KR960029931A - Multi-criteria expert fuzzy logic control method and device - Google Patents

Multi-criteria expert fuzzy logic control method and device Download PDF

Info

Publication number
KR960029931A
KR960029931A KR1019950001785A KR19950001785A KR960029931A KR 960029931 A KR960029931 A KR 960029931A KR 1019950001785 A KR1019950001785 A KR 1019950001785A KR 19950001785 A KR19950001785 A KR 19950001785A KR 960029931 A KR960029931 A KR 960029931A
Authority
KR
South Korea
Prior art keywords
fuzzy
value
unit
expert
fuzzy logic
Prior art date
Application number
KR1019950001785A
Other languages
Korean (ko)
Other versions
KR0121103B1 (en
Inventor
이봉국
김광춘
김종환
Original Assignee
이종수
Lg 산전 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 이종수, Lg 산전 주식회사 filed Critical 이종수
Priority to KR1019950001785A priority Critical patent/KR0121103B1/en
Publication of KR960029931A publication Critical patent/KR960029931A/en
Application granted granted Critical
Publication of KR0121103B1 publication Critical patent/KR0121103B1/en

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B11/00—Automatic controllers
    • G05B11/01—Automatic controllers electric
    • G05B11/36—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential
    • G05B11/42—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential for obtaining a characteristic which is both proportional and time-dependent, e.g. P. I., P. I. D.
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/0275—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using fuzzy logic only
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/0295—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using fuzzy logic and expert systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Automation & Control Theory (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Mathematical Physics (AREA)
  • Fuzzy Systems (AREA)
  • Feedback Control In General (AREA)

Abstract

본 발명은 화학, 발전, 수치 처리등의 제어 시스템에 퍼지논리 제어기술을 적용하는 기술에 관한 것으로, 일반적인 퍼지논리 제어기에 있어서는 소속함수의 파라미터를 변경하여 각각의 문제를 실험에 의한 반복 시행적인 학습법에 의해 해결해야 하므로 정교한 제어를 하기 위하여 규칙 설정에 대한 많은 경험을 필요로 하고, 시뮬레이션과 실험에 의한 많은 데이타가 요구되어 제어 대상에 따라 원하는 특성의 제어기 조정에 어려움이 있었는 바, 본 발명은 이를 해결하기 위하여 다기준 속성치를 이용하여 응답특성의 미세한 부분까지 정교한 제어를 할 수 있게 하고, 응답특성의 원하는 성능 지수를 최소화 하기 위해 수동조절이 아니라 전문가 기법에 의한 자동 조정이 가능하게 하였으며, 다기준 속성치의 평가와 중요도를 이용하여 각 규칙의 가중치를 구체적으로 원하는 사양으로 결정할 수 있게 하고, 정상 상태의 설정치만 운전자가 응답 요구를 할 수 있는 종래의 기술에 비해 상승시간, 오버슈트, 정정시간 등을 포함한 여러 응답을 요구할 수 있게 하였으며, 분산제어 시스템의 제어 적용범위를 확대할 수 있는 효과가 있다.The present invention relates to a technique for applying fuzzy logic control techniques to control systems such as chemistry, power generation, and numerical processing. In general fuzzy logic controllers, iteratively learns by experimenting each problem by changing the parameters of the membership function. In order to solve this problem, much control of rule setting is required for precise control, and a lot of data by simulation and experiment have been required. In order to solve this problem, it is possible to control precisely the minute part of response characteristics by using multi-criterion attribute values, and to automatically adjust by expert technique instead of manual adjustment to minimize the desired performance index of response characteristics. Weighting of each rule using the evaluation and importance of attribute values It is possible to determine the specific specification as desired, and it is possible to request various responses including rise time, overshoot, settling time, etc., compared to the conventional technology in which the driver can make a response request only when the steady state is set. This has the effect of extending the control coverage of the system.

Description

다기준 전문가형 퍼지논리 제어 방법 및 장치Multi-criteria expert fuzzy logic control method and device

본 내용은 요부공개 건이므로 전문내용을 수록하지 않았음Since this is an open matter, no full text was included.

