Bearing fault early warning and diagnosis method based on improved MSET and spectrum characteristics

Abstract

The invention discloses a bearing fault early warning and diagnosis method based on improved MSET and frequency spectrum characteristics. The method comprises the following steps: obtaining an original vibration signal; obtaining a fault characteristic frequency, and determining an actual frequency range according to the variable quantity of the fault characteristic frequency; carrying out envelope spectrum analysis: filtering the original vibration signal by using a fast spectrum kurtosis and band-pass filtering method, analyzing the filtered vibration signal to obtain an envelope spectrum, and further obtaining monitoring parameters; carrying out improved MSET modeling: establishing a historical memory matrix, establishing an MSET model by using the obtained historical memory matrix, and calculating an estimation vector of a vibration signal obtained in real time and a residual error of each monitoring parameter; carrying out fault early warning: constructing a similarity model by using the overall deviation degree and the residual deviation degree, calculating a similarity value of a historical memory matrix, constructing a monitoring threshold value, and performing fault early warning decision making; and carrying out fault diagnosis: constructing a fault contribution rate model by using the residual contribution degree and the frequency amplitude contribution degree for the signal after the early warning is sent out, and diagnosing the fault part of the bearing.

Description

technical field [0001] The invention relates to a bearing fault early warning and diagnosis method, in particular to a method for judging whether an early fault occurs in a bearing and identifying the type of fault by using the improved MSET and frequency spectrum features. Background technique [0002] Rotating machinery occupies an important position in industrial production. Its long-term efficient and stable operation is of great significance to ensure the safe and reliable operation of the system as a whole and reduce the production and maintenance costs of enterprises. Rolling bearings are one of the most commonly used and most easily damaged components of rotating machinery. Once a major failure occurs, the equipment and even the system will not operate normally, causing serious economic or safety problems. Therefore, ensuring the safe operation of rolling bearings is of great significance to the production efficiency and safety of rotating machinery equipment and pro...

AI Technical Summary

Problems solved by technology

However, such methods often require a large amount of fault data to pre-train the model, and the selection of parameters has a great impact on the model accuracy.

However, it is often difficult to obtain complete fault data in the actual processing process, so the practicability is poor.

In addition, the features based on machine learning and mathematical derivation lack physical meaning and are not sensitive enough to early faults in the signal, and the early warning ability is poor

Images