基于遗传BP神经网络的海底沉积物声速预报

陈文景; 郭常升; 王景强; 侯正瑜

doi:10.3969/j.issn.0253-4193.2016.01.011

基于遗传BP神经网络的海底沉积物声速预报

doi: 10.3969/j.issn.0253-4193.2016.01.011

1.
中国科学院海洋研究所, 山东青岛 266071;中国科学院海洋地质与环境重点实验室, 山东青岛 266071;中国科学院大学, 北京 100049
2.
中国科学院海洋研究所, 山东青岛 266071;中国科学院海洋地质与环境重点实验室, 山东青岛 266071
3.
国家海洋局第一海洋研究所海洋沉积与环境地质国家海洋局重点实验室, 山东青岛 266061

基金项目: 海洋公益性行业科研专项项目(200905025)。

计量
- 文章访问数: 1147
- HTML全文浏览量: 5
- PDF下载量: 772
- 被引次数: 0
出版历程
- 收稿日期: 2015-01-19
- 修回日期: 2015-06-23

A study on forecasting sound velocity of sea-floor sediments based on GA-BP method

1.
Institute of Oceanology, Chinese Academy of Sciences, Qingdao 266071, China;Key Laboratory of Marine Geology and Environment, Chinese Academy of Sciences, Qingdao 266071, China;University of Chinese Academy of Sciences, Beijing 100049, China
2.
Institute of Oceanology, Chinese Academy of Sciences, Qingdao 266071, China;Key Laboratory of Marine Geology and Environment, Chinese Academy of Sciences, Qingdao 266071, China
3.
Key Laboratory of Marine Sedimentology and Environment Geology, the First Institute of Oceanography, State Oceanic Administration, Qingdao 266061, China

摘要

摘要: 在海底沉积物声速预报中,针对传统经验公式存在预测精度差、适用范围窄、缺乏物理意义等问题,在已有BP神经网络预测的基础上,运用遗传算法优化其初始权值和阈值的方法,构建出基于含水量、孔隙度的声速预报模型。将南沙海域采集得到的海底沉积物样品分为两部分,抽取120组涵盖陆架、陆坡、海槽等地貌单元的样品作为训练数据,另外剩余6组作为测试数据。经试验对比后发现,在对本区域进行声速预报时,宜采用遗传算法优化的BP神经网络,其要优于传统的单参数、双参数回归拟合预报方法和国内外其他学者所得到的经验公式。此种预报方法具有一定的科学依据和广泛的应用前景,可在今后为建立明确、统一的声速预报模型提供参考。
- 遗传算法 /
- BP神经网络 /
- 海底沉积物 /
- 声速预报
Abstract: In the sea-floor sediments velocity prediction,there exist many problems according to the empirical equations,such as poor accuracy,the narrow scope of application,lack of exact physical meaning. Based on the existing BP neural network,genetic algorithm (GA) is used to optimize the initial weights and threshold. A sea-floor sediment sound velocity forecasting model is established with the relationship of water content,porosity and velocity. Measurement data of study samples from the southern South China Sea are applied. These data are divided into two parts,120 groups including continental shelf,slope,trough samples selected as the training data,the other 6 groups as test data. Experiments show that BP neural network based on GA is superior to the traditional single-parameter,double-parameter sound velocity forecasting empirical equation,which is recommended for the forecasting sound velocity of sea-floor sediments. This GA-BP method has certain scientific basis and broad application prospects in the future,can provide reference for the establishment of the accurate,uniform model.
- GA /
- BP neural network /
- sea-floor sediments /
- sound velocity forecast

HTML全文

参考文献(34)

Stoll R D,Bautista E O. Using the Biot theory to establish a baseline geoacoustic model for seafloor sediments[J]. Continental Shelf Research,1998,18(14): 1839-1857.

朱祖扬,王东,周建平,等. 基于非饱Biot-Stoll模型的海底沉积物介质声频散特性研究[J]. 地球物理学报,2012,55(1): 180-188. Zhu Zuyang,Wang Dong,Zhou Jianping,et al. Acoustic wave dispersion and attenuation in marine sediment based on partially gas-saturated Biot-Stoil model[J]. Chinese Journal of Geophysics,2012,55(1): 180-188.

