Ocean sound velocity profile acquisition method based on self-organizing competitive neural network

Abstract

The invention discloses an ocean sound velocity profile acquisition method based on a self-organizing competitive neural network, and relates to the field of ocean sound velocity profiles, which comprises the following steps: firstly, expressing a sample profile of a historical sound velocity profile as a form that average value is added to the orthogonal empirical function vector and then multiplied by the corresponding coefficient An of each order; processing the historical sea surface parameter Xn; forming a sample training vector by the An in the S1 and the historical sea surface parameterXn in the S2; training the sample set by adopting a self-organizing competitive neural network algorithm to form an artificial neuron topological structure; acquiring real-time sea surface parameters, inputting the real-time sea surface parameters into the neuron topological structure, and acquiring An corresponding to the real-time sea surface parameters; and finally, in combination with the historical average sound velocity profile, the EOF vector and the real-time EOF coefficient, expressing the sample profile as an An form to obtain a real-time ocean sound velocity profile. According to the method, the relation between the sound velocity profile contained in the sample data and the sea surface remote sensing parameters is mined through the artificial neural network, and the precisionof the obtained sound velocity profile can be improved.

Description

technical field [0001] The present invention relates to the technical field of ocean sound velocity profile, more specifically, it relates to an ocean sound velocity profile acquisition method based on self-organized competitive neural network. Background technique [0002] The sound velocity profile is the most basic acoustic parameter of the ocean, and it is the necessary ocean environment information for underwater acoustic applications such as underwater target recognition, ocean environment monitoring, and underwater communication. Since the ocean is a constantly changing complex system, the ocean sound velocity profile has strong time and space variation characteristics, and accurate large-area real-time ocean sound velocity profile acquisition is a technical problem that needs to be solved urgently. [0003] The most direct way to obtain the sound velocity profile is to measure it directly on the spot with equipment such as a sound velocity meter, but the cost is very...

AI Technical Summary

Problems solved by technology

In the application of global ocean sound velocity profile reconstruction, the sEOF-r method shows a certain accuracy, and at the same time, there are large errors in the application of some sea areas, which cannot meet the requirements of many underwater sonar equipment applications for accurate sound velocity profile information. Degree Requirements

Images