PSI - Issue 59

Author name / Structural Integrity Procedia 00 (2023) 000 – 000

Oleh Yasniy et al. / Procedia Structural Integrity 59 (2024) 271–278

277

0,017

300

Exper/Pred

Exper Pred

0,015

290

0,013

280

 (  i ) prediction, mm/mm

0,011

270

0,009

260

 , MPa

0,007

250

0,005

240

0,003

230

0,003

0,008

0,013

0,003

0,008

0,013

0,018

 (  i ) true, mm/mm

 (  i ) , mm/mm

Fig. 6. Predicted (   (  I ) prediction ) and experimental (   (  i ) true ) jump-like strain obtained by the method of neural networks

Fig. 7. Predicted and experimental dependences of the jump-like strain on the tensile stress obtained by the method of neural networks

5. Conclusions The careful selection of methods and datasets is important in achieving accurate prediction results. In addition, methods of supervised learning often show better results compared to other approaches. The neural networks method gives a prediction accuracy of 93.1%. In particular, the error between the results obtained by FE modelling and the experimental one does not exceed 12%. Therefore, comparing these results, it follows that the machine learning method is a powerful tool that can be used to solve problems in mechanics. References Alpaydin, E., 2010. Introduction to Machine Learning. MIT Press, pp. 584. Brunton, S. L., Kutz, J. N., 2019. Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control 1st Edition, Cambridge University Press, pp. 492 Didych, I., Yasniy, O., Fedak, S., Lapusta, Yu., 2022. Prediction of Jump - Like Creep Using Preliminary Plastic Strain. Procedia Structural Integrity 36, 166–170. Fedak, S., 2003. Jumplike Deformation of the AMg6 Alloy During Creep. Visnyk Ternopilskoho Derzhavnoho Tekhnichnoho Universytetu 8, 16 – 23. [in Ukrainian] Goodfellow, I., Bengio, Y., Courville, A., 2016. Deep Learning, The MIT Press, pp. 800. Harrington, P,. 2012. Machine Learning In Action, Manning, pp. 382. Haykin, S., 1999. Neural Networks: A Comprehensive Foundation. Prentice Hall, Hamilton, Ontario, pp.823. Javaheri, E., Kumala, V., Javaheri, A., Rawassizadeh, R., Lubritz, J., Graf, B., Rethmeier, M., 2020. Quantifying Mechanical Properties of Automotive Steels with Deep Learning Based Computer Vision Algorithms. Metals 10, 163. Mohanty, J.R., Verma, B.B., Parhi, D.R.K., Ray, D.R., 2009. Application of Artificial Neural Network for Predicting Fatigue Crack Propagation Life of Aluminum Alloys. Archives of Computational Materials Science and Surface Engineering 1, 133 – 138. Pidaparti, R.M.V., Palakal, M.J., 1995. Neural Network Approach to Fatigue-Crack-Growth Predictions Under Aircraft Spectrum Loadings. Journal of Aircraft 32, 825-831. Russell, S., Norvig P., 2020. Artificial Intelligence: A Modern Approach (Pearson Series in Artificial Intelligence) 4th Edition, Pearson pp. 1136 Smola, A., Vishwanathan, S.V.N., 2010. Introduction to Machine Learning. Cambridge University Press, pp. 234. Strizhalo, V.A., Vorob’ev, E.V., 1993. Low-Temperature Interrupted Yield of Structural Alloys. Strength of Material 25, 576  583.