论文部分内容阅读
分析了直流锅炉运行时各变量之间的耦合关系;针对直流锅炉参数多变、强耦合的特点,提出了一种改进的误差反向传播算法(BP)神经网络分散解耦方法,对直流锅炉汽温-压力控制系统进行解耦,然后采用基于BP神经网络的PID控制方法对解耦后的2个近似独立的单输入单输出系统进行控制.仿真实验结果表明:BP神经网络分散解耦控制算法具有很强的自学习功能和自适应解耦能力,能取得良好的控制效果.
Aiming at the characteristics of variable and strong coupling of boiler parameters, an improved error back propagation algorithm (BP) neural network decentralized decoupling method is proposed to analyze the relationship between the variables of the DC boiler. The temperature-pressure control system is decoupled, and then the PID control method based on BP neural network is used to control the decoupled two single-input and single-output systems which are approximately independent.The simulation results show that BP neural network is decentralized decoupling control The algorithm has a strong self-learning function and adaptive decoupling ability, can achieve good control effect.