A baseline-free multimodal pipe damage identification method by machine learning
DOI:
https://doi.org/10.24425/mms.2025.155807Abstract
Structural Health Monitoring (SHM) of pipe infrastructures is of paramount importance to prevent catastrophic failures induced by defects such as corrosion. Conventional damage identification methodologies are frequently faced with challenges, including baseline dependency, limitations inherent in single-sensor data, and considerable economic expenditure. This paper presents a novel, baseline-free, multi-modal damage identification methodology developed for Level 3 assessment of multiple damages, encompassing their detection, localisation, and quantification. Initially, Level 1 damage identification is accomplished through observation of the Regional Resonance Pair (RRP) phenomenon. Subsequently, potential damage regions are predicted by a Multilayer Perceptron (MLP) model that uses vibration modal frequencies, generating a Macro-F1 score of 0.8131 on the test set; this prediction is then integrated with a high-precision local point cloud, acquired via Line Structured Light (LSL) technology, to achieve precise Level 2 damage location, with a reported error as low as 1.78%. Following localisation, Level 3 quantification of the damage is performed using point cloud registration, fusion, and voxelisation techniques, enabling accurate prediction of damage volume with a quantification error of merely 2.47%.References
[1] Gu, Y., Liao, Z., Gu, M., Li, Z., Jia, J., & Tu, S.-T. (2023). A novel coupling method for ultrasonic transducer based on pressureless sintering of nano-Ag. Journal of Materials Research and Technology, 28, 2478-2487. https://doi.org/10.1016/j.jmrt.2023.12.167
[2] Gu, Y., Wang, M., Hou, Z., Jia, J., & Tu, S. (2024). Effect of the paste spreadability on ultrasonic transducer fabricated by pressureless sintering of nano-Ag. Measurement, 236, 115110. https://doi.org/10.1016/j.measurement.2024.115110
[3] Sharma, V. B., Tewari, S., Biswas, S., Lohani, B., Dwivedi, U. D., Dwivedi, D., Sharma, A., & Jung, J. P. (2021). Recent advancements in AI-enabled smart electronics packaging for structural health monitoring. Metals, 11(10), 1537. https://doi.org/10.3390/met11101537
[4] Sharma, V. B., Singh, K., Gupta, R., Joshi, A., Dubey, R., Gupta, V., Bharadwaj, S., Zafar, M. I., Bajpai, S., Khan, M. A., Srivastava, A., Pathak, D., & Biswas, S. (2021). Review of structural health monitoring techniques in pipeline and wind turbine industries. Applied System Innovation, 4(3), 59. https://doi.org/10.3390/asi4030059
[5] Sharma, V. B., Tewari, S., Biswas, S., & Sharma, A. (2023). A comprehensive study of techniques utilised for structural health monitoring of oil and gas pipelines. Structural Health Monitoring, 23(3), 1816-1841. https://doi.org/10.1177/14759217231183715
[6] Hassan, S. I., Dang, L. M., Mehmood, I., Im, S., Choi, C., Kang, J., Park, Y., & Moon, H. (2019). Underground sewer pipe condition assessment based on convolutional neural networks. Automation in Construction, 106, 102849. https://doi.org/10.1016/j.autcon.2019.102849
[7] Su, T.-C., Yang, M.-D., Wu, T.-C., & Lin, J.-Y. (2011). Morphological segmentation based on edge detection for sewer pipe defects on CCTV images. Expert Systems with Applications, 38(10), 13094-13114. https://doi.org/10.1016/j.eswa.2011.04.116
[8] Bayissa, W. L., Haritos, N., & Thelandersson, S. (2007). Vibration-based structural damage identification using wavelet transform. Mechanical Systems and Signal Processing, 22(5), 1194-1215. https://doi.org/10.1016/j.ymssp.2007.11.001
[9] Liu, B., Lu, H., Wu, Z., Li, S., & Liu, Q. (2020). Detection scheme of volume of repair of engineering equipment based on line structured light. Volume 2: Manufacturing Processes; Manufacturing Systems; Nano/Micro/Meso Manufacturing; Quality and Reliability. https://doi.org/10.1115/msec2020-8237
