Surface defect detection of cylindrical lithium-ion battery by multiscale image augmentation and classification

Abstract

While deep convolutional neural networks (CNNs) have recently made large advances in AI, the need of large datasets for deep CNN learning is still a barrier to many industrial applications where only limited data samples can be offered for system developments due to confidential issues. We thus propose an approach of multi-scale image augmentation and classification for training deep CNNs from a small dataset for surface defect detection on cylindrical lithium-ion batteries. In the proposed Lithium-ion battery Surface Defect Detection (LSDD) system, an augmented dataset of multi-scale patch samples generated from a small number of lithium-ion battery images is used in the learning process of a two-stage classification scheme that aims to differentiate defect image patches of lithium-ion batteries in the first stage and to identify specific defect types in the second stage. The LSDD approach is an efficient prototyping method of defect detection from limited training images for quick system evaluation and deployment. The experiments show that, based on only 26 source images, the proposed LSDD (i) constructs two augmented multi-scale datasets of 19,309 and 6889 image patches for training and test, respectively, (ii) achieves 93.67% accuracy for discriminating defect image patches in the first stage, and (iii) reaches 90.78% mean precision rate and 93.89% mean recall rate for defect type identification in the second stage. Our two-stage classification scheme has higher defect detection sensitivity than an intuitive one-stage classification scheme by 0.69%, and outperforms the one-stage scheme in identifying specific defect types. For comparing with YOLOv3 detector, less defect misdetections are observed in our approach as well.

Research on precision visual inspection technology based on new energy battery manufacturing

“…Because the processing goal of this paper is to extract the discrete contour image, the above formula can not be directly applied with the discrete contour curvature of the solution problem, need to be combined with the demand for the improvement of the above formula. For the processing of discrete dot matrix problems, the idea of difference is often used in mathematics [12] . The difference method approximates the derivative of the smooth curve by solving the difference quotient, which can be applied to the solution of discrete contour curvature.…”

Research on Artificial Intelligence Detection Method of Lithium Battery Surface Defects for Production Line

“…Harshad K. Dandage proposed a LSDD method for multi-scale image enhancement and classification. Using the enhanced data set of multi-scale patch samples generated from a small number of lithium-ion battery images, the recognition accuracy can reach 90.78% and the recall rate can reach 93.89% on the basis of only 26 source images [3]. Grazia Lo Sciuto, proposed a new method for defect classification of organic solar cells, and used a new feature extraction algorithm and EBNN with innovative pruning algorithm to identify and diagnose defects [4].…”

A real-time method for detecting bottom defects of lithium batteries based on an improved YOLOv5 model

“…Badmos et al [5] used deep learning computer vision methods to evaluate the quality of lithium-ion battery electrodes for automated detection of microstructural defects from light microscopy images of the sectioned cells. Dandage et al [6] proposed an approach of multi-scale image augmentation and classification for training deep convolutional neural networks (CNNs) from a small dataset for surface defect detection on cylindrical lithium-ion batteries. Peng et al [7] proposed a detection method based on x-ray technology and CNN for internal wrinkles detection in lithium-ion batteries.…”