基于HCMAC卡尔曼滤波器在组合导系统中的应用  

Applications of HCMAC/Kalman Filtering Technique in Integrated Navigation System

作　　者：张源[1] 陈伟[1] 

机构地区：[1]海军蚌埠士官学校航海系,安徽蚌埠233012

出　　处：《科技与企业》2015年第8期162-164,共3页Science-Technology Enterprise

基　　金：国家自然科学基金资助项目(41201478)

摘　　要：针对经典卡尔曼滤波器要求组合导航系统的动态模型和观测模型的噪声统计特性已知,而组合导航系统的噪声具有非先验性的问题,利用超闭球小脑神经网络(Hyperball Cerebellar Model Articulation Controller,HCMAC)良好的非线性逼近能力、泛化能力和自学习能力,设计HCMAC辅助卡尔曼滤波器,并应用于组合导航系统。仿真试验结果表明,该辅助算法与经典卡尔曼滤波算法相比较,精度提高了2倍,收敛时间缩短近200s,且有效地克服了传统神经网络学习速度慢、泛化能力弱的缺点,使系统具有自适应能力以应付动态环境的扰动,增强了组合导航系统的鲁棒性。Aimed at the conventional Kalman filter assumes that the statistical properties of the noise in dynamic model and observation system are exactly, but the noise in integrated system is uncertain. Then, taking advantage of the nonlinear approximation ability,generalization ability and self-learing ability, The combined the hyperball cerebellar model articulation controller （HCMAC） neural network aided Kalman filter is proposed. Simulations suggest that the precision of HCMAC is 2 times more than the one of Kalman filter, and convergence time is 200 second less than one. Thus it can overcome the shortcomings of the conventional neural network, such as slow learning speed and poor generalization ability, and make whole system has the adaptive capability to deal with the disturbance in dynamic situation, and robustness of the integrated navigation system is enhanced.

关 键 词：组合导航 卡尔曼滤波 小脑神经网络(CMAC) 超闭球小脑神经网络(HCMAC) 

分 类 号：TP242.2[自动化与计算机技术—检测技术与自动化装置]