Використання методу скінченних елементів для моделювання фізичних процесів у реальному часі за допомогою розподілених обчислень
Владислав КозубThis study investigated the application of the finite element method for modelling complex physical processes in real time. The aim of the research was to determine the effectiveness of this method when combined with distributed computing. An integrated model was developed, combining classical numerical analysis with modern distributed system technologies to ensure high accuracy and computational efficiency. It was established that the finite element method had traditionally been used for modelling heat transfer, deformations, and electromagnetic phenomena. However, modern requirements for monitoring and control created the need to adapt this method for distributed computing. Algorithms for the efficient distribution of computational tasks were developed, allowing data processing delays to be minimised. Experimental simulations showed that the use of distributed computing reduced calculation time by almost 14.5 times – from 420 seconds on a single node to 29 seconds on 16 nodes – while maintaining a relative error of 2-4%. More than 50 test runs were conducted, confirming the system’s operational stability. The use of an adaptive integration step reduced computation time by 15% compared to a fixed step, demonstrating the effectiveness of load distribution optimisation. The obtained results confirmed the high potential of this method for solving real engineering problems, where speed and accuracy of calculations were crucial. The proposed methodology was recommended for use in industrial processes, monitoring, and control systems, as it provided fast and accurate modelling of complex engineering tasks with high scalability
Використані джерела
[1] Aldrini, J.A., Chihi, I., & Sidhom, L. (2023). Fault diagnosis and self-healing for smart manufacturing: A review. Journal of Intelligent Manufacturing, 35, 2441-2473. doi: 10.1007/s10845-023-02165-6.
[2] Aro, R.P., Hachem, B., Clin, J., Mac-Thiong, J., & Duong, L. (2020). Real‐time biomechanics using the finite element method and machine learning: Review and perspective. Medical Physics, 48(1), 7-18. doi: 10.1002/mp.14602.
[3] Bondarchuk, O., Kozub, V., & Kozub, Y. (2024). Analysis of the effectiveness of machine learning algorithms in big data processing. Computer-Integrated Technologies: Education, Science, Production, 56, 107-116. doi: 10.36910/67752524-0560-2024-56-13.
[4] Chen, H., Chen, J., Liu, X., Zhang, Z., Huang, Y., Zhang, Z., & Liu, H. (2025). Accelerated quasi-static FEM for real-time modeling of continuum robots with multiple contacts and large deformation. ArXiv. doi: 10.48550/arXiv.2503.06922.
[5] Chippagiri, S., Ravula, P., & Gangwani, D. (2024). Optimizing load balancing and task scheduling in cloud computing based on nature-inspired optimization algorithms. European Journal of Theoretical and Applied Sciences, 2(6), 794-805. doi: 10.59324/ejtas.2024.2(6).71.
[6] Fu, Y., Downey, A.R., Yuan, L., Huang, H.-T., & Ogunniyi, E.A. (2025). Simulation-in-the-loop additive manufacturing for real-time structural validation and digital twin development. Additive Manufacturing, 98, article number 104631. doi: 10.1016/j.addma.2024.104631.
[7] Garcia-Gasulla, M., Houzeaux, G., Ferrer, R., Artigues, A., López, V., Labarta, J., & Vázquez, M. (2019). MPI+X: Task-based parallelisation and dynamic load balance of finite element assembly. International Journal of Computational Fluid Dynamics, 33(3), 115-136. doi: 10.1080/10618562.2019.1617856.
[8] Ghosh, P., Eisele, S., Dubey, A., Metelko, M., Madari, I., Volgyesi, P., & Karsai, G. (2020). Designing a decentralized fault-tolerant software framework for smart grids and its applications. Journal of Systems Architecture, 109, article number 101759. doi: 10.1016/j.sysarc.2020.101759.
[9] Herrero-Perez, D., & Martínez Barberá, H. (2025). Multi-GPU acceleration for finite element analysis in structural mechanics. Applied Sciences, 15(3), article number 1095. doi: 10.3390/app15031095.
