基于ReliefF算法的钛合金电弧增材沉积层尺寸与光谱特性的相关性分析

doi:10.3964/j.issn.1000-0593(2024)07-2002-09

摘要
参考文献
相关文章 (15)

全文: PDF (11508 KB)
输出: BibTeX | EndNote (RIS)

摘要：电弧增材制造具有沉积效率高、成本低、沉积形状和尺寸不受限制等优点，而目前电弧增材制造成型件的成型精度难以精确保证。沉积层尺寸作为评价构件成型质量的标准之一，对判断加工质量以及缺陷补偿至关重要。实时监测电弧增材制造过程中沉积层尺寸的变化状态，对于优化工艺参数，确保增材制造构件的成型质量具有重要意义。电弧光谱信息可以反映电弧状态，电弧状态与成型质量密切相关，因此研究电弧光谱与沉积层尺寸的关系具有重要意义。以钛合金(TC4)材料作为基板和焊丝，电弧等离子体光谱信号为研究对象，研究GTAW增材电弧光谱特性与沉积层尺寸的相关性。搭建光谱采集系统，采集熔池上方、熔池外围、钨极下方不同位置的电弧光谱信号。基于谱线分离性高原则，分别选取波长为404.20 nm的TiⅠ谱线、波长为416.36 nm的TiⅡ谱线、波长为420.20、434.81、480.50和487.98 nm的ArⅡ谱线以及波长为696.54和794.82 nm的ArⅠ谱线，提取其谱线的峰强特征，结合ReliefF算法分别挖掘不同谱线强度特征与沉积层尺寸的相关性。结果表明，三组位置的所有谱线中熔池上方的波长为404.03 nm的TiⅠ元素谱线、416.36 nm的TiⅡ元素谱线以及794.82 nm的ArⅠ元素谱线谱峰强度特征与沉积层尺寸具有较强的相关性。分别研究相同位置的不同谱线峰强特征与沉积层尺寸的相关性差异，结果表明熔池上方与沉积层尺寸相关性最大特征谱线为波长696.54 nm的ArⅠ谱线、熔池外围和钨极下方与沉积层尺寸相关性最大的特征谱线为波长794.82的ArⅠ谱线。为减小随机误差，采用PCA算法将三个电弧光谱采集位置上与沉积层尺寸相关性最大的谱线对应的强度特征进行融合，获得新的融合特征，结合K近邻算法建立沉积层尺寸预测模型，分别计算这四个特征预测样本类别的准确率，发现融合特征预测样本所属的沉积层尺寸的准确率更高。基于此新特征结合阈值分割法实现动态监测沉积层尺寸变化。

关键词：电弧光谱；特征选择；特征融合；ReliefF

Abstract：Arc additive manufacturing has the advantages of high deposition efficiency, low cost, and unrestricted deposition shape and size. However, the dimensional accuracy of the formed parts by arc additive manufacturing is still difficult to guarantee accurately. The size of the deposited layer is one of the criteria for evaluating the quality of component formation, and it is crucial for judging processing quality and defect compensation. Therefore, real-time monitoring of the variation of the deposited layer size during the arc additive manufacturing process is of great significance for optimizing process parameters and ensuring the formation quality of additive manufacturing components. Arc spectral information can reflect the arc state, closely related to the forming quality. Therefore, studying the relationship between arc spectrum and deposited layer size is very important. This study used titanium alloy (TC4) material as the substrate and welding wire, and the arc plasma spectral signals were studied to investigate the correlation between GTAW additive arc spectral characteristics and deposited layer size. Firstly, a spectral acquisition system was constructed to collect arc spectral signals at different positions above the molten pool, around the molten pool, and below the tungsten electrode. Secondly, based on the principle of high spectral line separation, the wavelengths of 404.20 nm TiⅠ spectral line, 416.36 nm TiⅡ spectral line, 420.20, 434.81, 480.50, and 487.98 nm ArⅡ spectral lines, and 696.54 and 794.82 nm ArⅠ spectral lines were selected. The peak intensity features of these spectral lines were extracted, and the ReliefF algorithm was used to explore the correlations between different spectral line intensity features and deposited layer size. The results showed that among all the spectral lines, the peak intensity features of the 404.03 nm TiⅠ element spectral line, 416.36 nm TiⅡ element spectral line, and 794.82 nm ArⅠ element spectral line above the molten pool had a strong correlation with the deposited layer size. At the same time, combining the ReliefF algorithm, the correlations between peak intensity features of different positions and deposited layer size were studied. The results showed that the spectral line with the strongest correlation between the molten pool above and the deposited layer size was the 696.54 nm ArⅠ spectral line, and the spectral line with the strongest correlation between the molten pool around and below the tungsten electrode and the deposited layer size was the 794.82 nm ArⅠ spectral line. Furthermore, to reduce random errors, the PCA algorithm was used to fuse the intensity features corresponding to the three spectral lines with the highest correlation with the deposited layer size, and a new fusion feature was obtained. Then, combining the K-nearest neighbors algorithm, a deposited layer size prediction model was established. The fused feature and the feature values of samples with the highest correlation with the deposited layer size at different positions were extracted, and the accuracy of predicting the sample's category based on these four features was calculated. The results showed higher accuracy for predicting the deposited layer size based on the fused feature. Finally, based on this new feature, combined with the threshold segmentation method, dynamic monitoring of the variation of the deposited layer size was achieved.

