A new SVM regression approach for mechanical load identification

Issue title: Selected Papers from the 14th International Symposium on Applied Electromagnetics and Mechanics (ISEM 2009), Part II

Article type: Research Article

Authors: Mao, Wentao^{a; *} | Hu, Dike^a | Yan, Guirong^a

Affiliations: [a] MOE Key Laboratory of Strength and Vibration, Xi'an Jiaotong University, Xi'an, 710049, China

Correspondence: [*] Corresponding author: Wentao Mao, MOE Key Laboratory of Strength and Vibration, Xi'an Jiaotong University, Xi'an, 710049, China. Tel.: +86 29 82660978; Fax: +86 29 82664849; E-mail: maowt.mail@gmail.com

Abstract: Most traditional approaches to load identification usually perform not very well because the inverse identification problem in most practical cases is ill-posed. In this paper, a new approach to the identification of dynamic loads based on the solution path algorithm of support vector regression is proposed. A general framework of dynamic load identification using support vector regression is derived and the corresponding identification model using solution path algorithm is established. The results of numerical and experimental tests on cylinder vibration system show that the proposed approach greatly outperforms existing methods, i.e., direct inverse identification method, ε-SVR and LS-SVM, in terms of identification accuracy and numerical stability. As a conclusion, the proposed approach is applicable to a wide variety of mechanical cases.

Keywords: Load identification, support vector regression, inverse problem

DOI: 10.3233/JAE-2010-1213

Journal: International Journal of Applied Electromagnetics and Mechanics, vol. 33, no. 3-4, pp. 1001-1008, 2010