Fault diagnosis method based on OLPP feature reduction

Abstract

A fault diagnosis method based on OLPP feature reduction in rotary machine fault diagnosis field includes that a vibration signal is performed with EMD to construct Shannon entropy to obtain high-dimensional feature vectors, and then OLPP is adopted reduce the high-dimensional vectors to low-dimensional feature vectors which are inputted to a Morlet MWSVM for fault recognition. The OLPP preserving local and overall structure retains the low-dimensional internal features of the nonlinear manifold structure, and the MWSVM has self-adaptive decisive power and can be used as a terminal classifier. The invention sufficiently excels the advantages of EMD, OLPP and MWSVM respectively in fault feature extraction, information compression and pattern recognition, not only realizes the full automatic process from fault feature extraction to fault diagnosis, but also has high fault diagnosis accuracy and self-adaptive diagnosis capacity.

Description

technical field [0001] The invention relates to a fault diagnosis method, in particular to a fault diagnosis method based on Orthogonal Local Preserving Mapping (OLPP) feature reduction. Background technique [0002] Fault diagnosis technology of rotating machinery is an equipment diagnosis technology developed with the development of modern industrial mass production. The location, cause, severity and state of equipment failure, the technology of predicting equipment reliability and life, and proposing solutions. The research content involves pattern recognition, modern control theory, signal processing technology, artificial intelligence, electronic technology, statistical mathematics , fuzzy mathematics, computer science, gray system theory and many other aspects, the most important method is to analyze the vibration signal and other signals of the rotating machinery based on the principle of mechanical dynamics to diagnose the fault of the rotating machinery. [0003] I...

AI Technical Summary

Problems solved by technology

The incompleteness of this basis leads to the inability of the classification support vector machine (SVM) to approach any classification interface on this subspace, and the adaptability is not ideal.

[0006] Due to the above reasons, the use of modern time-frequency analysis methods represented by Empirical Mode Decomposition (EMD) to process nonlinear and non-stationary signals actually measured for fault diagnosis of rotating machinery has not made significant progress so far.

Images