OVERVIEW OF THE USE OF ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING IN APPLIED MECHANICS
DOI:
https://doi.org/10.31471/1993-9965-2024-1(56)-79-91Keywords:
applied mechanics, machine learning, artificial intelligence, fracture mechanics, material science.Abstract
The development of information technology, computing power and the emergence of new methods for processing large amounts of data have led to the emergence of a new paradigm - Big Data Science. The main approaches to working with big data are artificial intelligence and machine learning. Their use allows computer programs to make inferences and predictions based on input data, and to extract useful information from it. The use of artificial intelligence and machine learning in the field of applied mechanics can significantly expand the possibilities for conducting research and solving practical problems. The purpose of this paper is to review the possibilities of applying AI and ML methods to solve problems in applied mechanics, and to present considerations for the implementation of the research process using ML, the importance of preliminary preparation, and data processing for the successful application of methods in research. The review provides definitions for machine learning and artificial intelligence, analyses the typical procedure and basic principles of conducting research using ML, the main algorithms and the sequence of research using them, regression models, classification and clustering methods. It considers the requirements for the volume, completeness and reliability of the data used in the study. The article describes the processes of collecting research data, the stages of its processing and preparation, and the factors that influence the choice of a model. The processes of training the model and evaluating its behaviour and performance are considered. A review of research in applied mechanics using artificial intelligence or machine learning methods is carried out. In particular, the article analyses the use of methods in manufacturing defect detection, manufacturing quality assessment, manufacturing process automation, structural health monitoring, and fracture mechanics and materials science research. Conclusions are drawn on the reasons for the proliferation of the use of ML and AI methods in applied mechanics research, and the dominant approaches are presented. The importance of addressing the challenges related to the volume and quality of research data and the use of preprocessing techniques is emphasised due to their crucial role in the implementation of ANN.
Downloads
References
Hansen C., Johnson C., Pascucci V., Silva C. The Fourth Paradigm: Data-Intensive Scientific Discovery. 2009. С. 153–163. https://doi.org/10.1007/978-3-642-33299-9_1.
Veres O. M., Olyvko R. M. Klasyfikatsiia metodiv analizu Velykykh danykh, Visnyk Natsio-nalnoho Universytetu «Lvivska Politekhnika» «Informatsiini Systemy Ta Merezhi», 2018. Jun. Р. 84. URL: http://nbuv.gov.ua/UJRN/VNULPICM_2017_872_12 [In Ukrainian]
Wickramasinghe C. S., Amarasinghe K., Marino D. L., Rieger C., Manic M. Explainable Unsupervised Machine Learning for Cyber-Physical Systems. IEEE Access. 2021. Iss. 9. Р. 131824–131843. DOI: https://doi.org/10.1109/ACCESS.2021.3112397.
Sutton R. S., Barto A. G. Reinforcement learning: an introduction. Cambridge, Massa-?hu-setts: The MIT Press, 2018. 526 с. ISBN 978-0-262-03924-6. https://doi.org/10.1109/TNN.1998.712192.
James G., Witten D., Hastie T., Tibshirani R. An introduction to statistical learning: with applications in R. New York, NY: Springer, 2021. 607 с. ISBN 978-1-07-161417-4. https://doi.org/10.1007/978-1-0716-1418-1.
Guo K., Yang Z., Yu C.-H., Buehler M. J. Artificial intelligence and machine learning in design of mechanical materials. Materials Horizons. 2021. Vol. 8, Iss. 4. P. 1153–1172. https://doi.org/10.1039/D0MH01451F.
Hushchyn I. V., Sych D. O. Analiz vplyvu poperednoi obrobky tekstu na rezultaty tekstovoi klasyfikatsii. Molodyi Vchenyi, No 10(1), P. 264–266, 2018. URL: https://www.molodyivchenyi.ua/index.php/journal/article/view/3755. [In Ukrainian]
Artkin F. Applications of Artificial Intelligence in Mechanical Engineering. European Journal of Science and Technology. 2022. https://doi.org/10.31590/ejosat.1224045.
Wiangkham A., Aengchuan P., Kasemsri R., Pichitkul A., Tantrairatn S., Ariyarit A. Improvement of Mixed-Mode I/II Fracture Toughness Modeling Prediction Performance by Using a Multi-Fidelity Surrogate Model Based on Fracture Criteria. Materials. 2022. Vol. 15, Iss. 23. P. 8580. https://doi.org/10.3390/ma15238580.
