Mamdani Model For Automatic Rule Generation of A Miso System
|
 |
|
Post a Comment
|
 |
|
|
|
|
ABSTRACT:
This paper describes a method of generating rule based fuzzy control for multiple input single input systems. The rule generated by the program uses Gaussian membership function from time series data. This automatic rule will be used to forecast the same time series and the effective of the algorithm is measured by SSE and MSE. We choose n=17 as the number of Gaussian membership function and using 200 data for the training. The forecasting is carried on 187 rules after deleting conflicting / redundant rules to test or validate 975 next Data. The final result shows that the capability of Rule Generation Fuzzy Logic in forecasting not optimal. We can show that automatic rule generation using Gaussian membership function in Mamdani model of fuzzy control system is not sufficient.
|
|
|
|
STATISTICS
|
|
Click on # to view
|
|
Citations
|
|
0
|
|
References
|
|
0
|
|
Comments
|
|
0
|
|
Quality
|
|
0/0.00
|
|
Interest
|
|
0/0.00
|
|
View(er)s
|
|
2/43
|
|
|
|
|
|
|
| Prev |
Next |
|