An innovative deep neural network coordinating with percussion-based technique for automatic detection of concrete cavity defects
Source abstract
Abstract
Cavity defects are usually invisible in concrete, failure to detect and repair them in time could significantly weaken the load-bearing capacity of engineering structures, potentially threatening the structural safety during the construction and operation periods. Therefore, it is essential to explore efficient approaches to detect concrete cavity defects. In this study, we propose a novel method to detect concrete cavity defects based on percussion and deep learning (DL) techniques. First, the percussion sound dataset was collected from concrete specimens with different types of precast cavity defects. Next, an innovative DL framework named the multi-scale convolutional bidirectional memory network (MCBMNet) was developed for classifying these percussion sound signals associated with specified concrete cavity defects. The MCBMNet utilizes the multi-scale convolutional operation to generate various scale features directly from raw percussion sounds, and then employs the bidirectional memory units to capture intrinsic feature connections and enhance feature separability, thus improving prediction accuracy and robustness. Finally, two experimental cases, including water-free and water-filled conditions, were designed to test the feasibility of the proposed method considering the influences of humidity environment in reality. Experimental results well demonstrate the excellent performances of the proposed MCBMNet for concrete cavity defect detection, with its average accuracy over 98% in both cases. Additionally, the anti-noise capacity and adaptability of MCBMNet were thoroughly investigated, which outperforms conventional learning algorithms.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Geophysical Methods and Applications · Infrastructure Maintenance and Monitoring · Structural Health Monitoring Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (66)
Show source-provided references
1. Innovation in use and research on cementitious material10.1016/j.cemconres.2007.09.025 ↗
2. Monitoring the curing process of in-situ concrete with piezoelectric-based techniques – a practical application10.1177/14759217221087916 ↗
3. Concrete deterioration: causes, diagnosis, and minimising risk10.1179/095066001101528420 ↗
4. Damping ratio as an indicator of void space beneath the concrete face slab of rockfill dams10.1016/j.ndteint.2020.102395 ↗
5. Damage identification in beam-type structures: frequency-based method vs mode-shape-based method10.1016/S0141-0296(02)00118-9 ↗
6. Damage detection method for RC members using local vibration testing10.1016/j.engstruct.2018.10.031 ↗
7. The effect of the steel–concrete interface on chloride-induced corrosion initiation in concrete: a critical review by RILEM TC 262-SCI10.1617/s11527-019-1387-0 ↗
8. Influence of artificial cracks and interfacial defects on the corrosion behavior of steel in concrete during corrosion initiation under a chloride environment10.1016/j.conbuildmat.2020.119165 ↗
9. Comparison of core sampling and visual inspection for assessment of concrete sewer pipe condition10.2166/wst.2013.138 ↗
10. Sub-surface simulated damage detection using Non-destructive testing techniques in reinforced-concrete slabs10.1016/j.conbuildmat.2019.04.223 ↗
11. Interfacial imperfection detection for steel-concrete composite structures using NDT techniques: a state-of-the-art review10.1016/j.engstruct.2021.112778 ↗
12. Void detection beneath reinforced concrete sections: the practical application of ground-penetrating radar and ultrasonic techniques10.1016/j.jappgeo.2011.06.003 ↗
13. Ultrasonic signal processing methods for detection of defects in concrete pipes10.1016/j.autcon.2011.06.012 ↗
14. Concrete quality designation based on ultrasonic pulse velocity10.1016/j.conbuildmat.2016.08.158 ↗
15. High spatial resolution imaging for damage detection in concrete based on multiple wavelet decomposition10.1016/j.conbuildmat.2021.126057 ↗
16. Damage detection using ultrasonic techniques in concrete-filled steel tubes (CFSTs) columns10.3390/s22124400 ↗
17. Monitoring of concrete structures using the ultrasonic pulse velocity method10.1088/0964-1726/24/11/113001 ↗
18. Experimental studies on void detection in concrete-filled steel tubes using ultrasound10.1016/j.conbuildmat.2016.10.061 ↗
19. A framework for automated time-lapse thermography data processing10.1016/j.conbuildmat.2019.07.233 ↗
20. Semi real-time detection of subsurface consolidation defects during concrete curing stage10.1016/j.conbuildmat.2020.121489 ↗
21. Comparison of infrared thermography, ground-penetrating radar and ultrasonic pulse echo for detecting delaminations in concrete bridges10.1016/j.conbuildmat.2019.07.320 ↗
22. Defect detection of concrete structures using both infrared thermography and elastic waves10.1016/j.autcon.2008.05.004 ↗
23. Inspection of insulated concrete form walls with ground penetrating radar10.1016/j.conbuildmat.2011.06.044 ↗
24. GPR detection of several common subsurface voids inside dikes and dams10.1016/j.enggeo.2009.12.001 ↗
25. Identifying concrete structure defects in GPR image10.1016/j.measurement.2020.107839 ↗
