摘要
在模糊系统的变节点自适应模糊神经网络实现的基础上 ,提出一种混合GA优化算法。该算法采用混合编码策略 ,利用GA对模糊规则和隶属函数同时优化 ,而对结论参数则用最小二乘法估计。算法综合了GA强大空间搜索能力和传统优化方法的快速收敛和高精度的优点 ,在保证全局优化能力的条件下 ,综合考虑了模糊控制器的复杂程度、训练速度和控制精度。仿真结果及应用表明了该算法的有效性。
This paper proposes a hybrid genetic algorithm (GA) based on an adaptive fuzzy-neural network with varying nodes. This algorithm simultaneously designs membership functions and rule sets using GA with hybrid coding scheme and the corresponding consequent parameters are estimated using least square estimation. The hybrid GA combines the advantages of GA's strong search capacity and conventional optimization technologies's fast convergence and accuracy merits. Therefore, the algorithm achieves a trade-off between accuracy, reliability and computing time in global optimization. The application demonstrates its effectiveness.
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2001年第1期73-76,共4页
Systems Engineering and Electronics
基金
国家自然科学基金!资助课题 (6 990 40 0 4)
