Rolling bearing fault diagnosis method and system combining edge calculation and deep learning

Abstract

The invention discloses a rolling bearing fault diagnosis method and system combining edge calculation and deep learning, and the method comprises the steps: enabling a data preprocessing module in edge calculation equipment to carry out the preprocessing of a collected vibration signal of a rolling bearing, and obtaining sample data; performing fault diagnosis and classification on the sample data obtained through preprocessing in the previous step by using a fault detection and diagnosis module based on deep learning in the edge computing equipment; storing a fault processing knowledge base in the edge computing device, and giving an alarm signal and a coping scheme according to the fault category. The system comprises a signal acquisition module, a signal transmission module, and an edge computing device carrying a data preprocessing module, a fault detection and diagnosis module and a fault processing knowledge base, wherein the edge computing device is arranged at a data source. According to the method, edge calculation and deep learning are combined, the response speed and accuracy of rolling bearing fault diagnosis are improved, and real-time performance and intelligence are met.

Description

technical field [0001] The invention belongs to the field of edge computing and intelligent bearing fault diagnosis, and in particular relates to a rolling bearing fault diagnosis method and system combining edge computing and deep learning. Background technique [0002] Bearing failure is one of the most common mechanical equipment failures. To ensure the normal operation of bearings and to detect bearing failures in time is crucial to production and life safety. Traditional methods diagnose bearings by studying time-frequency domain signals, such as wavelet packet transform (WPT), empirical wavelet transform (EWT), fast Fourier transform (FFT), etc., but these methods require professionals to analyze signals and extract features. The adaptive ability is poor, the process is cumbersome, the diagnostic effect still needs to be improved, and the diagnostic methods still need to be intelligent. [0003] In recent years, deep learning has achieved remarkable results in the fie...

AI Technical Summary

Problems solved by technology

Although the method of deep learning has improved the accuracy of bearing fault diagnosis, the collection of fault data and subsequent analysis of the fault mode cannot meet the needs of real-time detection of industrial equipment, and edge computing solves this problem. , using an open platform to directly provide the most up-to-date services

Images