Local linear model trees for on-line identification of time-variant nonlinear dynamic systems
This paper discusses on-line identification of time-variant nonlinear dynamic systems. A neural network (LOLIMOT, ) based on local linear models weighted by basis functions and constructed by a tree algorithm is introduced. Training of this network can be divided into a structure and a parameter optimization part. Since the network is linear in its parameters a recursive least-squares algorithm can be applied for on-line identification. Other advantages of the proposed local approach are robustness and high training and generalisation speed. The simplest recursive version of the algorithm requires only slightly more computations than a recursive linear model identification. The locality of LOLIMOT enables on-line learning in one operating region without forgetting in the others. A drawback of this approach is that systems with large structural changes over time cannot be properly identified, since the model structure is fixed.
Unable to display preview. Download preview PDF.
- Nelles O., Isermann R.: “Radial Basis Function Networks for Interpolation of Local Linear Models”, submitted to IEEE Conference on Decision and Control, Kobe, Japan, 1996Google Scholar
- Narendra K.S., Parthasarathy K.: “Identification and Control of Dynamical Systems Using Neural Networks”, IEEE Transactions on Neural Networks, Vol. 1, No. 1, March 1990Google Scholar
- Takagi, T., Sugeno M.: “Fuzzy Identification of Systems and its Application to Modelling and Control”, IEEE Transactions on Systems, Man and Cybernetics Vol. 15, No. 1, 1985Google Scholar
- Johansen T.A., Foss B.A.: “Constructing NARMAX Models Using ARMAX Models”, International Journal of Control, Vol. 58, No. 5, 1993Google Scholar
- Murray-Smith R.: “A Local Model Network Approach to Nonlinear Modelling”, Ph.D. Thesis, University of Strathclyde, UK, 1994Google Scholar
- Breiman L., Friedman J., Olshen R., Stone C.J.: “Classification and Regression Trees”, Wadsworth Belmont, CA, 1984Google Scholar
- Friedman J.H.: “Multivariate Adaptive Regression Splines (with discussion)”, Annals of Statistics, March, 1991Google Scholar
- Nelles O., Isermann R., Sinsel S.: “Local Basis Function Networks for Identification of a Turbocharger”, IEE UKACC, Exeter, 1996Google Scholar
- Nelles O.: “On the Identification with Neural Networks as Series-Parallel and Parallel Models”, International Conference on Artificial Neural Networks, Paris, Oct. 1995Google Scholar