论文部分内容阅读
为改善转台系统性能,针对传统的PID控制参数难以获得较理想的控制效果,设计了一种基于改进型BP神经网络的PID控制器。介绍了PID控制器的结构和BP神经网络算法描述,利用最小二乘法和神经网络建立被控对象的预测数学模型,并用该模型所计算的预测输出取代预测输出的实测值,对基于BP网络的PID控制器的权值调整算法进行改进。以某转台模型为对象,建立了转台控制系统的数学模型并对其进行仿真。仿真结果表明,改进型BP神经网络PID控制器具有良好的控制效果,跟踪精度高、性能稳定及鲁棒性强,能更为有效地应用到转台系统中。
In order to improve the turntable system performance, it is difficult to obtain the ideal control effect for the traditional PID control parameters. A PID controller based on the improved BP neural network is designed. The structure of PID controller and the description of BP neural network algorithm are introduced. The prediction mathematical model of the controlled object is established by using least square method and neural network. The predicted output calculated by the model is substituted for the measured output, PID controller weight adjustment algorithm to be improved. Taking a turntable model as an example, a mathematical model of turntable control system is established and simulated. The simulation results show that the improved BP neural network PID controller has a good control effect, high tracking accuracy, stable performance and robustness, and can be more effectively applied to the turntable system.