Department of Mechanical Engineering, Petroleum University of Technology, Abadan, Iran
10.48311/mme.2026.123003.83090
Abstract
Reliable corrosion monitoring becomes more difficult when a diagnostic model is expected to remain effective beyond the experiment used for its development. This study combines Lamb-wave measurements with machine learning to assess corrosion in 316L stainless steel, with particular emphasis on transfer between independent experiments. A public laboratory dataset containing two corrosion experiments was analyzed, comprising 429 corrosion states and 12 directed piezoelectric actuator-sensor paths per state. Damage indices, baseline-relative descriptors, and frequency-domain features were evaluated using conventional machine-learning models and a physics-guided path-attention multi-task learning framework (PG-PAMTL). Performance was assessed under within-experiment validation, strict zero-shot transfer, and unsupervised domain adaptation. In the strict cross-experiment setting, PG-PAMTL achieved a macro ROC-AUC of 0.830 and a PR-AUC of 0.871, indicating substantially stronger transferability than the conventional benchmarks. Domain adaptation increased the classification ROC-AUC only marginally to 0.832, but its effect was more evident for severity estimation, where the macro MAE decreased from 39.3 to 32.5 µm. Permutation analysis showed that predictive information was concentrated in a limited number of sensing paths and in both waveform-change and frequency-domain features. A separate sensitivity analysis also confirmed that a known bubble-related disturbance affected transfer performance. Experimental progression, however, was strongly associated with corrosion severity, limiting the interpretation of the regression results. The findings therefore support Lamb-wave machine learning for cross-experiment corrosion detection, while showing that reliable absolute severity estimation still requires validation under more independent experimental conditions.
[1] M. S. B. Reddy, D. Ponnamma, K. K. Sadasivuni, S. Aich, S. Kailasa, H. Parangusan, M. Ibrahim, S. Eldeib, O. Shehata, M. Ismail, et al., “Sensors in advancing the capabilities of corrosion detection: A review,” Sensors and Actuators A: Physical, vol. 332, Art. no. 113086, 2021, doi: 10.1016/j.sna.2021.113086.
[2] V. Vasagar, M. K. Hassan, A. M. Abdullah, A. V. Karre, B. Chen, K. Kim, N. Al-Qahtani, and T. Cai, “Non-destructive techniques for corrosion detection: A review,” Corrosion Engineering, Science and Technology, vol. 59, no. 1, pp. 56–85, 2024,doi: 10.1177/1478422X241229621.
[3] C. R. Farrar and K. Worden, “An introduction to structural health monitoring,” Philosophical Transactions of the Royal Society A, vol. 365, no. 1851, pp. 303–315, 2007, doi:10.1098/rsta.2006.1928.
[4] M. Mitra and S. Gopalakrishnan, “Guided wave based structural health monitoring: A review,” Smart Materials and Structures, vol. 25, no. 5, Art. no. 053001, 2016, doi: 10.1088/0964-1726/25/5/053001.
[5] P. Cawley, “Guided waves in long range nondestructive testing and structural health monitoring: Principles, history of applications and prospects,” NDT & E International, vol. 142, Art. no. 103026, 2024, doi: 10.1016/j.ndteint.2023.103026.
[6] Z. Su, L. Ye, and Y. Lu, “Guided Lamb waves for identification of damage in composite structures: A review,” Journal of Sound and Vibration, vol. 295, nos. 3–5, pp. 753–780, 2006,doi: 10.1016/j.jsv.2006.01.020.
[7] R. Gorgin, Y. Luo, and Z. Wu, “Environmental and operational conditions effects on Lamb wave based structural health monitoring systems: A review,” Ultrasonics, vol. 105, Art. no. 106114, 2020,doi: 10.1016/j.ultras.2020.106114.
[8] A. J. Croxford, J. Moll, P. D. Wilcox, and J. E. Michaels, “Efficient temperature compensation strategies for guided wave structural health monitoring,” Ultrasonics, vol. 50, nos. 4–5, pp. 517–528, 2010,doi: 10.1016/j.ultras.2009.11.002.
[9] P. B. Nagy, F. Simonetti, and G. Instanes, “Corrosion and erosion monitoring in plates and pipes using constant group velocity Lamb wave inspection,” Ultrasonics, vol. 54, no. 7, pp. 1832–1841, 2014, doi: 10.1016/j.ultras.2014.01.017.
[10] T. R. Hay, R. L. Royer, H. Gao, X. Zhao, and J. L. Rose, “A comparison of embedded sensor Lamb wave ultrasonic tomography approaches for material loss detection,” Smart Materials and Structures, vol. 15, no. 4, p. 946, 2006,doi: 10.1088/0964-1726/15/4/007.
