Abnormal detection method, device, equipment and storage medium for cotton spinning paper cylinder

Abstract

The invention belongs to the technical field of deep learning, and discloses an abnormal detection method, device, equipment and storage medium of a cotton spinning paper cylinder. The method includes: obtaining normal cotton spinning paper drum images and abnormal cotton spinning paper drum images; dividing the abnormal cotton spinning paper drum images into a test set, and dividing the normal cotton spinning paper drum images into a training set and a testing set; training an autoencoder according to the training set , to obtain the trained autoencoder; test the trained autoencoder according to the test set to obtain the target autoencoder; obtain the image of the cotton spinning paper tube to be tested, and input the image of the cotton spinning paper tube to be tested into the target autoencoder, It is judged whether the cotton spinning paper cylinder to be tested corresponding to the image of the cotton spinning paper cylinder to be tested is an abnormal cotton spinning paper cylinder. Through the above method, the self-supervised learning autoencoder is trained based on the normal image to obtain the target autoencoder, and finally the target autoencoder is used to detect the image of the cotton spinning paper tube to be tested, so as to accurately detect the abnormal cotton spinning paper tube.

Description

Abnormal detection method, device, equipment and storage medium of cotton spinning paper tube technical field The present invention relates to deep learning technical field, relate in particular to a kind of abnormal detection method, device, device of cotton spinning paper tube. equipment and storage media. Background technique [0002] In the production and processing process of the product, the abnormal model is the key factor affecting the product yield. how to cull Abnormal models of products are a major problem that plagues enterprises. However, the current method of removing anomalous models mainly relies on human Sea tactics, carry out a net-type investigation. On the one hand, this kind of method consumes a lot of manpower, which leads to increased production costs; on the other hand, it does not There are slight differences in the standards for measuring abnormality by the same quality inspector, which is easy to cause leakage. [0003] Nowadays, the use o...

AI Technical Summary

Problems solved by technology

[0007] The main purpose of the present invention is to provide an abnormal detection method, device, equipment and storage medium for cotton spinning paper tubes, aiming to solve the technical problem of how to accurately screen out abnormal cotton spinning paper tubes in the prior art

Images