[10] Homeniuk, S.I., & Kozub, V.Yu. (2023). Parallel algorithm for forming the stiffness matrix of a finite element. Scientific Notes of the V.I. Vernadsky TNU. Series: Technical Sciences, 34(73), 82-87. doi: 10.32782/2663-5941/2023.1/12.
[11] Kayum, S., & Rogowski, M. (2019). High-performance computing applications’ transition to the cloud in the oil & gas industry. Retrieved from https://ieee-hpec.org/2019/2019Program/program_htm_files/c-HPEC_Website_Cloud.pdf.
[12] Kiran, U., Sharma, D., & Gautam, S.S. (2023). A GPU-based framework for finite element analysis of elastoplastic problems. Computing, 105, 1673-1696. doi: 10.1007/s00607-023-01169-7.
[13] Ma, Z., Lou, Y., Li, J., & Jin, X. (2020). An explicit asynchronous step parallel computing method for finite element analysis on multi-core clusters. Engineering with Computers, 36, 443-453. doi: 10.1007/s00366-019-00704-5.
[14] Meethal, R.E., Kodakkal, A., Khalil, M., & Ghantasala, A. (2022). Finite element method-enhanced neural network for forward and inverse problems. ArXiv. doi: 10.48550/arXiv.2205.08321.
[15] Ogundairo, O. (2024). Adaptive mesh refinement in numerical methods for fractional differential equations. Journal of Mathematics and Mathematics Education.
[16] Olm Serra, M. (2019). Scalable domain decomposition methods for finite element approximations of transient and electromagnetic problems. (Doctoral thesis, Polytechnic University of Catalonia, Barcelona, Spain).
[17] Pal, S., Jhanjhi, N.Z., Shawkat, A., Akila, D., Ali Almazroi, A., & Alsubaei, F.S. (2023). A hybrid edge-cloud system for networking service components optimization using the internet of things. Electronics, 12(3), article number 649. doi: 10.3390/electronics12030649.
[18] Seventekidis, P., Giagopoulos, D., Arailopoulos, A., & Markogiannaki, O. (2020). Structural health monitoring using deep learning with optimal finite element model generated data. Mechanical Systems and Signal Processing, 145, article number 106972. doi: 10.1016/j.ymssp.2020.106972.
[19] Shen, X., Zuo, Y., Kong, J., & Martinez, W. (2024). Artificial intelligence applications in high-frequency magnetic components design for power electronics systems: An overview. IEEE Transactions on Power Electronics, 39(7), 8478-8496. doi: 10.1109/TPEL.2024.3381431.
[20] Siddiq, M.A. (2020). Data-driven finite element method: Theory and applications. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 235(17), 3329-3339. doi: 10.1177/0954406220938805.
[21] Tang, Z., Xiaohui, D., Zhenbao, L., & Xiuli, D. (2022). Implementation of real-time hybrid simulation based on GPU computing. Structural Design of Tall and Special Buildings, 31(12), article number e1942. doi: 10.1002/tal.1942.
[22] Tripathy, S.S., Imoize, A.L., Rath, M., Tripathy, N., Bebortta, S., Lee, C.-C., Chen, T.-Y., Ojo, S., Isabona, J., & Pani, S.K. (2022). A novel edge-computing-based framework for an intelligent smart healthcare system in smart cities. Sustainability, 15(1), article number 735. doi: 10.3390/su15010735.
[23] Wang, Y., Gao, L., Qu, J., Xia, Z., & Deng, X. (2021). Isogeometric analysis based on geometric reconstruction models. Frontiers of Mechanical Engineering, 16, 782-797. doi: 10.1007/s11465-021-0648-0.
[24] Younis, A., Qiu, B., & Pompili, D. (2020). Latency-aware hybrid edge cloud framework for mobile augmented reality applications. In Proceedings of the 17th annual IEEE international conference on sensing, communication, and networking (pp. 1-9). Como: IEEE. doi: 10.1109/SECON48991.2020.9158429.
[25] Zhang, N., Xu, K., Yin, Z.Y., Li, K.-Q., & Jin, Y.-F. (2025). Finite element-integrated neural network framework for elastic and elastoplastic solids. Computer Methods in Applied Mechanics and Engineering, 433, article number 117474. doi: 10.1016/j.cma.2024.117474.