You are on page 1of 11

Artificial Intelligent Control

Fuzzy Logic

Dr. Ir. Ari Santoso, DEA


Email:santoso@ee.its.ac.id

1
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

Artificial Intelligent Control


• Fuzzy Logic
• Fuzzy Logic Controller
• Neural Network
• Adaptive NeuroFuzzy Inference System
(ANFIS)
• Genetic Algorithm
• Knowledge Based Control

2
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

1
Artificial Intelligent Control
• Assesment :
• HW : 20%
• UTS : 30%
• UAS : 30%
• Final Project (Group) : 20%
2 weeks before UAS

3
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

Introduction
• Illustration

4
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

2
Introduction
• Illustration

Possible definition of the set high levels in tank

5
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

Fuzzy Set
• The set of young people :
• Young : 17, 19, 20 years
• But 30, 40 years ? or 10, 13 years ?
• 80 years is old and 2 years is baby
• The set of water temperature’s
• Hot : 60oC, 70oC
• But : 90oC, 100oC, 110oC ? or 10oC, 0oC ?
Ali ate X eggs for breakfast, where X ∈ U = {1,2,….,8} if we may associate
a probability distribution p by observing Ali eating breakfast for 100 days

U={ 0 1 2 3 4 5 6 7 8}
p={0.1 0.7 0.2 0 0 0 0 0 0}

6
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

3
Fuzzy Set
• The set of young people :
• Young : 17, 19, 20 years
• But 30, 40 years ? or 10, 13 years ?
• 80 years is old and 2 years is baby

7
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

Membership function
• Assume the universe U is represented by a
number of samples : U ={ 0 20 40 60 80 100}

• Membership values : π={ 0 0.04 0.31 0.69 0.96 1 }

8
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

4
Linguistic Variable

• Speed : very slow, slow, fast, very fast


• Temperature : very cold, cold, warm, hot
very hot
• Age : baby, young, old

If the level is low then V1 is Open

9
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

Operation On Fuzzy Sets


• Intersection of A and B is : A ∩ B ≡ a min b
• Union of A and B is : A ∪ B ≡ a max b
• Complement of A : A ≡ 1− a
• Fuzzy set X of fuzzy subset Y : X ⊆Y

10
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

5
Operation On Fuzzy Sets

• Exp. : let U={0,1,2,3,4,5,6,7,8,9,10}


• C= {0.2 0.5 0.8 1 0.7 0.3 0 0 0 0}
• I= {0 0 0.2 0.4 0.6 0.8 1 1 1 1}
• C∩I={ 0 0 0.2 0.4 0.6 0.3 0 0 0 0}
• C∪I={0.2 0.5 0.8 1 0.7 0.8 1 1 1 1}
• I = {1 1 0.8 0.6 0.4 0.2 0 0 0 0}

11
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

Operation On Fuzzy Sets


• The other operations :

12
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

6
Operation On Fuzzy Sets

• The modifier of Linguistic Variable :


• Very a ≡ a2 and more or less a ≡ a1/2

• Exp. U={0 20 40 60 80 100}


• Young = {1 0.6 0.1 0 0 0 }
• Young2 ={1 0.36 0.01 0 0 0 }
• Young4 ={1 0.13 0 0 0 0 }

13
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

Fuzzy Logic

• On-Off Logic or 0-1 Logic


• Exp. X={0.1 0.3 2 3 4 } Volt
{Off Off Off On On}
Fuzzy Logic
• Exp. X={0.1 0.3 2 3 4 } Volt
{ VS VS S M B}
VS : Very Small ; S : Small ; M : Medium
B : Big

14
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

7
Fuzzy Logic
• Symbol

15
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

Fuzzy Logic
• Symbol

16
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

8
Fuzzy Logic
• Symbol

There are thus 10 winning outcomes


out of 32 possible

17
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

Fuzzy Logic
• Symbol

18
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

9
Fuzzy Logic
• Symbol

19
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

Fuzzy Logic
• Mamdani implication
• a ⇒ b ≡ a o.min b

where o.min is the outer product, applying min to


each element of the cartesian product of a and b

20
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

10
Fuzzy Logic
• Mamdani implication

21
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

Inference
• If-Then
• Y=f(x)
• The famous of rule :

22
Laboratory of Control Engineering-Department of Electrical Engineering-ITS

11

You might also like