KR970062896A - Fuzzy inference method using the similarity of observation data and conditional part of rule base - Google Patents

Fuzzy inference method using the similarity of observation data and conditional part of rule base Download PDF

Info

Publication number
KR970062896A
KR970062896A KR1019960004903A KR19960004903A KR970062896A KR 970062896 A KR970062896 A KR 970062896A KR 1019960004903 A KR1019960004903 A KR 1019960004903A KR 19960004903 A KR19960004903 A KR 19960004903A KR 970062896 A KR970062896 A KR 970062896A
Authority
KR
South Korea
Prior art keywords
similarity
observation data
rule base
degree
fuzzy inference
Prior art date
Application number
KR1019960004903A
Other languages
Korean (ko)
Other versions
KR0160748B1 (en
Inventor
조영임
Original Assignee
김광호
삼성전자 주식회사
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 김광호, 삼성전자 주식회사 filed Critical 김광호
Priority to KR1019960004903A priority Critical patent/KR0160748B1/en
Publication of KR970062896A publication Critical patent/KR970062896A/en
Application granted granted Critical
Publication of KR0160748B1 publication Critical patent/KR0160748B1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/048—Fuzzy inferencing

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Automation & Control Theory (AREA)
  • Feedback Control In General (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

본 발명은 퍼지추론방법에 관한 것으로서 특히, 규칙베이스의 조건부와 관측데이타의 유사도를 이용한 퍼지 추론방법에 관한 것이다. 본 발명에 의한 퍼지추론방법은 최대-최소 합성 중심법을 적용하여 규칙베이스의 각 조건부와 관측데이타의 적합도를 측정하는 제1과정; 규칙베이스의 각 조건부와 관측데이타의 유사도를 측정하는 제2과정; 제1과정에서 계산된 적합도와 상기 제2과정에서 측정한 유사도를 각각 승산하여 규칙베이스의 각 결론부에 대한 조합정도를 구하는 제3과정; 및 제3과정에서 구한 조합정도와 복수개의 결론부에 대하여 최대-최소 합성 중심법을 적용하여 비퍼지값을 계산하는 제4과정으로 이루어짐을 특징으로 한다. 따라서, 본 발명은 관측데이타와 각 규칙들과의 유사도를 측정한 후 평균 유사도 이상인 결론부만을 조합으로써 효율적이며 계산시간이 단축된다. 또한, 관측데이타와 각 규칙들과의 퍼지추론에 적용함으로써 보다 정확한 제어를 할 수 있다.The present invention relates to a fuzzy inference method, and more particularly, to a fuzzy inference method using a similarity of observation data and a condition part of a rule base. A fuzzy inference method according to the present invention comprises a first step of measuring a fitness of each condition part of a rule base and an observation data by applying a maximum-minimum synthesis center method; A second step of measuring similarity between each condition part of the rule base and the observation data; A third step of calculating a degree of combination for each conclusion part of the rule base by multiplying the degree of similarity calculated in the first step and the degree of similarity measured in the second step, respectively; And a fourth step of calculating a non-fuzzy value by applying a maximum-minimum synthesis center method to the combination degree obtained in the third step and a plurality of concluding parts. Therefore, the present invention is effective in reducing the calculation time by measuring only the similarity between the observation data and each rule, and then combining only the conclusions that are equal to or greater than the average similarity. In addition, it can be applied to fuzzy reasoning of observation data and each rule, so that more accurate control can be achieved.

Description

규칙베이스의 조건부와 관측데이타의 유사도를 이용한 퍼지추론방법Fuzzy inference method using the similarity of observation data and conditional part of rule base

본 내용은 요부공개 건이므로 전문내용을 수록하지 않았음Since this is a trivial issue, I did not include the contents of the text.

Claims (3)