[10] Wenbin, M., Zhiwen, D., Xiang, L., & Hang, Z. (2024) Study on submarine pipeline suspension internal detection based on vibration response analysis, Chinese Journal of Engineering Design 31(03), 348-356. https://doi.org/10.3785/j.issn.1006-754X.2024.03.170
[11] Wang, M., Gu, Y., Fu, Y., Zhu, Y., Jia, J., & Tu, S. (2024). Baseline-free damage identification in clamped-clamped pipes based on regional resonance pairs. International Journal of Pressure Vessels and Piping, 105416. https://doi.org/10.1016/j.ijpvp.2024.105416
[12] Singh, A., & Kaloni, S. (2023). Unsupervised ambient vibration-based feature extraction for structural damage detection. In Communications in Computer and Information Science, 554-565. https://doi.org/10.1007/978-3-031-37940-6_45
[13] Timilsena, H., Singh, A., Kumar, M., & Goyal, S. (2024). Comparative study of seismic analysis of RCC building using IS Code 1893:2016 (Part-1) and Nepal Building Code 105:2020. In 2024 1st International Conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI (ICSCAI), 1-14. https://doi.org/10.1109/icscai61790.2024.10866768
[14] Xingsheng, X., Guoliang, H., Wencai, Z., Lifan, Y.,& Gang, L. (2024) Research on power generation performance of vibration energy collecting magnetorheological damper, Chinese Journal of Engineering Design 31(02), 201-209. https://doi.org/10.3785/j.issn.1006-754X.2024.03.139
[15] Fang, X., Li, Q., Zhu, J., Chen, Z., Zhang, D., Wu, K., Ding, K., & Li, Q. (2022). Sewer defect instance segmentation, localisation, and 3D reconstruction for sewer floating capsule robots. Automation in Construction, 142, 104494. https://doi.org/10.1016/j.autcon.2022.104494
[16] Ma, D., Liu, J., Fang, H., Wang, N., Zhang, C., Li, Z., & Dong, J. (2021). A multi-defect detection system for sewer pipelines based on StyleGAN-SDM and fusion CNN. Construction and Building Materials, 312, 125385. https://doi.org/10.1016/j.conbuildmat.2021.125385
[17] Zhou, Y., Ji, A., & Zhang, L. (2022). Sewer defect detection from 3D point clouds using a transformer-based deep learning model. Automation in Construction, 136, 104163. https://doi.org/10.1016/j.autcon.2022.104163
[18] Vandiver, J. K. (1975). Detection of structural failure on fixed platforms by measurement of dynamic response. Offshore Technology Conference. https://doi.org/10.4043/2267-ms
[19] Yuen, M. (1985). A numerical study of the eigenparameters of a damaged cantilever. Journal of Sound and Vibration, 103(3), 301-310. https://doi.org/10.1016/0022-460x(85)90423-7
[20] Vaish, R., Dwivedi, U., Tewari, S., & Tripathi, S. (2021). Machine learning applications in power system fault diagnosis: Research advancements and perspectives. Engineering Applications of Artificial Intelligence, 106, 104504. https://doi.org/10.1016/j.engappai.2021.104504
[21] Tewari, S., & Dwivedi, U. (2018). Ensemble-based big data analytics of lithofacies for automatic development of petroleum reservoirs. Computers & Industrial Engineering, 128, 937-947. https://doi.org/10.1016/j.cie.2018.08.018
[22] Nguyen, H. D., Dao, N. D., & Shin, M. (2025). Capability of machine learning to predict seismic damage states of reinforced concrete wall structures. Journal of Building Engineering, 112620. https://doi.org/10.1016/j.jobe.2025.112620
[23] Li, L., Chang-Richards, A., Boston, M., Elwood, K., & Brunsdon, D. (2025). A machine learning-supported rapid classification of building damage following the 2010-2011 Canterbury earthquakes. Journal of Building Engineering, 112807. https://doi.org/10.1016/j.jobe.2025.112807
[24] Wu, X., Ghaboussi, J., & Garrett, J. (1992). Use of neural networks in detection of structural damage. Computers & Structures, 42(4), 649-659. https://doi.org/10.1016/0045-7949(92)90132-j
