Intelligent PSR Estimator for Feature Extraction of a Passive Sonar Target

Abstract

In real-time sonar classification, the propeller shaft rate (PSR) estimator for a feature extraction of the passive sonar target has the following problems: it requires an accurate and efficient performance due to the difficulty of distinguishing the harmonic family composed of the PSR fundamental and its harmonics from multiple spectral lines in the frequency spectrum, and it requires an easy design procedure in terms of structure and parameters. To solve these problems, an intelligent PSR estimator (IPSRE) using expert knowledge and the evolution strategy (ES) is proposed here. Simulation results show that the proposed algorithm effectively solves sonar classification problems in real-time.