改进遗传模糊神经网络在舰船组合导航中的应用  

Application of the Fuzzy Neural Networks Based on the Improved Genetic Algorithms in Ship Integrated Navigation System

作　　者：刘建娟[1] 徐晓苏[1] 

机构地区：[1]东南大学仪器科学与工程系,南京210096

出　　处：《舰船电子工程》2006年第2期63-66,共4页Ship Electronic Engineering

基　　金：国家自然科学基金项目(编号:60374046)资助;国家自然科学基金项目(编号:50575042)资助;总装备部国防预研基金项目(编号:514090101035W0609)资助

摘　　要：由于舰船组合导航系统的实际运行环境比较恶劣,系统精确的数学模型及噪声的统计特性不易先验得到,而导致常规卡尔曼滤波器失效。尝试将改进遗传算法优化的模糊神经网络用于舰船组合导航系统中,仿真结果表明,提出的算法比较有效,并且精度和常规卡尔曼滤波算法相当。Because it is more dicky that the real running environment of ship integrated navigation system, the exact mathematics model of system and the characteristic of yawp is difficult to get, and cause the routine kalman filter to lose efficiency. In this paper, the fuzzy neural networks based on the improved genetic algorithms was used in the system. The simulation results indicate that the algorithm is more effective, and the precision is equivalent to routine kalman filter.

关 键 词：改进遗传算法 模糊神经网络 组合导航 

分 类 号：U666.1[交通运输工程—船舶及航道工程]