Transfer Learning-Based Detection of Pile Defects in Low-Strain Pile Integrity Testing
Source abstract
Abstract
Pile foundations are critical structural elements, and their integrity is essential for ensuring the stability and safety of construction projects. Low-strain pile integrity testing (LSPIT) is widely used for defect detection; however, conventional manual interpretation of reflectograms is both time-consuming and susceptible to human error. This study presents a deep learning-driven approach utilizing transfer learning with convolutional neural networks (CNNs) to automate pile defect detection. A dataset of 328 reflectograms collected from real construction sites, including 246 intact and 82 defective samples, was used to train and evaluate the model. To address class imbalance, oversampling techniques were applied. Several state-of-the-art pretrained CNN architectures were compared, with ConvNeXtLarge achieving the highest accuracy of 98.2%. The accuracy reported was achieved on a dedicated test set using real reflectogram data from actual construction sites, distinguishing this study from prior work relying primarily on synthetic data. The proposed novelty includes adapting pre-trained CNN architectures specifically for real-world pile integrity testing, addressing practical challenges such as data imbalance and limited dataset size through targeted oversampling techniques. The proposed approach demonstrates significant improvements in accuracy and efficiency compared to manual interpretation methods, making it a promising solution for practical applications in the construction industry. The proposed method demonstrates potential for generalization across varying pile lengths and geological conditions, though further validation with broader datasets is recommended.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Geophysical Methods and Applications · Non-Destructive Testing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Engineering, Manisa Celal Bayar University, Yunusemre, 45140 Manisa, Türkiye
Octahedron Innovation Informatics Electronics and Mining Services Inc., Manisa Technopark, Yunusemre, 45140 Manisa, Türkiye
Canbula Sofware Research and Development Ltd. Co., Manisa Technopark, Yunusemre, 45140 Manisa, Türkiye
Funding
Technology and Innovation Funding Programs Directorate (TEYDEB) of The Scientific and Technological Research Council of Turkiye (TUBITAK)
References (56)
Show source-provided references
1. European Commission (2025, January 15). Cordis EU Research ResultsPileinspect (Integrity Testing of Deep Foundation Piles).Technical Report, European Commission. Available from European Commission Research Results. Available online: https://cordis.europa.eu/project/id/605676/it.
2. Thermal integrity testing of cast in situ piles: An alternative interpretation approach10.1177/1475921720960042 ↗
3. Rui, Y., Kechavarzi, C., O’Leary, F., Barker, C., Nicholson, D., and Soga, K. (2017). Integrity testing of pile cover using distributed fibre optic sensing. Sensors, 17.10.3390/s17122949 ↗
4. Rausche, F. (2004, January 13–17). Non-destructive evaluation of deep foundations. Proceedings of the 5th Conference of the International Conference on Case Histories in Geotechnical Engineering, New York, NY, USA.
5. Capabilities of auxiliary techniques for low strain impact testing of piles foundations10.37538/2224-9494-2023-1(36)-59-71 ↗
6. Low strain integrity testing of piles: Three-dimensional effects10.1061/(ASCE)1090-0241(2003)129:11(1057) ↗
7. Wang, H., Zhang, S., Li, J., Yuan, Y., and Zhang, H. (2023). Classification of low-strain foundation pile testing signal using recurrent neural network. Buildings, 13.10.3390/buildings13051228 ↗
8. Cui, D., Yan, W., Wang, X., and Lu, L. (2017). Towards intelligent interpretation of low strain pile integrity testing results using machine learning techniques. Sensors, 17.10.3390/s17112443 ↗
9. Zhang, C., and Zhang, J. (2009, January 22–24). Application of artificial neural network for diagnosing pile integrity based on low strain dynamic testing. Proceedings of the Computational Structural Engineering: Proceedings of the International Symposium on Computational Structural Engineering, Shanghai, China.10.1007/978-90-481-2822-8_94 ↗
