ATS Telegraph Pattern Recognition Using a Neural Network
-
摘要: 空中交通服务电报采用固定的信息编组方式组织报文.由于传输差错及人为因素引起了报文的非标准化,计算机自动处理困难.本文提出了基于模式识别、神经网络技术的报文处理算法,并进行了仿真实验,结果表明该算法具有较高的报文正确识别率,以及维护简单、扩充方便灵活的优点.Abstract: The air traffic service (ATS) telegraphs are composed of fixed information groups. The transmission errors and artificial factors lead to the nonstandard contents of telegraphs, which make the difficulties for the computer to process. In order to solve the problem, pattern recognition and neural network, which can increase the rate of recognition and rate of picking-up right information greatly, are adopted to process the nonstandard messages. This is the key for intelligentized air traffic control. Numerical simulation shows that this method has higher recognition rate and more efficiency. The other excellences of this method are easy to maintain and update.
-
Key words:
- air traffic control /
- pattern recognition /
- neural networks /
- AFTN
-
[1] 黄德双.神经网络模式识别系统理论[M]. 北京:电子工业出版社,1996. [2] 焦李成.神经网络的应用与实现[M].西安:西安电子科技大学出版社,1993. [3] 张乃尧,阎平凡.神经网络与模糊控制[M].北京:清华大学出版社,1998. [4] Harrison Lee H, Saunders Pamela J, Saraceni Peter J. Artificial intelligence and expert systems for avionics . In:12th AIAA/IEEE Digital Avionics Systems Conference . 1993.25~28. [5] 陈念贻.模式识别优化技术及其应用[M].北京:中国石化出版社,1996. [6] 中国民用航空总局文件 [1994] 84号,中国民用航空飞行动态固定格式电报的拍发规定[S].1994.
点击查看大图
计量
- 文章访问数: 4503
- HTML全文浏览量: 98
- PDF下载量: 1597
- 被引次数: 0