Research on the Method of Features Extraction for Non-Stationary Transient Signal Based on EMD Method

For solving the problem of features extraction on non-stationary transient impact signal, a novel method of features extraction is proposed by signal processing theory. Firstly, the intrinsic mode function (IMF) of the signal is extracted using the empirical mode decomposition (EMD). Combined with Hilbert transformation, the instantaneous frequency of transient single-frequency vibration signal extracted model is established to extract the instantaneous frequency. Secondly, the Hilbert spectrum can be obtained by IMF and the Hilbert boundary spectrum is obtained. The transient characteristic of torsional vibration signal can be extracted effectively using the method. Compared with wavelet decomposition, this algorithm not only avoids the frequency overlapping in the wavelet decomposition, but also overcomes the difficulty in selecting elementary wavelet. The numerical simulation shows the feasibility of the method. The example analysis of transient signal shows the reliability of the method.