Key words：Arc spectrum;Feature selection;Character merger;ReliefF

收稿日期: 2023-08-21 修订日期: 2024-03-19

中图分类号:

TG403

基金资助: 河南省科技研发计划联合基金项目（222103810035），龙门实验室前沿探索课题（LMQYTSKT004），国家自然科学基金青年科学基金项目（51705137）资助

作者简介: 肖笑，女，1985年生，河南科技大学材料科学与工程学院副教授 e-mail: xiaoxiaonov@163.com

引用本文:

肖笑，王雪晴，张弛，葛学元，李芳. 基于ReliefF算法的钛合金电弧增材沉积层尺寸与光谱特性的相关性分析[J]. 光谱学与光谱分析, 2024, 44(07): 2002-2010.
XIAO Xiao, WANG Xue-qing, ZHANG Chi, GE Xue-yuan, LI Fang. Correlation Analysis Between the Size and Spectral Characteristics of Titanium Alloy Arc Additive Deposition Layer Based on ReliefF Algorithm. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(07): 2002-2010.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2024)07-2002-09 或 https://www.gpxygpfx.com/CN/Y2024/V44/I07/2002

[1] HUANG Jian-kang, WU Hao-sheng, YU Xiao-quan, et al(黄健康, 吴昊盛, 于晓全, 等). Material Reports(材料学报), 2023, (14): 1.
[2] HUANG Qiu-shi, LI Liang-qi, GAO Bin-bin(黄秋实, 李良琦, 高彬彬). Defense Manufacturing Technology(国防制造技术), 2012, (5): 26.
[3] Mereddy S, Bermingham M J, StJohn D H, et al. Journal of Alloys and Compounds, 2017, 695: 2097.
[4] Wu B, Pan Z, Ding D, et al. Journal of Manufacturing Processes, 2018, 35: 127.
[5] Davis A E, Breheny C I, Fellowes J, et al. Materials Science and Engineering: A, 2019, 765: 138289.
[6] DONG Chun-lin, TAN Jin-hong, LIN Zhi-cheng, et al(董春林, 谭锦红, 林志成, 等). Metal Working(金属加工), 2020，(7): 16.
[7] NI Cheng, ZHU Ke-yu, FAN Ji-kang, et al(倪程, 朱科宇, 范霁康, 等). Welding & Joining(焊接), 2022, (1): 1.
[8] LI Jun-yue, SONG Yong-lun, LI Huan, et al(李俊岳, 宋永伦, 李桓, 等). Transactions of the China Welding Institution(焊接学报), 2002(6): 5.
[9] ZHANG Zhi-fen, YANG Zhe, REN Wen-jing, et al(张志芬, 杨哲, 任文静, 等). Transactions of the China Welding Institution, 2019, 40(1): 19.
[10] Chen B, Yao Y, Tan C, et al. The International Journal of Advanced Manufacturing Technology, 2018, 96(9-12): 4231.
[11] Yu H, Ye Z, Chen S. The International Journal of Advanced Manufacturing Technology, 2013, 68(9): 2713.
[12] Zhang C, Gao M, Chen C, et al. Additive Manufacturing, 2019, 30: 100869.
[13] Tanaka M, Tsujimura Y, Yamazaki K, et al. Welding in the World，2021, 56(1-2): 30.
[14] Hu Y, Chen H, Liang X, et al. Journal of Manufacturing Processes, 2021, 64: 851.
[15] LIU Ning, FAN Cheng-lei, YANG Chun-li, et al(刘宁, 范成磊, 杨春利, 等). Welding & Joining(焊接), 2013，(6): 30.
[16] Zhang Z F, Yu H W, Lv N, et al. Journal of Materials Processing Technology, 2013, 213(7): 1146.
[17] Zhang Z F, Yang Z, Ren W J, et al. Journal of Materials Processing Technology, 2019, 42: 51.
[18] MA Jing-ying, XUAN Heng-nong(马晶莹, 宣恒农). Computer Applications and Software(计算机应用与软件), 2017, 34(7): 298.
[19] WU Chen-wen, LI Chen-yang, GUO Shu-jin, et al(吴辰文, 李晨阳, 郭叔瑾, 等). Application Research of Computers(计算机应用与研究), 2018, 35(9): 2610.
[20] WANG You-rong, WANG Zhen-wei, et al(王友荣, 王振威, 等). Chinese Hydraulics & Pneumatics(液压与气动), 2015, (12): 18.
[21] YU Zhong-bin, ZHANG Lin, LI Shuo, et al(于忠斌, 张林, 李硕, 等). FAMEN(阀门), 2021，(6): 323.
[22] GU Ying-kui, YANG Zi-qian, ZHU Fan-long(古莹奎, 杨子茜, 朱繁泷). China Mechanical Engineering(中国机械工程), 2015，(11): 1532.