Lithium battery unit defect detection method

Abstract

The invention provides a lithium battery unit defect detection method. The main technical scheme is that images of the front side and reverse side of a lithium battery unit are acquired, a Tucker machine supporting method is applied, defected and non-defected lithium battery unit image sets which are preprocessed are trained to obtain weight tensor, core tensor and other parameters, then the unit images to be detected are judged by applying the Tucker machine supporting method according to the parameters obtained through training to complete defect classification, and accordingly detection results are obtained. The lithium battery unit defect detection method utilizes the machine, uses tensor type of weight parameters obtained through Tucker decomposition and can completely retain information and structures of image data, and classification accuracy is improved. The lithium battery unit defect detection method can be widely applied to image based defect detection.

Description

technical field [0001] The invention relates to the field of defect detection in automatic production, in particular to a defect detection method for a lithium battery unit. Background technique [0002] In recent years, with the development of microelectronics technology, miniaturized equipment is increasing day by day. Lithium batteries can be seen everywhere in daily life, and are widely used in digital products such as mobile phones and notebook computers, as well as transportation tools such as automobiles and ships. [0003] The lithium battery unit detected in the present invention adopts the stacking process, and the battery positive and negative plates and the diaphragm are put together for thermal sealing to form a battery unit piece, and a battery stack is formed by superimposing the unit pieces, and the capacity design space is large. The characteristics of this lithium battery production process are: the use of electrode collector material pretreatment process a...

AI Technical Summary

Problems solved by technology

[0005] In view of the high cost and low efficiency of manual detection of lithium battery unit defects at present, which cannot meet the requirements of rapid and high-quality production of lithium batteries, the present invention proposes a lithium battery unit defect detection method, which uses machine vision technology to obtain lithium battery unit Image, after the image preprocessing of the lithium battery cell image, the method of supporting the Tucker machine is used to perform machine learning and classification on the defect, so as to obtain the defect detection result with high accuracy

The invention has the advantages of: on the one hand, it overcomes the problems of low efficiency and low accuracy of manual detection of lithium battery cells; on the other hand, it applies a learning method that supports Tucker machines, decomposes high-dimensional data on images, and maintains the multi-dimensional structure of image data The features in it solve the problem of inaccurate detection results caused by the destruction of the two-dimensional structure of the image in common learning methods such as support vector machines, so that accurate and high-quality lithium battery unit detection results can be obtained and lithium battery products can be improved. quality

Images