Fast Time-varying modal parameter identification algorithm based on two-layer linear neural network learning for subspace tracking

Full Text (PDF, 282KB), PP.16-22

Views: 0 Downloads: 0

Author(s)

Kai Yang 1,* Kaiping Yu 1

1. Department of Astronautical Science and Mechanics, Harbin Institute of Technology, Harbin, Heilongjiang, China

* Corresponding author.

DOI: https://doi.org/10.5815/ijieeb.2011.01.03

Received: 8 Nov. 2010 / Revised: 23 Dec. 2010 / Accepted: 2 Jan. 2011 / Published: 8 Feb. 2011

Index Terms

Subspace tracking, time-varying modal parameter, identification algorithm, neural network learning

Abstract

The key of fast identification algorithm of time-varying modal parameter based on subspace tracking is to find efficient and fast subspace-tracking algorithm. This paper presents a modified version of NIC(Novel Information Criterion) adopted in two-layer linear neural network learning for subspace tracking, which is applied in time-varying modal parameter identification algorithm based on subspace tracking and get a new time-varying modal parameter identification algorithm. Comparing with the original subspace-tracking algorithm, there is no need to set a key control parameter in advance. Simulation experiments show that new time-varying modal parameter identification algorithm has a faster convergence in the initial period and a real experiment under laboratory conditions confirms further its validity of the time-varying modal identification algorithm presented in this paper.

Cite This Paper

Kai Yang, Kaiping Yu, "Fast Time-varying modal parameter identification algorithm based on two-layer linear neural network learning for subspace tracking", International Journal of Information Engineering and Electronic Business(IJIEEB), vol.3, no.1, pp.16-22, 2011. DOI:10.5815/ijieeb.2011.01.03

Reference

[1]Zou Jingxiang, Yu Kaiping and Pang Shiwei. Methods of time-varying structural parameter identification[J]. Advances in mechanics, 2000, 30(3):370-377

[2]Kefu Liu . Extension of modal analysis to linear time-varying system[J] . Journal of Sound and Vibration, 1999, 226(1):149-167

[3]Kefu Liu . Identification of linear time-varying system[J] . Journal of Sound and Vibration, 1997,206(4):487-505

[4]Juang J N and Pappa R S . An eigensystem realization algorithm for modal parameter identification and model reduction[J] . Journal of Guidance, Control and Dynamic, 1985,8(5):620-627

[5]Longman R W and Juang J N . Recursive form of the Eigensystem Realization algorithm for system identification[J] . Journal of Guidance, Control and Dynamic, 1989, 12(5):647-652

[6]Yu Kaiping, Xie Lili, Fan Jiuming et.al . A parameter identification of simple supported beams system carrying a moving mass[J] . Earthquake engineering and engineering vibration, 2002, 22(5):14-17

[7]Pang Shiwei, Yu Kaiping and Zou Jingxiang . Improved subspace method with application in linear tie-varying structural modal parameter indentification[J] . Chinese Journal of applied mechanics, 2005, 22(2):184-189

[8]Yang Lifang, Yu Kaiping, Pang Shiwei et. al . Comparison study on identification methods applied to linear time-varying structures[J] . Journal of Vibration and Shock, 2007,26(3):8-12

[9]F Tasker, A Bosse, S Fisher . Real-time modal parameter estimation using subspace methods:theory[J] . Mechanical Systems and Signal Processing,1998,12(6):797-808

[10]A Bosse, F Tasker, S Fisher . Real-time modal parameter estimation using subspace methods: application[J] . Mechanical Systems and Signal Processing, 1998, 12(6):809-823

[11]E M Dowling, L P Ammann and R D Degroat . A TQR-iteration based adaptive SVD for real time angel and frequency tracking[J] . IEEE Transactions on Signal Processing, 1994,42(4):914-926

[12]Wu Riqiang, Yu Kaiping and Zou Jingxiang . An improved subspace method and its application to parameter identification of time-varying structures[J] . Engineering Mechaics,2002,19(4):67-70

[13]Michel Verhaegen , Xiaode Yu . A class of subspace model identification algorithms to identify periodically and arbitrarily time-varying systems[J] . Automatica, 1995, 31:201-216

[14]Hiroshi Oku and Hidenori Kimura . Recursive 4SID algorithms using gradient type subspace tracking[J] . Automatica, 2002,38:1035-1043

[15]Pang Shiwei, Yu Kaiping and Zou Jingxiang. A projection approximation recursive subspace method for identification of modal parameter of time-varying structures [J]. Engineering Mechanics, 2002, 22(5):115-119

[16]Pang Shiwei, Yu Kaiping and Zou Jingxiang . Time-varying system identification using recursive subspace method based on free response data[J] . Journal of Vibration Engineering,2005, 18(2):233-237

[17]Bin Yang . Projection Approximation subspace tracking[J] . IEEE Transactions of Signal Processing, 1995, 43(1):95-107

[18]K Abed-Meraim, A Chkeif and Y Hua . Fast orthonormal PAST algorithm[J] . IEEE Signal Processing Letters, 2000, 7(3):60-62

[19]Bin Yang . An extension of the PASTd algorithm to both rank and subspace tracking[J] . IEEE Signal Processing Letters, 1995, 2(9):179-182

[20]Imran Ali, Doug Nyun Kim and Taikyeong Ted Jeong . A new subspace tracking algorithm using approximation of Gram-Schmidt procedure . In: 2009 International Conference on Information and Multimedia Technology, 2009, 245-248

[21]Yingbo Hua, Yong Xiang, Tianping Chen and so on . A new look at the power method for fast subspace tracking [J]. Digital Signal Processing, 1999,9:297-314

[22]Yingbo Hua, Yong Xiang, Tiangping Chen, Karim Abedmeraim et al . Natural power method for fast subspace tracking . In:Proceeding of the 1999 IEEE Signal Processing Society Workshop, Neural Networks for Signal Processing, 1999, 176-185

[23]Roland Badeau, Bertrand David and Gael Richard . Fast approximated power iteration subspace tracking[J] . IEEE Transactions on Signal Processing, 2005, 53(8):2391-2341

[24]Yongfeng Miao and Yingbo Hua . Fast Subspace Tracking by a Novel Information Criterion . Signals, Systems and Computer, the Thirty-First Asilomar Conference, 1997, vol2:1312-1316

[25]Yongfeng Miao and Yingbo Hua . Fast Subspace Tracking and Neural Network Learing by a Novel Information Criterion . IEEE Transactions on Signal Processing, 1998,46(7):1967-1979

[26]Amir Valizadeh, Mehdi Farrokhrooz and Ali Rafiei . Fast Signal Subspace Tracking Using Two-Layer Linear Neural Network Learning. 16th Mediterranean Conference on Control and Automation . France, 2008:1828-1832

[27]E Esmailzadeh and M Ghorashi . Vibraton analysis of beams traversed by uniform partially distributed moving masses[J] . Journal of Sound and Vibration, 1995, 184(1):9-17