Feature extraction of ship-radiated noise by 1 \frac12 spectrum

The properties of 1 \frac12 spectrum are proved and performances are analyzed in this paper. By means of the spectrum, the fundamental frequency component of the harmonic signals can be enhanced. Gaussian color noise and symetrical distribution noise can be canceled. And non-quadratic phase coupling harmonic components can be eliminated. The ship-radiated noise is analyzed and its 7 features are extracted with the spectrum. In light of B-P artificial neural network, three type ships are classified according to their features. The correct classification rates about the three type ships A, B and C are 90%, 91.3% and 85.7%, respectively.