Deep Network-Assisted Quality Inspection of Laser Welding on Power Battery
Reliable quality control of laser welding on power batteries is an important issue due to random interference in the production process. In this paper, a quality inspection framework based on a two-branch network and conventional image processing is proposed to predict welding quality while outputti...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/21/8894 |
_version_ | 1797631292172402688 |
---|---|
author | Dong Wang Yongjia Zheng Wei Dai Ding Tang Yinghong Peng |
author_facet | Dong Wang Yongjia Zheng Wei Dai Ding Tang Yinghong Peng |
author_sort | Dong Wang |
collection | DOAJ |
description | Reliable quality control of laser welding on power batteries is an important issue due to random interference in the production process. In this paper, a quality inspection framework based on a two-branch network and conventional image processing is proposed to predict welding quality while outputting corresponding parameter information. The two-branch network consists of a segmentation network and a classification network, which alleviates the problem of large training sample size requirements for deep learning by sharing feature representations among two related tasks. Moreover, coordinate attention is introduced into feature learning modules of the network to effectively capture the subtle features of defective welds. Finally, a post-processing method based on the Hough transform is used to extract the information of the segmented weld region. Extensive experiments demonstrate that the proposed model can achieve a significant classification performance on the dataset collected on an actual production line. This study provides a valuable reference for an intelligent quality inspection system in the power battery manufacturing industry. |
first_indexed | 2024-03-11T11:21:46Z |
format | Article |
id | doaj.art-cf83e51825dd4863990ac6d72bce33cf |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T11:21:46Z |
publishDate | 2023-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-cf83e51825dd4863990ac6d72bce33cf2023-11-10T15:12:36ZengMDPI AGSensors1424-82202023-11-012321889410.3390/s23218894Deep Network-Assisted Quality Inspection of Laser Welding on Power BatteryDong Wang0Yongjia Zheng1Wei Dai2Ding Tang3Yinghong Peng4State Key Laboratory of Mechanical Systems and Vibration, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Mechanical Systems and Vibration, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Mechanical Systems and Vibration, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Mechanical Systems and Vibration, Shanghai Jiao Tong University, Shanghai 200240, ChinaState Key Laboratory of Mechanical Systems and Vibration, Shanghai Jiao Tong University, Shanghai 200240, ChinaReliable quality control of laser welding on power batteries is an important issue due to random interference in the production process. In this paper, a quality inspection framework based on a two-branch network and conventional image processing is proposed to predict welding quality while outputting corresponding parameter information. The two-branch network consists of a segmentation network and a classification network, which alleviates the problem of large training sample size requirements for deep learning by sharing feature representations among two related tasks. Moreover, coordinate attention is introduced into feature learning modules of the network to effectively capture the subtle features of defective welds. Finally, a post-processing method based on the Hough transform is used to extract the information of the segmented weld region. Extensive experiments demonstrate that the proposed model can achieve a significant classification performance on the dataset collected on an actual production line. This study provides a valuable reference for an intelligent quality inspection system in the power battery manufacturing industry.https://www.mdpi.com/1424-8220/23/21/8894power batterylaser weldingtwo-branch networkcoordinate attentionHough transformquality inspection |
spellingShingle | Dong Wang Yongjia Zheng Wei Dai Ding Tang Yinghong Peng Deep Network-Assisted Quality Inspection of Laser Welding on Power Battery Sensors power battery laser welding two-branch network coordinate attention Hough transform quality inspection |
title | Deep Network-Assisted Quality Inspection of Laser Welding on Power Battery |
title_full | Deep Network-Assisted Quality Inspection of Laser Welding on Power Battery |
title_fullStr | Deep Network-Assisted Quality Inspection of Laser Welding on Power Battery |
title_full_unstemmed | Deep Network-Assisted Quality Inspection of Laser Welding on Power Battery |
title_short | Deep Network-Assisted Quality Inspection of Laser Welding on Power Battery |
title_sort | deep network assisted quality inspection of laser welding on power battery |
topic | power battery laser welding two-branch network coordinate attention Hough transform quality inspection |
url | https://www.mdpi.com/1424-8220/23/21/8894 |
work_keys_str_mv | AT dongwang deepnetworkassistedqualityinspectionoflaserweldingonpowerbattery AT yongjiazheng deepnetworkassistedqualityinspectionoflaserweldingonpowerbattery AT weidai deepnetworkassistedqualityinspectionoflaserweldingonpowerbattery AT dingtang deepnetworkassistedqualityinspectionoflaserweldingonpowerbattery AT yinghongpeng deepnetworkassistedqualityinspectionoflaserweldingonpowerbattery |