[11] P. Belanger and P. Cawley, “Feasibility of low frequency straight-ray guided wave tomography,” NDT & E International, vol. 42, no. 2, pp. 113–119, 2009,doi: 10.1016/j.ndteint.2008.10.006.
[12] W. Li and Y. Cho, “Quantification and imaging of corrosion wall thinning using shear horizontal guided waves generated by magnetostrictive sensors,” Sensors and Actuators A: Physical, vol. 232, pp.251–258,2015,doi: 10.1016/j.sna.2015.06.008.
[13] Z. Zhang, H. Pan, X. Wang, and Z. Lin, “Machine Learning-Enriched Lamb Wave Approaches for Automated Damage Detection,” Sensors, vol. 20, no. 6, Art. no. 1790, 2020, doi: 10.3390/s20061790.
[14] C. Schnur, P. Goodarzi, Y. Lugovtsova, J. Bulling, J. Prager, K. Tschöke, J. Moll, A. Schütze, and T. Schneider, “Towards interpretable machine learning for automated damage detection based on ultrasonic guided waves,” Sensors, vol. 22, no. 1, Art. no. 406, 2022, doi: 10.3390/s22010406.
[15] A. Abbassi, N. Römgens, F. F. Tritschel, N. Penner, and R. Rolfes, “Evaluation of machine learning techniques for structural health monitoring using ultrasonic guided waves under varying temperature conditions,” Structural Health Monitoring, vol. 22, no. 2, pp. 1308–1325, 2023, doi:10.1177/14759217221107566.
[16] M. Rautela, J. Senthilnath, J. Moll, and S. Gopalakrishnan, “Combined two-level damage identification strategy using ultrasonic guided waves and physical knowledge assisted machine learning,” Ultrasonics, vol. 115, Art. no. 106451, 2021,doi:10.1016/j.ultras.2021.106451.
[17] X. Wang, M. Lin, J. Li, J. Tong, X. Huang, L. Liang, Z. Fan, and Y. Liu, “Ultrasonic guided wave imaging with deep learning: Applications in corrosion mapping,” Mechanical Systems and Signal Processing, vol. 169, Art. no. 108761, 2022, doi:10.1016/j.ymssp.2021.108761.
[18] Y. Ran, C. Qian, X. Wang, W. Zhang, and R. Wang, “Corrosion Monitoring in Automotive Lap Joints Based on Imaging Methods of Lamb Waves,” Sensors, vol. 24, no. 24, Art. no. 8092, 2024,doi: 10.3390/s24248092.
[19] L. Huang, Z. Luo, L. Zeng, and J. Lin, “Detection and localization of corrosion using the combination information of multiple Lamb wave modes,” Ultrasonics, vol. 138, Art. no. 107246, 2024, doi: 10.1016/j.ultras.2024.107246.
[20] H. Sun, W. Shao, J. Song, X. Yang, Y. Wang, and X. Qing, “Corrosion quantification of plate-type structures using Lamb wavefield and monogenic signal processing,” Ultrasonics, vol. 130, Art.no.106935,2023,doi: 10.1016/j.ultras.2023.106935.
[21] S. Sawant, A. Sethi, S. Banerjee, and S. Tallur, “Unsupervised learning framework for temperature compensated damage identification and localization in ultrasonic guided wave SHM with transfer learning,” Ultrasonics, vol. 130, Art. no. 106931, 2023,doi:10.1016/j.ultras.2023.106931.
[22] V. Nerlikar, O. Mesnil, R. Miorelli, and O. D’Almeida, “Damage detection with ultrasonic guided waves using machine learning and aggregated baselines,” Structural Health Monitoring, vol. 23, no. 1, pp. 443–462, 2024, doi: 10.1177/14759217231169719.
[23] J. Li, M. Wang, H. Chen, P. Wang, and W. Wang, “Investigation on characteristics of tensile damage and microstructure evolution of steel AISI 316L by nonlinear ultrasonic Lamb wave,” International Journal of Pressure Vessels and Piping, vol. 198, Art. no. 104680, 2022,doi: 10.1016/j.ijpvp.2022.104680.
[24] J. Hua, X. Cao, Y. Yi, and J. Lin, “Time-frequency damage index of Broadband Lamb wave for corrosion inspection,” Journal of Sound and Vibration, vol. 464, Art. no. 114985, 2020,doi: 10.1016/j.jsv.2019.114985.
[25] V. T. Rathod and D. Roy Mahapatra, “Ultrasonic Lamb wave based monitoring of corrosion type of damage in plate using a circular array of piezoelectric transducers,” NDT & E International, vol. 44, no. 7, pp. 628–636, 2011, doi: 10.1016/j.ndteint.2011.07.002.
[26] D. Wang, W. Zhang, X. Wang, and B. Sun, “Lamb-Wave-Based Tomographic Imaging Techniques for Hole-Edge Corrosion Monitoring in Plate Structures,” Materials, vol. 9, no. 11, Art. no. 916, 2016, doi: 10.3390/ma9110916.
