[1]张勋,马豪伯,徐博,等.基于样本熵和IFOA-GRNN的多普勒计程仪信号失真重构[J].应用科技,2020,47(3):80-86.[doi:10.11991/yykj.201909019]
 ZHANG Xun,MA Haobo,XU Bo,et al.Reconstruction of Doppler velocity logmeter signal distortion based on sample entropy and IFOA-GRNN[J].Applied science and technology,2020,47(3):80-86.[doi:10.11991/yykj.201909019]
点击复制

基于样本熵和IFOA-GRNN的多普勒计程仪信号失真重构(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第47卷
期数:
2020年3期
页码:
80-86
栏目:
自动化技术
出版日期:
2020-07-05

文章信息/Info

Title:
Reconstruction of Doppler velocity logmeter signal distortion based on sample entropy and IFOA-GRNN
作者:
张勋1 马豪伯1 徐博1 李权明1 杨慧影2 周佳加1
1. 哈尔滨工程大学 自动化学院,黑龙江 哈尔滨 150001;
2. 西安卫星测控中心,陕西 西安 710043
Author(s):
ZHANG Xun1 MA Haobo1 XU Bo1 LI Quanming1 YANG Huiying2 ZHOU Jiajia1
1. College of Automation, Harbin Engineering University, Harbin 150001, China;
2. Xi’an Satellite Control Center, Xi’an 710043, China
关键词:
水下无人航行器传感器故障重构广义回归神经网络样本熵海流估计
Keywords:
underwater unmanned vehiclesensorfault reconstructiongeneralized regression neural networksample entropyocean current estimation
分类号:
TP277
DOI:
10.11991/yykj.201909019
文献标志码:
A
摘要:
在水下无人航行器(UUV)的航行过程中,由于内部复杂磁场的干扰,用于测量自身速度和航位推算的多普勒计程仪(DVL)有可能会出现信号失真。为此提出一种基于样本熵与广义回归神经网络的DVL信号失真的重构方法。首先引入鸡群优化算法(CSO)中求解高维优化问题的思想,增强传统果蝇优化算法(FOA)中局部搜索的能力和跳出局部极值点的能力。然后使用改进的果蝇优化算法(IFOA)对广义回归神经网络进行训练,得到UUV的估计速度。在UUV航行过程中,实时计算DVL输出信号的样本熵,根据设定阈值判断DVL的工作状态。最后使用DVL正常的航行数据与海流估计修正UUV航行过程中的海流干扰。DVL失真情况下的UUV应急导航仿真试验验证其有效性。
Abstract:
During the navigation of an underwater unmanned vehicle (UUV), due to complex electromagnetic interference of high-speed propellers, the Doppler velocity logmeter (DVL) used to measure speed and dead reckoning may have signal distortion. A method for reconstruction of DVL signal distortion based on sample entropy and generalized regression neural network is proposed. Firstly, the idea of solving high-dimensional optimization problems in the chicken swarm optimization(CSO) is introduced, and the ability of local search in traditional fruit-fly optimization algorithm(FOA) and the ability to jump out of local extremum points are enhanced. The generalized regression neural network is trained using the improved FOA (IFOA) to obtain the estimated speed of UUV. During the UUV navigation process, the sample entropy of the DVL output signal is calculated in real time, and the working state of the DVL is determined according to the set threshold. Finally, DVL normal navigation data and ocean current estimation are used to correct the current interference during UUV navigation. The UUV emergency navigation simulation test under DVL distortion verified its effectiveness.

