Stress Prediction Using Machine Learning and Optimization
Received: 28 December 2025 | Revised: 27 January 2026, 14 February 2026, and 27 February 2026 | Accepted: 28 February 2026 | Online: 4 April 2026
Corresponding author: G. Mahalakshmi
Abstract
Conventional stress prediction methods have high computational cost and poor generalization and noise sensitivity, which can limit their application in real-time. To address these challenges, this study presents an integrated framework that combines signal preprocessing, lightweight feature extraction, segmentation, classification, and adaptive optimization. Ultrasonic Guided Wave (UGW) signals are first processed using a Butterworth filter to suppress noise and enhance signal quality. The features are then extracted through Tiny Machine Learning (TinyML), enabling efficient deployment on resource‑constrained devices. For segmentation, a Multi‑Scale Attention Augmented U‑Net (MA‑U‑Net) is employed to capture stress fields across multiple resolutions while focusing on critical regions. Classification of damage states is performed using a Multilayer Perceptron (MLP), which effectively models nonlinear interactions. Finally, an Adaptive Stress-Strain Optimization Strategy (ASSOS) refines the model parameters under physics‑based constraints to ensure robust convergence. The framework was validated on the Open Guided Wave dataset, achieving 98.75% accuracy, with precision, recall, and F1 scores exceeding 98%. Comparative analysis confirmed superior performance over conventional FEM and Random Forest models. This unified approach offers a scalable solution for structural health monitoring. This proposed framework is a combined scheme, very precise and efficient in the prediction of the stress, offering scalable structural health monitoring.
Keywords:
machine learning, Butterworth filter, stress prediction, multilayer perceptron, Adaptive Stress Strain Optimization Strategy (ASSOS)Downloads
References
M. Tanveer, M. U. Elahi, J. Jung, M. M. Azad, S. Khalid, and H. S. Kim, "Recent Advancements in Guided Ultrasonic Waves for Structural Health Monitoring of Composite Structures," Applied Sciences, vol. 14, no. 23, Nov. 2024, Art. no. 11091. DOI: https://doi.org/10.3390/app142311091
J. Heimann, S. Mustapha, B. Yilmaz, and J. Prager, "Guided Waves in Composite Overwrapped Pressure Vessels and Considerations for Sensor Placement Toward Structural Health Monitoring—An Experimental Study," Journal of Nondestructive Evaluation, Diagnostics and Prognostics of Engineering Systems, vol. 8, no. 3, Aug. 2025, Art. no. 031007. DOI: https://doi.org/10.1115/1.4067667
X. Sui, "Structural Health Monitoring Technology: Advances in Multi-Modal Sensing and Data Fusion," in Proceedings of the 2025 2nd International Conference on Electrical Engineering and Intelligent Control (EEIC 2025), vol. 279, A. J. Moshayedi, Ed. Atlantis Press International BV, 2025, pp. 924–941. DOI: https://doi.org/10.2991/978-94-6463-864-6_80
K. Luo, C. Li, H. Zhang, and Y. Zhang, "Baseline-free multimodal damage detection framework for composite plate-like structures using Mamba with guided waves," Measurement, vol. 257, Jan. 2026, Art. no. 118958. DOI: https://doi.org/10.1016/j.measurement.2025.118958
H. Lu, S. C. 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, July 2025, Art. no. 112772. DOI: https://doi.org/10.1016/j.ymssp.2025.112772
A. Elhanashi, P. Dini, S. Saponara, and Q. Zheng, ''Advancements in TinyML: Applications, Limitations, and Impact on IoT Devices,'' Electronics, vol. 13, no. 17, Sept. 2024. DOI: https://doi.org/10.3390/electronics13173562
M. Maurizi, C. Gao, and F. Berto, "Predicting stress, strain and deformation fields in materials and structures with graph neural networks," Scientific Reports, vol. 12, no. 1, Dec. 2022, Art. no. 21834. DOI: https://doi.org/10.1038/s41598-022-26424-3
M. Y. Takara and K. A. Flanigan, "A Multimodal Fusion Architecture and Dataset: Advancing Camera and Geophone Integration for Smarter Infrastructure," in Structural Health Monitoring 2025, 2025. DOI: https://doi.org/10.12783/shm2025/37371
