Presentation is loading. Please wait.

Presentation is loading. Please wait.

Lecture 12 Introduction to Neural Networks and Fuzzy Logic President UniversityErwin SitompulNNFL 12/1 Dr.-Ing. Erwin Sitompul President University

Similar presentations


Presentation on theme: "Lecture 12 Introduction to Neural Networks and Fuzzy Logic President UniversityErwin SitompulNNFL 12/1 Dr.-Ing. Erwin Sitompul President University"— Presentation transcript:

1 Lecture 12 Introduction to Neural Networks and Fuzzy Logic President UniversityErwin SitompulNNFL 12/1 Dr.-Ing. Erwin Sitompul President University http://zitompul.wordpress.com 2015

2 President UniversityErwin SitompulNNFL 12/2 Solution: Homework 11 Fuzzy ControlFuzzy Logic

3 President UniversityErwin SitompulNNFL 12/3 FC with 5 Rules Solution: Homework 11 (Cont.) Fuzzy ControlFuzzy Logic Rule 1:IF level is okay,THEN valve is no change. Rule 2: IF level is low, THEN valve is open fast. Rule 3: IF level is high, THEN valve is close fast. Rule 4: IF level is okay AND rate is negative, THEN valve is open slow. Rule 5: IF level is okay AND rate is positive, THEN valve is close slow. Rule 1:IF error is zero,THEN valve is no change. Rule 2: IF error is positive,THEN valve is open fast. Rule 3: IF error is negative,THEN valve is close fast. Rule 4: IF error is zero AND error rate is positive, THEN valve is open slow. Rule 5: IF error is zero AND error rate is negative, THEN valve is close slow. error = reference – level rate of error = – rate of level

4 President UniversityErwin SitompulNNFL 12/4 Solution: Homework 11 (Cont.) Fuzzy ControlFuzzy Logic Valve control signal [%/s] no change open fast close fast –30 –20 –10 0 10 20 30 1 open slow close slow Rate of level error [cm/s] zero positivenegative –4 –0.5 0 0.5 4 1 Level error [cm] zero positivenegative –5 –4 0 4 5 1 1 st Set of Membership Functions

5 President UniversityErwin SitompulNNFL 12/5 Solution: Homework 11 (Cont.) Fuzzy ControlFuzzy Logic

6 President UniversityErwin SitompulNNFL 12/6 Solution: Homework 11 (Cont.) Fuzzy ControlFuzzy Logic Level error [cm] zero positivenegative –5 -1 0 1 5 1 2 nd Set of Membership Functions Valve control signal [%/s] no change open fast close fast –30 –20 –10 0 10 20 30 1 open slow close slow Rate of level error [cm/s] zero positivenegative –4 –0.5 0 0.5 4 1

7 President UniversityErwin SitompulNNFL 12/7 Solution: Homework 11 (Cont.) Fuzzy ControlFuzzy Logic

8 President UniversityErwin SitompulNNFL 12/8 Solution: Homework 11 (Cont.) Fuzzy ControlFuzzy Logic Level error [cm] zero positivenegative –10 –? 0 ? 10 1 3 rd Set of Membership Functions Valve control signal [%/s] no change open fast close fast –30 –20 –10 0 10 20 30 1 open slow close slow Rate of level error [cm/s] zero positivenegative –4 –0.5 0 0.5 4 1

9 President UniversityErwin SitompulNNFL 12/9 Solution: Homework 11 (Cont.) Fuzzy ControlFuzzy Logic

10 President UniversityErwin SitompulNNFL 12/10 PID-like Fuzzy Controllers Fuzzy P Controller u + – e r y Fuzzy ControlFuzzy Logic

11 President UniversityErwin SitompulNNFL 12/11 PID-like Fuzzy Controllers Fuzzy PD Controller u + – e r y Fuzzy ControlFuzzy Logic

12 President UniversityErwin SitompulNNFL 12/12 PID-like Fuzzy Controllers Fuzzy PID Controller u e r y + – Weakness: too many rules Fuzzy ControlFuzzy Logic

13 President UniversityErwin SitompulNNFL 12/13 PID-like Fuzzy Controllers Fuzzy PD+I Controller r + – e y uu Fuzzy ControlFuzzy Logic

14 President UniversityErwin SitompulNNFL 12/14 PID-like Fuzzy Controllers r u + – e y + + uu Fuzzy PD+I Controller Fuzzy ControlFuzzy Logic

15 President UniversityErwin SitompulNNFL 12/15 PID-like Fuzzy Controllers Fuzzy PD+I Controller r u + – e y + + Fuzzy ControlFuzzy Logic

16 President UniversityErwin SitompulNNFL 12/16 End of the Lecture Fuzzy ControlFuzzy Logic


Download ppt "Lecture 12 Introduction to Neural Networks and Fuzzy Logic President UniversityErwin SitompulNNFL 12/1 Dr.-Ing. Erwin Sitompul President University"

Similar presentations


Ads by Google