参考文献/References:

[1] 解玉文, 胡凯, 罗响, 等. 高速无人遥控潜水器永磁推进器的无位置传感器控制[J]. 电机与控制应用, 2018, 45(12): 36-39
[2] 茅于东, 周丛曦, 艾佳方. 舰载电子装备电磁干扰应对技术研究[J]. 电子技术与软件工程, 2019(5): 107-108
[3] 严浙平, 王璐. UUV水下定位方法的研究现状与进展[J]. 哈尔滨工程大学学报, 2017, 38(7): 989-1000
[4] 唐会林. SINS/DVL/UTP/VP组合导航系统在UUV回收中的应用[J]. 应用科技, 2016, 43(3): 1-7
[5] 李长征, 张瑜. 基于广义回归神经网络的传感器故障检测[J]. 推进技术, 2017, 38(9): 2130-2137
[6] 禹建丽, 黄鸿琦, 陈洪根, 等. 神经网络在变压器故障诊断中的应用研究[J]. 控制工程, 2018, 25(10): 1898-1904
[7] XIE Xihua, XU Lei, ZHOU Liang, et al. GRNN model for fault diagnosis of unmanned helicopter rotor’s unbalance[C]//HUANG Bo, YAO Yufeng. Proceedings of the 5th International Conference on Electrical Engineering and Automatic Control. Berlin, Heidelberg: Springer, 2016: 539-547.
[8] AZIZI R, ATTARAN B, HAJNAYEB A, et al. Improving accuracy of cavitation severity detection in centrifugal pumps using a hybrid feature selection technique[J]. Measurement, 2017, 108: 9-17.
[9] SONG Dengwei, LIU Hongmei, QI Le, et al. A general purpose adaptive fault detection and diagnosis scheme for information systems with superheterodyne receivers[J]. Complexity, 2018, 2018: 4763612.
[10] CHAI Jiajia, JIN Xiaobo. Research on fault diagnosis of servo valve based on deep learning[C]. //Proceedings of 2017 Prognostics and System Health Management Conference. Harbin, China, 2017: 1-7.
[11] YANG Lu, WANG Jian, ZHANG Guigang, et al. An expert system reasoning machine based on the combination of fault tree and generalized regression neural network[C]//Proceedings of the 2016 12th World Congress on Intelligent Control and Automation. Guilin, China, 2016: 1303-1306.
[12] 王友卫, 凤丽洲, 朱建明, 等. 一种基于全局- 局部双向驱动的改进果蝇优化算法[J]. 哈尔滨工业大学学报, 2018, 50(5): 93-101
[13] 方波, 陈红梅. 一种新的双策略进化果蝇优化算法[J]. 山东大学学报(工学版), 2019, 49(3): 22-31
[14] 朱珍. 基于一种改进的粒子群算法在云计算中的任务调度研究[J]. 科技通报, 2019, 35(4): 115-119
[15] 严浙平, 李滋, 陈涛, 等. 基于GA-BP神经网络的UUV航向容错控制[J]. 传感技术学报, 2013, 26(9): 1236-1242
[16] 吕福星, 邓芳明, 吴翔, 等. 基于样本熵和峭度的自确认气体传感器故障诊断方法[J]. 仪表技术与传感器, 2017(9): 1-4, 12
[17] 李永健, 刘吉华, 张卫华, 等. 改进样本熵及其在列车轴承损伤检测中的应用[J]. 仪器仪表学报, 2018, 39(9): 179-186
[18] 邓飞跃, 唐贵基. 基于时间- 小波能量谱样本熵的滚动轴承智能诊断方法[J]. 振动与冲击, 2017, 36(9): 28-34
[19] 杨大为, 冯辅周, 赵永东, 等. VMD样本熵特征提取方法及其在行星变速箱故障诊断中的应用[J]. 振动与冲击, 2018, 37(16): 198-205
[20] 许凡, 方彦军, 孔政敏. 基于EEMD的样本熵的滚动轴承AP聚类故障诊断[J]. 仪表技术与传感器, 2017(6): 129-135
[21] 向北平, 周建, 倪磊, 等. 基于样本熵的改进小波包阈值去噪算法[J]. 振动、测试与诊断, 2019, 39(2): 410-451
[22] 严浙平, 吴迪, 周佳加, 等. 基于UUV动力学模型的导航方法[J]. 华中科技大学学报(自然科学版), 2013, 41(11): 108-113

相似文献/References:

