Keyhole Depth Prediction in Laser Deep Penetration Welding of Titanium Alloy Based on Spectral Information

Laser deep penetration welding has been widely applied in industrial fields. However, keyhole depth during the welding process significantly affects the service performance of final products. Based on the spectral signals generated in the laser welding process, this study employs a Long Short-Term M...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunqian Li, Yanfeng Gao, Hao Pan, Donglin Tao, Hua Zhang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Metals
Subjects:
Online Access:https://www.mdpi.com/2075-4701/15/5/527
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850125981404102656
author Yunqian Li
Yanfeng Gao
Hao Pan
Donglin Tao
Hua Zhang
author_facet Yunqian Li
Yanfeng Gao
Hao Pan
Donglin Tao
Hua Zhang
author_sort Yunqian Li
collection DOAJ
description Laser deep penetration welding has been widely applied in industrial fields. However, keyhole depth during the welding process significantly affects the service performance of final products. Based on the spectral signals generated in the laser welding process, this study employs a Long Short-Term Memory (LSTM) neural network to predict keyhole depth in titanium alloy welding. A coaxial plasma optical information acquisition system is established to collect spectral signals emitted from the welding plasma and analyze the relationship between keyhole depth and plasma spectral features. By analyzing the spectral signals and calculating the plasma temperature, the mapping model between the plasma temperature and keyhole depth is built. The LSTM network prediction results show that the average relative error between the predicted and actual values is 2.31%, which demonstrates that the method proposed in this study has high accuracy for predicting keyhole depth in laser deep penetration welding.
format Article
id doaj-art-99424303fd97404daaac0ded408c64f4
institution OA Journals
issn 2075-4701
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Metals
spelling doaj-art-99424303fd97404daaac0ded408c64f42025-08-20T02:34:01ZengMDPI AGMetals2075-47012025-05-0115552710.3390/met15050527Keyhole Depth Prediction in Laser Deep Penetration Welding of Titanium Alloy Based on Spectral InformationYunqian Li0Yanfeng Gao1Hao Pan2Donglin Tao3Hua Zhang4School of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaSchool of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaEngineering Research Center of Micro-Nano and Intelligent Manufacturing, Ministry of Education, Kaili 556011, ChinaSchool of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaSchool of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaLaser deep penetration welding has been widely applied in industrial fields. However, keyhole depth during the welding process significantly affects the service performance of final products. Based on the spectral signals generated in the laser welding process, this study employs a Long Short-Term Memory (LSTM) neural network to predict keyhole depth in titanium alloy welding. A coaxial plasma optical information acquisition system is established to collect spectral signals emitted from the welding plasma and analyze the relationship between keyhole depth and plasma spectral features. By analyzing the spectral signals and calculating the plasma temperature, the mapping model between the plasma temperature and keyhole depth is built. The LSTM network prediction results show that the average relative error between the predicted and actual values is 2.31%, which demonstrates that the method proposed in this study has high accuracy for predicting keyhole depth in laser deep penetration welding.https://www.mdpi.com/2075-4701/15/5/527laser deep penetration weldingkeyhole depth predictionLSTM modeltitanium alloy
spellingShingle Yunqian Li
Yanfeng Gao
Hao Pan
Donglin Tao
Hua Zhang
Keyhole Depth Prediction in Laser Deep Penetration Welding of Titanium Alloy Based on Spectral Information
Metals
laser deep penetration welding
keyhole depth prediction
LSTM model
titanium alloy
title Keyhole Depth Prediction in Laser Deep Penetration Welding of Titanium Alloy Based on Spectral Information
title_full Keyhole Depth Prediction in Laser Deep Penetration Welding of Titanium Alloy Based on Spectral Information
title_fullStr Keyhole Depth Prediction in Laser Deep Penetration Welding of Titanium Alloy Based on Spectral Information
title_full_unstemmed Keyhole Depth Prediction in Laser Deep Penetration Welding of Titanium Alloy Based on Spectral Information
title_short Keyhole Depth Prediction in Laser Deep Penetration Welding of Titanium Alloy Based on Spectral Information
title_sort keyhole depth prediction in laser deep penetration welding of titanium alloy based on spectral information
topic laser deep penetration welding
keyhole depth prediction
LSTM model
titanium alloy
url https://www.mdpi.com/2075-4701/15/5/527
work_keys_str_mv AT yunqianli keyholedepthpredictioninlaserdeeppenetrationweldingoftitaniumalloybasedonspectralinformation
AT yanfenggao keyholedepthpredictioninlaserdeeppenetrationweldingoftitaniumalloybasedonspectralinformation
AT haopan keyholedepthpredictioninlaserdeeppenetrationweldingoftitaniumalloybasedonspectralinformation
AT donglintao keyholedepthpredictioninlaserdeeppenetrationweldingoftitaniumalloybasedonspectralinformation
AT huazhang keyholedepthpredictioninlaserdeeppenetrationweldingoftitaniumalloybasedonspectralinformation