제3도는 본 발명의 다기준 전문가형 퍼지논리 제어장치에 대한 블록도.3 is a block diagram of a multi-criteria expert fuzzy logic control device of the present invention.

Claims (9)

설정치와 다기준 속성치에 의한 기준 사양치(xi*)를 결정하는 제1단계 중요도(g)를 초기화 하는 제2단계, 평가지수(P.I)의 임계치 및 가중치, 퍼지규칙의 퍼지변수를 결정하는 제3단계, 공정치(PV)를 이용하여 패턴을 추출하는 제4단계, 평가지수치를 계산하는 제5단계, 임계치의 초과 여부를 결정하여 중요데이타를 갱신하는 제6단계를 반복수행하는 전문가시스템 제어과정과, 중요도(g)를 초기화 하는 제7단계, 공정치(PV)의 퍼지화를 수행하는 제8단계, 공정치(PV)의 퍼지화를 수행하여 퍼지적분을 통해 가중치를 결정하는 제9단계, 추론에 의해 제어출력을 결정하는 제10단계, 상기의 과정을 수행하여 획득한 공정치(PV) 및 제어 출력치(MV)의 데이타를 저장하는 제11단계를 반복 수행하는 다기준 퍼지논리 제어과정으로 이루어지는 것을 특징으로 하는 다기준 전문가형 퍼지논리 제어방법.The first step of determining the reference specification value (xi * ) by the set value and the multi-reference attribute value. The second step of initializing the importance (g), the threshold and weight of the evaluation index (PI), and the fuzzy variable of the fuzzy rule. The expert system control process of repeating the third step, the fourth step of extracting the pattern using the process value (PV), the fifth step of calculating the evaluation index value, and the sixth step of updating important data by determining whether the threshold is exceeded. And a seventh step of initializing the importance (g), an eighth step of purging the process value PV, and a ninth step of determining the weight through fuzzy integration by performing the fuzzy process of the process value PV. The multi-reference fuzzy logic control process is repeated to repeat the tenth step of determining the control output by the step 11, the eleventh step of storing the data of the process value (PV) and the control output value (MV) obtained by performing the above process Multi-standard, characterized in that Doors formal type fuzzy logic control method. 제1항에 있어서, 제1단계의 기준 사양치(xi *)는 다음의 식으로 정의 되는 것을 특징으로 하는 다기준 전문가형 퍼지논리 제어방법.The multi-criteria expert fuzzy logic control method according to claim 1, wherein the reference specification value (x i * ) of the first step is defined by the following equation. i:1,2,3, exi: 시간영역상에서 정의된 사양 오차,ni:정규화 인자.i: 1,2,3, e xi : Specification error defined in the time domain, n i : Normalization factor. 제1항에 있어서, 제3단계의 평가지수(P.I.)의 임계치 및 가중치, 퍼지규칙의 퍼지변수는 다음의 식으로 정의되는 것을 특징으로 하는 다기준 전문가형 퍼지논리 제어방법.The multi-criteria expert fuzzy logic control method according to claim 1, wherein the threshold value, the weight of the evaluation index (P.I.) of the third step, and the fuzzy variable of the fuzzy rule are defined by the following equation. P.I:전체 시스템의 평가지수, i:평가지수의 가중치, exi:시간영역상에서 정의된 사양 오차.PI: index of evaluation of the whole system, i : Weight of the evaluation index, e xi : Specification error defined in the time domain. 제1항에 있어서, 제6단계의 중요데이타는 다음의 식으로 정의되는 것을 특징으로 하는 다기준 전문가형 퍼지논리 제어방법.The multi-criteria expert fuzzy logic control method according to claim 1, wherein the important data of the sixth step is defined by the following equation. i=1,2,3, μFP(exi:소정의 퍼지변수를 갖는 exi에 대한 소속함수,:소정의 규칙에서 후건부에 해당하는 퍼지변수.i = 1,2,3, μ FP (e xi : membership function for e xi with some fuzzy variables, : Fuzzy variable corresponding to post-consent part in a prescribed rule. 제1항에 있어서, 제9단계의 퍼지적분은 다음의 식으로 정의 되는 것을 특징으로 하는 다기준 전문가형 퍼지논리 제어방법.The multi-criteria expert fuzzy logic control method according to claim 1, wherein the fuzzy integral of the ninth step is defined by the following equation. Wi (n):가중치, hi (n):상승시간에 대한 부분 평가치, g:중요도 값.W i (n) : weight, h i (n) : partial estimate of rise time, g: importance. 제1항에 있어서, 제10단계의 제어출력은 다음의 식으로 정의되는 것을 특징으로 하는 다기준 전문가형 퍼지논리 제어방법.The multi-criteria expert fuzzy logic control method according to claim 1, wherein the control output of the tenth step is defined by the following equation. C(i):출력 퍼지집합 U(i)의 최대치, U*:퍼지논리 제어기(215)의 출력치(MV) W(i):가중치.C (i) : Maximum value of output fuzzy set U (i) , U * : Output value of purge logic controller 215 (MV) W (i) : Weight value. 