Beruflich Dokumente
Kultur Dokumente
Robert Fuller
Directory
Table of Contents
Begin Article
c 2010 rfuller@abo.fi
November 4, 2010
Table of Contents
3. Defuzzification methods
y* e u y
Controller System
So, our task is the find a crisp control action z0 from the fuzzy
rule-base and from the actual crisp inputs x0 and y0 :
Toc JJ II J I Back J Doc Doc I
f logic
Section 2: Fuzzy is incontroller
general a nonlinear function. 11
y* e u y
Controller System
Fuzzifier
crisp x in U
fuzzy set in U
Fuzzy Fuzzy
Inference Rule
Engine Base
fuzzy set in V
crisp y in V
Defuzzifier
control rule
<i : if (x is Ai and y is Bi ) then (z is Ci )
is implemented by a fuzzy implication Ri and is defined as
Ri (u, v, w) = Ai (u) and Bi (v) Ci (w)
where the logical connective and is implemented by the mini-
mum operator, i.e.
Ai (u) and Bi (v) Ci (w) =
Ai (u) Bi (v) Ci (w) = min{Ai (u), Bi (v)} Ci (w)
Of course, we can use any t-norm to model the logical connec-
tive and.
Fuzzy control rules are combined by using the sentence con-
nective also.
That is,
x0 y0 R1 , . . . , x0 y0 Rn )
C = Agg(
taking into consideration that
x0 (u) = 0, u 6= x0
and
y0 (v) = 0, v 6= y0 ,
the computation of the membership function of C is very sim-
ple:
C(w) = Agg{A1 (x0 ) B1 (y0 ) C1 (w),
. . . , An (x0 ) Bn (y0 ) Cn (w)}
for all w W .
The procedure for obtaining the fuzzy output of such a knowl-
edge base can be formulated as
x0 y0 R1 ) . . . (
C = ( x0 y0 Rn ).
That is,
C(w) = A1 (x0 ) B1 (y0 ) C1 (w)
An (x0 ) Bn (y0 ) Cn (w)
for all w W .
3. Defuzzification methods
z0
First-of-Maxima defuzzification
Figure 4: First-of-Maxima defuzzification method.
method.
If Cfuzzy
is notset C is defined
discrete as
then defuzzified value of a fuzzy set C
"
is defined as R z dz
z0 = "GG z dz
z0 = RG dz
G
dz
where G denotes the set of maximizing
where G denotes the set of maximizing element element
of C.
of C.
z0
18
Max-Criterion. This method chooses an arbitrary value,
z0
A suitable
Using defuzzificationtheorem
the Stone-Weierstrass methodWang
would(1992)
have showed
to choose
that
between
fuzzy different
logic control controlofactions
systems the form(choose one of two
triangles
<i : if xinisthe
AiFigure)
and y isand thenztransform
Bi then is Ci , i = the
1, . .fuzzy
.,n
set into a crisp value.
Toc JJ II J I Back J Doc Doc I
Section 4: Effectivity of fuzzy logic control systems. 28
with
Ai (u) and Bi (v) Ci (w) = Ai (u)Bi (v)Ci (w)
Centroid defuzzification method
Pn
i=1 i3 Ai (x)Bi (y)
z= P n
i=1 Ai (x)Bi (y)
where i3 is the center of Ci .