基于IGA-RBF神经网络的导弹控制系统故障诊断

来源期刊:中南大学学报(自然科学版)2011年第z1期

论文作者:张文广 史贤俊 唐静 肖支才

文章页码:870 - 875

关键词:RBF神经网络;正交最小二乘法;遗传算法;故障诊断

Key words:RBF neural network; orthogonal least squares algorithm; genetic algorithm; fault diagnosis

摘    要:建立基于RBF神经网络的故障观测器模型以实现导弹控制系统的故障诊断,并针对传统RBF网络算法的不足,提出一种将改进的遗传算法(IGA)与正则化正交最小二乘法(ROLS)相结合的两级RBF学习方法。经过训练的RBF网络观测器与实际的系统并行工作,通过比较RBF观测器的估计输出和系统的实测输出产生残差,通过检测残差即可诊断系统是否出现故障。实验结果表明:基于IGA-RBF神经网络的故障观测器能够有效地实现导弹控制系统的故障诊断。

Abstract: A failure observer based on RBF neural network was developed to realize the fault diagnosis of missile control system, and considering the shortage of traditional RBF learning method, a two-level learning method was proposed for designing radial basis function (RBF) network based on improved genetic algorithm optimization (IGA) and regularized orthogonal least squares (ROLS). The trained RBF observer worked concurrently with the actual system. Comparing the estimated output with the actual measurements, the residual signal was generated and then analyzed to report the occurrence of faults. The experimental results show that the failure observer based on the RBF neural network is effective in detecting the failure of the missile control system.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号