Cloud, fog and edge end cooperative bearing state monitoring and management method and system

Abstract

The invention discloses a cloud, fog and edge end cooperative bearing state monitoring and management system and method. The method comprises the steps that a bearing operation signal is obtained, the noise reduction, feature extraction and other signal processing are conducted, a result is uploaded to fog end equipment, the fog end equipment updates the bearing digital twin model according to the information uploaded by the edge end, performs fault diagnosis and life prediction of digital-analog fusion, uploads a result and part of edge end information to the cloud end, and receives a customized bearing fault diagnosis and life prediction model issued by the cloud end; and the cloud end receives fog end information, performs spatio-temporal data indexing, calculates a customized bearing fault diagnosis and service life prediction model for the fog end, and provides a predictive maintenance scheme. According to the scheme, the defects that an existing bearing operation and maintenance system based on the big data technology is few in calculation hierarchy, single in function and dependent on data driving are overcome, and an efficient calculation framework and an accurate diagnosis and prediction scheme are provided for predictive maintenance.

Description

technical field [0001] The invention belongs to the technical field of mechanical diagnosis intelligence and digitization, and in particular relates to a bearing state monitoring and management method and system coordinated by cloud, fog and edge terminals. Background technique [0002] High-end bearings are the key load-bearing and transmission components of rotating machinery in major equipment such as wind turbines and high-speed rail, and their service life determines the refurbishment period and reliability of the complete machine. The working conditions of high-end bearings are complex, with extreme working conditions such as high speed, high temperature, overload shock, and large-scale fluctuations in working conditions. This makes the bearing prone to peeling, pitting and slipping during long-term use, and eventually leads to bearing failure. The online bearing condition monitoring and management system can dynamically obtain the bearing operating status in real time...

AI Technical Summary

Problems solved by technology

[0004] Through literature research, it can be found that most of the existing bearing condition monitoring and management systems are only implemented on a single platform at the edge or cloud. Due to the huge pressure of data transmission, it is difficult for the equipment to achieve real-time feedback to the monitored equipment, and the addition of fog end equipment can not only share the burden of calculation and transmission for the former two, but also provide a good personalized diagnosis platform

In addition, most of the existing cloud (fog) edge collaborative bearing condition monitoring and management systems can only realize the data-driven bearing fault diagnosis function, and cannot accurately realize the predictive maintenance function, while the digital twin bearing life prediction combined with digital and analog can accurately simulate Damage expansion of faulty bearings, calculation of remaining life, and providing a strong basis for spare parts allocation

Images