船舶在海洋中航行时,需要雷达系统对航道进行实时监控,此时水下目标的自动识别就显得尤为重要,只有对水下潜在的危险目标进行实时的预测,才能保证航行的安全。因此,本文着重对水下目标的特性识别方法进行了研究,通过BP网络模型建立了能够提取水下目标特征值的算法,同时对输出层和隐含层进行优化,得到了较为理想的水下目标识别模型。仿真结果表明,通过BP网络模型对目标识别算法的优化,目标的识别率都获得了较为明显的提升。
In order to ensure the safety of navigation, it is very important to recognize the underwater targets in real time when the ship is sailing in the ocean, and the real-time monitoring of the waterway is required by the radar system. Therefore, this paper focuses on the recognition method of underwater target characteristics, through the BP network model to establish the algorithm to extract the underwater target eigenvalue, while the output layer and the hidden layer optimization, get the ideal underwater Target recognition model. The simulation results show that the target recognition algorithm is improved and the recognition rate of the target is improved obviously by the BP network model.
2017,39(1A): 118-120 收稿日期:2016-10-12
DOI:10.3404/j.issn.1672-7619.2017.01.040
分类号:TN929.5
作者简介:陈晓伟(1981-),女,硕士,讲师,研究方向为软件工程、数据挖掘及网络。
参考文献:
[1] 张明远, 于铭. 基于小波包分解的水下物体探测仪目标特征提取[J]. 林业机械与木工设备, 2009(3):24-27.
[2] 公茂法, 张言攀, 柳岩妮, 等. 基于BP网络算法优化模糊Petri网的电力变压器故障诊断[J]. 电力系统保护与控制, 2015(3):113-117.
[3] 姚李孝, 宋玲芳, 李庆宇, 等. 基于模糊聚类分析与BP网络的电力系统短期负荷预测[J]. 电网技术, 2005(1):20-23.
[4] 祝文姬, 何怡刚. 基于遗传BP网络的模拟电路故障诊断方法及其应用[J]. 计算机辅助设计与图形学学报, 2009(9):1283-1289.
[5] WU Ji-dong, LI Ning, YANG Hui-juan, et al. Risk evaluation of heavy snow disasters using BP artificial neural network:the case of Xilingol in Inner Mongolia[J]. Stochastic Environmental Research and Risk Assessment, 2008, 226:1342-1345.
[6] DUAN Bao-fu, LI Jun-meng, ZHANG Meng. BP neural network model on the forecast for blasting vibrating parameters in the course of hole-by-hole detonation[J]. Journal of Coal Science and Engineering (China), 2010, 163:657-660.