Vibration equipment fault diagnosis method and system

Abstract

The invention discloses a vibration equipment fault diagnosis method and system, and relates to the field of equipment fault diagnosis. Vibration equipment vibrates non-periodically and/or is asymmetric in the aspect of appearance. The method comprises the following steps of: arranging two groups of vibration sensors on a vibration equipment shell at two sides of a centroid plane, wherein each group of vibration sensors comprises a plurality of vibration sensors, each vibration sensor is used for acquiring dynamic vibration signal of the equipment, and the centroid plane is parallel to a planewhere a vibration equipment base is located; analyzing the dynamic vibration signal acquired by each vibration sensor to obtain a feature weighting signal, and generating a contour feature signal ofthe vibration equipment according to all the feature weighting signals; carrying out dimensionality reduction on the contour feature signal on the basis of a nonlinear manifold learning method so as to obtain low-dimensional feature descriptions of the vibration equipment; and classifying the low-dimensional feature descriptions by adoption of a classifier so as to obtain a fault diagnosis result.The method and system are capable of effectively reducing minor and interference information in original vibration data so as to obtain stable and correct fault diagnosis results.

Description

technical field [0001] The invention relates to the field of equipment fault diagnosis, in particular to a fault diagnosis method and system for vibration equipment. Background technique [0002] Fault diagnosis technology is widely used in the operation status analysis and health management of mechanical vibration equipment. At present, the fault diagnosis methods for mechanical vibration equipment are mostly for rotating vibration equipment, impact vibration equipment, reciprocating vibration equipment, etc. The original vibration of these equipment The information has obvious periodicity or changing characteristics, and the fault diagnosis is mostly to analyze the vibration signal in the frequency domain, such as Fourier transform, wavelet analysis, etc., or use methods such as neural networks, and some diagnostic methods will also combine the time domain information for feature-level fusion or decision-level fusion. [0003] For some vibrating equipment with asymmetric ...

AI Technical Summary

Problems solved by technology

[0003] For some vibration equipment with asymmetric shape and aperiodic vibration signal, the existing equipment vibration fault diagnosis methods are not ideal

For example, there are many mechanical vibration equipment in ships with complex structures, and fault diagnosis is difficult. At present, there are few researches on fault diagnosis of marine asymmetric and aperiodic vibration equipment. Most of them focus on feature selection and feature transformation of original vibration information, which is difficult to obtain. Accurate fault diagnosis results, the main difficulty lies in: the fault diagnosis of ship mechanical vibration equipment is based on a large number of parameter information of equipment operation, usually a large amount of original vibration data is collected through various vibration sensors placed, and these original data not only contain a large amount of redundant information and interference information, and these raw data include the main feature information that plays a key role and the secondary feature information that plays an auxiliary role. Appropriate description of the vibration characteristics of asymmetric non-periodic vibration equipment, thus affecting the accuracy of the final fault diagnosis

Images