基于BP神经网络的多变量PID解耦控制

Multivariate Decoupling Control Based on Back Propagation Neural Network

基于神经网络实现智能PID控制的策略,它以经典的PID控制为基础,通过神经网络参数整定实现,进而进行自学,用于多变量系统的解耦控制。本文给出了网络的结构和算法,对一组二变量强耦合时变系统进行了仿真。通过计算机仿真证明了基于神经网络的PID控制器网络结构简单规范具有良好的自学习和自适应解耦控制能力。系统易于实现,融解耦器与控制器于一体,适用于非线性多变量系统的解耦控制。能够使解耦后的系统具有良好的动态和静态性能,特别是依据BP控制规律来确定网络连接权的初值,还具有参数快速收敛的优点。

Intelligent PID control strategy, which is based on neural network, is according to classical PID control, realized through neural network parameter setting which has self study function for multivariate decoupling control. The structure and the algorithm were given and the real-time simulation results of double variable and strong- coupled time-varying system were shown in the paper. It proved that PID control based on neural network has preferably self study and self adapting decoupling control ability through simulation. The system, which inosculates the decoupler and controler, is easy to implement and applicable for multivariate decoupling control. It makes the decoupled system have better dynamic behavior and static characteristic. Especially, it makes parameters astringe fast when determing initial value of network according to BP control law.