摘要
利用模糊控制的推理功能使神经网络得以简化，减少了学习单元的数量，提高了收敛速度．利用神经网络的并行特点使模糊控制表更容易实现，利用ＢＰ算法为自适应模糊控制提供了一种通用的规则再增强自适应算法．仿真验证了这种再增强模糊神经网络控制器的合理性．
This paper uses the inference ability of fuzzy control to make up the low-speed and complexities of artificial neural network. On the other hand, the neural network makes it easy to deal with fuzzy control. The BP algorithm provides fuzzy self-organizing with a general reforcement method. Based on these advantages, a reinforcement fuzzy neural network controller is designed. Its reasonablity is verified by simulation.
关键词
模糊控制
神经元特征函数
控制器
BP算法
fuzzy control, fuzzy language, membership, neural activation function,self-organizing, BP algorithm
