Rolling bearing fault diagnosis method and system based on discrete cosine cyclic spectrum coherence

Abstract

The invention provides a rolling bearing fault diagnosis method and system based on discrete cosine cyclic spectrum coherence, and belongs to the technical field of mechanical equipment fault diagnosis. The method comprises the steps: obtaining a time domain vibration signal of a rolling bearing; extracting discrete cosine cyclic spectrum coherent features from the time domain vibration signals to obtain a two-dimensional discrete cosine cyclic spectrum coherent feature map; and obtaining a final diagnosis result according to the two-dimensional discrete cosine cyclic spectrum coherent feature map and a preset convolutional neural network model. Based on the discrete cosine cyclic spectrum coherent features and the improved convolutional neural network model, accurate and rapid diagnosis of the rolling bearing fault can be realized under data distribution change conditions such as data imbalance and working condition change.

Description

technical field [0001] The invention relates to the technical field of mechanical equipment fault diagnosis, in particular to a rolling bearing fault diagnosis method and system based on discrete cosine cyclic spectrum coherence. Background technique [0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art. [0003] Rotating machinery is a very widely used equipment in modern industry. As a key component of rotating machinery, bearings have an important impact on the operating effect, stability and service life of rotating machinery. But due to harsh operating environments and sudden load changes, the health of bearings can deteriorate over time. At the same time, factors such as installation errors, poor lubrication, debris contamination, wear and other factors can also cause damage to the bearing structure. Failure to detect faults and maintain them in time may lead to breakdown of...

AI Technical Summary

Problems solved by technology

[0005] At present, most fault diagnosis methods based on CNN assume that the training set and test set obey the same data distribution, without considering the domain adaptability of the diagnosis method. The impact of imbalance and changes in working conditions makes the data distribution in the new task different from the training set, which will seriously deteriorate the effectiveness of the diagnostic method; in addition, the actual collected bearing vibration signals contain a lot of noise, which will pollute or even cover up Weak fault information, so it is necessary to use efficient signal processing technology to extract more obvious fault features, but the currently used signal processing methods cannot extract high-quality features on the one hand, and on the other hand, the processing process is computationally intensive and inefficient

All of the above factors hinder the application of diagnostic methods in real industrial settings.

Images