Biot M A. Generalized theory of acoustic propagation in porous dissipative media[J]. The Journal of the Acoustical Society of America,1962,34(9A): 1254-1264.

Stoll R D. Acoustic Waves in Saturated Sediment[M]//Physics of Sound in Marine Sediments. US:Springer,1974:19-39.

Wood A B. A Textbook of Sound[M]. 3rd edition. London:The Macmillan Company,1964.

Buckingham M J. Theory of acoustic attenuation,dispersion,and pulse propagation in unconsolidated granular materials including marine sediments[J]. The Journal of the Acoustical Society of America,1997,102(5): 2579-2596.

Hamilton E L. Geoacoustic Modeling of the Sea Floor[J]. Acoustical society of America,1980,68:1313-1340.

Anderson R S. Statistical correlation of physical properties and sound velocity in sediments[G]//Physical Sound in Marine Sediments. US : Springer,1974: 481-518.

Orsi T H,Dunn D A. Sound velocity and related physical properties of fine-grained abyssal sediments from the Brazil Basin (South Atlantic Ocean)[J]. Journal of the Acoustical Society of America,1990,88(3):1536-1542.

卢博. 海底浅层沉积物声速与物理性质[J]. 科学通报,1994(5):435-437. Lu Bo. Acoustic velocity and physical properties of the bottom sediment[J]. Chinese Science Bulletin,1994(5):435-437.

唐永禄. 海底沉积物孔隙度与声速的关系[J]. 海洋学报,1998,20(6): 39-43. Tang Yonglu. The relationship between porosity of sea bed sediment and sound velocity[J]. Haiyang Xuebao,1998,20(6): 39-43.

邹大鹏,吴百海,卢博. 海底沉积物声速经验方程的分析和研究[J]. 海洋学报,2007,29(4): 43-50. Zou Dapeng,Wu Baihai,Lu Bo. Analysis and study on the sound velocity empirical equations of seafloor sediments[J]. Haiyang Xuebao,2007,29(4): 43-50.

阚光明,苏元峰,李官保,等. 南黄海中部海底沉积物原位声速与物理性质相关关系[J]. 海洋学报,2013,35(3):166-171. Kan Guangming,Su Yuanfeng,Li Guanbao,et al. The correlations between in-situ sound speeds and physical parameters of seafloor sediments in the middle area of the southern Huanghai Sea[J]. Haiyang Xuebao,2013,35(3):166-171.

Han T C,Liu B H,Kan G M,et al. Joint elastic-electrical properties of sediments in the Yellow Sea[J]. Science China Earth Sciences,2012,55(1): 143-148.

罗忠辉,卢博,杨永. 人工神经网络技术在海底沉积物声速预报中的应用[J]. 海洋技术,2009(4): 40-43,57. Luo Zhonghui,Lu Bo,Yang Yong. Application of artificial neural network technology in sound velocity prediction for marine sediments[J]. Ocean Technology,2009(4): 40-43,57.

Yang F,Liu J. Seabed classification using BP neural network based on GA[J]. Acta Oceanologica Sinica,2003,23(4):523-531.

姚才,金龙,黄明策,等. 遗传算法与神经网络相结合的热带气旋强度预报方法试验[J]. 海洋学报,2007,29(4): 11-19. Yao Cai,Jin Long,Huang Mingce,et al. An experiment with methods of forecasting tropical cyclones intensity base on combination of the genetic algorithm and artificial neural network[J]. Haiyang Xuebao,2007,29(4): 11-19.

唐秋华,刘保华,陈永奇,等. 基于改进BP神经网络的海底底质分类[J]. 海洋测绘,2009(5): 40-43,56. Tang Qiuhua,Liu Baohua,Chen Yongqi,et al. Seabed classification with improved BP neural network[J]. Hydrographic Surveying and Charting,2009(5): 40-43,56.

Sedki A,Ouazar D,El Mazoudi E. Evolving neural network using real coded genetic algorithm for daily rainfall-runoff forecasting[J]. Expert Systems with Applications,2009,36(3): 4523-4527.

