Nonlinear system identification; Model selection; Genetic Algorithms
Abstract :
[en] The Non-Linear Resonant Decay Method is an approach for the identification of non-linear systems with large
numbers of degrees of freedom. The identified non-linear model is expressed in linear modal space and
comprises the modal model of the underlying linear system with additional terms representing the non-linear
behaviour. Potentially, a large number of these non-linear terms will exist but not all of them will be significant.
The problem of deciding which and how many terms are required for an accurate identification has previously
been addressed using the Forward Selection and Backward Elimination techniques. In this paper, a Genetic
Algorithm optimisation is proposed as an alternative to those methods. A simulated 5-DOF lumped parameter
non-linear system is used to demonstrate the proposed optimisation. The use of separate data sets for the
identification and validation of the modal model is also investigated. It is found that the Genetic Algorithm
approach yields significantly better results than the Backward Elimination and Forward Selection algorithms in
many cases.
Disciplines :
Mechanical engineering
Author, co-author :
Platten, Michael F; University of Manchester > School of Engineering
Wright, Jan Robert; University of Manchester > School of Engineering
Worden, Keith; University of Sheffield > Department of Mechanical Engineering
Cooper, Jonathan Edward; University of Manchester > School of Engineering
Dimitriadis, Grigorios ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Interactions Fluide-Structure - Aérodynamique expérimentale
Language :
English
Title :
Non-Linear Identification Using a Genetic Algorithm Approach for Model Selection
Publication date :
January 2005
Event name :
International Modal Analysis Conference IMAC 23
Event organizer :
Society for Experimental Mechanics
Event place :
Orlando, Florida, United States
Event date :
du 31 janvier au 3 fevrier 2005
Audience :
International
Main work title :
Proceedings of the 23rd International Modal Analysis Conference
Wright, JR; Platten, MF; Cooper, JE and Sarmast, M, 'Identification of multi-degree of freedom weakly nonlinear systems using a model based in modal space' (keynote paper), COST International Conference on Structural System Identification, 2001.
Al-Hadid, MA and Wright, JR, 'Developments in the force-state mapping technique for non-linear systems and the extension to the localisation of non-linear elements in a lumped parameter system', Mechanical Systems and Signal Processing, 3(3), 269-290, 1989.
Masri, SF; Sassi, H and Caughey, TK, 'Nonparametric identification of nearly arbitrary nonlinear systems', Journal of Applied Mechanics, 49, 619-627, 1982.
Fonseca, CM; Mendes, EM; Fleming, PJ and Billings, SA, 'Non-linear model term selection with genetic algorithms', IEEE/IEE Workshop on Natural Algorithms in Signal Processing, 1993.
Mao, KZ and Billings, SA, 'Variable selection in non-linear systems modelling', Mechanical Systems and Signal Processing, 13(2), 351-366, 1999.
Platten, MF; Wright, JR; Cooper, JE and Sarmast, M, 'Identification of Multi-Degree of Freedom Non-Linear Simulated and Experimental Systems', Proceedings of the International Seminar on Modal Analysis, 2002.
Platten, MF; Wright, JR and Cooper, JE, 'Identification of a simulated continuous structure with discrete nonlinear components using an extended modal model', 7th Biennial Conference on Engineering Systems Design and Analysis, 2004.
Platten, MF; Wright, JR and Cooper, JE, 'Identification of a continuous structure with discrete non-linear components using an extended modal model', Proceedings of the International Seminar on Modal Analysis, 2004.
Williams, R; Crowley, J and Vold, H, 1986, 'The Multivariate Mode Indicator Function in Modal Analysis', Proceedings of 4th International Modal Analysis Conference, 1986.
Man, KF; Tang, KS and Kwong, S, 'Genetic algorithms - concepts and designs', Springer-Verlag, ISBN 1852330724, 1999.
