Equipment vibration abnormity diagnosis method and system

Abstract

The invention discloses an equipment vibration abnormity diagnosis method and system, and the method comprises the steps: collecting a vibration signal of to-be-detected equipment in real time, and carrying out the time-frequency transformation of the vibration signal; extracting feature data of the vibration signal after time-frequency transformation by using a noise reduction auto-encoder; utilizing a self-attention mechanism model to calculate probability values of the to-be-detected equipment in different operation states corresponding to the feature data; and judging whether the vibration of the to-be-detected equipment is abnormal or not according to the probability value. According to the invention, noise coupled by the vibration signal is eliminated by using the noise reduction self-coding module, and the diagnosis result of the vibration signal is obtained by using the self-attention mechanism model, so that the accuracy and timeliness of the equipment abnormality diagnosis result can be effectively improved.

Description

technical field [0001] The invention relates to the field of equipment detection, in particular to a method and system for diagnosing abnormal equipment vibration. Background technique [0002] In the automated electric energy measurement and verification production line, various rotating parts are used. Gears and rolling bearings are common parts in rotating machinery and are key stress-bearing parts in the production line. Due to the complex and changeable operating conditions, gears and bearings have long Working under alternating loads, it is extremely prone to failure. [0003] Rotating transmission parts will generate vibration signals during operation, and mechanical faults will be directly reflected in the abnormal vibration signals. Therefore, the mechanical faults can be diagnosed and early-warned by analyzing the vibration signals. [0004] However, the existing equipment abnormality diagnosis methods are easily disturbed by the vibration of the surrounding envir...

AI Technical Summary

Problems solved by technology

[0004] However, the existing equipment abnormality diagnosis methods are easily disturbed by the vibration of the surrounding environment, and it is difficult to detect equipment vibration abnormality information in a timely and accurate manner, which will affect the production efficiency of the verification at the slightest level, and will cause damage to the measurement equipment at the worst, thus bringing economic loss

Images