Summary
A statistical method for detecting the optimum time of control for a linear system with quadratic loss, is discussed. When the initial state is unknown and only one control action is available, both the optimum time of control and the amount of control are determined from the current observations at that time. Some simulated results are presented and our heuristic method is shown to be fairly satisfactory for practical use. An idea of reducing the bias of our estimate for the optimum time, is also proposed.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Adorno, D. S. (1962). Optimal control of certain linear systems with quadratic loss, I,Information and Control,5, 1–12.
Kreindler, E. and Jameson, A. (1972). Optimality of linear control systems,IEEE Trans. Automat. Contr., AC-17, 349–351.
Kushner, H. J. (1964). On the optimum timing of observations for linear control systems with unknown initial state,IEEE Trans. Automat. Contr., AC-9, 144–150.
Kushner, H. J. (1971).Introduction to Stochastic Control, Holt, Rinehart and Winston, Inc.
Additional information
The Institute of Statistical Mathematics
About this article
Cite this article
Suzuki, G. Detecting optimum time of control action for a manufacturing system. Ann Inst Stat Math 30, 15–26 (1978). https://doi.org/10.1007/BF02480195
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF02480195