In our daily life from the production lines in manufacturing plants, medical equipment, and agriculture to the consumer products such as washing machine and air-conditioner, FLC can be applied. The important part in FLC is during the process in selecting the membership function. The membership function of a fuzzy set is a generalization of the indicator function in classical sets. In fuzzy logic, it represents the degree of truth as an extension of valuation.
As for an example, the controller temperature sets for plastic extruders by FLC. When extruding certain materials, the temperatures along the extruder must be accurately controlled in accordance with properties of the particular polymer and of the extruder. If the temperatures are not accurately controlled, the molten polymer will not be uniform and may decompose as a result of excessive temperatures.
One of the problems associated with the prior art extruder control systems occurs in the design of the barrel zone temperature controllers (Tsai & Lu, 1998; Lu & Tsai, 2001). Preferably, these controllers are designed with a high sensitivity to disturbance signals. However, when a change in a temperature set point occurs, there is a danger in saturating the zone temperature controllers as the magnitude of the temperature set point changes are generally greater than the magnitude of disturbances. Hence, the sensitivity of the controller to disturbance signals must be reduced to prevent saturation of the controllers to set point changes (Tsai & Lu, 1998; Lu & Tsai, 2001; Altinten, et al., 2006).
Thus it is important to select the accurate membership functions for temperature setting an extruder control systems. However, conventional FLC uses membership function generated by human operator, where the membership function selection process is done with trial and error and it is runs step by step, which is too long in solving the problem (Torres, 2000; Altinten et al, 2006). For a new approach for optimum coding of fuzzy controllers via Genetic Algorithms (GA), GA are used to determine membership function specially designed in situations as above.
The controller must operate in two modes (Bela, 2006; Hung & Sheng, 2006).
1. In automatic mode, it increases from a fixed initial point to a fixed set point at a fixed rate. Designing a conventional controller for these operational specifications is routine.
2. In autonomous mode, however, the control system must cope with abnormal situations that can shut down plant operation. Recovery from such conditions involves reheating from arbitrary initial points at different rates and possibly to different set points. A conventional controller cannot handle all these situations efficiently.
According to the situations, this is why we need to use control system based on FLC, but manually designing the membership function of FLC to satisfy such requirements is to possess one common weakness where conventional FLC use membership function generated by human operator (Torres, 2000; Altinten et al, 2006). Thus, GA used to design FLC. GA are a rule of the resolution that is carried out at the same time to several solutions and they are done randomly to increase the efficiency as well as taking the fastest processes in solving the problems (Torres, 2000; Galantucci et al, 2004; Altinten et al, 2006; and Gen et al, 2008).
.
