论文部分内容阅读
将遗传算法引入到模糊神经网络控制器的学习过程中，提出了一种综合遗传算法和梯度下降法优势的混合遗传算法。它一方面改善了梯度法的收敛性，使模糊系统对专家知识的依赖性大为降低，提高了系统的智能化水平；另一方面有效地提高了遗传算法的搜索效率，强化了模糊系统的学习能力。仿真结果证明了算法的有效性。
The genetic algorithm is introduced into the learning process of fuzzy neural network controller. A hybrid genetic algorithm which combines the advantages of genetic algorithm and gradient descent method is proposed. On the one hand, it improves the convergence of gradient method, reduces the dependence of fuzzy system on expert knowledge greatly, improves the intelligent level of the system; on the other hand, it effectively improves the search efficiency of genetic algorithm and strengthens the fuzzy system’s Learning ability. Simulation results prove the effectiveness of the algorithm.