基于BP神经网络PID算法的风力摆控制系统的设计
|
摘要
随着智能控制技术的发展,将神经网络技术与传统PID控制技术相结合,并应用到控制系统中去已成为一种趋势。在对风力摆控制系统进行需求分析的基础上,针对其具有非线性和参数不确定等特点,提出了基于BP神经网络PID算法的风力摆控制系统的设计方案,将BP神经网络应用到传统PID控制中,设计出了系统的软硬件结构,实现了有效控制风力摆按指定角度画线、指定时间恢复静止和画圆的功能。研究结果表明:采用BP神经网络PID算法的控制系统具有更强的稳定性和控制精度。
With the development of intelligent control technology, it has become a trend to combine the neural network technology with the traditional PID control technology and apply it to the control system. Based on the requirement analysis of wind pendulum control system and its characteristics of nonlinear and uncertain parameters, a design scheme of wind pendulum control system based on BP neural network PID algorithm was proposed. With BP neural network applied to the traditional PID control, the hardware and software structures of the system were designed, the functions of controlling the wind swing to draw lines at a specified angle, restoring static at a specified time and drawing circles were realized. The research result shows that the control system with BP neural network PID algorithm has stronger stability and control precision.
With the development of intelligent control technology, it has become a trend to combine the neural network technology with the traditional PID control technology and apply it to the control system. Based on the requirement analysis of wind pendulum control system and its characteristics of nonlinear and uncertain parameters, a design scheme of wind pendulum control system based on BP neural network PID algorithm was proposed. With BP neural network applied to the traditional PID control, the hardware and software structures of the system were designed, the functions of controlling the wind swing to draw lines at a specified angle, restoring static at a specified time and drawing circles were realized. The research result shows that the control system with BP neural network PID algorithm has stronger stability and control precision.
引文
[1]牧彬,米征,盛凯,等.BP神经网络PID控制器在无人机编队飞行中的应用[J].测控技术,2017,36(4):66-69.
[2]韩宇萌,贾晓洪,王炜强,等.基于BP神经网络的捷联导引头控制系统设计[J].测控技术,2016,35(10):70-74.
[3]袁静,王锐,江力.多自由度工业机器人基于神经网络的自适应PID控制[J].计算机应用,2017,37(S1):123-125.
[4]倪洪启,王帅军,王树强,等.BP神经网络PID控制对液压控制系统的改进[J].锻压技术,2015,40(11):67-70.
[5]童诗白,华成英.模拟电子技术基础[M].4版.北京:清华大学出版社,2006.
[6]曲朝阳,计超,郭晓利,等.基于传递函数自我优化的BP网络算法改进[J].电测与仪表,2014,51(11):56-59.
[7]张敏,徐启华.基于改进BP的神经网络模型参考自适应控制[J].软件,2015(7):118-123.
[8]崔皆凡,谢炜,马桂新,等.基于BP神经网络PID的改进偏差耦合同步控制[J].微电机,2016,49(12):54-57.
[9] Dong W L,Qu D C,Dong W J. A PID neural network control strategy based on GA-BP algorithm[J]. Ordnance Industry Automation,2011,30(2).
[10]潘琦.用于风力摆系统的控制算法及软硬件实现研究[D].长春:吉林大学,2016.
[2]韩宇萌,贾晓洪,王炜强,等.基于BP神经网络的捷联导引头控制系统设计[J].测控技术,2016,35(10):70-74.
[3]袁静,王锐,江力.多自由度工业机器人基于神经网络的自适应PID控制[J].计算机应用,2017,37(S1):123-125.
[4]倪洪启,王帅军,王树强,等.BP神经网络PID控制对液压控制系统的改进[J].锻压技术,2015,40(11):67-70.
[5]童诗白,华成英.模拟电子技术基础[M].4版.北京:清华大学出版社,2006.
[6]曲朝阳,计超,郭晓利,等.基于传递函数自我优化的BP网络算法改进[J].电测与仪表,2014,51(11):56-59.
[7]张敏,徐启华.基于改进BP的神经网络模型参考自适应控制[J].软件,2015(7):118-123.
[8]崔皆凡,谢炜,马桂新,等.基于BP神经网络PID的改进偏差耦合同步控制[J].微电机,2016,49(12):54-57.
[9] Dong W L,Qu D C,Dong W J. A PID neural network control strategy based on GA-BP algorithm[J]. Ordnance Industry Automation,2011,30(2).
[10]潘琦.用于风力摆系统的控制算法及软硬件实现研究[D].长春:吉林大学,2016.