DocumentCode
3339992
Title
Qualitative, causal reasoning about device behavior
Author
Iwasaki, Yumi
Author_Institution
Dept. of Comput. Sci., Carnegie-Mellon Univ., Pittsburgh, PA, USA
fYear
1988
fDate
25-27 May 1988
Firstpage
39
Lastpage
44
Abstract
The methods of causal ordering provide an operational means to determine the causal relations among the variables in a model of the equilibrium behavior of a device. The author extends the method to dynamic models as well as mixed models of equilibrium and dynamic equations. He defines self-containment for dynamic and mixed structures and describes causal ordering in such structures. For correct application of the method of causal ordering, the equations comprising the model of a device must be such that each of them comes from an understanding of a conceptually distinct mechanism. To ensure that an equation model satisfies this requirement, an explicit representation of the understanding of mechanisms underlying an equation model was developed. Equations are generated automatically from this representation. An example involving the mixed model of an evaporator is used to illustrate the proposed approach
Keywords
artificial intelligence; knowledge engineering; causal ordering; causal relations; device behavior; dynamic equations; dynamic models; equation model; equilibrium behavior; evaporator; mixed structures; qualitative causal reasoning; self-containment; variables; Aerodynamics; Aerospace electronics; Artificial intelligence; Computer science; Contracts; Equations; Monitoring; Predictive models; Stability analysis; US Department of Defense;
fLanguage
English
Publisher
ieee
Conference_Titel
Artificial Intelligence for Industrial Applications, 1988. IEEE AI '88., Proceedings of the International Workshop on
Conference_Location
Hitachi City
Type
conf
DOI
10.1109/AIIA.1988.13267
Filename
13267
Link To Document