论文部分内容阅读
提出一种用遗传算法直接从输入输出数据中提取模糊规则以逼近任意非线性函数的方法。该方法首先把输入空间进行模糊划分,然后用遗传算法优化各隶属函数的参数,最终得到一组模糊规则,它们能以非常高的精度逼近非线性函数。仿真结果和置信度检验证明了该方法的有效性。此外,该方法能方便地用于模糊控制器的设计和自适应调整
A genetic algorithm is proposed to directly extract the fuzzy rules from the input and output data to approximate any non-linear function. In the method, the input space is first divided into fuzzy parts, and then the genetic algorithm is used to optimize the parameters of each membership function. Finally, a set of fuzzy rules are obtained, which can approach the nonlinear functions with very high accuracy. Simulation results and confidence tests prove the effectiveness of this method. In addition, this method can be conveniently used for fuzzy controller design and adaptive adjustment