Nonlinear feature analysis and extraction of ship noise signal based on limit cycle

Nonlinear analysis method was used here to study the limit cycle phenomenon in ship noise, and the results show that there is period-doubling or chaos in the limit cycle of vibration noise being the main component in ship noise in phase space. Then the fractal dimension and distribution density ratio were used to calculate the strangeness and shape of limit cycle, and a new algorithm for calculating the fractal dimension was put forward. Finally, the fractal dimension and distribution density ratio were chosen as the feature parameters of ship noise for classifying sea ship and undersea ship by using neural network classifier. The experimental results show that the nonlinear features based on the limit cycle of ship noise is effective in classifying two classes of ship targets, hence the research published here provides a novel effective method for the feature extraction of ship noise signals.