This paper reports a bearing fault detection method based on kurtosis-based adaptive bandstop filtering (KABS) and iterative autocorrelation (IAC). The interferences in the bearing signal can be removed by KABS filtering, whereas IAC is employed for noise reduction and signal enhancement. In the KABS method, two window-merging schemes are proposed to identify the frequency bands potentially containing interferences and to preserve those covering fault frequencies. Issues related to the selection of the number of autocorrection iterations are also discussed. The proposed method can be used for bearing fault detection in a low signal-to-noise ratio (SNR) and low signal-to-interference ratio (SIR) environment. The implementation of the proposed method does not require prior knowledge of the fault-excited resonant frequency. The performance of the proposed method has been examined by simulation analysis, with favorable comparisons to the Hilbert enveloping, energy operator, and spectrum kurtosis methods. Its effectiveness in bearing fault detection has also been demonstrated using experimental data.
Research on a Rolling Bearing Fault Detection Method with Wavelet Convolution Deep Transfer Learning
