关键词: 时变自回归模型；小波基；参数估计； 时频分析； 故障诊断

Abstract:

Time-varying autoregressive (TVAR) modeling method of non-stationary signal was studied. In the proposed method, time-varying parametric identification of non-stationary signal can be translated into a linear time-invariant problem by introducing a set of wavelet basis functions. Then, the parameters were estimated using recursive least square algorithm with a forgetting factor and the adaptive time-frequency analysis was achieved. The simulation results show that the proposed approach is superior to the short time Fourier transform and Wigner distribution. At last, the proposed method is applied to the fault diagnosis of bearing,and experimental result shows the proposed method is effective in feature extraction.

Key words: time-varying autoregressive model, wavelet base, parameter estimation, time-frequency distribution, fault diagnosis