10. Koteleva, N., and Loseva, E. (2022). Development of an algorithm for determining defects in cast-in-place piles based on the data analysis of low strain integrity testing. Appl. Sci., 12.10.3390/app122010636 ↗
11. Liu, W., Tian, S., and Hu, L. (2022). Classification of pile foundation integrity based on convolutional neural network. Arab. J. Geosci., 15.10.1007/s12517-022-10057-x ↗
12. Wu, C.S., Zhang, J.Q., Qi, L.L., and Zhuo, D.B. (2022). Defect identification of concrete piles based on numerical simulation and convolutional neural network. Buildings, 12.10.3390/buildings12050664 ↗
13. Wu, J. (2023). Pile damage detection using machine learning with the multipoint traveling wave decomposition method. Sensors, 23.10.3390/s23198308 ↗
14. Najafabadi, M.M., Villanustre, F., Khoshgoftaar, T.M., Seliya, N., Wald, R., and Muharemagic, E. (2015). Deep learning applications and challenges in big data analytics. J. Big Data, 2.10.1186/s40537-014-0007-7 ↗
15. Survey on deep learning with class imbalance10.1186/s40537-019-0192-5 ↗
16. Tremblay, J., Prakash, A., Acuna, D., Brophy, M., Jampani, V., Anil, C., To, T., Cameracci, E., Boochoon, S., and Birchfield, S. (2018, January 18–22). Training deep networks with synthetic data: Bridging the reality gap by domain randomization. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA.10.1109/CVPRW.2018.00143 ↗
17. Nikolenko, S. (2021). Synthetic Data for Deep Learning, Springer.10.1007/978-3-030-75178-4 ↗
18. Ćosić, M., Folić, R., and Šušić, N. (2016, January 15–17). Review of scientific insights and a critical analysis of pile capacity and pile integrity tests. Proceedings of the International Conference on Civil Engineering Design and Construction (Science and Practice), Varna, Bulgaria.
19. Churkin, A. (2020). Development Of Geophysical Complex Application Technique For Buried Monolithic Structures Quality Control. [Ph.D. Thesis, Moscow State University].
20. Spectral analysis of cross-hole sonic logging data for pile integrity assessment
21. Hingorani, M. (2019, January 19–21). Interpretation of low-strain pile integrity test results. Proceedings of the Indian Geotechnical Conference, Surat, India.
22. Comparison of pulse echo and transient response pile integrity test methods
23. Wang, H., Hu, C., Nguyn, T., Tsai, H., and Wang, C. (2019, January 14–18). Flexural wave impulse response evaluation of pile bent foundations. Proceedings of the 16th Asian Regional Conference on Soil Mechanics and Geotechnical Engineering, Taipei, Taiwan.
24. Zad, A. (2013). Determination of Embedded Length and General Condition of Utility Poles Using Non-Destructive Testing Methods. [Ph.D. Thesis, University of Technology Sydney].
25. (2014). Standard Test Method for Integrity Testing of Concrete Deep Foundations by Ultrasonic Crosshole Testing (Standard No. ASTM D6760-08).
26. Kordjazi, A., Coe, J.T., and Afanasiev, M. (2021). Nondestructive evaluation of drilled shaft construction anomalies using full waveform tomography of simulated crosshole measurements. J. Nondestruct. Eval., 40.10.1007/s10921-020-00728-8 ↗
27. Brettman, T., and Frank, M. (1996, January 11–13). Comparison of Crosshole and Single Hole Sonic Integrity Logging Methods. Proceedings of the 5th International Conference on the Application of Stress Wave Theory to Piles, Orlando, FL, USA.
28. Palm, M. (2012). Single-Hole Sonic Logging—A Study of Possibilities and Limitations of Detecting Flaws in Piles. [Master’s Thesis, KTH].
29. Wightman, W., Jalinoos, F., Hanna, K., and Sirles, P. (2003). Application of Geophysical Methods to Highway Related Problems, Federal Highway Administration. Technical Report.
30. Application of time domain reflectometer for detecting necking defects in bored piles10.1016/j.ndteint.2018.09.006 ↗
31. McCarter, W.J., Forde, M.C., and Whittington, H. Application of electrical resistivity to integrity testing of concrete load-bearing piles. Proceedings of the 4th International Conference on Non-Destructive Testing, Grenoble, France. Available online: https://researchportal.hw.ac.uk/en/publications/application-of-electrical-resistivity-to-integrity-testing-of-con.
