双种群约束QPSO-BP的声速剖面反演方法Inversion method of sound velocity profile based on QPSO-BP with two population constraints
孙佳龙,张杰,唐玥,孙苗,张正阳,张弛
摘要(Abstract):
海水中声速剖面反演可以及时获取海洋环境信息,对于改善和提高水声设备的工作性能以及海洋的研究和开发都具有重要意义。针对声速剖面反演过程中,神经网络存在容易过早收敛的不足,该文提出了基于双种群约束QPSO-BP的声速剖面反演方法。利用Argo获取的温度和盐度数据,以2004—2017年经验正交函数所得到的特征向量和历史声速剖面作为训练样本,以BP神经网络反演声速剖面的模型作为基础,并在QPOS-BP算法基础上引入了双种群约束策略,通过与2018年6月和12月的实测声速剖面数据进行比较,双种群约束QPSO-BP声速预测模型在精度上比BP神经网络和QPSO-BP网络模型分别平均提高了35%和25%。结果表明,双种群约束QPSO-BP能有效提高声速剖面反演精度。
关键词(KeyWords): 声速剖面;QPSO-BP;双种群约束;Argo
基金项目(Foundation): 国家自然科学基金项目(40974016);; 自然资源部海洋信息技术创新中心开放基金课题、连云港高新区重点研发计划项目(ZD201905);; 江苏省高校海洋科学技术优势学科建设项目、测绘工程国家一流本科专业建设点建设项目
作者(Author): 孙佳龙,张杰,唐玥,孙苗,张正阳,张弛
DOI: 10.16251/j.cnki.1009-2307.2021.08.018
参考文献(References):
- [1] 何利,李整林,彭朝晖,等.南海北部海水声速剖面声学反演[J].中国科学(物理学力学天文学),2011,41(1):49-57.(HE Li,LI Zhenglin,PENG Zhaohui,et al.Inversion for sound speed profiles in the northern of South China Sea[J].Scientia Sinica(Physica,Mechanica & Astronomica),2011,41(1):49-57.)
- [2] PARK J C,KENNEDY R M.Remote sensing of ocean sound speed profiles by a perceptron neural network[J].IEEE Journal of Oceanic Engineering,1996,21(2):216-224.
- [3] 韩梅,魏亮,周艳霞.改进型经验正交函数海洋声速剖面预报方法[J].海洋科学,2009,33(1):30-33.(HAN Mei,WEI Liang,ZHOU Yanxia.An improved empirical orthogonal functions(EOF) on the forecast of ocean sound speed profile[J].Marine Sciences,2009,33(1):30-33.)
- [4] 李洪超,文汉江,蔡艳辉,等.基于Argo浮标和EOF建立区域海水三维声速场的方法[J].测绘科学,2012,37(2):74-76.(LI Hongchao,WEN Hanjiang,CAI Yanhui,et al.Modeling three-dimensional acoustic field in the ocean by using Argo and EOF[J].Science of Surveying and Mapping,2012,37(2):74-76.)
- [5] 张旭,张永刚,张健雪,等.一种新的声速剖面结构参数化方法[J].海洋学报:中文版,2011,33(5):54-60.(ZHANG Xu,ZHANG Yonggang,ZHANG Jianxue,et al.A new model for calculating sound speed profile structure[J].Acta Oceanologica Sinica,2011,33(5):54-60.)
- [6] 唐俊峰,杨士莪.由传播时间反演海水中的声速剖面[J].哈尔滨工程大学学报,2006,27(5):733-736.(TANG Junfeng,YANG Shi’e.Sound speed profile in ocean inverted by using travel time[J].Journal of Harbin Engineering University,2006,27(5):733-736.)
- [7] 孙文川,暴景阳,金绍华,等.多波束海底地形畸变校正与声速剖面反演[J].武汉大学学报(信息科学版),2016,41(3):349-355.(SUN Wenchuan,BAO Jingyang,JIN Shaohua,et al.Inversion of sound velocity profiles by correcting the terrain distortion[J].Geomatics and Information Science of Wuhan University,2016,41(3):349-355.)