Alemu Y., Lahmer T., Walther C. Damage Detection with Data-Driven Machine Learning Models on an Experimental Structure. Eng. 2024. Vol. 5. P. 629–656. https://doi.org/10.3390/eng5020036.
Konovalenko I., Maruschak P., Brevus V., Prentkovskis O. Recognition of Scratches and Abrasions on Metal Surfaces Using a Classifier Based on a Convolutional Neural Network. Metals. 2021. Vol. 11, Iss. 4. P. 549. https://doi.org/10.3390/met11040549.
Davari N., Veloso B., Costa G. D. A., Pereira P. M., Ribeiro R. P., Gama J. A Survey on Data-Driven Predictive Maintenance for the Railway Industry. Sensors. 2021. Vol. 21, Iss. 17. P. 5739. https://doi.org/10.3390/s21175739.
Peres R. S., Dionisio Rocha A., Leitao P., Barata J. IDARTS – Towards intelligent data analysis and real-time supervision for industry 4.0. Computers in Industry. 2018. Vol. 101. P. 138–146. https://doi.org/10.1016/j.compind.2018.07.004.
Raja H. A., Kudelina K., Asad B., Vaimann T., Kallaste A., Rassõlkin A., Khang H. V. Signal Spectrum-Based Machine Learning Approach for Fault Prediction and Maintenance of Electrical Machines. Energies. 2022. Vol. 15, Iss. 24. P. 9507. https://doi.org/10.3390/en15249507.
Khorsheed R. M., Beyca O. F. An integrated machine learning: Utility theory framework for real-time predictive maintenance in pumping systems. Proceedings of the Institution of Mechanical Engineers, Part B. Journal of Enginee-ring Manufacture. 2021. Vol. 235, Iss. 5. P. 887–901. https://doi.org/10.1177/0954405420970517.
Maniraj J., Arockiasamy F. S., Kumar C. R., Kumar D. A., Jenish I., Suyambulingam I., Rangappa S. M., Siengchin S. Machine Learning Techniques for the Design and Optimization of Polymer Composites: A Review. E3S Web of Conferences. 2023. Vol. 428. P. 02013. https://doi.org/10.1051/e3sconf/202342802013.
Soni M., Misra S. Machine-Learning-Assisted Design of Multiband Terahertz Metamaterial Absorber. ACS Applied Optical Materials. 2023. Vol. 1, Iss. 10. P. 1679–1687. https://doi.org/10.1021/acsaom.3c00246.
Zhang A., Liu Y., Yang J., Li Z., Zhang C., Li Y. Shenyang Blower Works Group Machine Learning Based Design Optimization of Centri-fugal Impellers. 2022. https://doi.org/10.33737/gpps21-tc-235.
Dworschak F., Dietze S., Wittmann M., Schleich B., Wartzack S. Reinforcement Learning for Engineering Design Automation. Advanced Engineering Informatics. 2022. Vol. 52. P. 101612. https://doi.org/10.1016/j.aei.2022.101612.
Koester M. Making Industrial Analytics work for Factory Automation Applications. Machine Learning for Cyber Physical Systems. Ред. Beyerer J., Kühnert C., Niggemann O. Berlin, Heidelberg: Springer Berlin Heidelberg, 2019.
P. 116–122. https://doi.org/10.1007/978-3-662-58485-9_13.
Ziatdinov M., Dyck O., Maksov A., Li X., Sang X., Xiao K., Unocic R. R., Vasudevan R., Jesse S., Kalinin S. V. Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identifi-cation and Tracking Local Transformations. ACS Nano. 2017. Vol. 11, Iss. 12. P. 12742–12752. https://doi.org/10.1021/acsnano.7b07504.
Yasnii О. P., Pastukh O. А., Pyndus Yu. І., Lutsyk N. S., Didych I. S. Prediction of the Diagrams of Fatigue Fracture of D16T Aluminum Alloy by the Methods of Machine Learning. Materials Science. 2018. Vol. 54, Iss. 3. P. 333–338. https://doi.org/10.1007/s11003-018-0189-9.
Yasniy O., Didych I., Lapusta Y. Prediction of fatigue crack growth diagrams by methods of machine learning under constant amplitude loading. Acta Metallurgica Slovaca. 2020. Vol. 26, Iss. 1. P. 31–33. https://doi.org/10.36547/ams.26.1.346.
