A Welch-EWT-SVD time–frequency feature extraction model for deformation monitoring data

•The Welch-EWT-SVD model is proposed to extract time–frequency features from non-linear and non-stationary deformation monitoring data.•The frequency range division method avoids the loss of feature information caused by over-decomposition.•The signal-to-noise ratio of the simulated signal processed with Welch-EWT-SVD is improved by 16.220.•The relative error rates of each modal frequency identified by Welch-EWT-SVD are kept within 0.10%. It is a considerable challenge to accurately extract time–frequency features from non-linear and non-stationary deformation monitoring data. In this contribution, a time–frequency feature extraction model that integrates the Welch algorithm, empirical wavelet transform (EWT), and singular value decomposition (SVD) (Welch-EWT-SVD) is proposed. To avoid the impact of unreasonable spectral segmentation, the signal is decomposed at multiple levels based on the Welch power spectrum. The decomposed signal is then processed by EWT to obtain Intrinsic Mode Functions (IMFs). Finally, SVD is adopted to further denoise the IMFs to finely extract time–frequency features. Simulation tests and a field test at the Great Wall are conducted to validate the proposed method. The results demonstrate that Welch-EWT-SVD outperforms EWT, EMD, and Welch-EWT methods in terms of accuracy for time–frequency feature extraction. According to the simulation results, the relative error rate of its extracted frequency is kept within a maximum of 0.10%.