Research & Application Of Fuzzy Algorithm Based On Evolutionary Programming

Without building the exact math model, the design of the fuzzy controller has a nice robustness. But in designing a fuzzy model and a fuzzy controller, we encounter a major difficulty in the identification of an optimized fuzzy rule base, which is traditional achieved by a tedious trial and error process. The thesis presents an approach to automatic design of optimal fuzzy rule bases for modeling and control using evolutionary programming. To check the effectiveness of the suggested approach, three examples for modeling and control are examined. The main contents are concluded as follows:1. In order to overcoming the difficulties of creating model of nonlinear system, The paper adopts the approach to build Fuzzy model and use three layer structure evolution programming to identify T-S fuzzy model, this algorithm can optimize the structure and parameter of the T-S fuzzy model directly.2. In view of the difficulties to controlling nonlinear system, the paper presents an approach to automatic design of optimal fuzzy rules for PID parameter using improved evolutionary programming. Compared with the traditional PID control algorithm, the PID parameter adjustment scheme adopts linguistic fuzzy rules instead of using fixed parameter. It provides a new way for controlling nonlinear system.3. Owning to the practical facts including mechanism complex, frequent disturbance, establishing model hardly, nonlinear and so on, double layer evolution programming and fuzzy algorithm is presented to apply in combusting control. The simulation result in the main steam pressure control shows that the proposed method can improve the efficiency of the units and get over the impact of inner and outer disturbing.