Underwater acoustic target identifying method based on ship-radiated noise optimization features

Abstract

The invention discloses an underwater acoustic target identifying method based on ship-radiated noise optimization features. The underwater acoustic target identifying method based on ship-radiated noise optimization features includes steps that carrying out angular domain framing operation on ship target training-radiated noise data; extracting spectrum features of the target of ship target-radiated noise data for training and testing; carrying out power transform on the spectrum features to extract optimization features; determining parameters of the stick-breaking prior hidden Markov model of each frame in the ship target-radiated noise data; calculating testing ship target-radiated noise data optimization features and conditional likelihood function values of the stick-breaking prior hidden Markov models corresponding to frames of the ship target-radiated noise data for training; using the class attributes of the frame of the ship target training-radiated noise data corresponding to the maximum conditional likelihood function value as the class attributes of ship target testing-radiated noise data. The underwater acoustic target identifying method based on ship-radiated noise optimization features is used for improving the underwater acoustic target identifying performance.

Description

technical field [0001] The invention belongs to the technical field of underwater acoustics, in particular to an underwater acoustic target recognition method based on optimized features of ship radiation noise. Background technique [0002] Underwater acoustic automatic target recognition technology can provide information such as the attributes and categories of target ships. It is an important part of modern sonar systems and a key technology to realize the intelligence of other underwater equipment systems. [0003] Ship radiated noise refers to the noise generated by the mechanical operation and ship motion on the ship and radiated into the water. It is mainly composed of mechanical noise, hydrodynamic noise and propeller noise, and contains rich target physical information. Among them, the mechanical noise is the noise sound wave caused by the vibration of the ship's hull and radiated into the sea during the movement of the main engine, propulsion device and auxiliary ...

AI Technical Summary

Problems solved by technology

[0006] (1) Only the relationship between the radiation noise of each ship is studied, and the fixed spatial structure and occlusion characteristics between the ship sounding bodies contained in the data are ignored. When the number of recognition targets increases, the recognition performance drops rapidly

[0007] (2) The difference in radiation noise data caused by the relative position and occlusion of the same target at different observation angles is not considered. Only one model is established for a ship target. The model is relatively rough and the recognition performance is not good.

[0008] (3) The recognition performance of the model is not considered when the number of samples available for training is small. When the number of samples used for training is relatively small, the recognition performance is greatly reduced

[0009] (4) There is a manual model selection problem, that is, the parameter set size of the model is determined manually, and the correctness of the given parameter set size determines the final recognition performance

When the data is large, it is difficult to determine the correct parameter set size resulting in poor recognition performance

[0010] Therefore, in view of the above-mentioned defects in the current prior art, it is necessary to carry out research to provide a solution to solve the defects in the prior art and avoid the problem of degradation of recognition performance when recognition targets increase and noise increases

Images