Predictor-Based Tensor Regression (PBTR) for LPV subspace identification

The major bottleneck in state-of-the-art Linear Parameter Varying (LPV) subspace methods is the curse-of-dimensionality during the first regression step. In this paper, the origin of the curse-of-dimensionality is pinpointed and subsequently a novel method is proposed which does not suffer from this bottleneck. The problem is related to the LPV sub-Markov parameters. These have inherent structure and are dependent on each other. But state-of-the-art LPV subspace methods parametrize the LPV sub-Markov parameters independently. This means the inherent structure is not preserved in the parametrization. In turn this leads to a superfluous parametrization with the curse-of-dimensionality. The solution lies in using parametrizations which preserve the inherent structure sufficiently to avoid the curse-of-dimensionality. In this paper a novel method based on tensor regression is proposed. This novel method is named the Predictor-Based Tensor Regression method (PBTR). This method preserves the inherent structure sufficiently to avoid the curse-of-dimensionality. Simulation results show that PBTR has superior performance with respect to both state-of-the-art LPV subspace techniques and also non-convex techniques.

[1]  Lennart Ljung,et al.  System identification (2nd ed.): theory for the user , 1999 .

[2]  Jan-Willem van Wingerden,et al.  LPV Identification of Wind Turbine Rotor Vibrational Dynamics Using Periodic Disturbance Basis Functions , 2013, IEEE Transactions on Control Systems Technology.

[3]  Michel Verhaegen,et al.  Subspace identification of MIMO LPV systems using a piecewise constant scheduling sequence with hard/soft switching , 2007, 2007 European Control Conference (ECC).

[4]  M. Athans,et al.  Gain Scheduling: Potential Hazards and Possible Remedies , 1992, 1991 American Control Conference.

[5]  Jan-Willem van Wingerden,et al.  Tensor regression for LPV subspace identification , 2015 .

[6]  Alessandro Chiuso,et al.  The role of vector autoregressive modeling in predictor-based subspace identification , 2007, Autom..

[7]  Haiping Lu,et al.  MPCA: Multilinear Principal Component Analysis of Tensor Objects , 2008, IEEE Transactions on Neural Networks.

[8]  Hongtu Zhu,et al.  Tensor Regression with Applications in Neuroimaging Data Analysis , 2012, Journal of the American Statistical Association.

[9]  Magnus Jansson.  A NEW SUBSPACE IDENTIFICATION METHOD FOR OPEN AND CLOSED LOOP DATA , 2005 .

[10]  M. Verhaegen,et al.  LPV subspace identification using a novel nuclear norm regularization method , 2011, Proceedings of the 2011 American Control Conference.

[11]  Michel Verhaegen,et al.  Subspace identification of MIMO LPV systems using a periodic scheduling sequence , 2007, Autom..

[12]  Bassam Bamieh,et al.  Identification of linear parameter varying models , 1999, Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304).

[13]  Fernando D. Bianchi,et al.  Gain scheduling control of variable-speed wind energy conversion systems using quasi-LPV models , 2005 .

[14]  Michel Verhaegen,et al.  Subspace identification of Bilinear and LPV systems for open- and closed-loop data , 2009, Autom..

[15]  Gene H. Golub,et al.  Generalized cross-validation as a method for choosing a good ridge parameter , 1979, Milestones in Matrix Computation.

[16]  Michel Verhaegen,et al.  Identification of fully parameterized linear and nonlinear state-space systems by projected gradient search , 2003 .

[17]  Gary J. Balas,et al.  LINEAR, PARAMETER-VARYING CONTROL AND ITS APPLICATION TO AEROSPACE SYSTEMS , 2002 .

[18]  Michael Buchholz,et al.  Identification of a bilinear and parameter-varying model for lithium-ion batteries by subspace methods , 2013, 2013 American Control Conference.

[19]  Weiwei Guo,et al.  Tensor Learning for Regression , 2012, IEEE Transactions on Image Processing.

[20]  Haiping Lu,et al.  A survey of multilinear subspace learning for tensor data , 2011, Pattern Recognit..

[21]  Torben Knudsen.  Consistency analysis of subspace identification methods based on a linear regression approach , 2001, Autom..

[22]  Bart De Moor,et al.  Subspace identification of bilinear systems subject to white inputs , 1999, IEEE Trans. Autom. Control..

[23]  Hossam Seddik Abbas,et al.  On the State-Space Realization of LPV Input-Output Models: Practical Approaches , 2012, IEEE Transactions on Control Systems Technology.

[24]  Joe Brewer,et al.  Kronecker products and matrix calculus in system theory , 1978 .

[25]  Bassam Bamieh,et al.  LPV model identification for gain scheduling control: An application to rotating stall and surge control problem , 2006 .

[26]  J. Suykens,et al.  Nuclear Norms for Tensors and Their Use for Convex Multilinear Estimation , 2011 .

[27]  Michel Verhaegen,et al.  Tensor regression for LTI subspace identification , 2015, 2015 American Control Conference (ACC).

[28]  Jan Swevers,et al.  AN APPLICATION OF INTERPOLATING GAIN-SCHEDULING CONTROL , 2007 .

[29]  Carsten W. Scherer,et al.  LPV control and full block multipliers , 2001, Autom..

[30]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[31]  Demetri Terzopoulos,et al.  Multilinear Analysis of Image Ensembles: TensorFaces , 2002, ECCV.

[32]  Lawton H. Lee,et al.  Identification of Linear Parameter-Varying Systems Using Nonlinear Programming , 1999 .

[33]  M. Lovera,et al.  Identification for gain-scheduling: a balanced subspace approach , 2007, 2007 American Control Conference.