Advertisement

Adaptive forgetting in recursive identification through multiple models

  • P. Andersson
Session 4 Detection Of Changes In Systems
Part of the Lecture Notes in Control and Information Sciences book series (LNCIS, volume 62)

Abstract

A new recursive identification method, Adaptive Forgetting through Multiple Models — AFMM, is presented and evaluated using computer simulations. AFMM is especially suited for identification of systems with jumping parameters or parameters that change in an irregular fashion. It can be viewed as a particular way of implementing adaptive gains or adaptive forgetting factors for recursive identification. The new method essentialy consists of multiple Recursive Least Squares (RLS) algorithms running in parallel, each with a corresponding weighting factor. The simulations indicate that AFMM is able to track rapidly changing parameters well, and that the method is robust in several respects.

Keywords

Kalman Filter Recursive Identification Gaussian Density Function Recursive Little Square Recursive Bayesian Estimation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Alspach, D. L. and H. W. Sorenson (1972). Nonlinear Bayesian Estimation Using Gaussian Sum Approximations, IEEE Trans Automatic Control, Vol AC-17, No 4, pp 439–448.Google Scholar
  2. Anderson, B. D. O. and J. B. Moore (1979). Optimal Filtering, Prentice Hall.Google Scholar
  3. Andersson, P. (1983). Adaptive forgetting in recursive identification through multiple models. Internal report LiTH-ISY-I-0638, Department of Electrical Engineering, Linköping University, Linköping, Sweden.Google Scholar
  4. Benveniste, A. and G. Ruget (1982). A Measure of the Tracking Capability of Recursive Stochastic Algorithms with Constant Gains, IEEE Trans Automatic Control, Vol. AC-27, No 3, pp 639–649.Google Scholar
  5. Dumont, G. A. (1982). Self-tuning Control of a Chip Refiner Motor Load, Automatica, Vol 18, No 3, pp 307–314.Google Scholar
  6. Fortescue, T. R., L. S. Kershenbaum and B. E. Ydstie (1981). Implementation of Self-tuning Regulators with Variable Forgetting Factors, Automatica, Vol 17, pp 831–835.Google Scholar
  7. Goodwin, G. C. and K. S. Sin (1984). Adaptive Prediction, Filtering and Control, Prentice Hall, to appear.Google Scholar
  8. Hägglund, T. (1982). Adaptive Control with Fault Detection, Report TFRT-7242, Department of Automatic Control, Lund Institute of Technology, Lund, Sweden.Google Scholar
  9. Hägglund, T. (1983). Recursive Least Squares Identification with Forgetting of Old Data, Report TFRT-7254, Department of Automatic Control, Lund Institutet of Technology, Lund, Sweden.Google Scholar
  10. Jazwinski, A. H. (1970). Stochastic Processes and Filtering Theory, Academic Press, New York.Google Scholar
  11. Kesten, H. (1958). Accelerated Stochastic Approximation, Ann Math Stat, Vol 29, pp 41–59.Google Scholar
  12. Ljung, L. and T. Söderström (1983). Theory and Practice of Recursive Identification, MIT Press.Google Scholar
  13. Lo, J. T-H. (1972). Finite-Dimensional Sensor Orbits and Optimal Nonlinear Filtering, IEEE Trans Information Theory, Vol IT-18, No 5, pp 583–588.Google Scholar
  14. Lozano, R. (1983). Convergence Analysis of Recursive Identification Algorithms with Forgetting Factor, Automatica, Vol 19, No 1, pp 95–97.Google Scholar
  15. Sorenson, H. W. and D. L. Alspach (1971). Recursive Bayesian Estimation Using Gaussian Sums, Automatic, Vol 7, pp 465–479.Google Scholar
  16. Trulsson, E. (1983). Adaptive Control Based on Explicit Criterion Minimization, Linköping Studies in Science and Technology. Dissertations. No 106.Google Scholar
  17. Wellstead, P. E. and S. P. Sanoff (1981). Extended self-tuning algorithm, Int J Control, Vol 34, No 3, pp 433–455.Google Scholar
  18. Willsky, A. S. (1976). A Survey of Design Methods for Failure Detection in Dynamic Systems, Automatica, Vol 12, pp 601–611.Google Scholar

Copyright information

© Springer-Verlag 1984

Authors and Affiliations

  • P. Andersson
    • 1
  1. 1.Division of Automatic Control Department of Electrical EngineeringLinköping UniversityLinköpingSweden

Personalised recommendations