26. Detection of cavities around concrete sewage pipelines using impact-echo method10.1016/j.tust.2017.02.002 ↗
27. Evaluation of bridge decks with overlays using impact echo, a deep learning approach10.1016/j.autcon.2020.103133 ↗
28. Depth detection of void defect in sandwich-structured immersed tunnel using elastic wave and decision tree10.1016/j.conbuildmat.2021.124756 ↗
29. Tapping and listening: a new approach to bolt looseness monitoring10.1088/1361-665X/aac962 ↗
30. Bolt-looseness detection by a new percussion-based method using multifractal analysis and gradient boosting decision tree10.1177/1475921720912780 ↗
31. An innovative deep neural network–based approach for internal cavity detection of timber columns using percussion sound10.1177/14759217211028524 ↗
32. Shear loading detection of through bolts in bridge structures using a percussion-based one-dimensional memory-augmented convolutional neural network10.1111/mice.12602 ↗
33. If structure can exclaim: a novel robotic-assisted percussion method for spatial bolt-ball joint looseness detection10.1177/1475921720923147 ↗
34. Bolt preload monitoring based on percussion sound signal and convolutional neural network (CNN)10.1080/10589759.2022.2030735 ↗
35. Automated structural bolt looseness detection using deep learning-based prediction model10.1002/stc.2899 ↗
36. Monitor concrete moisture level using percussion and machine learning10.1016/j.conbuildmat.2019.117077 ↗
37. Timber moisture detection using wavelet packet decomposition and convolutional neural network10.1088/1361-665X/abdc08 ↗
38. A CNN-integrated percussion method for detection of FRP–concrete interfacial damage with FEM reconstruction10.1177/14759217221082007 ↗
39. Detection of sand deposition in pipeline using percussion, voice recognition, and support vector machine10.1177/1475921720918890 ↗
40. Percussion-based pipeline ponding detection using a convolutional neural network10.3390/app12042127 ↗
41. A novel percussion-based method for multi-bolt looseness detection using one-dimensional memory augmented convolutional long short-term memory networks10.1016/j.ymssp.2021.107955 ↗
42. 1D-TICapsNet: an audio signal processing algorithm for bolt early looseness detection10.1177/1475921720976989 ↗
43. Depth detection of subsurface voids in concrete-filled steel tubular (CFST) structure using percussion and decision tree10.1016/j.measurement.2020.107869 ↗
44. Detection of subsurface voids in concrete-filled steel tubular (CFST) structure using percussion approach10.1016/j.conbuildmat.2020.119761 ↗
45. Percussion-based quasi real-time void detection for concrete-filled steel tubular structures using dense learned features10.1016/j.engstruct.2022.115197 ↗
46. A hybrid of deep CNN and bidirectional LSTM for automatic speech recognition
47. Image recognition with deep neural networks in presence of noise – Dealing with and taking advantage of distortions10.3233/ICA-170551 ↗
48. Intelligent monitoring and assessment on early-age hydration and setting of cement mortar through an EMI-integrated neural network10.1016/j.measurement.2022.111984 ↗
49. 1D convolutional neural networks and applications: a survey10.1016/j.ymssp.2020.107398 ↗
50. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks10.1016/j.jsv.2016.10.043 ↗
51. One-dimensional convolutional neural network-based damage detection in structural joints10.1007/s13349-020-00434-z ↗
52. Lamb wave based damage detection in metallic plates using multi-headed 1-dimensional convolutional neural network10.1088/1361-665X/abdd00 ↗
53. Automated identification of compressive stress and damage in concrete specimen using convolutional neural network learned electromechanical admittance10.1016/j.engstruct.2022.114176 ↗
54. Integrated electromechanical impedance technique with convolutional neural network for concrete structural damage quantification under varied temperatures10.1016/j.ymssp.2020.107467 ↗
55. Deep learning-based autonomous damage-sensitive feature extraction for impedance-based prestress monitoring10.1016/j.engstruct.2022.114172 ↗
56. Bidirectional recurrent neural networks10.1109/78.650093 ↗
57. Learning to forget: continual prediction with LSTM10.1162/089976600300015015 ↗
58. A review on the long short-term memory model10.1007/s10462-020-09838-1 ↗
59. A bearing fault diagnosis model based on CNN with wide convolution kernels10.1007/s12652-021-03177-x ↗
60. S. Ioffe, C. Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, in: B. Francis, B. David (Eds.) Proceedings of the 32nd International Conference on Machine Learning, PMLR, Proceedings of Machine Learning Research, 2015, pp. 448--456.
61. Framewise phoneme classification with bidirectional LSTM and other neural network architectures10.1016/j.neunet.2005.06.042 ↗
62. BiCuDNNLSTM-1dCNN — A hybrid deep learning-based predictive model for stock price prediction10.1016/j.eswa.2022.117123 ↗
63. A deep learning approach for real-time detection of atrial fibrillation10.1016/j.eswa.2018.08.011 ↗
64. Looseness detection in cup-lock scaffolds using percussion-based method10.1016/j.autcon.2020.103266 ↗
65. Z. Zhang, Improved Adam Optimizer for Deep Neural Networks, 2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS), 2018, pp. 1-2.10.1109/IWQoS.2018.8624183 ↗
66. Visualizing data using t-SNE