浏览全部资源
扫码关注微信
1.电子科技大学 自动化工程学院,四川 成都 611731
2.电子科技大学 长三角研究院(湖州), 浙江 湖州 313001
李福生,博士,教授,研究方向:光谱信息学及人工智能算法研究,E-mail:lifusheng@uestc.edu.cn
收稿日期:2024-10-27,
修回日期:2024-12-06,
录用日期:2024-12-11,
纸质出版日期:2025-06-15
移动端阅览
吕树彬,万优,李福生,杨婉琪.基于XRF的CARS-GAF-MobileNet铝合金牌号分类研究[J].分析测试学报,2025,44(06):1161-1168.
LÜ Shu-bin,WAN You,LI Fu-sheng,YANG Wan-qi.Research on CARS-GAF-MobileNet Aluminum Alloy Grades Classification Based on XRF[J].Journal of Instrumental Analysis,2025,44(06):1161-1168.
吕树彬,万优,李福生,杨婉琪.基于XRF的CARS-GAF-MobileNet铝合金牌号分类研究[J].分析测试学报,2025,44(06):1161-1168. DOI: 10.12452/j.fxcsxb.241027487.
LÜ Shu-bin,WAN You,LI Fu-sheng,YANG Wan-qi.Research on CARS-GAF-MobileNet Aluminum Alloy Grades Classification Based on XRF[J].Journal of Instrumental Analysis,2025,44(06):1161-1168. DOI: 10.12452/j.fxcsxb.241027487.
铝合金以其卓越的特性在工业上得到广泛应用,对铝合金的牌号进行准确分类能够进一步推动制造业等领域的发展。该文提出了一种新的铝合金X射线荧光(XRF)光谱分类框架CARS-GAF-MobileNet(CGM)。首先,采用XRF光谱仪获取铝合金样本的XRF光谱数据;然后,提出一种基于多元素校正的竞争性自适应重加权采样(CARS)算法对数据进行变量筛选;随后,使用格拉姆角场(GAF)将一维光谱转换为二维光谱图像,并通过色彩映射将灰度图转为RGB图;最后,将转换后的二维光谱图作为Mobilenet-V3模型的输入,对铝合金样本进行分类。实验结果表明,所提出的CGM框架的最终分类准确率可以达到94.3%,能够对不同牌号的铝合金样品进行精确识别。CGM是一种具有潜力的铝合金牌号识别框架,对铝合金分类问题具有较好的理论指导和应用价值。
Aluminum alloys are widely used in industry due to their excellent characteristics,and accurate classification of aluminum alloys grades can further promote the development of manufacturing and other fields. In this paper,a new aluminum alloy X-ray fluorescence(XRF) spectral classification framework CARS-GAF-MobileNet(CGM)was proposed. First,an XRF spectrometer was used to obtain XRF spectral data of the aluminum alloy samples. Then,a multi-element calibration-based competitive adaptive reweighted sampling(CARS) was proposed to select variables for the data. Next,the one-dimensional spectra were converted into two-dimensional spectral images using Gramian angular field(GAF),and the grayscale images were converted into RGB images by color mapping. Finally,the converted 2D spectral images were inputs to the Mobilenet-V3 model to classify the aluminum alloy samples. The experimental results showed that the final classification accuracy of the proposed CGM framework could reach 94.3%,which could accurately identify aluminum alloy samples of different grades. The CGM is a promising framework for identifying aluminum alloy grades,and it has superior theoretical guidance and application value for the aluminum alloy classification problem.
Arias L , Balladares E , Parra R , Sbarbaro D , Torres S . Minerals , 2021 , 11 ( 1 ): 1 - 17 .
Chen G X , Zhou S B , Chen X , Liu Y S , Zhao L L , Han W . Spectrosc. Spectral Anal. (陈国喜,周松斌,陈欣,刘忆森,赵路路,韩威. 光谱学与光谱分析), 2022 , 42 ( 12 ): 3811 - 3816 .
Chen J , Ding Y , Hu A , Chen W , Wang Y F , Zhao M L , Shu Y . Opt. Express , 2023 , 31 ( 25 ): 41129 - 41148 .
Liu X Y , Zhang D C , Feng Z Q , Ding J , Yang R Q , Sun S J , Wang K J , Zhu J F , Wei Z Y . Acta Photonica Sin. (刘旭阳,张大成,冯中琦,丁捷,杨润强,孙思佳,王柯俭,朱江峰,魏志义. 光子学报), 2021 , 50 ( 10 ): 173 - 180 .
