[IEEE 2018 OCEANS - MTS/IEEE Kobe Techno-Ocean (OTO) - Kobe (2018.5.28-2018.5.31)] 2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO) - DEMON Spectrum Extraction Method Using Empirical Mode Decomposition

摘要： The noise radiated by a ship is modulated at a rate dictated by some parameters of the propeller and engine (number of blades, rotational speed). Evaluation of that modulation provides information on the ship, such as the shaft rotation frequency, that can be used for ship classification. The method for estimation of the envelope modulation is known as DEMON (Detection of Envelope Modulation on Noise). Traditionally, the ship noise is bandpass filtered in different frequency bands before the envelope analysis. The bandwidth and the number of the bandpass filters is not known. In this paper a new DEMON spectrum extraction method is proposed using empirical mode decomposition (EMD), in which the band number and width are automatically determined. In performance test, a feedforward neural network is used for 5 kinds ship noise classification, and the percentage of correct classification reaches 91.6%.