基于水文测量的潮汐预报与显示系统的设计与实现

发布时间：2018-03-30 05:22

本文选题：潮汐预测　切入点：神经网络　出处：《大连海事大学》2016年硕士论文

【摘要】：潮汐是海洋环境中最重要的组成部分之一,潮汐对海洋产业的影响至关重要,我国有着18000千米的海岸线,潮汐对我国的生产生活都有着很大的影响,尤其是对船舶的航行非常重要的影响。探究潮汐的规律一直是人类社会不断追求的,潮汐的预报也是十分重要的。随着社会的发展互联网越来越方便了人们的生活,人们可以利用互联网查询潮汐数据和其他海洋数据了。目前潮汐的预测方法主要是利用调和常数计算潮汐分潮的方法,还有一些人利用潮汐的历史数据采用非线性的数学预测手段对潮汐进行预测,例如混沌理论、神经网络、支持向量机等,但都存在预报精度不高的问题。本文主要采用了利用人工鱼群算法优化的BP神经网络对潮汐进行预测,并建立了基于此预测的B/S架构的潮汐预报与显示系统。本文的具体内容和结论如下：1.建立了利用人工鱼群优化的BP神经网络预测潮汐的模型,利用影响潮汐的最重要的两个天体(太阳和月球)的十个参数对潮汐进行预测。2.搭建了基于B/S架构的四层架构的潮汐预报与显示系统,利用网络对潮汐进行实时的查询。3.本文选取香港长洲的潮汐监测站的三个月整点监测的潮汐数据作为历史数据进行分析和预测,预测出了未来一个月内的整点潮汐值,取得了较为准确的预测值。
[Abstract]:Tide is one of the most important components in the marine environment. The influence of tide on marine industry is very important. China has a coastline of 18000 km, and the tide has a great impact on the production and life of our country. Especially the very important influence on the navigation of ships. It is always the pursuit of human society to explore the law of tide, and the prediction of tide is also very important. With the development of society, the Internet has become more and more convenient for people to live. People can use the Internet to query tidal data and other ocean data. Some people use historical data of tides to predict tides by nonlinear mathematical methods, such as chaos theory, neural networks, support vector machines and so on. In this paper, the BP neural network, which is optimized by artificial fish swarm algorithm, is used to predict the tide. A tidal prediction and display system based on the B / S structure is established. The main contents and conclusions of this paper are as follows: 1. A BP neural network model based on artificial fish swarm optimization for tidal prediction is established. Using ten parameters of the two most important celestial bodies (the sun and the moon), which affect the tide, to predict the tide. 2. A four-layer tidal prediction and display system based on the B / S architecture is built. In this paper, the tidal data from the tidal monitoring station in Cheung Chau, Hong Kong, are selected as historical data for analysis and prediction, and the tidal values of the whole point in the coming month are predicted. More accurate prediction values have been obtained.
【学位授予单位】：大连海事大学
【学位级别】：硕士
【学位授予年份】：2016
【分类号】：P731.34

【相似文献】