가중치를 이용한 퍼지논리 제어장치에 있어서, 중요도(g)의 변경을 원하는 시스템 응답 사양(평가지수의 임계치, 다기준 속성치)을 만족할때까지 퍼지규칙을 이용한 전문가 기법의 추론에 의해 수행하는 전문가 시스템부(120)를 포함한 피엠에스부(100)와, 다기준 속성치(상승시간, 오버슈트, 정정시간 등)의 부분평가치(h)와 퍼지 척도인 중요도(g)를 이용한 퍼지적분을 도입하여 가중치를 결정하는 다기준 퍼지논리 제어부(210)를 포함한 피씨에스부(200)로 구성한 것을 특징으로 하는 다기준 전문가형 퍼지논리 제어장치.In the fuzzy logic control apparatus using weights, an expert system unit which performs by inference of expert technique using fuzzy rules until the system response specification (critical value of evaluation index, multi-critical attribute value) of desired importance (g) is satisfied. Introduces the PMS unit 100 including 120, and a fuzzy integral using a partial evaluation value (h) of multi-criteria attribute values (rising time, overshoot, settling time, etc.) and importance (g) that is a fuzzy measure. Multi-standard expert-type fuzzy logic control device, characterized in that consisting of the PC unit 200 including a multi-reference fuzzy logic control unit 210 to determine the. 제7항에 있어서, 전문가 시스템부(120)는 제어 시스템의 성능지수를 관리하는 성능지수부(121)와, 상기 성능지수부(121)의 성능지수를 이용하여 퍼지규칙에 의한 규칙베이스 관리와 추론을 수행하여 새로운 퍼지 척도치인 중요도(g)를 결정하는 규칙베이스(122)와, 공정치(PV)의 패턴을 추출하는 패턴 추출부(123)와, 상기 성능지수과 규칙베이스, 패턴 형태를 표시 및 관리하고, 관리부(10)의 공정관리 및 모니터부(112)와 필요한 데이타를 공유하는 전문가 시스템 모니터부(124)로 구성한 것을 특징으로 하는 다기준 전문가형 퍼지논리 제어장치.8. The expert system unit 120 according to claim 7, wherein the expert system unit 120 manages the performance index of the control system and the rule base management according to the fuzzy rule using the performance index of the performance index unit 121 and A rule base 122 for determining importance g as a new fuzzy measure value by performing inference, a pattern extractor 123 for extracting a pattern of process values PV, and displaying the performance index, rule base, and pattern shape A multi-standard expert type fuzzy logic control device, comprising: an expert system monitor unit 124 for managing and sharing necessary data with the process management and monitoring unit 112 of the management unit 10. 제7항에 있어서, 다기준퍼지논리 제어부(210)는 상기 전문가 시스템부(120)에 의해 갱신되는 퍼지척도 데이타를 저장함으로써 중요도를 관리하는 퍼지척도부(211)와, 다기준 속성치의 부분 평가치를 관리하는 부분평가 다기준부(212)와, 상기 중요도와 부분 평가치를 사용하여 퍼지적분을 수행하는 퍼지적분부(213)와, 결정된 가중치를 관리하는 가중치부(214)와, 상기 가중치부(214)의 출력으로 퍼지추론을 수행하여 그에 따른 제어출력치(MV)를 생성하고 이를 공정부(301)에 출력하는 퍼지논리 제어기(215)로 구성한 것을 특징으로 하는 다기준 전문가형 퍼지논리 제어장치.8. The multi-criterion fuzzy logic control unit 210 according to claim 7, wherein the multi-criteria fuzzy logic control unit 210 stores fuzzy scale data updated by the expert system unit 120 to manage importance, and partial evaluation of multi-criterion attribute values. Partial evaluation multi-reference unit 212 for managing values, a fuzzy integration unit 213 for performing fuzzy integration using the importance and partial evaluation values, a weighting unit 214 for managing the determined weights, and the weighting unit ( A multi-standard expert fuzzy logic controller comprising fuzzy logic controller 215 for performing fuzzy inference with the output of 214 to generate the control output value MV and output it to the process unit 301. . ※ 참고사항 : 최초출원 내용에 의하여 공개하는 것임.※ Note: The disclosure is based on the initial application.
KR1019950001785A 1995-01-28 1995-01-28 Control method and apparatus for multi-reference expert type fuzzy logic KR0121103B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1019950001785A KR0121103B1 (en) 1995-01-28 1995-01-28 Control method and apparatus for multi-reference expert type fuzzy logic

