Motor fault diagnosis system and method based on edge calculation and deep learning

Abstract

The invention relates to a motor fault diagnosis system and method based on edge calculation and deep learning. Edge side equipment can configure an acquisition device, preprocesses vibration or current signals and then performs empirical mode decomposition (EMD), a built-in deep residual network diagnosis model of the diagnosis module inputs n IMF components to perform fault diagnosis, and a diagnosis result and fault data are uploaded to a cloud service center; and the cloud service center periodically trains the deep residual error network diagnosis model by using historical data and the fault data, issues the trained deep residual error network diagnosis model to each edge side equipment, and updates the deep residual error network diagnosis model in the edge side equipment. The motorequipment can be diagnosed in real time through the calculation of the edge side equipment, the motor state can be timely and quickly diagnosed, and only the processed data is transmitted to the cloudcenter, so that the time delay caused by the data transmission speed and bandwidth limitation is greatly reduced, and the data processing pressure of the cloud center is remarkably relieved.

Description

technical field [0001] The invention relates to the technical field of motor fault diagnosis, in particular to a motor fault diagnosis system and method based on edge computing and deep learning. Background technique [0002] The application of motors in modern industry is very common. Whether it is a large factory enterprise or a small factory enterprise, you can see the motor everywhere, and the large motors on some important production lines are very important to the enterprise. Once a failure occurs, it may It will cause the entire production line to stop working, and more seriously, it may cause major economic losses and casualties to the enterprise, so the normal and stable operation of the motor is very important to the enterprise. [0003] At present, most of the maintenance of the motor is carried out by the on-site maintenance personnel to check the vibration, noise and shell temperature of the motor every day, and evaluate the state of the motor based on years of ...

AI Technical Summary

Problems solved by technology

[0007] Aiming at the problem that it is necessary to transmit all the diagnostic data back to the cloud server for diagnostic calculation and the low diagnostic accuracy of the shallow neural network, the present invention provides a motor fault diagnosis system and method based on edge computing and deep learning. Applying Deep Learning Algorithms on Edge Devices to Diagnose Motor Faults

Images