Professional Documents
Culture Documents
241-320 Design Architecture and Engineering For Intelligent System
241-320 Design Architecture and Engineering For Intelligent System
January 2010
Preview: Outline
241-320 Design Architecture & Fuzzy System 3 241-320 Design Architecture & Fuzzy System 4
Engineering for Intelligent System Engineering for Intelligent System
What does Fuzzy Logic mean? What does Fuzzy Logic mean? (cont.)
241-320 Design Architecture & Fuzzy System 5 241-320 Design Architecture & Fuzzy System 6
Engineering for Intelligent System Engineering for Intelligent System
1
Fuzzy is Just Human Fuzzy is Economical
Fuzziness as a principle of economics:
Humans primarily use fuzzy terms: large, small, fast,
– Precision is expensive.
slow, warm, cold, ...
– Only apply as much precision to a problem as
We say: necessary.
“If the weather is nice and I have a little time, I will
probably go for a work along the river.”
We don’t say:
Precision
“If the temperature is above 24 degrees and the cloud
may not
cover is less than 10 percent, and I have 3 hours time,
significant in
I will go for a work with a probability of 0.47.”
the real world
241-320 Design Architecture & Fuzzy System 7 241-320 Design Architecture & Fuzzy System 8
Engineering for Intelligent System Engineering for Intelligent System
241-320 Design Architecture & Fuzzy System 9 241-320 Design Architecture & Fuzzy System 10
Engineering for Intelligent System Engineering for Intelligent System
2
Fuzzy Membership Function (cont.)
Shapes for Membership Functions
Fuzzy Membership Function (cont.)
241-320 Design Architecture & Fuzzy System 13 241-320 Design Architecture & Fuzzy System 14
Engineering for Intelligent System Engineering for Intelligent System
• So the 1st person has a membership of 0.3 and so is not very tall.
• The 2nd person has a membership of 0.95 and so he has a high
It just says that people taller than or equal to 6 feet are tall. degree of membership in the fuzzy set of tall men.
241-320 Design Architecture & Fuzzy System 15 241-320 Design Architecture & Fuzzy System 16
Engineering for Intelligent System Engineering for Intelligent System
In essense Outline
241-320 Design Architecture & Fuzzy System 17 241-320 Design Architecture & Fuzzy System 18
Engineering for Intelligent System Engineering for Intelligent System
3
Fuzzy (Linguistic) Variables Fuzzy (Linguistic) Variables (cont.)
Fuzzy Linguistic Variables are used to represent Temp: {Freezing, Cool, Warm, Hot}
qualities spanning a particular spectrum Degree of Truth or "Membership"
– Can be seen as the vocabulary of a Fuzzy Logic System
Example, Temp: {Freezing, Cool, Warm, Hot}
– Q: What is the temperature?
– A: It is warm.
– Q: How warm is it?
– A: ?? -> This somehow refers to the Membership Function
241-320 Design Architecture & Fuzzy System 19 241-320 Design Architecture & Fuzzy System 20
Engineering for Intelligent System Engineering for Intelligent System
241-320 Design Architecture & Fuzzy System 21 241-320 Design Architecture & Fuzzy System 22
Engineering for Intelligent System Engineering for Intelligent System
241-320 Design Architecture & Fuzzy System 23 241-320 Design Architecture & Fuzzy System 24
Engineering for Intelligent System Engineering for Intelligent System
4
Fuzzy Disjunction Fuzzy Conjunction
AB max (A, B) AB min(A, B)
A B = C "Quality C is the disjunction of A B = C "Quality C is the conjunction of
Quality A and B" Quality A and B"
241-320 Design Architecture & Fuzzy System 25 241-320 Design Architecture & Fuzzy System 26
Engineering for Intelligent System Engineering for Intelligent System
A fuzzy rule is a linguistic expression of causal Fuzzy Control combines the use of fuzzy linguistic
dependencies between linguistic variables in form of variables with fuzzy logic
if-then statements. Example: Speed Control
General form: IF <antecedent> then <consequence> Q: How fast am I going to drive today?
Example: A: It depends on the weather.
– If temperature is cold and oil price is cheap -> So, this implies disjunction or conjunction of
• Then heating is high fuzzy operations
5
Example: Fuzzy Control (cont.) Example: Fuzzy Control (cont.)
Temp: {Freezing, Cool, Warm, Hot}
Rules:
If it's Sunny and Warm, drive Fast
Sunny(Cover) Warm(Temp) Fast(Speed)
If it's Cloudy and Cool, drive Slow
Cover: {Sunny, Partly, Overcast} Speed: {Slow, Fast} Cloudy(Cover) Cool(Temp) Slow(Speed)
Driving Speed is the combination of output of these
rules...
241-320 Design Architecture & Fuzzy System 31 241-320 Design Architecture & Fuzzy System 32
Engineering for Intelligent System Engineering for Intelligent System
– 65 F°
– 25 % Cloud Cover ?
241-320 Design Architecture & Fuzzy System 33 241-320 Design Architecture & Fuzzy System 34
Engineering for Intelligent System Engineering for Intelligent System
If it's Sunny and Warm, drive Fast Speed is 20% Slow and 70% Fast
Sunny(Cover)Warm(Temp)Fast(Speed)
0.8 0.7 = 0.7
Fast = 0.7
241-320 Design Architecture & Fuzzy System 35 241-320 Design Architecture & Fuzzy System 36
Engineering for Intelligent System Engineering for Intelligent System
6
Example: Fuzzy Control (cont.) Example: Fuzzy Control (cont.)
Defuzzification: Constructing the Output Defuzzification: Constructing the Output
Speed is 20% Slow and 70% Fast Speed is 20% Slow and 70% Fast
Fuzzy Logic Control allows for the smooth Inputs to a fuzzy system can be:
interpolation between variable centroids with – fuzzy, e.g. (Score = Moderate), defined by
relatively few rules membership functions;
This does not work with crisp logic (traditional Boolean) – exact, e.g.: (Score = 190); defined by crisp values
– a crisp number x, denoting the most typical value Outputs from a fuzzy system can be:
Provides a natural way to model some types of – fuzzy, i.e. a whole membership function.
human expertise in a computer program
– exact, i.e. a single value is produced .
241-320 Design Architecture & Fuzzy System 39 241-320 Design Architecture & Fuzzy System 40
Engineering for Intelligent System Engineering for Intelligent System