[27] Z. Guo, R. Zhou, Y. Gao, W. Fu, and Q. Yu, “Towards ultrasonic guided wave fine-grained damage detection on hierarchical multi-label classification network,” Mechanical Systems and Signal Processing, vol. 218, Art. no. 111582, 2024,doi: 10.1016/j.ymssp.2024.111582.
[28] Y. Shen, J. Wu, J. Chen, W. Zhang, X. Yang, and H. Ma, “Quantitative Detection of Pipeline Cracks Based on Ultrasonic Guided Waves and Convolutional Neural Network,” Sensors, vol. 24, no. 4, Art. no. 1204, 2024, doi: 10.3390/s24041204.
[29] C. Nicard, M. Rébillat, O. Devos, M. El May, F. Letellier, S. Dubent, M. Thomachot, M. Fournier, P. Masse, and N. Mechbal, “In-situ monitoring of µm-sized electrochemically generated corrosion pits using Lamb waves managed by a sparse array of piezoelectric transducers,” Ultrasonics, vol. 147, Art. no. 107527, 2025,doi: 10.1016/j.ultras.2024.107527.
[30] H. Lu, S. Cantero-Chinchilla, B. Rotsaert, A. Croxford, K. Gryllias, and D. Chronopoulos, “Damage identification using ultrasonic Lamb waves with multi-scale adaptive attention Transformer-based unsupervised domain adaptation,” Mechanical Systems and Signal Processing, vol. 234, Art. no. 112772, 2025, doi:10.1016/j.ymssp.2025.112772.
[31] C. Nicard, M. Rébillat, O. Devos, M. El May, F. Letellier, S. Dubent, M. Thomachot, M. Fournier, P. Masse, and N. Mechbal, “COQTEL project dataset: Corrosion quantification trough extended use of Lamb waves,” Data in Brief, vol. 59, Art. no. 111393, 2025,doi: 10.1016/j.dib.2025.111393.
[32] C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, pp. 273–297, 1995, doi: 10.1007/BF00994018.
[33] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794, 2016, doi:10.1145/2939672.2939785.
[34] R. Caruana, “Multitask learning,” Machine Learning, vol. 28, pp. 41–75, 1997, doi: 10.1023/A:1007379606734.
[35] B. Sun and K. Saenko, “Deep CORAL: Correlation alignment for deep domain adaptation,” in Computer Vision – ECCV 2016 Workshops, pp. 443–450, 2016, doi:10.1007/978-3-319-49409-8_35.
[36] H. R. Künsch, “The jackknife and the bootstrap for general stationary observations,” The Annals of Statistics, vol. 17, no. 3, pp. 1217–1241, 1989, doi:10.1214/aos/1176347265.
[37] A. Altmann, L. Toloşi, O. Sander, and T. Lengauer, “Permutation importance: A corrected feature importance measure,” Bioinformatics, vol. 26, no. 10, pp. 1340–1347, 2010,doi:10.1093/bioinformatics/btq134.
[38] A. N. Angelopoulos and S. Bates, “Conformal prediction: A gentle introduction,” Foundations and Trends in Machine Learning, vol. 16, no. 4, pp. 494–591, 2023, doi:10.1561/2200000101.
Khodadosti, M. & Taheri, A. (2027). Laboratory Assessment of Corrosion in 316L Stainless Steel Based on Lamb Waves and Machine Learning. Modares Mechanical Engineering, 27(4), 327–338. https://doi.org/10.48311/mme.2026.123003.83090
MLA
Khodadosti, M., & Taheri, A. "Laboratory Assessment of Corrosion in 316L Stainless Steel Based on Lamb Waves and Machine Learning", Modares Mechanical Engineering, 27, 4, 2027, 327–338. doi: 10.48311/mme.2026.123003.83090
HARVARD
Khodadosti, M., & Taheri, A. (2027). 'Laboratory Assessment of Corrosion in 316L Stainless Steel Based on Lamb Waves and Machine Learning', Modares Mechanical Engineering, 27(4), pp. 327–338. doi: 10.48311/mme.2026.123003.83090
CHICAGO
Khodadosti, M. & Taheri, A., "Laboratory Assessment of Corrosion in 316L Stainless Steel Based on Lamb Waves and Machine Learning." Modares Mechanical Engineering, 27 4 (2027): 327–338, doi: 10.48311/mme.2026.123003.83090
VANCOUVER
Khodadosti M., Taheri A. Laboratory Assessment of Corrosion in 316L Stainless Steel Based on Lamb Waves and Machine Learning. Modares Mechanical Engineering. 2027;27(4):327–338 (In Persian). doi: 10.48311/mme.2026.123003.83090