[25] Worden, K., & Lane, A. J. (2001). Damage identification using support vector machines. Smart Materials and Structures, 10(3), 540-547. https://doi.org/10.1088/0964-1726/10/3/317
[26] Agrawal, A. K., & Chakraborty, G. (2018). Structural damage detection by integrating short time Fourier transform, principal component analysis and logistic regression. In CRC Press eBooks (pp. 971-976). https://doi.org/10.1201/9781351174664-122
[27] Zhou, Q., Ning, Y., Zhou, Q., Luo, L., & Lei, J. (2012). Structural damage detection method based on random forests and data fusion. Structural Health Monitoring, 12(1), 48-58. https://doi.org/10.1177/1475921712464572
[28] Leon-Medina, J. X., Anaya, M., Parés, N., Tibaduiza, D. A., & Pozo, F. (2021). Structural damage classification in a jacket-type wind-turbine foundation using principal component analysis and extreme gradient boosting. Sensors, 21(8), 2748. https://doi.org/10.3390/s21082748
[29] Sharma, V. B., & Biswas, S. (2020). Modern Smart Sensing Technology in Structural Health Monitoring. In 2020 International Conference on Smart Innovations in Design, Environment, Management, Planning and Computing (ICSIDEMPC) (pp. 105-108). https://doi.org/10.1109/icsidempc49020.2020.9299595
[30] Huang, M., Xu, Z., Cai, C., Chen, D., Yin, W., & He, X. (2025). Vibration-based damage detection in laminated composite plates: a novel approach using superposition of higher-order derivatives of mode shapes. Structural Health Monitoring. https://doi.org/10.1177/14759217251334803
[31] Alvandi, A., & Cremona, C. (2005). Assessment of vibration-based damage identification techniques. Journal of Sound and Vibration, 292(1-2), 179-202. https://doi.org/10.1016/j.jsv.2005.07.036
[32] Sharma, V. B., Dubey, R., Bhatt, A., Bharadwaj, S., Srivastava, A., & Biswas, S. (2022). A Method For Extracting Deformation Features from Terrestrial Laser Scanner 3d Point Clouds Data in Rgipt Building. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B2-2022, 267-272. https://doi.org/10.5194/isprs-archives-xliii-b2-2022-267-2022
[33] Wang, W., Niu, H., Qiu, S., Wang, J., Luo, Y., Zaheer, Q., & Peng, J. (2024). Railway-fastener point cloud segmentation and damage quantification based on deep learning and synthetic data augmentation. Journal of Computing in Civil Engineering, 39(2). https://doi.org/10.1061/jccee5.cpeng-6026
[34] Liu, X., Yu, B., Cai, D., & Wang, R. (2024). Potential damage area detection of bridges based on single-temporal point cloud. Measurement Science and Technology, 36(1), 015214. https://doi.org/10.1088/1361-6501/ad9041
[35] Li, N., Wu, R., Li, H., Wang, H., Gui, Z., & Song, D. (2023). M2FNET: Multimodal fusion network for airport runway subsurface defect detection using GPR data. IEEE Transactions on Geoscience and Remote Sensing, 61, 1-16. https://doi.org/10.1109/tgrs.2023.3308205
[36] Hinks, T., Carr, H., Truong-Hong, L., & Laefer, D. F. (2012). Point Cloud Data Conversion into Solid Models via Point-Based Voxelisation. Journal of Surveying Engineering, 139(2), 72-83. https://doi.org/10.1061/(asce)su.1943-5428.0000097
[37] Yoon, Y., Lee, J., Yoo, S., & Choi, H. (2002). A New Method for In-plane Vibration Analysis of Circular Rings with Widely Distributed Deviation. Journal of Sound and Vibration, 254(4), 787-800. https://doi.org/10.1006/jsvi.2001.4124
[38] Allaei, D., Soedel, W., & Yang, T. (1986). Natural frequencies and modes of rings that deviate from perfect axisymmetry. Journal of Sound and Vibration, 111(1), 9-27. https://doi.org/10.1016/s0022-460x(86)81419-5
[39] Fox, C. (1990). A simple theory for the analysis and correction of frequency splitting in slightly imperfect rings. Journal of Sound and Vibration, 142(2), 227-243. https://doi.org/10.1016/0022-460x(90)90554-d
[40] Ewins, D. J. (2009). Modal testing: Theory, Practice and Application. John Wiley & Sons.
