Cargando…

Grad-MobileNet: A Gradient-Based Unsupervised Learning Method for Laser Welding Surface Defect Classification

Deep learning technology has advanced rapidly and has started to be applied for the detection of welding defects. In the manufacturing process of power batteries for new energy vehicles, welding defects may occur due to the high directivity, convergence, and penetration of the laser beam. The accura...

Descripción completa

Detalles Bibliográficos
Autores principales: Xiao, Sizhe, Liu, Zhenguo, Yan, Zhihong, Wang, Mingquan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10181709/
https://www.ncbi.nlm.nih.gov/pubmed/37177766
http://dx.doi.org/10.3390/s23094563
_version_ 1785041639546290176
author Xiao, Sizhe
Liu, Zhenguo
Yan, Zhihong
Wang, Mingquan
author_facet Xiao, Sizhe
Liu, Zhenguo
Yan, Zhihong
Wang, Mingquan
author_sort Xiao, Sizhe
collection PubMed
description Deep learning technology has advanced rapidly and has started to be applied for the detection of welding defects. In the manufacturing process of power batteries for new energy vehicles, welding defects may occur due to the high directivity, convergence, and penetration of the laser beam. The accuracy of deep learning prediction relies heavily on big data, but balanced big data of welding defects is hard to acquire at the battery production site. In this paper, the authors construct a dataset named RIAM, which consists of images captured from an industrial environment for laser welding of power battery modules. RIAM contains four types of images: Normality, Lack of fusion, Surface porosity, and Scaled surface. The characteristics of RIAM are carefully considered in the application scenarios. Moreover, this paper proposes a gradient-based unsupervised model named Grad-MobileNet, which can be trained with only a few normal images and can extract the feature gradients of the input images. Welding defects can then be classified by the gradient distribution. This model is based on MobileNetV3, which is a lightweight convolutional neural network (CNN), and achieves 99% accuracy, which is higher than the accuracy expected from supervised learning.
format Online
Article
Text
id pubmed-10181709
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-101817092023-05-13 Grad-MobileNet: A Gradient-Based Unsupervised Learning Method for Laser Welding Surface Defect Classification Xiao, Sizhe Liu, Zhenguo Yan, Zhihong Wang, Mingquan Sensors (Basel) Article Deep learning technology has advanced rapidly and has started to be applied for the detection of welding defects. In the manufacturing process of power batteries for new energy vehicles, welding defects may occur due to the high directivity, convergence, and penetration of the laser beam. The accuracy of deep learning prediction relies heavily on big data, but balanced big data of welding defects is hard to acquire at the battery production site. In this paper, the authors construct a dataset named RIAM, which consists of images captured from an industrial environment for laser welding of power battery modules. RIAM contains four types of images: Normality, Lack of fusion, Surface porosity, and Scaled surface. The characteristics of RIAM are carefully considered in the application scenarios. Moreover, this paper proposes a gradient-based unsupervised model named Grad-MobileNet, which can be trained with only a few normal images and can extract the feature gradients of the input images. Welding defects can then be classified by the gradient distribution. This model is based on MobileNetV3, which is a lightweight convolutional neural network (CNN), and achieves 99% accuracy, which is higher than the accuracy expected from supervised learning. MDPI 2023-05-08 /pmc/articles/PMC10181709/ /pubmed/37177766 http://dx.doi.org/10.3390/s23094563 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Xiao, Sizhe
Liu, Zhenguo
Yan, Zhihong
Wang, Mingquan
Grad-MobileNet: A Gradient-Based Unsupervised Learning Method for Laser Welding Surface Defect Classification
title Grad-MobileNet: A Gradient-Based Unsupervised Learning Method for Laser Welding Surface Defect Classification
title_full Grad-MobileNet: A Gradient-Based Unsupervised Learning Method for Laser Welding Surface Defect Classification
title_fullStr Grad-MobileNet: A Gradient-Based Unsupervised Learning Method for Laser Welding Surface Defect Classification
title_full_unstemmed Grad-MobileNet: A Gradient-Based Unsupervised Learning Method for Laser Welding Surface Defect Classification
title_short Grad-MobileNet: A Gradient-Based Unsupervised Learning Method for Laser Welding Surface Defect Classification
title_sort grad-mobilenet: a gradient-based unsupervised learning method for laser welding surface defect classification
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10181709/
https://www.ncbi.nlm.nih.gov/pubmed/37177766
http://dx.doi.org/10.3390/s23094563
work_keys_str_mv AT xiaosizhe gradmobilenetagradientbasedunsupervisedlearningmethodforlaserweldingsurfacedefectclassification
AT liuzhenguo gradmobilenetagradientbasedunsupervisedlearningmethodforlaserweldingsurfacedefectclassification
AT yanzhihong gradmobilenetagradientbasedunsupervisedlearningmethodforlaserweldingsurfacedefectclassification
AT wangmingquan gradmobilenetagradientbasedunsupervisedlearningmethodforlaserweldingsurfacedefectclassification