作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2008, Vol. 34 ›› Issue (7): 186-188. doi: 10.3969/j.issn.1000-3428.2008.07.066

• 人工智能及识别技术 • 上一篇    下一篇

基于神经网络改进算法的飞控系统故障诊断

刘小雄,章卫国,李广文   

  1. (西北工业大学自动化学院,西安 710072)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-04-05 发布日期:2008-04-05

Fault Diagnosis in Flight Control System Based on Improved Algorithm of Neural Network

LIU Xiao-xiong, ZHANG Wei-guo, LI Guang-wen   

  1. (College of Automation, Northwestern Polytechnical University, Xi’an 710072)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-04-05 Published:2008-04-05

摘要: 应用神经网络技术对复杂的飞行控制系统进行故障诊断对提高飞机的可靠性和容错能力具有重要意义。为了提高网络的学习效率和稳定性,该文提出一种改进的径向基神经网络学习算法,使用混合共轭梯度优化算法对网络参数进行调整。利用神经网络对某型飞机的飞行控制系统进行故障诊断,仿真结果表明该神经网络具有较强的故障识别能力。

关键词: 飞行控制系统, 径向基神经网络, 故障诊断

Abstract: Fault diagnosis is very important for enhancing the safety and reliability of flight control sys tem. To improve the learning efficiency and stability of neural network, an improved learning algorithm for the adaptive Radio Basis Function(RBF) neural network is proposed. Network parameter is optimized by efficient hybrid conjugate gradient optimization algorithm. The scheme is illustrated through simulations applying the flight control system of a fighter. Simulation results show that fault identification is achieved.

Key words: flight control system, RBF neural network, fault diagnosis

中图分类号: