Early failure identification method based on SILLE (Supervised Increment Locally Linear Embedding) dimensionality reduction

Abstract

The invention relates to an early failure identification method based on SILLE (Supervised Increment Locally Linear Embedding) dimensionality reduction. The method comprises the following steps of: acquiring characteristic information of early failures of complex rotating machinery from two action domains including a time domain and a frequency domain, establishing time-and-frequency domain characteristic set vectors representing different failure characteristics comprehensively, automatically reducing the high-frequency time-and-frequency domain characteristic set vectors into low-dimension characteristic vectors with higher distinction degrees by virtue of SILLE, and inputting the low-dimension characteristic vectors into a classifier for classification and decision, thus obtaining early failure identification results of test samples. The early failure identification method can be used for giving full play to the superiority of time-and-frequency domain characteristic sets on comprehensive failure characteristic excavation, the superiority of an SILLE technology on information reduction and the superiority of the classifier on mode identification, and guaranteeing the automation, high precision, rapidness and universality of the early failure identification method for the rotating machinery.

Description

technical field [0001] The invention relates to the technical field of fault identification, in particular to an early fault identification method based on dimension reduction of supervised incremental local linear embedding (SILLE). Background technique [0002] The early fault identification technology of rotating machinery is an equipment diagnosis technology developed with the development of modern industrial mass production. It is to study the early faults of rotating machinery, that is, when the abnormal performance of rotating machinery is relatively weak and no typical accidents have occurred. Before, master the operation status of the rotating machinery, determine the location, cause or severity of the early failure of the rotating machinery, predict the reliability and life of the equipment, and propose the corresponding maintenance plan. The research content involves signal processing technology, information fusion Technology, dimension reduction theory, pattern r...

AI Technical Summary

Problems solved by technology

[0010] Aiming at the problem that the existing early fault identification method of rotating machinery is difficult to realize the unification of automation, high precision, rapidity and versatility, the present invention proposes a dimension reduction method based on supervised incremental local linear embedding (SILLE) Early fault identification method, this method first obtains the characteristic information of early faults of complex rotating machinery from the time domain and the frequency domain, and then uses the supervised incremental local linear embedding (SILLE) to integrate the high-dimensional time-frequency domain feature set The vector is automatically reduced to a low-dimensional feature vector with better discrimination, and input into the classifier for early failure mode identification

Images