一种基于改进的粒子群优化算法的神经网络PID控制器  被引量:7

Neural PID controller based on improved particle swarm optimization algorithm

在线阅读下载全文

作  者:金林骏 方建安[1] 潘磊宁 

机构地区:[1]东华大学信息科学与技术学院,上海201620

出  处:《机电工程》2015年第2期295-300,共6页Journal of Mechanical & Electrical Engineering

摘  要:针对多输入多输出(MIMO)复杂过程控制中控制性能偏慢等问题,对神经网络PID控制器以及PID控制理论物理机制之间的相互作用进行了研究。对神经元PID控制器隐层和输出层之间的初始权值进行了归纳,提出了一种粒子群优化算法,提高了PSO算法的收缩因子以保证优化的收敛性,并进行了Matlab仿真。研究结果表明,所提出的神经网络PID控制器的改进粒子群算法优化,在高耦合效应的复杂MIMO对象中具有良好的精度以及快速响应的特性。Aiming at the complicated process control in the control performance is slow and other issues, neural network PID controller and the interaction between the physical mechanism of PID control theory were studied. The initial weights between neuron PID controller hidden layer and output layer were summarized. A kind of particle swarm optimization algorithm was put forward. The shrinkage factor of PS0 algorithm was improved to guarantee the convergence of optimization and Matlab simulation was used. The research results indicate that the neural PID controller optimized by improved particle swarm optimization algorithm has good accuracy and fast response characteristics in the complex MIMO object in high coupling effect.

关 键 词:神经网络 PID控制器 多输入多输出 解耦 改进的粒子群优化算法 

分 类 号:TP273[自动化与计算机技术—检测技术与自动化装置]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象