摘要
常规PID的控制,不但其参数难以整定,而且还依赖于对象的精确数学模型,适应性较差,对复杂过程不能保证其控制精度。根据反应釜温度时间滞后具有非线性、强耦合、不确定性过程的控制需要,提出了一种基于BP神经网络的PID控制方法。并介绍了神经网络PID控制器的算法,对经典PID参数选取进行了分析。仿真结果表明,与传统PID算法相比,该控制方法可实现有效的控制,具有实现简单、控制效果好的特点。
It is hard to find parameters for conventional PID,and it depends on the accurate mathematical model of the plant. Its adaptability is worse,so the control accuracy of complex process can not be guaranteed. A new method of PID control method based on BP neural network is proposed because of the non-linear,strong coupling and uncertainty in reaction kettle temperature control. The algorithm of PID neural network controller and the selection of classical PID parameters are introduced and analyzed. This method is shown to be effective and simple for implementation.
出处
《微型机与应用》
2010年第20期84-86,共3页
Microcomputer & Its Applications
关键词
常规PID
BP神经网络
仿真
conventional PID
BP neural network
simulation