水下接近觉及多目标定位方法研究  

Underwater proximate sensor and localization of multi-targets

作　　者：徐筱龙[1] 徐国华[1] 

机构地区：[1]华中科技大学船舶与海洋工程学院,武汉430073

出　　处：《仪器仪表学报》2010年第3期588-593,共6页Chinese Journal of Scientific Instrument

基　　金：国防科工委"十一"五基础研究(D2420060075)资助项目

摘　　要：针对水下环境下作业,根据水下超声传播与反射原理研制了一种新型接近觉传感器。本文详细介绍了水下接近觉的工作原理及组成,并对基于此传感器的多目标定位进行了仿真研究;与目前国内外所采用的几何相交定位技术不同,本文所采用BP神经网络定位方法突破了目前方法中定位目标数目的限制,通过区域模糊定位和角度精确定位的两类仿真实验表明了所采用方法的有效性及定位精度。A new proximate sensor for underwater condition is proposed and the design is based on the analysis and test of ultrasonic traveling and echoing in water.In this paper,the working principle and components of the proximate sensor are introduced in detail.Different from currently used geometric interpolation method,a novel multi-target localization method based on BP Neural Network is presented,which has the advantage that there is no limitation on target number.Two kinds of simulation experiments were performed;one is region localization and the other is accurate angle localization.Simulation results show that the proposed method is efficient and has enough accuracy.

关 键 词：水下 接近觉 BP神经网络 定位 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]