CAJ | 학술논문

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.
침대수하배경하작업,근거수하초성전파여반사원리연제료일충신형접근각전감기.본문상세개소료수하접근각적공작원리급조성,병대기우차전감기적다목표정위진행료방진연구;여목전국내외소채용적궤하상교정위기술불동,본문소채용BP신경망락정위방법돌파료목전방법중정위목표수목적한제,통과구역모호정위화각도정학정위적량류방진실험표명료소채용방법적유효성급정위정도.
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.