Method for judging bearing fault based on CEEMDAN decomposition, electronic equipment and storage medium

Abstract

The invention discloses a method for judging a bearing fault based on CEEMDAN decomposition, electronic equipment and a storage medium, and the method comprises the steps: carrying out the CEEMDAN decomposition of an original acceleration signal of a bearing, and obtaining an intrinsic mode function component; calculating the kurtosis K of the intrinsic mode function component of each layer, and adding the corresponding values of the intrinsic mode function components of each layer with the kurtosis K greater than a set value to obtain a reconstructed acceleration signal; performing envelope demodulation on the reconstructed acceleration signal to obtain an envelope spectrum; calculating a bearing characteristic frequency according to the bearing signal and the rotating speed; and checking the amplitude of the characteristic frequency of the bearing in the envelope spectrum, and if the amplitude of a certain characteristic frequency exceeds an envelope threshold value, determining that the bearing part corresponding to the characteristic frequency has a fault. According to the invention, the signal resolution can be effectively improved, the interference of noise and other vibration signals can be weakened, and the loss and mode overlapping of fault signals can be avoided. The detection capability of weak fault characteristic signals is obviously improved, and the fault part of the bearing can be effectively identified.

Description

technical field [0001] The invention belongs to the technical field of bearing fault diagnosis, and in particular relates to a method for judging bearing faults based on CEEMDAN decomposition, an electronic device and a storage medium. Background technique [0002] The working conditions of rolling bearings are often in harsh environments such as corrosion and high pressure, so the probability of failure is much higher than that of other components. The traditional fault detection method is manual direct detection, which mainly depends on the subjective experience of the inspectors. Rolling bearings will emit different vibration signals when they operate under different conditions, so the vibration signals can be studied instead of direct detection. This method can be operated without relying on experienced inspectors to achieve non-contact inspection. However, the defect information of rolling bearings may be disturbed by complex noise, which makes the defect information d...

AI Technical Summary

Problems solved by technology

[0004] However, in the process of practical application of CEEMDAN, the method of adding noise and the value of the overall average number of times need to be determined empirically in most cases, and the decomposition effect is often not ideal, and the detection ability of CEEMDAN for weak fault characteristic signals cannot be achieved, so Accurately determine the specific fault location of the bearing

Images