Genetic Adapt Fuzzy Control System Why Fuzzy The real world is not black and white. The da
Genetic Adapt Fuzzy Control System
Why Fuzzy
The real world is not black and white. The day in and day out human
reasoning is all but EXACT. However, the classical logic and the
traditional control systems are based on exact reasoning. Fuzzy logic,
also known as imprecise reasoning, allows us solving problems with fuzzy
boundaries as we handle daily routines. Fuzzy logic is a formulation of
logic using mathematical framework to deal concepts such as few, very,
much, and many. Fuzzy logic can help us make decisions when lack of
specific facts or the knowledge is imprecise or far from complete.
Human experts can handle situations beyond their knowledge with
gracefully degraded accuracy, but the traditional control systems
normally breakdown when the environment is out of their design scope.
Many environments are difficult to model mathematically, especially for
systems with uncertainties or nonlinearties. When applying
conventional control logic to these environments, it requires human
interactions or interventions. On the other hand fuzzy control system
is not based on strict mathematical model. Not only it is easier and
quicker to build a control system but it also degrades gracefully.
Apply Genetic Algorithm in Fuzzy Control System
However, there are drawbacks in fuzzy logic control systems. The fuzzy
sets and rules must be determined properly for the system to function
correctly. This introduces a problem for some fuzzy systems and fuzzy
chips. The problem is that the rules and sets must be coded up front
instead tuned at site. Another problem is that because of its imprecise,
it is difficult for users to come up with an optimal solution. As a
result, users are spending more time in tuning up fuzzy sets and rules.
While fuzzy logic mimics the human's imprecise reasoning, the genetic
algorithm mimics the evolution of the nature. Applying genetic algorithm
in fuzzy control eliminates problems associated with fuzzy system. The
genetic algorithm uses randomization techniques to reach local optimum
without exhausting searches through the solution state space. With
randomization, genetic algorithm is also capable of escaping from local
optimum and hopping into a new and better state.
What Is Genetic Adapt Fuzzy Control System
The GeneticAdapt Fuzzy control system (GAF) combines powerful
features from fuzzy logic and genetic algorithm. GAF allows users to
generate a fuzzy control system by simply defining the inputs, outputs,
measured data set, and initial rule sets. GAF uses genetic algorithm to
derive proper rules and fuzzy sets from the initial rules. By changing,
adding, deleting rules and fuzzy membership sets, the genetic algorithm
automatically adapts and optimizes the fuzzy control system. Besides
optimizes fuzzy rules, GAF also provides users the capability to
simulate and debug their applications. GAF replaces complex
conventional control algorithm with simple fuzzy rules contained in
English like text files. It builds run time data directly from the rule
files to eliminate intermediate compilation and achieve quick turn
around time.
EMail Fredric L. Rice / The Skeptic Tank
