IOCAS-IR  > 海洋地质与环境重点实验室
基于遗传BP神经网络的海底沉积物声速预报
陈文景
Subtype硕士
Thesis Advisor郭常升
2016-05
Degree Grantor中国科学院大学
Place of Conferral青岛
Degree Discipline海洋地质
Keyword遗传算法 Bp神经网络 海底沉积物 声速预报
Abstract随着海洋地质学等学科的发展,以及海洋工程和海洋开发的需要,海底沉积物声学特性研究具有重要的现实意义,并受到越来越广泛的重视。海底沉积物通常被认为是一种固液双相介质,其结构和物理性质直接决定了声波在其中的传播速度,是声波传播的物理基础。构建明确、统一的海底沉积物声速与物理参数模型,对于开展声速反演、地声模型建立、工程实践等方面的研究都具有重要的意义。
国内外的研究学者对纵波声速与沉积物物理参数之间的相关关系进行了大量实际调查工作,建立了适用于不同海域沉积物的声速与物理参数之间的经验公式。这些经验公式的建立在一定程度上揭示了两者之间的相互关系,但由于经验公式大多采用简单的回归拟合得到,再加上海洋沉积环境的多样性及复杂性,在进行声速预报时,存在回归误差过大、适用范围有限、缺乏物理意义等问题。针对这些问题,本文将在已有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进行声速预报。同时,将南沙海域采集得到的海底沉积物样品分为两部分,随机抽取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。
Other AbstractWith the development of marine geology and other disciplines as well as the need of marine engineering and marine exploration, the study of acoustic characteristics of seafloor sediments has important practical significance, and has received more and more attention. The sediment is generally considered to be a solid-liquid medium. The physical properties of sediment directly determine sound velocity, which is the physical basis of sound wave propagation. The accurate and uniform model has an important significance for velocity inversion, geoacoustic model establishment, engineering practice.
The researchers at home and abroad have carried out a lot of practical investigation on the correlation between the velocity and the physical properties of the sediment. In the seafloor 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 seafloor 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 seafloor 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.
Subject Area海洋地质学
Document Type学位论文
Identifierhttp://ir.qdio.ac.cn/handle/337002/112501
Collection海洋地质与环境重点实验室
Affiliation中国科学院海洋研究所
Recommended Citation
GB/T 7714
陈文景. 基于遗传BP神经网络的海底沉积物声速预报[D]. 青岛. 中国科学院大学,2016.
Files in This Item:
File Name/Size DocType Version Access License
硕士毕业论文 - 基于遗传BP神经网络的(2677KB)学位论文 开放获取CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[陈文景]'s Articles
Baidu academic
Similar articles in Baidu academic
[陈文景]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[陈文景]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.