This paper presents a methodology for integrating common-sense and qualitative simulation of physical systems by the use of Fuzzy Sets . This allows a semi-quantitative extension to qualitative simulation that provides three significant advantages over existing techniques . Firstly, it allows a more detailed description of physical variables, through an arbitrary, but finite, discretisation of the quantity space, thereby reducing qualitative ambiguity at source. The adoption of Fuzzy Sets also allows common-sense knowledge to be utilised in defining values through the use of graded membership. Secondly, the fuzzy quantity space allows more detailed description of functional relationships in that both strength and sign information can be represented by fuzzy relations held against two or multi-variables . Thirdly, the quantity space allows ordering information on rates of change to be used to compute temporal durations of system states and the possible transitions. Thus, an ordering of the evolution of the states and the temporal durations is obtained. This knowledge is used to develop effective temporal filters that significantly reduce the number of spurious behaviours. Experimental results with the method are presented and comparison with other recently proposed methods is made. Submitted to: 4th International Workshop on Qualitative Simulation Contact: Professor Roy LEITCH *: This paper has also been submitted to the AAAI--90.
[1]
Qiang Shen,et al.
Fuzzy qualitative simulation
,
1993,
IEEE Trans. Syst. Man Cybern..
[2]
H. Carter.
Fuzzy Sets and Systems — Theory and Applications
,
1982
.
[3]
Ernest Davis,et al.
Constraint Propagation with Interval Labels
,
1987,
Artif. Intell..
[4]
Brian C. Williams,et al.
Doing Time: Putting Qualitative Reasoning on Firmer Ground
,
1986,
AAAI.
[5]
Roy Leitch,et al.
Task dependent tools for intelligent automation
,
1989,
Artif. Intell. Eng..
[6]
Olivier Raiman,et al.
Order of Magnitude Reasoning
,
1986,
Artif. Intell..
[7]
Piero Patrone Bonissone,et al.
The problem of linguistic approximation in system analysis
,
1979
.
[8]
Roy Leitch,et al.
Temporal Issues in Qualitative Reasoning
,
1989,
ÖGAI.
[9]
Peter Struss,et al.
Mathematical aspects of qualitative reasoning
,
1988,
Artif. Intell. Eng..
[10]
David L. Waltz,et al.
Understanding Line drawings of Scenes with Shadows
,
1975
.
[11]
Piero P. Bonissone,et al.
Selecting Uncertainty Calculi and Granularity: An Experiment in Trading-off Precision and Complexity
,
1985,
UAI.