[1]陶宝泉,付永庆,刘占亚.一种新型汽车轮胎胎温胎压传感器系统设计[J].应用科技,2009,36(10):19.[doi:10.3969/j.issn.1009-671X.2009.10.006]
 TAO Bao-quan,FU Yong-qing,LIU Zhan-ya.Design of a new tire pressure and temperature sensor system[J].Applied science and technology,2009,36(3):19.[doi:10.3969/j.issn.1009-671X.2009.10.006]
[2]冯驰,魏崇.基于信息融合的浮体轨迹测量[J].应用科技,2010,37(12):36.[doi:10.3969/j.issn.1009-671X.2010.12.010]
 FENG Chi,WEI Chong.Floating body track measurement based on information fusion[J].Applied science and technology,2010,37(3):36.[doi:10.3969/j.issn.1009-671X.2010.12.010]
[3]苏艳茹,王革思.基于差动变压器的浮子流量计位移检测研究[J].应用科技,2005,32(10):24.
 SU Yan_ru,WANG Ge_si.Investigation of the variable area flowmeter.s position based on the differtial transformer transducer[J].Applied science and technology,2005,32(3):24.
[4]刘滔,韩华亭,焦楷哲,等.非线性动态传感器系统Hammerstein神经网络补偿法[J].应用科技,2014,41(04):6.
 LIU Tao,HAN Huating,JIAO Kaizhe,et al.Compensation for the nonlinear dynamic system of a sensor using 〖JZ〗the Hammerstein neural network[J].Applied science and technology,2014,41(3):6.
[5]孙九瑞,孙晓晨.基于ZigBee的图书馆环境监控系统设计[J].应用科技,2015,42(03):49.[doi:10.3969/j.issn.1009-671X.201409001]
 SUN Jiurui,SUN Xiaochen.Design of the library environment monitoring system based on ZigBee[J].Applied science and technology,2015,42(3):49.[doi:10.3969/j.issn.1009-671X.201409001]
[6]付永庆,杨佳彬.基于磁致伸缩原理的汽车油量仪的设计[J].应用科技,2015,42(04):48.[doi:10.3969/j.issn.1009-671X.201411013]
 FU Yongqing,YANG Jiabin.Design of auto oil measuring instrument based on the magnetostrictive principle[J].Applied science and technology,2015,42(3):48.[doi:10.3969/j.issn.1009-671X.201411013]
[7]张勋,赵晓芳,时延利,等.UUV海面红外侦察图像自适应归并直方图拉伸增强算法[J].应用科技,2017,44(06):1.[doi:10.11991/yykj.201610012]
 ZHANG Xun,ZHAO Xiaofang,SHI Yanli,et al.Adaptive merging histogram stretching enhancement algorithm for UUV’s observing infrared images at sea[J].Applied science and technology,2017,44(3):1.[doi:10.11991/yykj.201610012]
[8]吴凌慧,徐冬.一种耐高温、耐恶劣环境大压力传感器的设计[J].应用科技,2018,45(04):142.[doi:10.11991/yykj.201709015]
 WU Linghui,XU Dong.Design of a high pressure sensor resisting high temperature and harsh environment[J].Applied science and technology,2018,45(3):142.[doi:10.11991/yykj.201709015]
[9]吴爽,焦淑红.船舶结构监测系统的应力预测研究[J].应用科技,2018,45(06):8.[doi:10.11991/yykj.201803009]
 WU Shuang,JIAO Shuhong.Prediction of stress pattern in the ship structure monitoring system[J].Applied science and technology,2018,45(3):8.[doi:10.11991/yykj.201803009]

备注/Memo

备注/Memo:
收稿日期:2019-09-29。
基金项目:国家自然科学基金项目(51709063);国家电网山东电力公司电力科学研究院项目(SGSDDK00PJS1700144)
作者简介:张勋,男,副教授
通讯作者:张勋,E-mail:zhangxun_hit@sina.com
更新日期/Last Update: 2020-08-05