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1019950001785A KR0121103B1 (en) 1995-01-28 1995-01-28 Control method and apparatus for multi-reference expert type fuzzy logic

Publications (2)

Publication Number Publication Date
KR960029931A true KR960029931A (en) 1996-08-17
KR0121103B1 KR0121103B1 (en) 1997-12-04

Family

ID=19407561

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1019950001785A KR0121103B1 (en) 1995-01-28 1995-01-28 Control method and apparatus for multi-reference expert type fuzzy logic

Country Status (1)

Country Link
KR (1) KR0121103B1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100865719B1 (en) * 2007-03-07 2008-10-29 세메스 주식회사 Pid controller using fuzzy criterion function and auto tuning method of the same

Also Published As

Publication number Publication date
KR0121103B1 (en) 1997-12-04

Similar Documents

Publication Publication Date Title
White Learning in artificial neural networks: A statistical perspective
Lu et al. Robust nonlinear system identification using neural-network models
JP2005523534A (en) Automatic neural network model generation and maintenance
JP2019021186A (en) Data processor, control system, data processing method, and program
CN114692494A (en) Lithium battery temperature field online modeling method and system
Bilbao Guillerna et al. Robustly stable multiestimation scheme for adaptive control and identification with model reduction issues
WO2019160138A1 (en) Causality estimation device, causality estimation method, and program
Rudner et al. Outcome-driven reinforcement learning via variational inference
Kosmatopoulos Control of unknown nonlinear systems with efficient transient performance using concurrent exploitation and exploration
Dias et al. Implementing the levenberg-marquardt algorithm on-line: A sliding window approach with early stopping
Du et al. Reinforcement learning
KR960029931A (en) Multi-criteria expert fuzzy logic control method and device
Dias et al. A sliding window solution for the on-line implementation of the Levenberg–Marquardt algorithm
Abonyi et al. Hybrid fuzzy convolution modelling and identification of chemical process systems
Howell et al. Control of a negative-ion accelerator source using neural networks
Ahmed et al. Phase-Amplitude Coordinate-Based Neural Networks for Inferring Oscillatory Dynamics
Ren et al. Adaptive Regulation for Hammerstein and Wiener Systems with Event-Triggered Observations
RU2510956C2 (en) Method for adaptive pid law-based control and system for realising said method
Dias et al. On-line training of neural networks: a sliding window approach for the Levenberg-Marquardt algorithm
Mohamed et al. Modelling of induction motor using non-linear neural network system identification
O’Brien Jr et al. Robust controller design for linear, time-varying systems
US6760692B1 (en) Structure of a trainable state machine
Righeto et al. Nonlinear plant identification by wavelets
Durnyak et al. Synthesis and Modeling of Systems with Combined Fuzzy P+ I-Regulators
Chaturvedi Factors affecting the performance of artificial neural network models

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: 20130515

Year of fee payment: 17

FPAY Annual fee payment

Payment date: 20140620

Year of fee payment: 18

EXPY Expiration of term