Modeling of QSTE340TM steel FCG curve by neural network
| Назва | Modeling of QSTE340TM steel FCG curve by neural network |
| Назва англійською | Modeling of QSTE340TM steel FCG curve by neural network |
| Автори | Oleh Yasniy, Liubov Tsymbaliuk, Nataliia Blashchak, Andriy Babiy |
| Принадлежність | Ternopil Ivan Puluj National Technical University, Ternopil, Ukraine |
| Бібліографічний опис | Modeling of QSTE340TM steel FCG curve by neural network / Oleh Yasniy, Liubov Tsymbaliuk, Nataliia Blashchak, Andriy Babiy // Scientific Journal of TNTU. — Tern.: TNTU, 2025. — Vol 120. — No 4. — P. 5–9. |
| Bibliographic description: | Yasniy O., Tsymbaliuk L., Blashchak N., Babiy A. (2025) Modeling of QSTE340TM steel FCG curve by neural network. Scientific Journal of TNTU (Tern.), vol 120, no 4, pp. 5–9. |
| DOI: | https://doi.org/10.33108/visnyk_tntu2025.04.005 |
| УДК | 004.8; 620.1 |
| Ключові слова |
QSTE340TM steel, machine learning, fatigue crack growth rate; neural network,
regression problem. |
This study focuses on modeling the fatigue crack growth rate of QSTE340TM steel using a neural network. This material is a thermomechanically rolled high-strength, low-alloy steel with a yield strength of at least 340 MPa, offering a combination of strength, weldability, and excellent cold-forming properties. It’s a go-to material for automotive and structural applications where durability and lightweight design are critical. The classical deterministic methods for assessing fatigue crack growth rates are often quite expensive and require a well-equipped testing facility. In contrast, in recent decades, the methods of machine learning have become widespread thanks to their ability to discover previously unobvious data-driven dependencies. Machine learning is a part of artificial intelligence. It is trained on existing data and improves over time without requiring explicit programming. The experimental dataset was taken from open scientific sources. It contained the fatigue crack growth rate data for four stress ratios of 0.1, 0.3, 0.5, and fatigue crack growth rate da/dN, and stress ratio R. The target feature was da/dN, and the two rest were treated as input features. The model was shown only the data with stress ratio R that was equal to 0.1, 0.3, and 0.7. The model was tested on fatigue crack growth rate data with a stress ratio (R) of 0.5. The neural network model in the form on multilayer perceptron was built. The model consisted of two hidden layers, each with 100 and 80 neurons, respectively. The activation function was RELU. The solver was chosen as Adam, and maximum iterations parameter was 500. The model's errors were as follows: MSE = 1.238e-10, MAE = 8.594e-06, and R² = 0.95346. From the obtained results, neural network gives quite accurate prediction results and can solve such kinds of problems. | |
| ISSN: | 2522-4433 |
| Перелік літератури |
1. QStE340TM Steel, Datasheet, Properties, Cross-Reference Table, Suppliers.
2. QStE340TM Steel – Solucky Steel.
3. SEW092 QStE340TM automotive low-carbon steel coils and sheets - BBN Steel Materials Supplier.
4. Zhang A., Lipton Z. C., Li M., Smola A. J. (2023) Dive into Deep Learning, 2023, Cambridge University Press.
5. Grus J. (2019) Data science from scratch: First principles with Python (2nd ed.), O’Reilly Media.
6. Nykytyuk S. О., Sverstiuk A. S., Klymnyuk S. I., (2023) Pyvovarchuk D. S., Palaniza Y. B. Approach to prediction and receiver operating characteristic analysis of a regression model for assessing the severity of the course Lyme borreliosis in children. Rheumatology, vol. 61, no. 5, pp. 345–352.
7. Mosiy L., Sverstiuk A. (2025) Methods Machine Learning for Classifying ECG Based on Rhythmic and Morphological Features. Bulletin of the National University “Lviv Polytechnic”. Information Systems and Networks Series, vol. 18, no. 2, pp. 113–128.
8. James G., Witten D., Hastie T., Tibshirani R., Taylor J. (2023) An Introduction to Statistical Learning: With Applications in Python, Springer.
