Fault feature adaptive extraction method based on wavelet entropy and EEMD (ensemble empirical mode decomposition)

Abstract

The invention discloses a fault feature adaptive extraction method based on wavelet entropy and EEMD (ensemble empirical mode decomposition). The method comprises the following steps: performing intrinsic mode decomposition on collected mechanical product operation historical signals by using ensemble empirical mode decomposition; calculating the wavelet energy entropy of the intrinsic mode function component obtained by decomposition; extracting an intrinsic mode function component containing most complex information; wavelet threshold noise reduction is carried out on the extracted intrinsic mode function component; and recombining the intrinsic mode function components after noise reduction. According to the method, the intrinsic mode function component with most energy information is adaptively determined by using the wavelet energy entropy, so that adaptive screening of the intrinsic mode function can be completed without depending on experience and test, and the fault characteristic frequency band is quickly extracted.

Description

technical field [0001] The invention relates to fault feature extraction technology, in particular to an adaptive fault feature extraction method based on wavelet entropy and EEMD. Background technique [0002] With the development and progress of science and technology, mechanical equipment occupies an important position in modern industrial applications. With the increasing complexity of equipment structure, feature extraction and further diagnosis and evaluation of operating process information of mechanical equipment are also more and more important. As an important component of mechanical equipment, rotating machinery is directly related to its performance. In order to ensure the long-term and efficient normal operation of rotating machinery, according to the health status of electromechanical equipment, reasonable maintenance can be organized to avoid excess maintenance and insufficient maintenance. Implementing "predictive maintenance" can effectively reduce equipmen...

AI Technical Summary

Problems solved by technology

At present, the vast majority of feature extraction technologies only rely on traditional root mean square and peak values ​​for feature extraction. This traditional feature extraction usually extracts a series of values ​​​​through a fixed algorithm, regardless of the actual operating environment and operating status of the device.

Also, just looking at the numerical change is not enough to know what kind of change the device is making

[0004] Feature extraction technology is one of the core technologies for mechanical equipment reliability evaluation and health management. In signal analysis technology, the most important is feature extraction and feature classification and recognition, and the quality of feature extraction largely affects subsequent features. The effect of classification and recognition, so feature extraction is the top priority. Traditional feature extraction techniques include: time-domain analysis, frequency-domain analysis, etc., which are not enough to express the specific reasons for different signals. They are only a single numerical representation and cannot be understood. It is difficult to identify the characteristic frequency of the fault and the number of key intrinsic mode functions (IMF) due to the changes in the equipment. Most studies have extracted the first or second IMF from the equipment operation process signal after ensemble empirical mode decomposition. Two or three Intrinsic Mode Functions (IMF) for frequency domain analysis. In fact, there are various signals. Under different working conditions, in order to mine enough information from the signal, the optimal number of Intrinsic Mode Functions (IMF) is required. may vary

Images