Micro-vibration motor defect failure classification method and device based on convolutional neural network

Abstract

The invention discloses a micro-vibration motor defect failure classification method and a micro-vibration motor defect failure classification device based on a convolutional neural network. Voltage signal images acquired at the two ends of an acquisition resistance connected in series with a micro-vibration motor electrifying loop are input into a trained convolutional neural network model, accurate identification of the micro-vibration motor defect varieties can be realized, the whole process is automatic identification operation, staff does not need to take part in the whole generation process too much, the detection efficiency is greatly improved and the labor production cost is reduced.

Description

technical field [0001] The invention belongs to the technical field of machine defect detection, and relates to a deep learning-based micro-vibration motor defect detection technology, in particular to a convolutional neural network-based micro-vibration motor defect method classification and device. Background technique [0002] Micro vibration motors are widely used in electronic devices such as mobile phones and smart wearables. With the rapid development of interactive electronic equipment in my country, the demand for micro vibration motors is increasing day by day, and the annual demand has reached more than 2 billion. How to quickly detect defective products in the production line has become a bottleneck limiting motor output. [0003] The mechanical vibration caused by the bearing defect of the micro vibration motor will lead to the eccentric oscillation of the air gap width, which will cause the change of the magnetic flux density. The change of the magnetic flux d...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problems of low efficiency and difficulty in ensuring the accuracy of defect detection of micro vibration motors based on artificial vision, the purpose of the present invention is to provide a method and device for classifying defects and faults of micro vibration motors based on convolutional neural network. While accurately classifying micro-vibration motor defects and faults, it simplifies operation difficulty and improves detection efficiency

Images