摘要
为了实现对四旋翼无人机的自稳定控制,首先对四旋翼无人机进行了动力学建模,提出了一种改变学习率的BP神经网络算法与PID控制相结合的姿态控制方法,并在相同环境下与常规PID控制器进行了仿真试验对比。仿真试验结果表明:基于改进型BP神经网络的PID控制器能够有效地实现无人机的自稳定控制,相比于常规PID控制器,基于改进型BP神经网络的PID控制器具有响应速度快\,超调量低\,鲁棒性强等优点。
In order to realize the self-stability control of the four-rotor UAV, the dynamics modeling of the four-rotor UAV is firstly built, and an attitude control method combining BP neural network algorithm with learning rate and PID control is proposed. The simulation test was compared with the conventional PID controller under the same environment. The simulation results show that the PID controller based on the improved BP neural network can effectively realize the self-stability control of the UAV. Compared with the conventional PID controller, the PID controller based on the improved BP neural network has a good feature of fast response speed, low overshoot and strong robustness.
引文
[ 1 ] 刘焕晔.小型四旋翼飞行器飞行控制系统研究与设计[D].上海:上海交通大学,2009.
[ 2 ] Mian A,Wang Daobo.Nonlinear Flight Control Strategy for an Underactuated Quadrotor Aerial Robot[J].IEEE AQTR,2008(1):8-16.
[ 3 ] 孟佳东,赵志刚.小型四旋翼无人机建模与控制仿真[J].兰州交通大学学报,2013,32(1):63-64
[ 4 ] 余后明,刘彦臣,刘玉斌,等.基于动态调节的小型四旋翼飞行器的控制系统[J].电光与控制,2018,25(9):106-109.
[ 5 ] 李俊,李运堂.四旋翼飞行器的动力学建模及PID控制[J].辽宁工程技术大学学报:自然科学版,2012,31(1):116-117
[ 6 ] 王敬志,任开春,胡斌.基于BP神经网络整定的PID控制[J].工业控制计算机,2011,24(3):72-73.
[ 7 ] 高觐悦.PID控制器参数优化中的仿真研究[J].计算机仿真,2011,28(3):259-262.
[ 8 ] 高富强,李萍,张磊敏,等.基于BP神经网络整定的PID控制及仿真[J].山东陶瓷,2017,40(3):27-31.
[ 9 ] 江杰,冯旭光,苏建彬.四旋翼无人机仿真控制系统设计[J].电光与控制,2015,22(2):27-30.
[10] 李献,骆志伟,于晋臣.MATLAB/Simulink系统仿真[M].北京:清华大学出版社,2017.