A multi-data compression tracking algorithm-based local fault remote diagnosis method for a rotary machine

Abstract

The invention discloses a multi-data compression tracking algorithm-based local fault remote diagnosis method for a rotary machine, and the method comprises the steps of S1, analyzing possible faultsof equipment and corresponding fault feature information, and collecting a mechanical vibration signal and a rotating speed signal of an equipment end; S2, intercepting a section of time domain signalat the equipment end, and using a shift constant K-SVD learning method for carrying out pattern training; S3, performing real-time compressed sampling on the acquired vibration signal data accordingto a compressed sensing principle; S4, carrying out remote transmission on the path, the rotating speed working condition information and the compressed and sampled data which are obtained by the equipment end through training and learning; S5, at a receiving end, constructing a shift invariant sparse dictionary by using the pattern, and recovering fault characteristics by using the compressed data of the three channels on the same sensor through a multi-data compression tracking algorithm at the same time; and S6, determining the fault problem of the equipment according to the extracted faultfeature information. The method provided by the invention can quickly extract fault features and solve the problem of long-distance transmission of a large amount of data.

Description

technical field [0001] The invention relates to the field of fault diagnosis of rotating machines such as gearboxes, in particular to a method for remote diagnosis of local faults of rotating machines based on a multi-data compression tracking algorithm. Background technique [0002] Remote fault diagnosis of rotating machinery has always been a difficulty in evaluating the health status of rotating machinery due to the complexity, instability, and large noise components of vibration signals. At the same time, the huge amount of data also brings a heavy burden to long-distance transmission. As an important indicator of mechanical health assessment, vibration signals often contain important fault feature information. Accurate and convenient extraction of fault feature information is an important means of fault diagnosis of rotating machinery. [0003] Commonly used rotating machinery fault diagnosis methods mainly include empirical mode decomposition, wavelet transform and me...

AI Technical Summary

Problems solved by technology

Empirical mode decomposition method is easy to cause modal mixing and inaccurate fault diagnosis. Wavelet transfo

Images