32. Özbaş, F. (2007). Quality Control of Piles Constructed in Clayey Soils with Sonic Integrity Testing (SIT). [Master’s Thesis, İstanbul Teknik Üniversitesi].
33. Stengel, T., Wackerl, M., and Beckhaus, K. (2022). Transient 3D-thermal-analysis of bored piles—Comparison of two software tools and validation using a test pile. e-J. Nondestruct. Test., 27.10.58286/27335 ↗
34. Thermal integrity profiling of cast-in situ piles in sand using fiber-optic distributed temperature sensing10.1016/j.jrmge.2023.02.028 ↗
35. Dommersnes, E. (2019). Potential Utilization of Neutron Logging for Casing Cement Evaluation. [Master’s Thesis, University of Stavenger].10.2118/202973-MS ↗
36. Mohammed, R., Rawashdeh, J., and Abdullah, M. (2020, January 7–9). Machine learning with oversampling and undersampling techniques: Overview study and experimental results. Proceedings of the 2020 11th International Conference on Information and Communication Systems (ICICS), Irbid, Jordan.10.1109/ICICS49469.2020.239556 ↗
37. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning10.1109/TMI.2016.2528162 ↗
38. Cui, Y., Song, Y., Sun, C., Howard, A., and Belongie, S. (2018, January 18–22). Large scale fine-grained categorization and domain-specific transfer learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00432 ↗
39. Azimi, M., Eslamlou, A.D., and Pekcan, G. (2020). Data-driven structural health monitoring and damage detection through deep learning: State-of-the-art review. Sensors, 20.10.3390/s20102778 ↗
40. Transfer learning-based data anomaly detection for structural health monitoring10.1177/14759217221142174 ↗
41. Pre-trained convolutional neural networks as feature extractors for tuberculosis detection10.1016/j.compbiomed.2017.08.001 ↗
42. Varshni, D., Thakral, K., Agarwal, L., Nijhawan, R., and Mittal, A. (2019, January 20–22). Pneumonia detection using CNN based feature extraction. Proceedings of the 2019 IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT), Coimbatore, India.10.1109/ICECCT.2019.8869364 ↗
43. Rajaraman, S., Antani, S.K., Poostchi, M., Silamut, K., Hossain, M.A., Maude, R.J., Jaeger, S., and Thoma, G.R. (2018). Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images. PeerJ, 6.10.7717/peerj.4568 ↗
44. Deep feature extraction and classification of hyperspectral images based on convolutional neural networks10.1109/TGRS.2016.2584107 ↗
45. Villaruz, J.A. (2021). Deep convolutional neural network feature extraction for berry trees classification. J. Adv. Inf. Technol., 12.10.12720/jait.12.3.226-233 ↗
46. Chollet, F. (2017). Xception: Deep Learning with Depthwise Separable Convolutions. arXiv.10.1109/CVPR.2017.195 ↗
47. Simonyan, K., and Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv.
48. He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.10.1109/CVPR.2016.90 ↗
49. He, K., Zhang, X., Ren, S., and Sun, J. (2016). Identity Mappings in Deep Residual Networks. arXiv.10.1007/978-3-319-46493-0_38 ↗
50. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv.
51. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2019). MobileNetV2: Inverted Residuals and Linear Bottlenecks. arXiv.10.1109/CVPR.2018.00474 ↗
52. Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2018). Densely Connected Convolutional Networks. arXiv.10.1109/CVPR.2017.243 ↗
53. Zoph, B., Vasudevan, V., Shlens, J., and Le, Q.V. (2018). Learning Transferable Architectures for Scalable Image Recognition. arXiv.10.1109/CVPR.2018.00907 ↗
54. Tan, M., and Le, Q.V. (2020). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv.
55. Tan, M., and Le, Q.V. (2021). EfficientNetV2: Smaller Models and Faster Training. arXiv.
56. Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022). A ConvNet for the 2020s. arXiv.10.1109/CVPR52688.2022.01167 ↗