摘要
对使用BP网络来代替嵌入式飞行数据传感(FADS)系统的空气动力学模型进行了研究。针对FADS系统的特点设计了一个具有双隐含层的BP网络模型并详细推导出了它的快速算法。文中不仅设计了数据集的产生方法,而且对数据集的划分进行了探讨。试验结果显示,动静压的平均绝对误差均在130Pa以内,可以满足FADS系统的设计要求。
This paper use BP network to model the flush airdata sensing system instead of using aerodynamic model. In connection with the cbaracteristics of FADS system, a neural network arcbitecture with two hidden layers and its fast algorithm are designed. Not only the method of producirtg training patterns but also the technique of compiling training data are discussed in detail. As a result, the absolute mean errors of static pressure and impact pressure are all less than 130 Pa in both the trained area and the nearby area, which can meet the requirement for the design of the FADS system.
出处
《航空学报》
EI
CAS
CSCD
北大核心
2006年第2期294-298,共5页
Acta Aeronautica et Astronautica Sinica
关键词
大气数据传感系统
神经网络
快速算法
训练集
airdata sensing system
neural network
fast algorithm
training pattern
