摘要
为了实现受操作空间限制和辐射环境下,高温气冷堆蒸汽发生器传热管道堵管钨极惰性气体保护电弧焊(tungsten inert gas welding, TIG)的质量监测,搭建了一套基于光纤光谱仪的TIG焊接过程实时监测系统,用于核电传热管道堵管TIG焊接熔深监测.试验研究采用该系统采集电弧光谱,利用主成分分析法获取不同焊缝熔深的光谱主成分特征,创新性提出了一种ATT-L2R-BiLSTM深度学习模型,实现了堵管TIG焊接过程中焊缝熔深的分类识别.结果表明,实验室条件下模型准确率可达92.61%,比Bi-LSTM网络准确率提高5.11%,该模型在核电蒸汽发生器堵管验证平台进行了测试和验证,准确率达到99.26%,最终,实现了光谱信息不完备下TIG焊接质量特征深度挖掘,以及TIG焊接熔深的精准评估.
In order to monitor the quality of TIG welding for blocked tube welding of high-temperature gas-cooled reactor steam generators under the constraints of operation space and radiation environment,a real-time monitoring system based on a fiber optic spectrometer for TIG welding process was developed for monitoring the depth of penetration during welding.This study used the system to collect arc spectra and utilized Principal Component Analysis to obtain the spectral principal components of different weld penetration depths.An innovative ATT-L2R-BiLSTM deep learning model was proposed to achieve classification and recognition of weld penetration depth during blocked tube TIG welding.The results show that the model achieved an accuracy of 92.61%under laboratory conditions,which is 5.11%higher than that of the Bi-LSTM network.The model was tested and verified on a blocked tube verification platform for nuclear power steam generators,achieving an accuracy of 99.26%.Finally,deep mining of welding quality features and precise evaluation of weld penetration depth during TIG welding were achieved under incomplete spectral information.
作者
白子键
李治文
张志芬
秦锐
张帅
徐耀文
温广瑞
BAI Zijian;LI Zhiwen;ZHANG Zhifen;QIN Rui;ZHANG Shuai;XU Yaowen;WEN Guangrui(National Key Laboratory of Aeronautical Power Systems and Plasma Technology,Xi'an Jiaotong University,Xi'an,710049,China;School of Mechanical Engineering,Xi'an Jiaotong University,Xi'an,710049,China;Xi’an Thermal Power Research Institute Co.,Ltd.,Xi'an,710054,China)
出处
《焊接学报》
EI
CAS
CSCD
北大核心
2024年第5期8-19,共12页
Transactions of The China Welding Institution
关键词
电弧光谱
钨极惰性气体保护焊
主成分分析法
在线监测
深度学习
arc spectroscopy
tungsten inert gas shielded welding
principal component analysis
online monitoring
deep learning
