Selected Integrated Weak Fault Feature Extraction with Improved Local Feature Decomposition

Abstract

The invention discloses a weak fault feature extraction method based on selective integration and improved local feature decomposition, which specifically includes: collecting vibration signals for normalization processing; adopting a boundary extension method based on mirror extension symmetrical points to extend both ends of the normalized signal use the SEILCD method to decompose the extended signal into multiple ISC components; estimate the energy of each ISC component at a confidence level of 95% and 99%; judge whether each ISC component is noise, and if it is a noise ISC component, use the minmax threshold The denoising method denoises the ISC, otherwise the AWOGS method is used to denoise the ISC; after denoising, the ISC is normalized and orthogonalized and time-frequency analysis is performed. The method of the invention can self-adaptively select the LCD interpolation average value curve and self-adaptive signal denoising, improves complex vibration signal processing capability, effectively enhances fault features, and further improves the accuracy and interpretability of fault diagnosis.

Description

technical field [0001] The invention relates to a selective integrated improved local characteristic-scale decomposition method for extracting weak fault features (selective ensemble improved local characteristic-scale decomposition, SEILCD), which belongs to the technical field of weak mechanical fault feature extraction. Background technique [0002] Rotating machinery is the key core equipment in coal mine production, mainly composed of motors, reducers, hydraulic brakes and other parts. Extracting fault-related information from mechanical operating parameters such as vibration, pressure, and temperature to monitor the operating status of rotating machinery is the main content of current mechanical fault monitoring research. A large number of production practices and theoretical studies have shown that more than 70% of faults are hidden in vibration signals. [0003] Time-frequency analysis method is the mainstream method of mechanical fault diagnosis, such as wavelet an...

AI Technical Summary

Problems solved by technology

Due to the difference in complexity and smoothness of each signal subcomponent, it is difficult to avoid the interpolation curve reflecting the overall trend of all signals by using a single envelope interpolation function, thus causing mode confusion

Images