PREDICTING STRUCTURAL DYNAMICS CHARACTERISTICS OF A TURBINE BLADE USING ARTIFICIAL INTELLIGENCE

Year 2025, Volume: 11 Issue: 3, 364 - 375, 31.12.2025

Ufuk Kortağ

Abstract

In high-performance engineering systems such as turbomachinery and aerospace structures, accurately predicting structural dynamic properties like natural frequency is critical for avoiding resonance, ensuring fatigue life, and maintaining rotordynamic stability. While finite element analysis (FEA) offers high accuracy, it becomes computationally expensive when repeated across a broad design space defined by geometric variations. To address this, a deep learning-based surrogate model was developed to predict natural frequencies from basic geometric parameters such as length, thickness, and angle of attack. A dataset of 21 geometrically distinct configurations was created using coarse-mesh FEA simulations, each taking approximately 30 seconds. Twenty samples were used for training a deep neural network (DNN), with one sample reserved for validation. The trained model achieved prediction times around 1 millisecond and relative errors of 1.1–3.3% within the training range and 0.1–16.5% outside it. This represents a drastic reduction in computational cost while maintaining acceptable accuracy. The proposed method enables rapid design iterations, sensitivity analysis, and early-stage decision-making in structural dynamics. It offers a practical alternative to traditional FEA for scenarios requiring fast and repeated evaluations across varying geometries.

Keywords

Gas Turbine Engine , Natural Frequency , Deep Learning , Finite Element Analysis , Artificial Intelligence

References

• [1] K. Kim and Y. S. Lee, "Modal characteristics and fatigue strength of compressor blades," J. Mech. Sci. Technol., vol. 28, pp. 1421–1429, 2014. doi: 10.1007/s12206-014-0129-z
• [2] Y. Kim, H. Cho, S. Park, H. Kim, and S. Shin, "Advanced Structural Analysis Based on Reduced-Order Modeling for Gas Turbine Blade," American Institute of Aeronautics and Astronautics Journal, vol. 56, no. 8, pp. 3369–3373, 2018. doi: 10.2514/1.J057063
• [3] A. Szczepankowski, R. Przysowa, J. Perczyński, and A. Kułaszka, "Health and Durability of Protective and Thermal Barrier Coatings Monitored in Service by Visual Inspection," Coatings, vol. 12, p. 624, 2022. doi: 10.3390/coatings12050624
• [4] A. Sahu and S. Chakravarty, "Regression-Based Neural Network Simulation for Vibration Frequencies of the Rotating Blade," in Springer Proc. Math. Stat., vol. 171, Singapore: Springer, 2016. doi: 10.1007/978-981-10-1454-3_2
• [5] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, pp. 436–444, 2015. doi: 10.1038/nature14539
• [6] M. Spodniak, M. Hovanec, and P. Korba, "A novel method for the natural frequency estimation of the jet engine turbine blades based on its dimensions," Heliyon, vol. 10, no. 4, 2024. doi: 10.1016/j.heliyon.2024.e26041
• [7] Y. Zhang, L. Chen, and M. Yang, “Deep convolutional neural networks for vibration-based fault identification and frequency prediction in turbine disks,” Mechanical Systems and Signal Processing, vol. 165, pp. 108300, 2022.
• [8] H. Li and W. Sun, “Dynamic response prediction of rotating machinery using hybrid LSTM networks under variable loading,” Journal of Sound and Vibration, vol. 532, pp. 117003, 2023.
• [9] S. K. Rao and P. K. Roy, “Reduced-order modeling of structural vibrations using POD and neural regression techniques,” Finite Elements in Analysis and Design, vol. 212, pp. 104729, 2023.
• [10] M. García, F. Muñoz, and J. Hernández, “Uncertainty-aware mode shape prediction using Gaussian process surrogate models,” Engineering Structures, vol. 274, pp. 115120, 2023.
• [11] L. Wang and Z. Luo, “Physics-informed neural networks for eigenvalue problems in structural dynamics,” Computer Methods in Applied Mechanics and Engineering, vol. 412, pp. 116054, 2023.
• [12] T. Ahmed and A. Khalid, “Metaheuristic-assisted ANN framework for natural frequency optimization of turbine blades,” Aerospace Science and Technology, vol. 144, pp. 108875, 2024.
• [13] ANSYS Inc., "ANSYS Theory Reference, Version 5.6," 1999. [Online]. Available: https://www.caee.utexas.edu/prof/kallivokas/teaching/ANSYS_examples/ansys56theory.pdf. [Accessed: May. 1, 2025].
• [14] M. Melina, H. Sukono, H. Napitupulu, and N. Mohamed, "A Conceptual Model of Investment-Risk Prediction in the Stock Market Using Extreme Value Theory with Machine Learning: A Semisystematic Literature Review," Risks, vol. 11, p. 60, 2023. doi: 10.3390/risks11030060