최대-최소 합성 중심법을 적용하여 규칙베이스의 각 조건부와 관측데이타의 적합도를 측정하는 제1과정; 규칙베이스의 각 조건부와 관측데이타의 유사도를 측정하는 제2과정; 상기 제1과정에서 계산된 적합도와 상기 제2과정에서 측정한 유사도를 각각 승산하여 규칙베이스의 각 결론부에 대한 조합정도를 구하는 제3과정; 및 상기 제3과정에서 구한 조합정도와 복수개의 결론부에 대하여 최대-최소 합성 중심법을 적용하여 비퍼지값을 계산하는 제4과정으로 이루어짐을 특징으로 하는 규칙베이스의 조건부와 관측데이타의 유사도를 이용한 퍼지 추론방법.A first step of measuring the fitness of each condition part of the rule base and the observation data by applying the maximum-minimum synthesis center method; A second step of measuring similarity between each condition part of the rule base and the observation data; A third step of calculating a degree of combination for each conclusion part of the rule base by multiplying the degree of similarity calculated in the first step and the degree of similarity measured in the second step, respectively; And a fourth step of calculating a non-purged value by applying a maximum-minimum synthesis center method to the combination degree obtained in the third step and a plurality of concluding parts. Fuzzy inference method. 제1항에 있어서, 상기 제2과정에서 계산한 유사도는 규칙베이스의 조건부와 관측데이타의 최소연산에 의한 논리곱 대규칙베이스의 조건부와 관측데이타의 최대연산에 의한 논리합의 비율임을 특징으로 하는 규칙베이스의 조건부와 관측데이타의 유사도를이용한 퍼지추론방법.2. The method according to claim 1, wherein the similarity calculated in the second step is a ratio of a logical product by a minimum operation of the rule base and a minimum operation of the observation data to a conditional part of the rule base and a logical sum of a maximum operation of the observation data, A fuzzy inference method using the similarity of observation data and conditional part of base. 제1항에 있어서, 상기 제4과정은 상기 제2과정에서 측정한 유사도의 평균값을 계산한 후 유사도가 평균값 이상인 규칙베이스의 결론부에 대해서 조합원을 특징으로 하는 규칙베이스의 조건부와 관측데이타의 유사도를 이용한 퍼지추론방법.The method according to claim 1, wherein the fourth step is a step of calculating an average value of similarities measured in the second step, and calculating a degree of similarity between the condition part of the rule base and the observation data, Fuzzy inference method using. ※ 참고사항 : 최초출원 내용에 의하여 공개하는 것임.※ Note: It is disclosed by the contents of the first application.
KR1019960004903A 1996-02-27 1996-02-27 Fuzzy inference method using conditions of rule base and comparisions observation data KR0160748B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1019960004903A KR0160748B1 (en) 1996-02-27 1996-02-27 Fuzzy inference method using conditions of rule base and comparisions observation data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1019960004903A KR0160748B1 (en) 1996-02-27 1996-02-27 Fuzzy inference method using conditions of rule base and comparisions observation data

Publications (2)

Publication Number Publication Date
KR970062896A true KR970062896A (en) 1997-09-12
KR0160748B1 KR0160748B1 (en) 1998-12-15

Family

ID=19451931

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1019960004903A KR0160748B1 (en) 1996-02-27 1996-02-27 Fuzzy inference method using conditions of rule base and comparisions observation data

Country Status (1)

Country Link
KR (1) KR0160748B1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102623952B1 (en) * 2018-12-18 2024-01-10 한국전기연구원 Entrance-angle control method

Also Published As

Publication number Publication date
KR0160748B1 (en) 1998-12-15

Similar Documents

Publication Publication Date Title
KR950001521A (en) Neural network and how to use it
KR950001520A (en) Artificial neurons and how to use them
Carstensen Complexity of some parametric integer and network programming problems
EP0690557A1 (en) Fuzzy logic control process and device for induction motors
KR970062896A (en) Fuzzy inference method using the similarity of observation data and conditional part of rule base
KR930001059A (en) Apparatus and method for automatically generating membership functions and fuzzy inference rules for fuzzy inference systems
US5353380A (en) Approximate reasoning apparatus
KR940015920A (en) Fuzzy Reasoning Method with Improved Reasoning Speed
DE68922707D1 (en) Truth value flow processing unit.
KR950024083A (en) Neural network and how to operate it
EP0372509A3 (en) Processing unit using truth-valued flow
ATE156608T1 (en) PROCESSOR AND METHOD FOR FURUOUS INFERENCE, AND METHOD AND ARRANGEMENT FOR RULE DETERMINATION
Brown Some inequalities that arise in measure theory
Kubota Matrix inversion algorithms by means of automatic differentiation
LaMeres et al. Design and implementation of a fuzzy logic-based voltage controller for voltage regulation of a synchronous generator
KR950006634A (en) Partial Linear Regression Model Structure
KR920022119A (en) Fuzzy Inference Processing System
Matsuzawa et al. Finite element approximation of 𝐻-surfaces
EP0537350A1 (en) Approximate inference system, input device for approximate inference and device for creating membership function
JPH0572613B2 (en)
KR0169036B1 (en) The neural network of the associated memory having the nonlinear function
SOM Node assignment in heterogeneous computing(Report, May- Aug. 1992)
Feng Universal fuzzy controllers for discrete-time systems
Ohki et al. A fast computational algorithm of a fuzzy reasoning using the product‐sum‐gravity method
JPH02273833A (en) Fuzzy inference device and fuzzy rule evaluating device

Legal Events

Date Code Title Description
A201 Request for examination
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 20070727

Year of fee payment: 10

LAPS Lapse due to unpaid annual fee