Bearing anomaly detection method and system

Abstract

The invention discloses a bearing anomaly detection method and system. The method comprises the following steps: acquiring bearing acceleration sample data; preprocessing the acceleration sample data;mining feature data of the preprocessed acceleration sample data by adopting an automatic coding machine; carrying out clustering analysis on the characteristic data corresponding to each acceleration sample data; determining normal feature data and abnormal feature data according to a clustering analysis result; training the neural network by taking the feature data as a sample and taking normality or abnormality of the feature data as a label to obtain a neural network model; acquiring acceleration data of a to-be-detected bearing; preprocessing the acceleration data of the to-be-detected bearing; mining feature data of the preprocessed acceleration data of the to-be-detected bearing by adopting an automatic coding machine; and inputting the characteristic data of the acceleration dataof the to-be-detected bearing into the neural network model to obtain a result of whether the acceleration data of the to-be-detected bearing is abnormal. According to the invention, whether the bearing is abnormal or not can be directly identified.

Description

technical field [0001] The invention relates to the technical field of abnormality detection, in particular to a bearing abnormality detection method and system. Background technique [0002] Anomaly detection problem is an application in machine learning, a special application of classification problem. The so-called abnormal events are unexpected events that are very rare and difficult to predict in the samples. These abnormal samples generally cannot have similar characteristics, so it is difficult to classify these events into the same category. Anomalies are highly unevenly distributed in the sample and vary in ways that cannot be categorized. Anomaly problems are usually that some current knowledge is not enough to define its type, so a training set with labeled samples will not be provided, so the problem of anomaly detection is often modeled using an unsupervised method, or in a training set with only normal samples A machine learning model is trained on it, and an...

AI Technical Summary

Problems solved by technology

[0003] For the abnormal detection of bearings, since the periodic characteristics of the abnormal data are not obvious, and the data is noisy, it is impossible to classify all the abnormal data into one category, which brings great difficulties to the abnormal detection of bearings.

Images