Tide predicting method

Abstract

The invention relates to a tide predicting method for the tide is influenced by various factors, including cyclical factors, such as tidal generation force, and non-cyclical factors, such as wind power, atmospheric pressure, coast characteristics, rainfall, dip angles of the lunar orbit and the like. The predicting accuracy of the traditional harmonic analysis method is influenced by partial tide number, and the traditional harmonic analysis method cannot analyze the influence of non-cyclical factors; the artificial neural network method developed recent years overcomes the defect that the non-cyclical factors cannot be predicted by the harmonic analysis method to a certain extent, but has great data volume required by study training samples and wide involve range, can cover various possible conditions, but has less station historical data of non-cyclical factors. The invention provides a predict model, wherein factors which influence tide non-cyclically, such as wind directions, rainfall, storm surge, coast characteristics and the like, can be fused into the model, and small sample data can receive more accurate results. In the method, a support vector machine (SVM)-based predict model is established, wherein, an SVM toolbox is imported into MATLAB 7.8; training sample data is trained by utilizing svmtrain function; the formed model is tested by using a test sample svmpredict function; and the trained and tested data can predict the tide in the same tide test station.

Description

technical field [0001] The invention belongs to the field of automation and relates to a tide forecasting method. Background technique [0002] Tide forecasting occupies an extremely important position in the development and utilization of marine resources. With the development of the shipbuilding industry, the tonnage of ships is gradually increasing, and the characteristics of tides can be used to enter the port when the tide is high and leave the port when the sea water is about to fall. It can increase the traffic capacity of large ships; the tide forecast is related to the construction of the harbor wharf, and the height is determined according to the height of the local tide, so that the wharf will not be submerged by the high tide, and the boat will not be stranded at low tide; in the development of fishery resources, Accurately grasp the law of the tide, and can determine the location of the fishing area, the height of the net, and the sailing time, etc. during the f...

AI Technical Summary

Problems solved by technology

[0003] The commonly used method for tidal prediction is the harmonic analysis method, which uses the method of series decomposition to decompose the elliptical motion of the moon around the earth, the earth around the sun, and the perturbation motion between celestial bodies into a set of sine and cosine infinite series, according to the forecast Accuracy requirements, determine the selection of main series items, and then calculate the coefficients and initial angles of each level of number items according to the tide measured data in specific geographical locations, and then predict the tide height at a certain moment later according to the time, which has the main There are two limitations: 1) The harmonic analysis method selects a certain number of tides to predict, and its accuracy increases with the increase of the number of tides, but when the number of tides increases, the amount of calculation will also increase sharply and The improvement of accuracy is relatively slow. 306 tidal equinoxes are used in the "Tide Table" for forecasting. These tidal equinoxes are only a small part of the Bessel series and celestial perturbation series. have been neglected, but the combined effects of these items sometimes cause large errors in the forecast; 2) the influence of non-periodic factors cannot be forecasted, and some non-periodic factors such as typhoons, cold waves, precipitation, etc. have a great influence on the tide forecast impact, harmonic analysis is unpredictable

[0004] Data-based machine learning is an important aspect of modern intelligent technology. Research starts from observed data (samples) to find laws, and uses these laws to predict future data or unobservable data. Including pattern recognition, neural networks, etc., the current One of the important theoretical foundations common to machine learning methods is statistics. Neural networks are also involved in tidal prediction, but the form of its accurate model requires large sample data, and in practical problems, the number of samples is often limited Therefore, the theoretically excellent neural network method may not perform satisfactorily in practice.

Images