Motor fault diagnosis method based on k-means RBF neural network algorithm

Abstract

The invention relates to a motor fault diagnosis method based on a k-means RBF neural network algorithm. The method comprises that a motor fault sample set is extracted according to a k-means clustering algorithm, and the RBF neural network starts learning training by utilizing the fault sample set; after that the RBF neural network completes training, corresponding output weights of data centers of hidden nodes are not changed any more, the RBF neural network enters a working state then, and the trained RBF neural network records a fault feature via a data center and the connection weight; motor test data is normalized; the normalized motor test data is transmitted to the RBF neural network to form a fault symptom, and the fault symptom is transmitted to the RBF neural network; the transmitted fault symptom is compared with the fault feature recorded in the RBF neural network; and when the similarity between the transmitted fault symptom and the fault feature recorded in the RBF neural network, the RBF neural network transmits a fault type corresponding to the specific fault feature.

Description

technical field [0001] The present invention relates to the field of motor fault diagnosis, more specifically, the present invention relates to a motor fault diagnosis method based on k-means RBF (RadialBasisFunction: Radial Basis Function) neural network algorithm. Background technique [0002] Motors are important electrical equipment in modern production, and they will vibrate to varying degrees during operation. When the motor is running stably, the vibration has a typical characteristic and an allowable limit. However, when there is a fault inside the motor, for example, mechanical fault, unbalanced rotating part or electromagnetic reasons, it will cause unstable vibration of the motor. These vibration faults are very harmful to the motor, will reduce the service life of the motor, and have a major impact on production. [0003] In recent years, extensive research has been carried out on motor fault diagnosis technology at home and abroad. The main methods are as foll...

AI Technical Summary

Problems solved by technology

However, there are certain problems in the application of ANN in fault diagnosis, mainly because ANN needs a large number of representative samples for its learning before use.

Images