feature correlations, enhancing the discrimination of signal aliasing features induced by electromagnetic coupling among rebars. To address complex working conditions, a dataset of 1,740 samples comprising varying rebar quantities, cover thicknesses, spacings, and height differences was constructed. An interval random truncation strategy was employed to simulate scenarios involving incomplete signals. Five-fold cross-validation demonstrated that SOSANet achieves an F1-score of 99.34% for rebar quantity classification under complex working conditions, significantly outperforming 1D-CNN, Transformer, and other mainstream methods. Moreover, SOSANet maintains a high robustness with an F1-score of 99.03% under signal occlusion conditions.

1. Kot, Patryk, Magomed Muradov, Michaela Gkantou, George S. Kamaris, Khalid Hashim, and David Yeboah, "Recent advancements in non-destructive testing techniques for structural health monitoring," Applied Sciences, Vol. 11, No. 6, 2750, 2021.
doi:10.3390/app11062750 Google Scholar

2. Rabi, Musab, Rabee Shamass, and K. A. Cashell, "Structural performance of stainless steel reinforced concrete members: A review," Construction and Building Materials, Vol. 325, 126673, 2022.
doi:10.1016/j.conbuildmat.2022.126673 Google Scholar

3. Li, Bo, Yonghui Zhao, Ruiqing Shen, Wenda Bi, Shufan Hu, and Hai Huang, "Application of GPR in rebar detection of building structures," IOP Conference Series: Earth and Environmental Science, Vol. 660, No. 1, 012022, 2021.
doi:10.1088/1755-1315/660/1/012022

4. Sadowski, Łukasz, "Non-destructive testing for building evaluation," Buildings, Vol. 12, No. 7, 1030, 2022.
doi:10.3390/buildings12071030 Google Scholar

5. Drobiec, Łukasz, Radosław Jasiński, and Wojciech Mazur, "Accuracy of eddy-current and radar methods used in reinforcement detection," Materials, Vol. 12, No. 7, 1168, 2019.
doi:10.3390/ma12071168 Google Scholar

6. Liu, Huan, Changfeng Zhao, Yihao Liu, Haobin Dong, Jian Ge, and Zheng Liu, "Enhanced magnetic imaging for industrial metal workpiece detection through the combination of electromagnetic induction and magnetic anomalies," IEEE Transactions on Instrumentation and Measurement, Vol. 71, 1-9, 2022.
doi:10.1109/tim.2022.3191722 Google Scholar

7. Elson, Lucy, Adil Meraki, Lucas M. Rushton, Tadas Pyragius, and Kasper Jensen, "Detection and characterisation of conductive objects using electromagnetic induction and a fluxgate magnetometer," Sensors, Vol. 22, No. 16, 5934, 2022.
doi:10.3390/s22165934 Google Scholar

8. García-Martín, Javier, Jaime Gómez-Gil, and Ernesto Vázquez-Sánchez, "Non-destructive techniques based on eddy current testing," Sensors, Vol. 11, No. 3, 2525-2565, 2011.
doi:10.3390/s110302525 Google Scholar

9. Vidyaratne, Lasitha S., Mahbubul Alam, Alexander M. Glandon, Anna Shabalina, Chris Tennant, and Khan M. Iftekharuddin, "Deep cellular recurrent network for efficient analysis of time-series data with spatial information," IEEE Transactions on Neural Networks and Learning Systems, Vol. 33, No. 11, 6215-6225, 2022.
doi:10.1109/tnnls.2021.3072885 Google Scholar

10. Moritz, Niko, Takaaki Hori, and Jonathan Le, "Streaming automatic speech recognition with the transformer model," ICASSP 2020 --- 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 6074-6078, Barcelona, Spain, 2020.
doi:10.1109/ICASSP40776.2020.9054476

11. Rafiei, Alireza, Rasoul Zahedifar, Chiranjibi Sitaula, and Faezeh Marzbanrad, "Automated detection of major depressive disorder with EEG signals: A time series classification using deep learning," IEEE Access, Vol. 10, 73804-73817, 2022.
doi:10.1109/access.2022.3190502 Google Scholar

