基于BP神经网络的PID控制器参数调整  

Parameter Adjustment of PID Controller Based on BP Neural Network

作　　者：张永振 苏寒松[1] 刘高华[1] 廖泽龙 Zhang Yongzhen;Su Hansong;Liu Gaohua;Liao zelong(School of Electronic Information Engineering, Tianjin University, Tianjin 300072, Chin)

机构地区：[1]天津大学电子信息工程学院,天津300072

出　　处：《南开大学学报（自然科学版）》2018年第3期26-30,共5页Acta Scientiarum Naturalium Universitatis Nankaiensis

摘　　要：分别采用传统PID控制、BP神经网络PID控制算法,仿真控制传递函数为2阶的无刷直流电机.传统PID控制需要在初期给定比例、积分、微分系数值,而BP神经网络PID控制可以自适应调整比例、积分、微分系数值,从而实时改变被控对象的输入,使系统快速响应并稳定.Currently, the development of unmanned aerial vehicles is growing rapidly. For the control algorithm, traditional PID control can＇t meet the demand for rapid response in complex environments and applications. Neural network is a way of simulating human neuronal information transmission, which can approximate any nonlinear function. The traditional PID control and BP neural network PID control algorithm are used to simulate and control brushless DC motor of which transfer function is second order. Traditional PID control requires a given proportional, integral and differential coefficient at the beginning. However the BP neural network PID controller can adaptively adjust the proportional, integral, differential coefficient values. Thereby, changing input about the controlled object in real-time input makes quick system response and stability.

关 键 词：无人机 PID控制 BP神经网络 超调 学习规则 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]