Method for extracting fault signal feature of mechanical device

Abstract

The invention discloses a method for extracting the fault signal feature of a mechanical device. The method comprises steps of acquiring, by a sensor, the state signals of respective components of themechanical device; performing empirical wavelet transform on the acquired state signals to obtain the modal components of signal decomposition; calculating the correlation coefficients between respective modal components and an original signal, and selecting a plurality of modal components having the highest correlation with the original signal as the optimal modal components; constructing a Hankel matrix for the optimal modal components, and then performing singular value decomposition to obtain the feature values of the optimal modal components; subjecting the feature values of the optimalmodal components to dimensionality reduction, and combining the feature values subjected to the dimensionality reduction into a fault feature vector. The method can effectively remove the noise in theoriginal signal, retains the useful features in the original signal, and provides a necessary basis for the fault diagnosis of the mechanical device.

Description

technical field [0001] The invention belongs to the technical field of intelligent systems, and in particular relates to a method for extracting mechanical equipment fault signal features. Background technique [0002] As the assembly and conveying equipment of the automobile production line tends to become more complex and multi-functional, the daily maintenance and diagnosis of the equipment becomes more and more difficult. The traditional manual diagnosis and maintenance cannot meet the increasing production demand and efficiency. Therefore, it is necessary to improve the intelligence of manufacturing equipment, realize multi-dimensional perception of manufacturing information, collaborative fault diagnosis and operation health warning, so as to realize a general automatic fault method. In order to realize the fault diagnosis of mechanical equipment, it is first necessary to extract the fault features contained in the signal. The traditional signal feature extraction met...

AI Technical Summary

Problems solved by technology

Although these methods denoise the signal very well and obtain a good fault characteristic signal, they cannot directly perform automatic fault identification through machine learning algorithms.

Although some methods extract fault features from signals to form fault feature vectors, the extracted fault feature attributes are specific to a signal or a component and are not universal.

Images