12. Zhang, Yi-Fan, Peter J. Thorburn, Wei Xiang, and Peter Fitch, "SSIM --- A deep learning approach for recovering missing time series sensor data," IEEE Internet of Things Journal, Vol. 6, No. 4, 6618-6628, 2019.
doi:10.1109/jiot.2019.2909038 Google Scholar

13. Li, Frédéric, Kimiaki Shirahama, Muhammad Adeel Nisar, Xinyu Huang, and Marcin Grzegorzek, "Deep transfer learning for time series data based on sensor modality classification," Sensors, Vol. 20, No. 15, 4271, 2020.
doi:10.3390/s20154271 Google Scholar

14. Moghadas, Davood, "One-dimensional deep learning inversion of electromagnetic induction data using convolutional neural network," Geophysical Journal International, Vol. 222, No. 1, 247-259, 2020.
doi:10.1093/gji/ggaa161 Google Scholar

15. Yang, Lanqing, Yi-Chao Chen, Hao Pan, Dian Ding, Guangtao Xue, Linghe Kong, Jiadi Yu, and Minglu Li, "Magprint: Deep learning based user fingerprinting using electromagnetic signals," IEEE INFOCOM 2020 --- IEEE Conference on Computer Communications, 696-705, Toronto, ON, Canada, 2020.
doi:10.1109/INFOCOM41043.2020.9155534

16. Li, Xiaofeng, Hai Liu, Feng Zhou, Zhongchang Chen, Iraklis Giannakis, and Evert Slob, "Deep learning-based nondestructive evaluation of reinforcement bars using ground-penetrating radar and electromagnetic induction data," Computer-Aided Civil and Infrastructure Engineering, Vol. 37, No. 14, 1834-1853, 2022.
doi:10.1111/mice.12798 Google Scholar

17. Kim, Eunji, Sungzoon Cho, Byeongeon Lee, and Myoungsu Cho, "Fault detection and diagnosis using self-attentive convolutional neural networks for variable-length sensor data in semiconductor manufacturing," IEEE Transactions on Semiconductor Manufacturing, Vol. 32, No. 3, 302-309, 2019.
doi:10.1109/tsm.2019.2917521 Google Scholar

18. Yan, Xiaolan, Donglai Zhang, Shimin Pan, Enchao Zhang, and Wei Gao, "Online nondestructive testing for fine steel wire rope in electromagnetic interference environment," NDT & E International, Vol. 92, 75-81, 2017.
doi:10.1016/j.ndteint.2017.07.017 Google Scholar

19. Dong, Xintong, Yue Li, Tie Zhong, Ning Wu, and Hongzhou Wang, "Random and coherent noise suppression in DAS-VSP data by using a supervised deep learning method," IEEE Geoscience and Remote Sensing Letters, Vol. 19, 1-5, 2020.
doi:10.1109/lgrs.2020.3023706 Google Scholar

20. Ammari, Habib, Junqing Chen, Zhiming Chen, Darko Volkov, and Han Wang, "Detection and classification from electromagnetic induction data," Journal of Computational Physics, Vol. 301, 201-217, 2015.
doi:10.1016/j.jcp.2015.08.027 Google Scholar

21. Luo, Yutong, Xinyue Zhong, Minchen Zeng, Jialan Xie, Shiyuan Wang, and Guangyuan Liu, "CGLF-Net: Image emotion recognition network by combining global self-attention features and local multiscale features," IEEE Transactions on Multimedia, Vol. 26, 1894-1908, 2023.
doi:10.1109/tmm.2023.3289762 Google Scholar

22. Tang, Wensi, Guodong Long, Lu Liu, Tianyi Zhou, Michael Blumenstein, and Jing Jiang, "Omni-scale CNNs: A simple and effective kernel size configuration for time series classification," ArXiv Preprint ArXiv:2002.10061, 2020.
doi:10.48550/arXiv.2002.10061 Google Scholar

23. Vaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin, "Attention is all you need," Advances in Neural Information Processing Systems, Vol. 30, 2017. Google Scholar

