| Tide is one of the most important parts of marine environment since ancient times and it is very important to the marine industry. As our country has 18000 kilo-meters of coastline, tides have a great influence on the production and life of our country particularly on the navigation of the ship. Exploring the law of the tide has been the pursuit of human society all the time and the forecast of tide is also impor-tant.With the development of society, people’s life has become more and more con-venient with the Internet. People can do a great number of things by using Internet. The predictions and queries of tide can also be carried out on the Internet.At present, the method of predicting tide wave is mainly to calculate tide by us-ing harmonic constants. There are also some people who use the historical data of the tide to predict the tides by means of nonlinear mathematical forecasting. For instance, chaos theory, neural network and vector supporting machine. In this paper, the BP neural network which uses artificial fish algorithm optimization is used to predict the tide. The tidal prediction and display system based on the B/S architecture are been established. The specific contents and conclusions of this paper are as follows:1.BP neural network prediction model by using artificial fish swarm optimization was established. Use the two most important celestial bodies that impact on the tides to predict the tides:the ten parameters of the sun and the moon.2.The tide forecast and display system based on the three layer structure of B/S architecture is built up, and make real time forecasting and viewing of tides by using the Internet.3. This paper selects the whole point of monitoring of tidal data in three months of the Hong Kong Cheung Chau tide monitoring station as historical data for analysis and prediction. The prediction of the whole point in the next month has been pre-dicted and achieved more accurate forecast value. |
PDF Full Text Request