|
|
当然不是，你可以看看下面的比较，根据系统的实际情况选择相应的推理算法( C3 P$ ?- p! t+ t. o4 q6 `3 A7 h G
Comparison of Sugeno and Mamdani Systems( I4 C4 |1 V( a) w) `% Q* I
) E! a* r1 y5 P, ~
Because it is a more compact and computationally efficient representationthan a Mamdani system, the Sugeno system lends itself to the use ofadaptive techniques for constructing fuzzy models. These adaptivetechniques can be used to customize the membership functions so thatthe fuzzy system best models the data.! m+ p4 R3 [, {3 I& X4 @6 l0 A) ]
0 G9 {( J+ g& A# k0 ^Note You can use the MATLAB® command-line function mam2sug toconvert a Mamdani system into a Sugeno system (not necessarily witha single output) with constant output membership functions. It usesthe centroid associated with all of the output membership functionsof the Mamdani system.. ^( F, J* c, F
7 ?6 h3 F; c5 v" @+ i7 {The following are some final considerations about the two differentmethods.
2 ]1 V+ S8 D4 ]; {4 u% v
* h" c- M5 Q: e5 @! C ZAdvantages of the Sugeno Method:# x+ g) [+ X7 l: o; \7 o) A l
0 V% U' k( v! K" }8 o
It is computationally efficient.
0 o5 O z2 P, QIt works well with linear techniques (e.g., PID control).
x4 m4 O$ i; C1 g5 f+ Q& @It works well with optimization and adaptive techniques.- a% B3 [% Q7 Q( V% j
It has guaranteed continuity of the output surface.
0 l& R6 E/ v. v8 a) vIt is well suited to mathematical analysis., e" M8 N/ O9 ]6 m# C
G L% L# Z: hAdvantages of the Mamdani Method:
0 ]6 O: f# J- R* t' b0 K$ ^. g1 p: `, j& e; w
It is intuitive.
& |. o, ?1 E0 L2 K& hIt has widespread acceptance.( G+ E* |2 {- ~0 A$ c5 Y" n
It is well suited to human input. |
|
/1 
发表于 2020-10-19 14:26
收藏
淘帖
支持！
反对！
楼主