基于CMAC神经网络的自适应渠道输水自动控制研究  

Self-adapting Canal Automation Control Method Based on CMAC Neural Network

作　　者：韩延成[1] 高学平[1] 涂向阳[1] 张晨[1] 

机构地区：[1]天津大学水利水电系

出　　处：《灌溉排水学报》2007年第2期76-79,共4页Journal of Irrigation and Drainage

基　　金：山东省重点科研项目(2006;6)

摘　　要：介绍了小脑模型神经网络CMAC的原理及基于CMAC的自动控制方法。在渠道输水控制技术的基础上,依据CMAC神经网络学习速度快、能够表达复杂非线性关系、适合于适时控制的特点,提出了基于CMAC的渠道输水控制模型。仿真结果表明,基于CMAC的渠道输水控制,算法简单方便,具有实时性、稳定性和较强的鲁棒性,控制效果较为理想。The paper presents the CMAC neural network theory and the automation control method based on CMAC. According to the characteristics, which CMAC can show the complex nonlinear relations, have quick training speed, and is fit for real-time control better, the CMAC canal control is created. The simulation results show that the canal control method based on CMAC is simple, and have the features of realtime, stability, robustness, and have better control results.

关 键 词：CMAC PID 神经网络 控制 渠道 输水 非线性系统 

分 类 号：S274[农业科学—农业水土工程]