A Light Amphibious Airplane's Drop Test Identification Using Multi Kernel Least Square Support Vector Machines

Article Sidebar

PDF
Published: Jun 20, 2023
Keywords:
Multi-kernel LS-SVM Gaussian radial basis Landing gear drop dynamics Light amphibious airplane

Main Article Content

S. Chinvorarat
Department of Mechanical and Aerospace Engineering King Mongkut’s University of Technology North Bangkok, Bangkok 10800, Thailand
B. Watjatrakul
Department of Mechanical and Aerospace Engineering King Mongkut’s University of Technology North Bangkok, Bangkok 10800, Thailand
P. Nimdum
Department of Mechanical and Aerospace Engineering King Mongkut’s University of Technology North Bangkok, Bangkok 10800, Thailand
T. Sangpet
Department of Mechanical and Aerospace Engineering King Mongkut’s University of Technology North Bangkok, Bangkok 10800, Thailand
P. Vallikul
Department of Mechanical and Aerospace Engineering King Mongkut’s University of Technology North Bangkok, Bangkok 10800, Thailand

Abstract

This article uses multi-kernel least square support vector machines to determine the drop test dynamics for a light amphibious aircraft's stock strut landing gear. The kernel function to assess system nonlinearity is the Gaussian radial basis. The suggested multi-kernel LS-SVM model has shown to provide more accurate displacement output estimation than the traditional LS-SVM model, with RMSE values of 0.21766 and 0.062726 for the strut and wheel of the landing gear, respectively. The drop test of the light amphibious aircraft is conducted to validate the identification capabilities.

Article Details

How to Cite
Chinvorarat, S., Watjatrakul, B. ., Nimdum, P. ., Sangpet, T. ., & Vallikul, P. . (2023). A Light Amphibious Airplane’s Drop Test Identification Using Multi Kernel Least Square Support Vector Machines. Journal of Research and Applications in Mechanical Engineering, 11(1), JRAME–23. Retrieved from https://ph01.tci-thaijo.org/index.php/jrame/article/view/251409
Issue
Vol. 11 No. 1 (2023)
Section
RESEARCH ARTICLES
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

by-nc-sa

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

References

Curry NS. Airplane landing gear design: principle and practice. Washington: AIAA Education Series; 1988.

Daniels JN. A method for landing gear modeling and simulation with experimental Validation. Contractor Report 201601. Hampton: NASA; 1996.

Vapnik V. Estimation of dependences based on empirical data. Moscow: Nauka; 1979.

Vapnik V. The nature of statistical learning theory. NewYork: Springer-Verlag; 1995.

Cristianini N, Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning method. England: Cambridge University Press; 2000.

Suykens J. Support vector machines: a nonlinear modeling and control perspective. Eur J Control. 2001;7(2-3):311-327.

Suykens J, Van Gestel T, De Brabanter J, De Moor B, Vandewalle J. Least squares support vector machines. Singapore: World Scientific; 2002.

Resendiz-Trejo J, Yu W, Li X. Support vector machine for nonlinear system online identification. 3rd International Conference on Electrical and Electronics Engineering; 2006 Sep 6-8; Veracruz, Mexico. USA: IEEE; 2006. p. 1-4.

Viana F, Steffen V, Zanini M, Magalhaes S, Goes L. Identification of a nonlinear landing gear model using nature-inspired optimization. Shock Vib. 2008;15:257-272.

Tarhouni M, Laabidi K, Lahmari-Ksouri M. System identification based on multi-kernel least square support. Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation; 2010 Oct 24-26; Valencia, Spain. Portugal: SciTePress; 2010. p. 310-315.

Ding Y, Wei X, Nie H, Li Y. Discharge coefficient calculation method of landing gear shock absorber and its influence on drop dynamics. J Vibroengineering. 2018;20(7):2550-2561.

Chinvorarat S. Weiner model drop test identification of a light amphibious airplane. Eng J. 2022;26(1):25-37.

Chinvorarat S, Watjatrakul B, Nimdum P, Sangeet T, Soontornpasatch T, Vallikul, P. Static testing for composite wing of a two-seater amphibious airplane. IOP Conf Ser: Mater Sci Eng. 2019;501:012026.

Chinvorarat S, Watjatrakul B, Nimdum P, Sangeet T, Soontornpasatch T, Vallikul P. Six-degree of freedom mathematical dynamic model of a light-sport aircraft. IOP Conf Ser: Mater Sci Eng. 2020;886:012011.

Chinvorarat S, Vallikul P. A novel retractable landing gear of a light amphibious airplane design, synthesis, analysis, and implementation. Aircr Eng Aerosp Technol. 2021;93(10):1547-1558.

ASTM. ASTM F2245-20: Standard specification for design and performance of a light-sport airplane. West Conshohocken: ASTM; 2020.

Milwizky B, Cook EF. Analysis of landing-gear behavior. Report NACA-TN-2755. USA: NACA; 1952.

Wang XD, Ye MY. Nonlinear dynamic system identification using least squares support vector machine regression. Proceedings of 2004 International Conference on Machine Learning and Cybernetics; 2004 Aug 26-29; Shanghai, China. USA: IEEE; 2004. p. 941-945.

Jing S. Identification of a deterministic wiener system based on input least squares algorithm and direct residual method. Int J Model Identif Control. 2020;34(3):208-216.

Sonnenburg S, Ratsch G, Schfer C, Schlkopf B. Large scale multiple kernel learning. J Mach Learn Res. 2006;7:1531-1565.

Xue CJ, Han Y, Qi WG, Dai JH. Landing-gear drop-test rig development and application for light airplanes. J Aircr. 2012;49(6):2064-2076.

Abramowitz A, Ingraham PA, McGuire R. Vertical drop test of a shorts 3-30 airplane. DOT/FAA/AR-99/87. Washington: Office of Aviation Research; 1999.