摘要
为了对某全景式航空相机所产生的前向像移进行补偿,对前向像移产生的原理进行分析,并对像移补偿的方法进行研究。根据该型相机的工作原理,找到前向像移产生的机理。用神经网络模型(NNM)对系统时域响应的非线性特性进行辨识。根据NNM给出的扫描反射镜补偿角速度的预测值,通过最优算法调整控制信号,使被控对象跟踪理想补偿角速度的性能达到最优。该方法在该型相机前向像移补偿上克服了传统PID控制方法中所存在的不足,即精度低、响应慢、适应性差。实验结果表明:采用神经网络预测控制,扫描反射镜的实际补偿角速度输出跟踪理想补偿角速度的性能良好,优于传统方法。该方法可以应用于该型航空相机的像移补偿中。
In order to compensate forward image motion of a certain aviation camera, the reasons for it were analyzed, and the compensation methods were studied. Firstly, the mechanism of image motion was found out on the basis of the camera＇ s principle. Secondly, a neural network model （NNM） was used to identify the nonlinear characteristics of the system＇ s response in time domain. Finally, according to the prediction given by NNM, the control signal was adjusted by using optimal algorithm to make the tracking performance of the scanning mirror optimal. This method overcomes some shortcomings of traditional PID control, such as low accuracy, slow response and weak adaptability. The compensation results show that the compensated angular speed of scanning mirror can track the desired angular speed.
出处
《兵工学报》
EI
CAS
CSCD
北大核心
2012年第6期706-711,共6页
Acta Armamentarii
关键词
自动控制技术
航空相机
前向像移
像移补偿
神经网络
预测控制
automatic control technology
aviation pensation
neural network
predictive control camera
forward image motion
image motion tom-
