An Initialization Method for Nonlinear Model Reduction Using the CP Decomposition

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10169)


Every parametric model lies on the trade-off line between accuracy and interpretability. Increasing the interpretability of a model, while keeping the accuracy as good as possible, is of great importance for every existing model today. Currently, some nonlinear models in the field of block-oriented modeling are hard to interpret, and need to be simplified. Therefore, we designed a model-reduction technique based on the Canonical Polyadic tensor Decomposition, which can be used for a special type of static nonlinear multiple-input-multiple-output models. We analyzed how the quality of the model varies as the model order is reduced. This paper introduces a special initialization and compares it with a randomly chosen initialization point.

Using the method based on tensor decompositions ensures smaller errors than when using the brute-force optimization method. The resulting simplified model is thus able to keep its accuracy as high as possible.


Tensor decomposition CP decomposition Model order reduction Multiple-input-multiple-output model 



This work was supported in part by the Fund for Scientific Research (FWO-Vlaanderen), the Flemish Government (Methusalem), the Belgian Government through the Interuniversity Poles of Attraction (IAP VII) Program, the ERC advanced grant SNLSID under contract 320378, the ERC starting grant SLRA under contract 258581, and FWO project G028015N.


  1. 1.
    Johnson, K., Kuhn, M.: Applied Predictive Modeling. Springer, New York (2013)zbMATHGoogle Scholar
  2. 2.
    Giri, F., Bai, E.W.: Block-Oriented Nonlinear System Identification. Springer, London (2010)CrossRefzbMATHGoogle Scholar
  3. 3.
    Van Mulders, A., Vanbeylen, L., Usevich, K.: Identification of a block-structured model with several sources of nonlinearity. In: Proceedings of the 14th European Control Conference (ECC 2014), pp. 1717–1722 (2014)Google Scholar
  4. 4.
    Paduart, J.: Identification of nonlinear systems using polynomial nonlinear state space models. Ph.D. thesis, Vrije Universiteit Brussel (2012)Google Scholar
  5. 5.
    Schoukens, M., Marconato, A., Pintelon, R., Vandersteen, G., Rolain, Y.: Parametric identification of parallel Wiener-Hammerstein systems. Automatica 51(1), 111–122 (2015)MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Schoukens, M., Tiels, K., Ishteva, M., Schoukens, J.: Identification of parallel Wiener-Hammerstein systems with a decoupled static nonlinearity. In: The Proceedings of the 19th World Congress of the International Federation of Automatic Control (IFAC WC 2014), Cape Town, pp. 505–510 (2014)Google Scholar
  7. 7.
    Dreesen, P., Ishteva, M., Schoukens, J.: Decoupling multivariate polynomials using first-order information and tensor decompositions. SIAM J. Matrix Anal. Appl. 36(2), 864–879 (2015)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Tiels, K., Schoukens, J.: From coupled to decoupled polynomial representations in parallel Wiener-Hammerstein models. In: Proceedings of the 52nd IEEE Conference on Decision and Control, Florence, pp. 4937–4942 (2013)Google Scholar
  9. 9.
    Nocedal, J., Wright, S.: Numerical Optimization, 2nd edn. Springer, New York (2006)zbMATHGoogle Scholar
  10. 10.
    Cichocki, A., Mandic, D., Phan, A.-H., Caiafa, C., Zhou, G., Zhao, Q., De Lathauwer, L.: Tensor decompositions for signal processing applications, from two-way to multiway component analysis. IEEE Siganl Process. Mag. 32(2), 145–163 (2015)CrossRefGoogle Scholar
  11. 11.
    Kolda, T.G., Bader, B.W.: Tensor decomposition and applications. SIAM Rev. 51(3), 455–500 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Comon, P.: Tensor decomposition, state of the art and applications. In: Mathematics in Signal Processing V, pp. 1–24 (2002)Google Scholar
  13. 13.
    Sorber, L., Van Barel, M., De Lathauwer, L.: Optimization-based algorithms for tensor decompositions: canonical polyadic decomposition, decomposition in rank-\((L_r, L_r, 1)\) terms, and a new generalization. SIAM J. Optim. 23(2), 695–720 (2013)MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Bader, B.W., Kolda, T.G., et al.: Matlab tensor toolbox version 2.6, February 2015Google Scholar
  15. 15.
    Andersson, C., Bro, R.: The N-way toolbox for MATLAB. Chemom. Intell. Lab. Syst. 52(1), 1–4 (2000)CrossRefGoogle Scholar
  16. 16.
    Vervliet, N., Debals, O., Sorber, L., Van Barel, M., De Lathauwer, L.: Tensorlab 3.0, March 2016Google Scholar
  17. 17.
    Dreesen, P., Schoukens, M., Tiels, K., Schoukens, J.: Decoupling static nonlinearities in a parallel Wiener-Hammerstein system: a first-order approach, pp. 987–992 (2015)Google Scholar
  18. 18.
    Hollander, G., Dreesen, P., Ishteva, M., Schoukens, J.: Weighted tensor decomposition for approximate decoupling of multivariate polynomials. Technical report (2016)Google Scholar
  19. 19.
    Comon, P., Qi, Y., Usevich, K.: X-rank and identifiability for a polynomial decomposition model. arXiv:1603.01566 (2016)
  20. 20.
    Lim, L., Comon, P.: Nonnegative approximations of nonnegative tensors. J. Chemom. 23, 432–441 (2009)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Vrije Universiteit BrusselBrusselsBelgium

Personalised recommendations