24. Zeng, Pengyu, Guoliang Hu, Xiaofeng Zhou, Shuai Li, Pengjie Liu, and Shurui Liu, "Muformer: A long sequence time-series forecasting model based on modified multi-head attention," Knowledge-Based Systems, Vol. 254, 109584, 2022.
doi:10.1016/j.knosys.2022.109584 Google Scholar

25. Ren, Lei, Yuxin Liu, Di Huang, Keke Huang, and Chunhua Yang, "MCTAN: A novel multichannel temporal attention-based network for industrial health indicator prediction," IEEE Transactions on Neural Networks and Learning Systems, Vol. 34, No. 9, 6456-6467, 2023.
doi:10.1109/TNNLS.2021.3136768 Google Scholar

26. Chen, Ling, Donghui Chen, Zongjiang Shang, Binqing Wu, Cen Zheng, Bo Wen, and Wei Zhang, "Multi-scale adaptive graph neural network for multivariate time series forecasting," IEEE Transactions on Knowledge and Data Engineering, Vol. 35, No. 10, 10748-10761, 2023.
doi:10.1109/tkde.2023.3268199 Google Scholar

27. Xiao, Zhiwen, Xin Xu, Huanlai Xing, Shouxi Luo, Penglin Dai, and Dawei Zhan, "RTFN: A robust temporal feature network for time series classification," Information Sciences, Vol. 571, 65-86, 2021.
doi:10.1016/j.ins.2021.04.053 Google Scholar

28. Koido, Junji and Hiroshi Hoshikawa, "Electromagnetic testing method using tangential coil for measurement of covering thickness and diameter of rebars in concrete," AIP Conference Proceedings, Vol. 509, No. 1, 1723-1730, 2000.
doi:10.1063/1.1306240

29. Reed, Mark Alan and Waymond R. Scott, "Coil optimization method for electromagnetic induction systems," IEEE Sensors Journal, Vol. 13, No. 11, 4506-4512, 2013.
doi:10.1109/jsen.2013.2270135 Google Scholar

30. Xie, Shejuan, Zhirong Duan, Ji Li, Zongfei Tong, Mingming Tian, and Zhenmao Chen, "A novel magnetic force transmission eddy current array probe and its application for nondestructive testing of defects in pipeline structures," Sensors and Actuators A: Physical, Vol. 309, 112030, 2020.
doi:10.1016/j.sna.2020.112030 Google Scholar

31. Deleersnyder, Wouter, Benjamin Maveau, Thomas Hermans, and David Dudal, "Inversion of electromagnetic induction data using a novel wavelet-based and scale-dependent regularization term," Geophysical Journal International, Vol. 226, No. 3, 1715-1729, 2021.
doi:10.1093/gji/ggab182 Google Scholar

32. Minervini, Marcello, Maria Evelina Mognaschi, Paolo Di Barba, and Lucia Frosini, "Convolutional neural networks for automated rolling bearing diagnostics in induction motors based on electromagnetic signals," Applied Sciences, Vol. 11, No. 17, 7878, 2021.
doi:10.3390/app11177878 Google Scholar

33. Li, Shiyan, Xiaojuan Zhang, Kang Xing, and Yaoxin Zheng, "Fast inversion of subsurface target electromagnetic induction response with deep learning," IEEE Geoscience and Remote Sensing Letters, Vol. 19, 1-5, 2022.
doi:10.1109/lgrs.2022.3159269 Google Scholar

34. Richstein, Jörg, "Verifying the Goldbach conjecture up to 4⋅ 10¹⁴," Mathematics of Computation, Vol. 70, No. 236, 1745-1749, 2001.
doi:10.1090/s0025-5718-00-01290-4 Google Scholar

35. He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun, "Deep residual learning for image recognition," Proceedings of the IEEE conference on computer vision and Pattern Recognition, 770-778, 2016.

Dr. Jiale Chen

Professor Ronghua Zhang

Dr. Yuxiang Liu

Dr. Tongyan Liu

Dr. Anan Dai

Dr. Zishu Hu