Defuzzification: Methods and properties

被引：0
|
作者：
Van Leekwijck, W [1 ]
Kerre, EE [1 ]
机构：
[1] State Univ Ghent, Dept Appl Math & Comp Sci, Fuzziness & Uncertainty Modeling Res Unit, B-9000 Ghent, Belgium
来源：
FUZZY LOGIC AND INTELLIGENT TECHNOLOGIES FOR NUCLEAR SCIENCE AND INDUSTRY | 1998年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper first examines criteria that can be formulated for defuzzification in arbitrary universes, ordered universes, and the set of the real numbers. The most widely used defuzzification techniques are classified into different groups and the prototypes of each group are examined with respect to the defuzzification criteria. It is shown that the defuzzification methods used in fuzzy controllers in general do not fulfill the most basic criteria for defuzzification, but exhibit the highly practical property of continuity. Finally, an alternative defuzzification method for a Mamdani controller is presented. If a number of restrictions on the components of the controller are taken into account, it is possible to define a defuzzification method that satisfies the basic criteria for defuzzification, and at the same time guarantees the continuity of the overall fuzzy controller.
引用
收藏
页码：61 / 68
页数：8
相关论文
共 50 条
  • [1] Extended defuzzification methods and their properties
    Runkler, TA
    [J]. FUZZ-IEEE '96 - PROCEEDINGS OF THE FIFTH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-3, 1996, : 694 - 700
  • [2] On the neural defuzzification methods
    Halgamuge, SK
    Runkler, TA
    Glesner, M
    [J]. FUZZ-IEEE '96 - PROCEEDINGS OF THE FIFTH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-3, 1996, : 463 - 469
  • [3] Selection of appropriate defuzzification methods using application specific properties
    Runkler, TA
    [J]. IEEE TRANSACTIONS ON FUZZY SYSTEMS, 1997, 5 (01) : 72 - 79
  • [4] Defuzzification methods for Fuzzy Inventory model
    Li, Qunxia
    [J]. ADVANCED MECHANICAL DESIGN, PTS 1-3, 2012, 479-481 : 399 - 402
  • [5] Improvement possibilities of the maximum defuzzification methods
    Toth-Laufer, Edit
    [J]. 2019 IEEE 23RD INTERNATIONAL CONFERENCE ON INTELLIGENT ENGINEERING SYSTEMS (INES 2019), 2019, : 339 - 343
  • [6] Comparison of the Defuzzification Methods in Risk Assessment Applications
    Kocak, Sinan
    Toth-Laufer, Edit
    Pokoradi, Laszlo
    [J]. 2018 18TH IEEE INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND INFORMATICS (CINTI), 2018, : 229 - 233
  • [7] On methods of defuzzification of parametrically represented fuzzy numbers
    Nasibov E.N.
    Mert A.
    [J]. Automatic Control and Computer Sciences, 2007, 41 (5) : 265 - 273
  • [8] SOME PROPERTIES OF DEFUZZIFICATION NEURAL NETWORKS
    SONG, Q
    BORTOLAN, G
    [J]. FUZZY SETS AND SYSTEMS, 1994, 61 (01) : 83 - 89
  • [9] Fuzzy models induced by alternative defuzzification methods
    Filev, DP
    Yager, RR
    [J]. FUZZ-IEEE '96 - PROCEEDINGS OF THE FIFTH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-3, 1996, : 457 - 462
  • [10] Ranking and defuzzification methods based on area compensation
    Fortemps, P
    Roubens, M
    [J]. FUZZY SETS AND SYSTEMS, 1996, 82 (03) : 319 - 330
12345