单神经元PID在单元机组协调控制系统中的应用

基于神经网络PID控制和协调系统强耦合的特点，应用一种针对多输人、多输出解耦系统的单神经元PID解耦控制算法和结构，并在算法中增加了自适应学习速率，更好地实现对单元机组的解耦控制。仿真结果表明，这种单神经元PID解耦控制算法实现的控制与常规的PID控制比较，不仅具有较好的动态性能和稳态性能，而且还具有很强的自学习功能和自适应解耦能力。

Application of Neural Network PID in Coordinated Control Systems of Generation Units

Based on PID neural network control and the strong coupling characters of the coordinated systems, arithmetic and structure of single neural PID decoupling are proposed.The arithmetic can be used in multiple input and multiple output decoupling systems and can realize decoupling control for unit plants.The simulated results show that the arithmetic is better than the general PID decoupling. It not only has better dynamic performance and stability performance, but also has better self study and self adapting decoupling ability.