Review and Improvement of Several Optimal Intelligent Pitch Controllers and Estimator of WECS via Artificial Intelligent Approaches - Complex System Modelling and Control Through Intelligent Soft Computations - page 508

6.2 Protocol of Fuzzy Rule

In proposed method fuzzy if-then rules are coded as a numeral string and are
implied by its corresponding random fuzzy sets. Consequent class and the certainty
grade can be absolutely detailed by the heuristic

fitness function.
The following symbols are used for indicating the seven used linguistic values:
(1) very small, (2) small, (3) medium small, (4) medium, (5) medium large, (6) large,
(7) very large.
For example, the following fuzzy if-then rule is coded as “ 172 ” : If Xl is very

small then Y1 is very large and Y2 is small.

6.3 Interpretation of Fitness Function

In fuzzy exclusive systems a population of fuzzy if-then laws equate to a fuzzy rule-
based classi cation methodology. Fitness function is GFS encompass 2 section, one

of them analogized generated laws with optimal upscale, thus a rule that conceal
almost all the optimal values could be a genuine law. In the second section, symbol
alternative of laws have computation on wind turbine power formula, corre-
spondingly a law that has the best control on power and adjust it well, could be a
goal rule. Finally each piece of these parts has been distributed weight. As an
outcome the leading law will be nominated from inceptive random laws (Kasiri
et al. 2012b ).

6.4 Genetic Operations (GO)

A GA usually has the three genetic operators that act on the chromosomes of each
generation of the genetic algorithm. These operators include (Hisao et al. 1999 ):

1. Selection: In GA, pair of parents is selected from the current population
according to Darwin

fittest principle. Methods in this works
have employed the well-known roulette wheel selection method.
2. Crossover: After couples are formed an n-point crossover is performed. The
position of the n crossover points is determined randomly and according to gene
boundaries. Each couple will produce two off-springs.
3. Mutation: Mutation is a probabilistic choice of k chromosomes of the pool and
performing a random alternation of the genes at l points. The values of n, k and
l are among the dynamics of the GA and are

' s survivor of the

fixed by the user before the

execution of GA.

Finally, the algorithm replaces the worst fuzzy if-then rules with the smallest

fitness values with the newly generated fuzzy if-then rules with the utmost tness