Elsevier

Information Sciences

Volume 7, 1974, Pages 49-72
Information Sciences

Hierarchical structuring for system identification

https://doi.org/10.1016/0020-0255(74)90005-XGet rights and content

Abstract

Hierarchical system theory deals with the decomposition of large or unwieldy systems into smaller subsystems which are conceptually and computationally easier to manipulate. System identification-the determination of unknown system parameters-is an area of system theory in which hierarchical structuring may be particularly useful. For example, as system identification techniques are applied to societal systems, the dimensionality of the problem may become so large as to cause computational difficulties. For such problems, hierarchical techniques may offer a significant reduction in computational requirements.

This research investigates hierarchical structuring for system identification. The maximum a posteriori (MAP) identification criterion yields a two point boundary value problem (TPBVP) which is cast into a hierarchical structure. Two different methods-quasilinearization and invariant imbedding-are used to solve the subproblems which are then coordinated to achieve the overall problem solution. Several examples are solved to demonstrate the use of the developed algorithms.

References (10)

There are more references available in the full text version of this article.

Cited by (0)

This research was supported by the Air Force Office of Scientific Research under contract F44620-68-C-0023 and the National Science Foundation under Grant GK 33348.

View full text