9. Yasniy O., Tymoschuk D., Didych I., Zagorodna N., Malyshevska O. (2024) Modelling of automotive steel fatigue lifetime by machine learning method. ITTAP 2024: 4th International Workshop on Information Technologies: Theoretical and Applied Problems, Ternopil, Ukraine, Opole, Poland, 2024, pp. 165–172.
10. Yasniy O., Maruschak P., Lapusta Y. (2011) Probabilistic modeling of surface crack growth in a roll of continuous casting machine. International Journal of Fracture, vol. 172, pp. 113–120,
11. Yasnii О, Pastukh A, Pyndus Yu., Lutsyk N., Didych I. (2018) Prediction of the diagrams of fatigue fracture of D16T aluminum alloy by the methods of machine learning. Materials Science, vol. 54, no. 3, pp. 333–338.
12. Lu Y., Yang F., Chen Te. (2019) Effect of single overload on fatigue crack growth in QSTE340TM steel and retardation model modification. Engineering Fracture Mechanics, vol. 212, pp. 81–94,
13. ASTM E647-23a. Standard Test Method for Measurement of Fatigue Crack Growth Rates. Book of Standards Volume 03.01. 2023.
14. Yang F.,Chen Te., Lu Y. (2019) Data for: Effect of single overload on fatigue crack growth in QSTE340TM steel and retardation model modification, vol. 1.
|
| References: |
1. QStE340TM Steel, Datasheet, Properties, Cross-Reference Table, Suppliers.
2. QStE340TM Steel – Solucky Steel.
3. SEW092 QStE340TM automotive low-carbon steel coils and sheets - BBN Steel Materials Supplier.
4. Zhang A., Lipton Z. C., Li M., Smola A. J. (2023) Dive into Deep Learning, 2023, Cambridge University Press.
5. Grus J. (2019) Data science from scratch: First principles with Python (2nd ed.), O’Reilly Media.
6. Nykytyuk S. О., Sverstiuk A. S., Klymnyuk S. I., (2023) Pyvovarchuk D. S., Palaniza Y. B. Approach to prediction and receiver operating characteristic analysis of a regression model for assessing the severity of the course Lyme borreliosis in children. Rheumatology, vol. 61, no. 5, pp. 345–352.
7. Mosiy L., Sverstiuk A. (2025) Methods Machine Learning for Classifying ECG Based on Rhythmic and Morphological Features. Bulletin of the National University “Lviv Polytechnic”. Information Systems and Networks Series, vol. 18, no. 2, pp. 113–128.
8. James G., Witten D., Hastie T., Tibshirani R., Taylor J. (2023) An Introduction to Statistical Learning: With Applications in Python, Springer.
9. Yasniy O., Tymoschuk D., Didych I., Zagorodna N., Malyshevska O. (2024) Modelling of automotive steel fatigue lifetime by machine learning method. ITTAP 2024: 4th International Workshop on Information Technologies: Theoretical and Applied Problems, Ternopil, Ukraine, Opole, Poland, 2024, pp. 165–172.
10. Yasniy O., Maruschak P., Lapusta Y. (2011) Probabilistic modeling of surface crack growth in a roll of continuous casting machine. International Journal of Fracture, vol. 172, pp. 113–120,
11. Yasnii О, Pastukh A, Pyndus Yu., Lutsyk N., Didych I. (2018) Prediction of the diagrams of fatigue fracture of D16T aluminum alloy by the methods of machine learning. Materials Science, vol. 54, no. 3, pp. 333–338.
12. Lu Y., Yang F., Chen Te. (2019) Effect of single overload on fatigue crack growth in QSTE340TM steel and retardation model modification. Engineering Fracture Mechanics, vol. 212, pp. 81–94,
13. ASTM E647-23a. Standard Test Method for Measurement of Fatigue Crack Growth Rates. Book of Standards Volume 03.01. 2023.
14. Yang F.,Chen Te., Lu Y. (2019) Data for: Effect of single overload on fatigue crack growth in QSTE340TM steel and retardation model modification, vol. 1.
|
| Завантажити |  |