A fault prediction method, system, electronic device and readable storage medium

Abstract

The embodiment of the present application is to provide a fault prediction method, system, electronic equipment and readable storage medium, which belong to the technical field of vibration health monitoring of rotating machinery. The fault prediction method includes: the vibration sensor terminal node collects the vibration signal to be processed when the rotating machine is working, processes and obtains the vibration feature to be processed and transmits it to the edge server; the edge server generates network intermediate features according to the vibration feature to be processed and predicts whether the rotating machine Faults may occur; when the rotating machinery is predicted to be in a healthy state and the confidence level is high, the fault prediction is exited early; when the rotating machinery is predicted to be in a faulty state or predicted to be in a healthy state but the confidence level is not high, upload the intermediate features of the network to the cloud computing center ; The cloud computing center predicts whether the rotating machinery may fail according to the intermediate characteristics of the network, and obtains the final prediction result. This application aims to improve the accuracy and efficiency of fault prediction through the collaboration of edge servers and cloud computing centers.

Description

technical field [0001] The embodiments of the present application relate to the technical field of vibration health monitoring of rotating machinery, and in particular, relate to a fault prediction method, system, electronic equipment, and readable storage medium. Background technique [0002] In the industrial field, mechanical equipment is ubiquitous, and gradually tends to be complex, precise and automated, among which rotating mechanical equipment is widely used. Rotating machinery equipment is a mechanical structure with rotating parts. Typical rotating machinery equipment includes: large integrated machinery such as steam turbines, gas turbines and pumps, and mechanical parts such as bearings and gearboxes. However, the mechanical structure in rotating machinery equipment is also one of the mechanical structures with the highest failure rate, and equipment failures caused by rotating machinery failures such as bearing cracks account for more than 50%. [0003] The fai...

AI Technical Summary

Problems solved by technology

[0003] The failure of rotating machinery equipment may lead to the shutdown of the entire production line, and even bring significant economic losses and casualties to the enterprise, so failure maintenance is very important

[0004] At present, fault maintenance for rotating machinery mainly includes reactive maintenance, preventive maintenance, and Prognostics Health Management (PHM), but reactive maintenance is only performed after a fault occurs, resulting in long downtime and high maintenance costs , Preventive maintenance adopts the method of regular inspection and it is easy to bring a lot of unnecessary maintenance costs; and PHM judges the health status of the equipment when the machine is running, the downtime is relatively short, and the maintenance cost is low, but the traditional PHM uses an embedded single-chip microcomputer Predictive maintenance is carried out by bus connection with the local computing host, but the computing power of the local processing method is poor, which reduces the fault prediction effect, and the traditional PHM adopts a supervised learning method, which requires fault data for training, which is difficult for practical application

Images