СРАВНЕНИЕ ОСНОВНЫХ ЧАСТОТНО-ВРЕМЕННЫХ ПРЕОБРАЗОВАНИЙ СПЕКТРАЛЬНОГО АНАЛИЗА СИГНАЛОВ АКУСТИЧЕСКОЙ ЭМИССИИ

Abstract

Due to the intensive development of spectroscopic techniques for detecting acoustic emission signals, the problem of providing the best time-frequency resolution through the application of specific time-frequency transformation algorithms comes to the fore. The Short-Time Fourier Transform, the Wavelet Transform, the Smoothed Pseudo Wigner Distribution, the Choi-Williams Distribution, and the Hilbert-Huang Transform are currently the main time-frequency transformations used or integrated into the acoustic emission method. However, today in the literature, there is not enough information that allows evaluating time-frequency transformations regarding the effectiveness of their application to specify the features of discrete and continuous acoustic emission signals. On this basis, the authors carried out an experimental comparison of synthetic and actual model signals to determine the efficiency of specified time-frequency transformations. The synthetic model signals were a chirp signal, ideal sinusoids, and a Dirac delta function. The actual signals were a discrete acoustic emission signal from the Hsu Nelson source decomposed into dispersion modes in the acoustic channel and a continuous acoustic emission signal from the air outflow through a calibrated hole. The analysis shows that only the Fourier transform and the Wavelet transform can define all control features of model signals at the frequency components’ energy gap of about 25 dB. Wigner Distribution, Choi-Williams Distribution, and Hilbert-Huang Transform demonstrated higher time-frequency resolution did not identify frequency components of low energy. Therefore, the authors recommend using them to identify spectral changes in the resonance and discrete signals but in the narrow energy range. The Fourier transform and the Wavelet transform demonstrated the best result to analyze continuous acoustic emission. However, to use the latter, the procedure of selection of the optimal basis function is necessary. The study determined that the Hilbert-Huang transform allows identifying the frequency fluctuations, but it is necessary to develop ways to increase sensitivity and extract basic information from the spectrograms to enhance the validity of its results.