基于LM算法的组合导航系统的故障诊断  

The Fault Diagnosis of Integrated Navigation System Based on LM Algorithm

作　　者：钱华明[1] 姜波[1] 夏全喜[1] 

机构地区：[1]哈尔滨工程大学自动化学院,哈尔滨150001

出　　处：《中国造船》2009年第4期102-108,共7页Shipbuilding of China

摘　　要：LM(Levenberg-Marquardt)算法是梯度下降法与高斯-牛顿法的结合,在训练次数与精度上明显优于标准的BP算法。介绍了BP神经网络,采用LM算法对标准BP算法进行改进,并应用于船舶组合导航系统的故障诊断。仿真结果表明,LM算法可有效地提高学习速度,缩短训练时间,诊断效果好。The LM algorithm is the combination of the steepest decent algorithm with the Gauss-Newton algorithm. Concerned with the training process and accuracy, the LM algorithm is superior to traditional BP algorithm introduced in this paper. An improved algorithm of traditional BP based on LM（Levenberg-Marquardt） algorithm is proposed and applied to the fault diagnosis of marine integrated navigation system. Simulation results illustrate that LM algorithm could speed up learning process and reduce training time effectively. The diagnostic effect is good.

关 键 词：船舶 舰船工程 神经网络 LM算法 组合导航系统 故障诊断 

分 类 号：U666.1[交通运输工程—船舶及航道工程]