摘要
模糊系统的模糊推理方法常依赖于一系列由主观决定的参数，如模糊隶属函数、模糊关系矩阵等．如何确定这些参数会直接影响系统的性能．为了能对这些参数进行优化，文中采用一种新型的模糊推理方法，在此基础上，利用遗传算法产生出模糊推理方法中的最优参数．同时，在进化演变的搜索过程中，使用不断调整适应函数的手段，解决了遗传算法过早收敛于次优解的问题，提高了遗传算法的搜索精度．
The application of fuzzy reasoning method to fuzzy systems depends on a number of parameters, such as membership functions, that are usually decided upon subjectively. It was shown that the effect of fuzzy reasoning method may be improved if genetic algorithm is used. The genetic algorithm enables us to generate an optimal set of parameters for the fuzzy reasoning method based either on the initial subjective seletion or a random selection. In the genetic algorithm, the method of continuously changing of evaluation function along the process of search was proposed to solve the problem of convergence to sub optimum solution. Simulations are included to demonstrate the effectiveness and potential of the proposed method.
出处
《上海交通大学学报》
EI
CAS
CSCD
北大核心
1999年第11期1468-1470,共3页
Journal of Shanghai Jiaotong University