Lyu Y., Yang Z., Liang H., Zhang B., Ge M., Liu R., Zhang Z., Yang H. Artificial intelligence‐assisted fatigue fracture recognition based on morphing and fully convolutional networks. Fatigue & Fracture of Engineering Materials & Structures. 2022. Vol. 45, Iss. 6. P. 1690–1702. https://doi.org/10.1111/ffe.13693.
Schleder G. R., Padilha A. C. M., Acosta C. M., Costa M., Fazzio A. From DFT to machine learning: recent approaches to materials science – a review. Journal of Physics: Materials. 2019. Vol. 2, Iss. 3. P. 032001. https://doi.org/10.1088/2515-7639/ab084b.
Merchant A., Batzner S., Schoenholz S. S., Aykol M., Cheon G., Cubuk E. D. Scaling deep learning for materials discovery. Nature. 2023. Vol. 624, Iss. 7990. P. 80–85. https://doi.org/10.1038/s41586-023-06735-9.
Liu Y., Zhao T., Ju W., Shi S. Materials discovery and design using machine learning. Journal of Materiomics. 2017. Vol. 3, Iss. 3. P. 159–177. https://doi.org/10.1016/j.jmat.2017.08.002.
Isayev O., Oses C., Toher C., Gossett E., Curtarolo S., Tropsha A. Universal fragment descriptors for predicting properties of inorganic crystals. Nature Communications. 2017. Vol. 8, Iss. 1. P. 15679. https://doi.org/10.1038/ncomms15679.
Guo Z., Malinov S., Sha W. Modelling beta transus temperature of titanium alloys using artificial neural network. Computational Materials Science. 2005. Vol. 32, Iss. 1. P. 1–12. https://doi.org/10.1016/j.commatsci.2004.05.004.
Altun F., Kişi Ö., Aydin K. Predicting the compressive strength of steel fiber added lightweight concrete using neural network. Computational Materials Science. 2008. Vol. 42, Iss. 2. P. 259–265. https://doi.org/10.1016/j.commatsci.2007.07.011.
Topçu İ. B., Sarıdemir M. Prediction of properties of waste AAC aggregate concrete using artificial neural network. Computational Materials Science. 2007. Vol. 41, Iss. 1. P. 117–125. https://doi.org/10.1016/j.commatsci.2007.03.010.
Salahinejad M., Le T. C., Winkler D. A. Capturing the Crystal: Prediction of Enthalpy of Sublimation, Crystal Lattice Energy, and Melting Points of Organic Compounds. Journal of Chemical Information and Modeling. 2013. Vol. 53, Iss. 1. P. 223–229. https://doi.org/10.1021/ci3005012.
Häse F., Valleau S., Pyzer-Knapp E., Aspuru-Guzik A. Machine learning exciton dynamics. Chemical Science. 2016. Vol. 7, Iss. 8. P. 5139–5147. https://doi.org/10.1039/C5SC04786B.
Hansen K., Montavon G., Biegler F., Fazli S., Rupp M., Scheffler M., Von Lilienfeld O. A., Tkatchenko A., Müller K.-R. Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies. Journal of Chemical Theory and Computation. 2013. Vol. 9, Iss. 8. P. 3404–3419. https://doi.org/10.1021/ct400195d.
Ward L., Agrawal A., Choudhary A., Wolverton C. A general-purpose machine learning framework for predicting properties of inorganic materials. npj Computational Materials. 2016. Vol. 2, Iss. 1. P. 16028. https://doi.org/10.1038/
npjcompumats.2016.28.
Lo K., Wang L. L., Neumann M., Kinney R., Weld D. S. S2ORC: The Semantic Scholar Open Research Corpus. arXiv, 2019. https://doi.org/10.48550/ARXIV.1911.02782.
ChemDataExtractor. URL: http://chemdataextractor.org/.
Deep Search, IBM Research. URL: https://research.ibm.com/projects/deep-search.
Liu Y., Yang Z., Yu Z., Liu Z., Liu D., Lin H., Li M., Ma S., Avdeev M., Shi S. Generative artificial intelligence and its applica-tions in materials science: Current situation and future perspectives. Journal of Materiomics. 2023. Vol. 9, Iss. 4. P. 798–816. https://doi.org/10.1016/j.jmat.2023.05.001.
Chen L., Zhang W., Nie Z., Li S., Pan F. Generative models for inverse design of inorganic solid materials. Journal of Materials Informatics. 2021. https://doi.org/10.20517/jmi.2021.07.
Downloads
Published
How to Cite
Issue
Section
License
Авторські права....
1.png)
1.png){kind=logo}
