Lithium battery electrode surface defect detection method based on background normalization and centralized compensation algorithm

Abstract

The invention discloses a lithium battery electrode surface defect detection method based on background standardization and centralized compensation algorithms, which is realized through a measurement system constructed by lighting equipment, line array cameras, transmission devices, labeling machines, industrial computers and PLCs, specifically The implementation steps are as follows: use a line array camera to obtain the surface image of the lithium battery electrode; then use the background normalization algorithm to preprocess the electrode surface image; then perform rough defect detection, and perform automatic threshold segmentation on the preprocessed electrode surface image to obtain defects that may exist Finally, accurate detection of defects is carried out, and the automatic centralized compensation algorithm is used to accurately detect the areas where defects may exist, so as to obtain defect images. The lithium battery electrode surface defect detection method proposed by the present invention can meet the requirements of online real-time defect detection in the actual lithium battery industrial production process on the premise of ensuring the detection effect of the lithium battery electrode surface defect, and improve the production efficiency of the lithium battery.

Description

technical field [0001] The invention relates to the technical field of machine vision detection, in particular to a method for detecting surface defects of lithium battery electrodes based on background standardization and centralized compensation algorithms. Background technique [0002] Due to the advantages of high energy density and fast charging and discharging speed, lithium-ion batteries occupy a dominant position in the portable electronic communication equipment market, and gradually expand to the field of electric tools. At present, electrical appliances requiring portable power such as mobile phones, notebook computers, and micro-cameras have become an indispensable part of people's lives. In terms of power supplies, lithium-ion batteries are selected as the mainstream of the market without exception. According to statistics, the global mobile phone production is nearly 2.1 billion units per year, and the global annual production of notebook computers is about 150...

AI Technical Summary

Problems solved by technology

[0004] At present, there are many defect detection methods based on machine vision, and some methods are only suitable for defects with obvious gray value differences with the surrounding background; some defect detection methods have good detection results in actual situations, but are sensitive to noise and take too much time For example, a defect detection method in the frequency domain—a defect detection method based on Fourier transform combined with various filters such as Gaussian filters, this method can remove the texture background and make the defect become Obviously, but the amount of calculation is relatively large, and the calculation time is long, which cannot meet the requirements of online real-time detection in industry; in order to meet the requirements of online real-time detection in industrial production, researchers in related fields have proposed some methods to speed up defect detection. Algorithms such as Fast Fourier Transform (FFT) algorithm, Fast Regularized Metric (FRM) algorithm, Local Neighborhood Analysis (LNA) algorithm, etc.

However, the current detection methods used in the actual lithium battery industrial production for the detection of lithium battery electrode surface defects are not very mature. Well, even some small and medium-sized enterprises mainly use manual inspection to detect defects on the surface of lithium battery electrodes.

Images