Time-varying fault feature extraction of rolling bearing via time–frequency sparsity

Abstract

The joint time–frequency (TF) distribution is a critical method of describing the instantaneous frequency that changes with time. To eliminate the errors caused by strong modulation and noise interference in the process of time-varying fault feature extraction, this paper proposes a novel approach called second-order time–frequency sparse representation (SOTFSR), which is based on convex optimization in the domain of second-order short-time Fourier transform (SOSTFT) where the TF feature manifests itself as a relative sparsity. According to the second-order local estimation of the phase function, SOSTFT can provide a sparse TF coefficient in the short-time Fourier transform (STFT) domain. To obtain the optimal TF coefficient matrix from noisy observations, it is innovatively formulated as a typical convex optimization problem. Subsequently, a multivariate generalized minimax concave penalty is employed to maintain the convexity of the least-squares cost function to be minimized. The aim of the proposed SOTFSR is to obtain the optimal STFT coefficient in the TF domain for extraction of time-varying features and for perfect signal reconstruction. To verify the superiority of the proposed method, we collect the multi-component simulation signals and the signals under variable speed from a rolling bearing with an inner ring fault. The experimental results show that the proposed method can effectively extract the time-varying fault characteristics.

WBUN: an interpretable convolutional neural network with wavelet basis unit embedded for fault diagnosis

“…Feature extraction is a critical step in data-driven fault diagnosis [5]. Traditional feature extraction mainly relies on signal processing techniques such as short time Fourier transform [6], wavelet transform [7] and EMD [8]. These approaches enable researchers to extract crucial fault * Author to whom any correspondence should be addressed.…”

Demodulated synchrosqueezing S-transform and its application to machine-fault diagnosis

“…fault characteristics [11,12], and is able to extract detailed information from the non-linear frequency modulation (FM) feature of vibration signals. Short-time Fourier transforms (STFTs) [13,14] and continuous wavelet transforms (CWTs) [15][16][17] are the most popular forms of TFA. However, the effectiveness of such transforms is restricted by the selection of window or wavelet.…”

A Comparative Study of UNET Model for Bearing Fault Identification Based on Time-Series and Wavelet Transformed Vibration Images

“…Considering significance of timely bearing fault diagnosis, Deep Learning (DL) has been in the attention of researchers and can learn more efficiently with processed features compared to the models fed with the raw data [4,5]. Thus, feature processing of data allows to improve generalization capability of DL models [6][7][8][9]. In recent years, development of various DL methods have witnessed their excellent performance in fault diagnosis and prognosis owing to their generalization capacity [10].…”