Ren S , Zhang X , Ren D , Yang X T , Zhang L . J. Instrum. Anal. (任顺,张雄,任东,杨信廷,张力. 分析测试学报), 2020 , 39 ( 7 ): 829 - 837 .
Wang Q Y , Li F S , Jiang X Y , Wu S L , Xie T F , Huang W G . J. Instrum. Anal. (王清亚,李福生,江晓宇,邬书良,谢涛锋,黄温钢. 分析测试学报), 2020 , 39 ( 11 ): 1327 - 1333 .
Lu S B , Li F S , Yang W Q , Zhang Q L , Su J , Zhao R Q , Lu X . J. Anal. Atom. Spectrom. , 2024 , 39 ( 3 ): 942 - 953 .
Yang W Q , Li F S , Zhao Y C , Lu X , Yang S Y , Zhu P F . Anal. Methods , 2022 , 14 ( 40 ): 3944 - 3952 .
Hao W Y , Hao X J , Yang Y W , Liu X D , Liu Y K , Sun P , Sun R . J. Anal. Atom. Spectrom. , 2021 , 36 ( 11 ): 2509 - 2518 .
Zhang K , Zuo W , Chen Y . IEEE Trans. Image Process. , 2017 , 26 ( 7 ): 3142 - 3155 .
Bradbury J , Merity S , Xiong C M , Socher R . The International Conference on Learning Representations . Toulon , France , 2017 : 1 - 12 .
Yang W Q , Li Z Q , Li F S , Lü S B , Fan J J . Spectrosc. Spectral Anal. (杨婉琪,李智琪,李福生,吕树彬,樊佳婧. 光谱学与光谱分析), 2024 , 44 ( 3 ): 670 - 674 .
Tang J , Luo Y B , Li X Y , Chen Y C , Wang P , Lu T , Ji X B , Pang Y Q , Zhu L J . Spectrosc. Spectral Anal. (唐杰,罗彦波,李翔宇,陈云璨,王鹏,卢天,纪晓波,庞永强,朱立军. 光谱学与光谱分析), 2024 , 44 ( 3 ): 731 - 736 .
GB/T 3190 - 2020 . Chemical Composition of Wrought Aluminium and Aluminium Alloys. National Standards of the People's Republic of China(变形铝及铝合金化学成分. 中华人民共和国国家标准) .
Li H D , Liang Y Z , Xu Q S , Cao D S . Anal. Chim. Acta , 2009 , 648 ( 1 ): 77 - 84 .
Yang W Q , Li F S , Zhang Q L , Lu S B . Anal. Chim. Acta , 2024 , 1323 : 343073 .
Li G , Ao J X , Hu J Y , Hu D L , Liu Y , Huang Z Q . Expert Syst. Appl. , 2024 , 237 ( 1 ): 1 - 14 .
Li R J , Wu Y , Wu Q , Dey N , Crespo R G , Shi F Q . Measurement , 2022 , 189 ( 1 ): 1 - 11 .
Ozkok F O , Celik M . Comput. Methods Programs Biomed. , 2021 , 207 ( 1 ): 1 - 20 .
Howard A , Sandler M , Chu G , Chen L C , Chen B , Tan M X , Wang W J , Zhu Y K , Pang R M , Vasudevan V , Le Q V , Adam H . IEEE/CVF International Conference on Computer Vision , 2019 : 1314 - 1324 .
Glorot X , Bordes A , Bengio Y . JMLR Workshop and Conference Proceedings , 2011 : 315 - 323 .
Du J L , Liu Y Y , Yu Y N , Yan W L . Algorithms , 2017 , 10 ( 2 ): 1 - 15 .
Krizhevsky A , Sutskever I , Hinton G E . Commun. ACM , 2017 , 60 ( 6 ): 84 - 90 .
Szegedy C , Liu W , Jia Y . IEEE Conference on Computer Vision and Pattern Recognition , 2015 : 1 - 9 .
Zhang X Y , Zhou X Y , Lin M X , Sun J . IEEE Conference on Computer Vision and Pattern Recognition , 2018 : 6848 - 6856 .
Sandler M , Howard A , Zhu M L , Zhmoginov A , Chen L C . IEEE Conference on Computer Vision and Pattern Recognition , 2018 : 4510 - 4520 .
0
浏览量
59
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构