Surface Defect Image Classification of Lithium Battery Pole Piece Based on Deep Learning

Weisheng MAO; Linsheng LI; Yifan TAO; Wenyi ZHOU

doi:10.1587/transinf.2023EDP7058

Surface Defect Image Classification of Lithium Battery Pole Piece Based on Deep Learning

Weisheng MAO, Linsheng LI, Yifan TAO, Wenyi ZHOU

Full Text Views

0

Cite this

Summary :

Aiming at the problem of low classification accuracy of surface defects of lithium battery pole pieces by traditional classification methods, an image classification algorithm for surface defects of lithium battery pole piece based on deep learning is proposed in this paper. Firstly, Wavelet Threshold and Histogram Equalization are used to preprocess the detect image to weaken influence of noise in non-defect regions and enhance defect features. Secondly, a VGG-InceptionV2 network with better performance is proposed by adding InceptionV2 structure to the improved VGG network structure. Then the original data set is expanded by rotating, flipping and contrast adjustment, and the optimal value of the model hyperparameters is determined by experiments. Finally, the model in this paper is compared with VGG16 and GoogLeNet to realize the recognition of defect types. The results show that the accuracy rate of the model in this paper for the surface pole piece defects of lithium batteries is 98.75%, and the model parameters is only 1.7M, which has certain significance for the classification of lithium battery surface pole piece defects in industry.

Publication: IEICE TRANSACTIONS on Information Vol.E106-D No.9 pp.1546-1555

Publication Date: 2023/09/01

Publicized: 2023/06/12

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2023EDP7058

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Authors

Weisheng MAO
  Shanghai DianJi University
Linsheng LI
  Shanghai DianJi University
Yifan TAO
  Shanghai DianJi University
Wenyi ZHOU
  Shanghai DianJi University

Keyword

lithium battery pole piece, VGG-InceptionV2, defect classification

Cite this

Copy

Weisheng MAO, Linsheng LI, Yifan TAO, Wenyi ZHOU, "Surface Defect Image Classification of Lithium Battery Pole Piece Based on Deep Learning" in IEICE TRANSACTIONS on Information, vol. E106-D, no. 9, pp. 1546-1555, September 2023, doi: 10.1587/transinf.2023EDP7058.
Abstract: Aiming at the problem of low classification accuracy of surface defects of lithium battery pole pieces by traditional classification methods, an image classification algorithm for surface defects of lithium battery pole piece based on deep learning is proposed in this paper. Firstly, Wavelet Threshold and Histogram Equalization are used to preprocess the detect image to weaken influence of noise in non-defect regions and enhance defect features. Secondly, a VGG-InceptionV2 network with better performance is proposed by adding InceptionV2 structure to the improved VGG network structure. Then the original data set is expanded by rotating, flipping and contrast adjustment, and the optimal value of the model hyperparameters is determined by experiments. Finally, the model in this paper is compared with VGG16 and GoogLeNet to realize the recognition of defect types. The results show that the accuracy rate of the model in this paper for the surface pole piece defects of lithium batteries is 98.75%, and the model parameters is only 1.7M, which has certain significance for the classification of lithium battery surface pole piece defects in industry.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023EDP7058/_p

Copy

@ARTICLE{e106-d_9_1546,
author={Weisheng MAO, Linsheng LI, Yifan TAO, Wenyi ZHOU, },
journal={IEICE TRANSACTIONS on Information},
title={Surface Defect Image Classification of Lithium Battery Pole Piece Based on Deep Learning},
year={2023},
volume={E106-D},
number={9},
pages={1546-1555},
abstract={Aiming at the problem of low classification accuracy of surface defects of lithium battery pole pieces by traditional classification methods, an image classification algorithm for surface defects of lithium battery pole piece based on deep learning is proposed in this paper. Firstly, Wavelet Threshold and Histogram Equalization are used to preprocess the detect image to weaken influence of noise in non-defect regions and enhance defect features. Secondly, a VGG-InceptionV2 network with better performance is proposed by adding InceptionV2 structure to the improved VGG network structure. Then the original data set is expanded by rotating, flipping and contrast adjustment, and the optimal value of the model hyperparameters is determined by experiments. Finally, the model in this paper is compared with VGG16 and GoogLeNet to realize the recognition of defect types. The results show that the accuracy rate of the model in this paper for the surface pole piece defects of lithium batteries is 98.75%, and the model parameters is only 1.7M, which has certain significance for the classification of lithium battery surface pole piece defects in industry.},
keywords={},
doi={10.1587/transinf.2023EDP7058},
ISSN={1745-1361},
month={September},}

Copy

TY - JOUR
TI - Surface Defect Image Classification of Lithium Battery Pole Piece Based on Deep Learning
T2 - IEICE TRANSACTIONS on Information
SP - 1546
EP - 1555
AU - Weisheng MAO
AU - Linsheng LI
AU - Yifan TAO
AU - Wenyi ZHOU
PY - 2023
DO - 10.1587/transinf.2023EDP7058
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2023
AB - Aiming at the problem of low classification accuracy of surface defects of lithium battery pole pieces by traditional classification methods, an image classification algorithm for surface defects of lithium battery pole piece based on deep learning is proposed in this paper. Firstly, Wavelet Threshold and Histogram Equalization are used to preprocess the detect image to weaken influence of noise in non-defect regions and enhance defect features. Secondly, a VGG-InceptionV2 network with better performance is proposed by adding InceptionV2 structure to the improved VGG network structure. Then the original data set is expanded by rotating, flipping and contrast adjustment, and the optimal value of the model hyperparameters is determined by experiments. Finally, the model in this paper is compared with VGG16 and GoogLeNet to realize the recognition of defect types. The results show that the accuracy rate of the model in this paper for the surface pole piece defects of lithium batteries is 98.75%, and the model parameters is only 1.7M, which has certain significance for the classification of lithium battery surface pole piece defects in industry.
ER -