J. T. Hancock, T. M. Khoshgoftaar, and J. M. Johnson, ''Evaluating classifier performance with highly imbalanced Big Data,'' Journal of Big Data, vol. 10, no. 1, Apr. 2023, Art. no. 42. DOI: https://doi.org/10.1186/s40537-023-00724-5
M. S. Khan et al., ''Comparison of multiclass classification techniques using dry bean dataset,'' International Journal of Cognitive Computing in Engineering, vol. 4, pp. 6–20, June 2023. DOI: https://doi.org/10.1016/j.ijcce.2023.01.002
L. Pan et al., ''An ultra-sensitive resistive pressure sensor based on hollow-sphere microstructure induced elasticity in conducting polymer film,'' Nature Communications, vol. 5, no. 1, Jan. 2014, Art. no. 3002. DOI: https://doi.org/10.1038/ncomms4002
L. Maio, V. Memmolo, N. Christophel, S. Kohl, and J. Moll, ''Electromechanical admittance method to monitor ice accretion on a composite plate,'' Measurement, vol. 220, Oct. 2023, Art. no. 113290. DOI: https://doi.org/10.1016/j.measurement.2023.113290
S. Yu et al., ''Advancing spacecraft safety and longevity: A review of guided waves-based structural health monitoring,'' Reliability Engineering & System Safety, vol. 254, Feb. 2025, Art. no. 110586. DOI: https://doi.org/10.1016/j.ress.2024.110586
C. D. Coman, D. E. Crunteanu, G. Cican, and M. Stoia-Djeska, "Geometry Effects on Joint Strength and Failure Modes of Hybrid Aluminum-Composite Countersunk bolted Joints," Engineering, Technology & Applied Science Research, vol. 14, no. 1, pp. 12759–12768, Feb. 2024. DOI: https://doi.org/10.48084/etasr.6472
J. Wang, M. Schmitz, L. J. Jacobs, and J. Qu, ''Deep learning-assisted locating and sizing of a coating delamination using ultrasonic guided waves,'' Ultrasonics, vol. 141, July 2024, Art. no. 107351. DOI: https://doi.org/10.1016/j.ultras.2024.107351
L. Lomazzi, R. Junges, M. Giglio, and F. Cadini, ''Unsupervised data-driven method for damage localization using guided waves,'' Mechanical Systems and Signal Processing, vol. 208, Feb. 2024, Art. no. 111038. DOI: https://doi.org/10.1016/j.ymssp.2023.111038
C. Polle, S. Bosse, and A. S. Herrmann, ''Damage Location Determination with Data Augmentation of Guided Ultrasonic Wave Features and Explainable Neural Network Approach for Integrated Sensor Systems,'' Computers, vol. 13, no. 2, Jan. 2024. DOI: https://doi.org/10.3390/computers13020032
D. Mikhaylov, T. Polonelli, and M. Magno, ''On-Sensor TinyML Event-Based Fault Detection Strategies on Wind Turbine Blades,'' in 2024 IEEE Sensors Applications Symposium (SAS), Naples, Italy, July 2024, pp. 1–6. DOI: https://doi.org/10.1109/SAS60918.2024.10636542
G. Donati, F. Zonzini, and L. D. Marchi, ''Tiny Deep Learning Architectures Enabling Sensor-Near Acoustic Data Processing and Defect Localization,'' Computers, vol. 12, no. 7, June 2023. DOI: https://doi.org/10.3390/computers12070129
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, Jan. 2024. DOI: https://doi.org/10.1177/14759217231169719
X. Wu, M. Wang, J. Lin, and Z. Wang, ''Amoeba: An Efficient and Flexible FPGA-Based Accelerator for Arbitrary-Kernel CNNs,'' IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 32, no. 6, pp. 1086–1099, June 2024. DOI: https://doi.org/10.1109/TVLSI.2024.3383871
H. Zhang et al., "Transformer model combining cross-attention and self-attention guided by damage index for pipeline damage localization based on helical guided waves," Mechanical Systems and Signal Processing, vol. 231, May 2025, Art. no. 112669. DOI: https://doi.org/10.1016/j.ymssp.2025.112669
J. Moll et al., ''Open Guided Waves: online platform for ultrasonic guided wave measurements,'' Structural Health Monitoring, vol. 18, no. 5–6, pp. 1903–1914, Nov. 2019. DOI: https://doi.org/10.1177/1475921718817169
Downloads
How to Cite
License
Copyright (c) 2026 G. Mahalakshmi, G. Sujatha, Nisha Jebaseeli Antony, A. Bhuvaneshwari, S. Vasuki
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
