Harmonic Signals Retrieval Approach Based on Blind Source Separation

Abstract

A frequently encountered problem in signal processing is harmonic retrieval in additive colored Gaussian or non-Gaussian noise, especially when the frequencies of the harmonic signals are very close in space. The purpose of this paper is to develop an efficient Blind Source Separation (BSS) algorithm from linear mixtures of source signals, which enables to separate harmonic source signals using only one observed channel signal even if the frequencies of the harmonic signals are closely spaced. First, we establish the BSS based harmonic retrieval model in additive noise by using the only one observed channel, and analyze the fundamental principle by utilizing BSS method to retrieve harmonics. Then, we propose a BSS-based approach to the harmonic retrieval by resorting the concept of W-disjoint orthogonality in the over-complete BSS situation, and as a result, we get the separation algorithm using only one channel mixed signals. Simulation results show that the proposed separation algorithm-BSS-HR is able to separate the harmonic source signals.

Optimal Parameters for Multi-Pump Control System with Blind Source Separation Based on Independent Component Analysis

“…And A is an unknown mixing matrix, T ] [⋅ denotes matrix transpose. So, exact conditions for the BSS model were given when m and n are same constants and several methods for estimation of the model with the classic ICA have been proposed in the literature [3][4][5].…”

False Peaks Suppression based on Cross-High-Order Spectral QR Decomposition Approach

“…The harmonic retrieval problem arises in various areas such as radar, sonar, geophysics [1]. Harmonic retrieval in additive colored noise is an important research topic [2][3]. The realization of harmonic retrieval with hybrid colored noise includes the traditional and modern approaches.…”

“…The traditional approach, which can be achieved by the FFT method, has stability but low resolution. To increase the resolution of the spectral resolution, some improved methods have been developed, such as cross-spectral moment, SVD approach, cross-spectral MUSIC approach, cross-spectral Levinson method, but all these methods have low single-to-noise ratio (SNR) of the harmonic signal [2][3][4][5]. When SNR was very low, these approaches were not suitable to distinguish the spectral peaks from the false peaks.…”