Lithium battery surface defect detection method based on generative adversarial network

Abstract

The invention relates to a lithium battery surface defect detection method based on a generative adversarial network, which is mainly used for detecting surface image defects of a soft package lithiumion battery. According to a lithium ion surface image acquired by a high-precision CMOS industrial camera, the lithium battery surface defect detection method utilizes a generative adversarial network to perform fitting on a normal surface of the lithium ion surface image. Aiming at the detection of various defects on the surface of the lithium ion battery, a pre-trained generator is used for reconstructing a test image, and difference operation is carried out by utilizing the reconstructed image and the test image to obtain a region of interest; and by binarizing the difference image and screening the size of a connected domain, the lithium battery surface defect detection method eliminates a false detection area. Through the lithium battery surface defect detection method, the defect area on the surface of the lithium ion battery can be accurately judged, and defect detection is realized.

Description

technical field [0001] The invention belongs to the technical field of defect detection, and in particular relates to a method for detecting surface defects of a lithium battery based on a generated confrontation network. Background technique [0002] Lithium-ion battery is an environmentally friendly battery with long life, large storage capacity and fast charging and discharging speed. It is widely used in portable information devices such as mobile phones, and gradually extends to the field of power tools. With the popularization and application of Internet technology and the development of environmentally friendly alternative tools, the demand for lithium ions continues to increase, which is of great significance to the development of my country's informatization and green travel. [0003] In the production process of lithium-ion batteries, due to the imperfect production technology and product handling process, lithium-ion batteries, especially soft-pack lithium-ion bat...

AI Technical Summary

Problems solved by technology

[0006] The present invention solves the deficiency of the current method for detecting defects on the surface of soft-packed lithium-ion batteries. The problem to be solved by the present invention is: the defect detection technology for soft-packed lithium-ion batteries in the prior art relies on a large amount of label data, which greatly increases the waste of manpower and material resources, and Detection accuracy needs to be improved

Images