Ship radiated-noise recognition (I) the overall framework,analysis and extraction of line-spectrum

This series of papers deal with ship target recognition.The project is conducted by using fuzzy neural networks and basing recognition on the spectra of ship radiated noise.Paper (I) describes the characteristics of ship radiated-noise spectra,which are composed of two distinctive categories:the stationary and the non-stationary.The project framework is introduced in the paper.It includes two steps.One is to extract effectively recognizable features (those common in one category and those distinguish categories).The other is to memorize the characteristics of specific ship targets.The memorization is realized with specific ship characteristics pattern plate library (including line-spectrum,double-frequency spectrum and average power spectrum pattern plate library).Detailed discussions on theories,models,parameter analysis,line-spectrum extraction methods,as well as gaps between reality and theory concerning ship radiated-noise are also included in Paper (I).Paper (I) finally proposes a method of automatic extraction of line-spectrum by using maChines.Paper (Ⅱ) will discuss the stability,uniqueness of line-spectrum and its pattern plate.Paper (Ⅲ) will focus on the extraction of features from double-frequency spectrum and average power spectrum,and the establishment of their pattern plates.Paper (Ⅳ) will discuss fuzzy neural networks and recognition approaches.