- [8] 宋文华,胡涛,郭圣明,等.一种声速剖面展开的正交基函数获取方法[J].声学学报,2014,39(1):11-18.(SONG Wenhua,HU Tao,GUO Shengming,et al.A methodology to achieve the basis for the expansion of the sound speed profile[J].Acta Acustica,2014,39(1):11-18.)
- [9] 金丽玲,李建龙,徐文.自回归状态空间模型下时变声速剖面跟踪方法[J].声学学报,2016,41(6):813-819.(JIN Liling,LI Jianlong,XU Wen.Tracking of time-evolving sound speed profiles with the auto-regressive state-space model[J].Acta Acustica,2016,41(6):813-819.)
- [10] 张忠兵,马远良,倪晋平,等.基于声线到达时差的浅海声速剖面反演[J].西北工业大学学报,2002,20(1):36-39.(ZHANG Zhongbing,MA Yuanliang,NI Jinping,et al.A new and practical method for invertingsound speed profile in shallow water[J].Journal of Northwestern Polytechnical University,2002,20(1):36-39.)
- [11] 阚光明,刘保华,王揆洋,等.基于多波束声线传播的声速剖面反演法[J].海洋科学进展,2006,24(3):379-383.(KAN Guangming,LIU Baohua,WANG Kuiyang,et al.Method for inversing sound velocity profiles based on multi-beam sonic line travel[J].Advances in Marine Science,2006,24(3):379-383.)
- [12] 胡军,肖业伟,张东波,等.声速剖面反演预测方法[J].海洋科学进展,2019,37(2):245-254.(HU Jun,XIAO Yewei,ZHANG Dongbo,et al.Inversion prediction method for sound speed profile[J].Advances in Marine Science,2019,37(2):245-254.)
- [13] 屈科,朴胜春,朱凤芹.一种基于内潮动力特征的浅海声速剖面构建新方法[J].物理学报,2019,68(12):142-152.(QU Ke,PIAO Shengchun,ZHU Fengqin.A noval method of constructing shallow water sound speed profile based on dynamic characteristic of internal tides[J].Acta Physica Sinica,2019,68(12):142-152.)
- [14] 王德明,王莉,张广明.基于遗传BP神经网络的短期风速预测模型[J].浙江大学学报(工学版),2012,46(5):837-841.(WANG Deming,WANG Li,ZHANG Guangming.Short-term wind speed forecast model for wind farms based on genetic BP neural network[J].Journal of Zhejiang University(Engineering Science),2012,46(5):837-841.)
- [15] 江涛,张玉芳,王银辉.一种改进的粒子群算法在BP网络中的应用研究[J].计算机科学,2006,33(9):164-165,290.(JIANG Tao,ZHANG Yufang,WANG Yinhui.A study of application of an improved PSO algorithm in BP network[J].Computer Science,2006,33(9):164-165,290.)
- [16] 施展,陈庆伟.基于QPSO和拥挤距离排序的多目标量子粒子群优化算法[J].控制与决策,2011,26(4):540-547.(SHI Zhan,CHEN Qingwei.Multi-objective quantum-behaved particle swarm optimization algorithm based on QPSO and crowding distance sorting[J].Control and Decision,2011,26(4):540-547.)
- [17] 刘逸.粒子群优化算法的改进及应用研究[D].西安:西安电子科技大学,2013.(LIU Yi.Improvements and applications of particle swarm optimization algorithm[D].Xi’an:Xidian University,2013.)
- [18] 向毅,钟育彬.自适应阶段变异量子粒子群优化算法研究[J].计算机应用研究,2012,29(6):2035-2039.(XIANG Yi,ZHONG Yubin.Research on adaptive period mutation-based QPSO algorithm[J].Application Research of Computers,2012,29(6):2035-2039.)
- [19] 方伟,孙俊,谢振平,等.量子粒子群优化算法的收敛性分析及控制参数研究[J].物理学报,2010,59(6):3686-3694.(FANG Wei,SUN Jun,XIE Zhenping,et al.Convergence analysis of quantum-behaved particle swarm optimization algorithm and study on its control parameter[J].Acta Physica Sinica,2010,59(6):3686-3694.)