Haixiang G,Xiuwu L,Kejun Z,et al. Optimizing reservoir features in oil exploration management based on fusion of soft computing[J]. Applied Soft Computing,2011,11(1): 1144-1155.

熊明宽,吴自银,李守军,等. 基于遗传小波神经网络的海底声学底质识别分类[J]. 海洋学报,2014,36(5): 90-97. Xiong Mingkuan,Wu Ziyin,Li Shoujun,et al. Wavelet neural network identification and classification of sediment seabed sonar images based on genetic algorithms[J]. Haiyang Xuebao,2014,36(5): 90-97.

侯正瑜,郭常升,王景强. 南沙海域深水区表层沉积物声速与孔隙度相关关系[J]. 海洋科学,2013(7): 77-82. Hou Zhengyu,Guo Changsheng,Wang Jingqiang. Surface sediments acoustic velocity and porosity correlation in Nansha sea area abyssal region[J]. Marine Sciences,2013(7): 77-82.

任谢楠. 基于遗传算法的BP神经网络的优化研究及MATLAB仿真[D]. 天津:天津师范大学,2014. Ren Xienan. Study on optimization of BP neural network based on genetic algorithm and Matlab simulation[D]. Tianjin: Tianjin Normal University,2014.

Sun T H,Tien F C. Using backpropagation neural network for face recognition with 2D+3D hybrid information[J]. Expert Systems with Applications,2008,35(1): 361-372.

Raeesi M,Moradzadeh A,Doulati Ardejani F,et al. Classification and identification of hydrocarbon reservoir lithofacies and their heterogeneity using seismic attributes,logs data and artificial neural networks[J]. Journal of Petroleum Science and Engineering,2012,82: 151-165.

徐黎明,王清,陈剑平,等. 基于BP神经网络的泥石流平均流速预测[J]. 吉林大学学报(地球科学版),2013(1):186-191. Xu Liming,Wang Qing,Chen Jianping,et al. Forcast for average velocity of debris flow based on BP neural network[J]. Journal of Jilin University (Earth Science Edition),2013(1):186-191.

Holland J H. Adaptation in natural and artificial system [M]. Michigan: The University of Michigan Press,1975:12-27.

Bagley J D. The behavior of adaptation system which employ genetic and correlation algorithm[J]. Dissertation Abstracts International,1967,28(12):2-4.

王方旗,亓发庆,姚菁,等. 基于时间平均的海底沉积物声速预测[J]. 海洋学报,2012,34(4): 84-90. Wang Fangqi,Qi Faqing,Yao Jing,et al. A study on forecasting sound velocity of sea-floor sediments based on the time-average method[J]. Haiyang Xuebao,2012,34(4): 84-90.

Chen M P,Shieh Y T,Chyan J M. Acoustic and physical properties of surface sediments in Northern Taiwan Strait[J]. Acta Oceanographica Taiwanica,1988 (21): 92-118.

孟祥梅,刘保华,阚光明,等. 南黄海海底沉积物声学特性及其影响因素试验研究[J]. 海洋学报,2012,34(6): 74-83. Meng Xiangmei,Liu Baohua,Kan Guangming,et al. An experimental study on acoustic properties and their influencing factors of marine sediment in the southern Huanghai Sea[J].Haiyang Xuebao,2012,34(6): 74-83.

邹大鹏,吴百海,卢博. 海底沉积物孔隙度计算方法与声速反演的误差分析研究[J]. 热带海洋学报,2007(4):32-36. Zou Dapeng,Wu Baihai,Lu Bo. A research on error analysis of seabed sediment porosity by calculation method and sonic speed retrieval method[J]. Journal of Tropical Oceanography,2007(4):32-36.

李国勇. 神经模糊控制理论及应用[M]. 北京:电子工业出版社,2009. Li Guoyong. Neural fuzzy control theory and its application[M]. Beijing: Beijing Electron Industry Press,2009.

席裕庚,柴天佑,恽为民. 遗传算法综述[J]. 控制理论与应用,1996(6): 697-708. Xi Yugeng,Chai Tianyou,Yun Weimin. Survey on genetic algorithm[J]. Control Theory and Applications,1996(6): 697-708.

施引文献

资源附件(0)

访问统计