Precedent-based method for predicting the features of aviation components

The uncertainty of the initial data and the limited number of use cases significantly complicate the prediction of the features of new components of aviation technology in the early stages of development. The aim of the research is to form a method of precedent forecasting, which allow evaluating the features of the projected part of a product in conditions of a lack of a priori information and with a nonlinear relations between design conditions and target parameters.

The method is based on the representation of the design situation in the form of a vector of conditions (X) and a vector of predicted properties (Y), as well as on the use of an observation protocol based on previously developed analogues. In case of a small number of precedents, the author proposes a multidimensional linear extrapolation procedure based on constructing subspaces of conditions and solutions and projecting a new design situation onto the space of known analogues. Moreover, in case of a significant sample and a nonlinear connection between input and output parameters, the author provides a neural network model based on a self-organizing Kohonen map.

The article formalizes the conditions for the application of both procedures, defines their mathematical models, and determines the principles for choosing the structure of the prognostic network. The practical significance of the results lies in the possibility of using accumulated design precedents for a preliminary assessment of product properties, reducing the number of design iterations and increasing the validity of design decisions.

1. Anisimov K. S., Evdokimenkov V. N., Krasil’shchikov M. N. [et al.]. Optimizatsiya protsessa sovershenstvovaniya aviatsionnykh kompleksov na baze kontseptsii funktsional’nogo proyektirovaniya. Izvestiya RAN. Teoriya i Sistemy Upravleniya. 2022;1:105–123. https://doi.org/10.31857/S0002338822010036. EDN: MQHLSR. (In Russ.).

2. Chu T., Pei Y. Intelligent Optimization Design Technology for Typical Structural Parts of Aircraft. Artificial Intelligence Technologies and Applications. 2024;382:18–29. https://doi.org/10.3233/FAIA231279.

3. Liu Y., Zhang S., Zhang J. [et al.]. Towards the Design of Future Aircraft: A Critical Review On the Tools and Methodologies. Aerospace Research Communications. 2024;2:13096. https://doi.org/10.3389/arc.2024.13096.

4. Krupa G. P. Application of Agile Model-Based Systems Engineering in aircraft conceptual design. The Aeronautical Journal. 2019;123(1268):1561–1601. https://doi.org/10.1017/aer.2019.53.

5. Ciampa P. D., Nagel B. AGILE Paradigm: The next generation collaborative MDO for the development of aeronautical systems. Progress in Aerospace Sciences. 2020;119:100643. https://doi.org/10.1016/j.paerosci.2020.100643.

6. Aamodt A., Plaza E. Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches. AI Communications. 2001;7(1):39–59. https://doi.org/10.3233/AIC-1994-7104

7. Queipo N. V., Haftka R. T., Shyy W. [et al.]. Surrogatebased analysis and optimization. Progress in Aerospace Sciences. 2005;41(1):1–28. https://doi.org/10.1016/j.paerosci.2005.02.001.

8. Simpson T. W., Peplinski J. D., Koch P. N., Allen J. K. Metamodels for Computer-based Engineering Design: Survey and recommendations. Engineering with Computers. 2001;17:129–150. https://doi.org/10.1007/PL00007198.

9. Viana F. A. C., Simpson T. W., Balabanov V., Toropov V. Metamodeling in Multidisciplinary Design Optimization: How Far Have We Really Come? AIAA Journal. 2014;52(4):670–690. https://doi.org/10.2514/1.J052375.

10. Cottrell M., Olteanu M., Rossi F. [et al.]. Self-Organizing Maps, theory and applications. Revista de Investigacion Operacional. 2018;39(1):1–22.

11. Kohonen T., Oja E., Simula O. [et al.]. Engineering applications of the self-organizing map. Proceedings of the IEEE. 1996;84(10):1358–1384. https://doi.org/10.1109/5.537105.

12. Skuratov V., Kuzmin K., Nelin I., Sedankin M. Application of Kohonen self-organizing map to search for region of interest in the detection of objects. Eureka: Physics and Engineering. 2020;1:62–69. https://doi.org/10.21303/2461-4262.2020.001133. EDN: NWIMRZ.

13. Jin R., Chen W., Simpson T. W. Comparative Studies of Metamodeling Techniques Under Multiple Modeling Criteria. Structural and Multidisciplinary Optimization. 2001;23(1):1–13. https://doi.org/10.1007/s00158-001-0160-4.

14. Forrester A. I. J., Sуbester A., Keane A. J. Engineering Design via Surrogate Modelling: A Practical Guide. Chichester: John Wiley & Sons, 2008. 228 p. https://doi.org/10.1002/9780470770801.

15. Martins J. R. R. A., Lambe A. B. Multidisciplinary Design Optimization: A Survey of Architectures. AIAA Journal. 2013;51(9):2049–2075. https://doi.org/10.2514/1.J051895.

16. Sobieszczanski-Sobieski J., Haftka R. T. Multidisciplinary aerospace design optimization: survey of recent developments. Structural Optimization. 1997;14:1–23. https://doi.org/10.1007/BF01197554.

17. Tao F., Zhang M. Digital Twin Shop-Floor: A New Shop-Floor Paradigm Towards Smart Manufacturing. IEEE Access. 2017 ; 5 : 20418 –20427 . https://doi.org/10.1109/ACCESS.2017.2756069.

18. Lee J., Bagheri B., Kao H.-A. A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems. Manufacturing Letters. 2015;3:18–23. https://doi.org/10.1016/j.mfglet.2014.12.001.