A motor health monitoring and abnormal diagnosis method based on feature selection and Mahalanobis distance

Abstract

The invention provides an electric motor health monitoring and abnormity diagnostic method based on feature selection and the mahalanobis distance. The method includes the first step of conducting data acquisition on vibration signals, current signals and rotating speed signals of electric motors, conducting feature computing on the signals, constructing feature spaces and selecting feature vectors for calculation of the mahalanobis distance in a feature selection method, the second step of the mahalanobis distances of the electric motors in a normal operation state and constructing mahalanobis spaces indicating the normal operation state of the electric motors, and the third step of calculating the mahalanobis distances according to signals of tested electric motors with unknown health conditions with reference to statistic parameters of the motors in the normal operation state and judging the health condition of the tested electric motors through comparison of the mahalanobis spaces. Through the electric motor health monitoring and abnormity diagnostic method based on feature selection and the mahalanobis distance, since the signals of the electric motors in the normal operation state are used for constructing the mahalanobis spaces, health monitoring and abnormity diagnosis on the motors in an unknown operation state can be effectively achieved.

Description

technical field [0001] The invention belongs to the technical field of motor fault diagnosis, and in particular relates to a method for health monitoring and abnormality diagnosis of a motor. Background technique [0002] Motors are widely used in energy and chemical industry, transportation, medical equipment, office equipment and other fields. The working state of the motor is directly or indirectly related to the reliability of the equipment in these fields. Therefore, it is very urgent to implement health monitoring and abnormal diagnosis. Motor faults can be roughly divided into mechanical faults, such as bearing faults, rotor faults and stator faults; and electromagnetic faults, such as circuit, magnetic circuit system faults and insulation system faults. The existing motor fault diagnosis technology includes current analysis, vibration analysis, acoustic emission signal analysis and temperature analysis. The disadvantage is that it is difficult to realize the healt...

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the shortcomings of the existing fault diagnosis technology that it is difficult to realize the health monitoring and abnormal diagnosis of the motor under the unknown working state without a detailed understanding of the fault mode of the motor, the present invention provides a method that only needs to collect After the motor signal is used for training and constructed into a Mahalanobis space, it can effectively realize the motor fault diagnosis method based on feature selection and Mahalanobis distance for health monitoring and abnormal diagnosis of motors in unknown working states

Images