Brushless direct current motor sensor fault detection method based on convolutional neural network

Abstract

The invention discloses a brushless direct current motor sensor fault detection method based on a convolutional neural network. The method specifically comprises the following steps: acquiring original data of the brushless direct current motor during operation; converting the original data into a time-frequency spectrogram as a sample set through wavelet transform; marking fault types and fault degree of samples in the training set as known labels of the data samples; establishing a convolutional neural network, inputting the time-frequency spectrogram in the training set into the convolutional neural network, and extracting and classifying features of a previous layer; training a multi-class SVM classifier according to the given label and the extracted features; after training is completed, acquiring the prediction rate of the SVM classifier for each type of faults; and finally, analyzing the system state of the brushless direct current motor, and predicting possible faults. The invention can qualitatively and quantitatively evaluate the operation state of the monitored brushless direct current motor sensor and predict the development trend of the monitored brushless direct current motor sensor; therefore, the fault diagnosis process is more intelligent, and the detection accuracy is higher.

Description

technical field [0001] The invention belongs to the field of motor sensor fault detection, and specifically refers to a method for detecting a brushless DC motor sensor fault based on a convolutional neural network. Background technique [0002] Due to its small size, high efficiency, simple structure, stable operation, and easy control, brushless DC motors are widely used in many fields such as aerospace, industrial vehicles, and household appliances. The commutation of the traditional DC motor is carried out by mechanical commutation, so there are sparks and noises during the commutation process, which makes the life of the motor relatively short, while the commutation control of the brushless DC motor requires a position sensor to obtain the position of the rotor Signals, usually when the motor works in three phases and six states, it is necessary to obtain the position signals of six rotors to control the commutation process in one operation cycle, and obtain the positio...

AI Technical Summary

Problems solved by technology

The application of artificial neural network to sensor fault detection is a research hotspot now, but most of the existing Hall sensor fault diagnosis methods based on artificial neural network are based on BPNN, a classic artificial neural network, and for sensor fault detection, It can only solve the problem of one or two sensor failures. For other failure situations that single-phase sensors are prone to, there has not been too much in-depth discussion on this, and the existing detection methods are relatively complicated and the application occasions are limited.

Images