This paper describes the principles of application of the extended Kalman filter identification technique as a means of identification of linear systems with Gaussian random inputs. Major consideration is given to an algorithmic implementation rather than to theoretical background in an attempt to make the technique more widely available to the engineer. Results of simulation studies suggest guidelines to aid in successful application of the technique to experimental situations.
Get full access to this article
View all access options for this article.
References
1.
Kalman, R.E.1960. 'A new approach to linear filtering and prediction problems ', Trans ASME, J Basic Engng, 82D, 34-45.
2.
Kalman, R.E. and Bucy, R.1961. 'New results in linear filtering and prediction theory' , Trans ASME, J Basic Engng, 83D, 95-108.
3.
Lee, R.C.K.1964. Optimal estimation, identification and control, TheMassachusetts Institute of Technology (MIT Press).
4.
Mayne, D.Q.1965. 'Optimal non-stationary estimation of the parameters of a linear system with Gaussian inputs', J Contr, 14, 101-112.
