Evaluation of grain size grade of 12Cr1MoV steel based on portable laser-induced breakdown spectroscopy
LU Shengzi1, DONG Meirong*2, TANG Feiqiang2, WANG Lei1, SHANG Zihan2, CAI Junbin2
1. Guangdong Provincial Special Equipment Testing and Research Institute,Foshan 528251,China; 2. College of Electric Power,South China University of Technology,Guangzhou 510640,China
Abstract：Laser-induced breakdown spectroscopy (LIBS) is an atomic spectroscopy technique, and it has shown great potential in the field of metal failure detection.As one of the important indicators to measure metal aging,the detection of grain size grade by LIBS is of great significance for the prediction of failure characteristics.In this study,12Cr1MoV steel,which is widely used in industry,was selected and the grain size grade of the metal was evaluated using a portable LIBS device.Firstly,principal component analysis(PCA),linear discriminant analysis(LDA),recursive feature elimination(RFE)-LDA were used to reduce the dimensionality of the spectral data.Then the metal grain size grade evaluation model was established based on the data after dimensionality reduction using the support vector machine(SVM) and multilayer perceptron(MLP) classification algorithms.The influence of the remaining features on the classification performance of the model after the preliminary RFE screening of the data was explored.The results showed that the combination of RFE and LDA could improve the classification accuracy of the evaluation model,and it was found that the model constructed by further combination with MLP classification algorithm had the highest classification accuracy,which reached 94.05%.The proposed modeling scheme could effectively realize the evaluation of grain size grade of 12Cr1MoV steel based on portable LIBS equipment.
[1] Harmon R S,Lawley C J M,Watts J,et al.Laser-induced breakdown spectroscopy-an emerging analytical tool for mineral exploration[J].Minerals,2019,9(12):718. [2] Vieitez M O,Hedberg J,Launila O,et al.Elemental analysis of steel scrap metals and minerals by laser-induced breakdown spectroscopy[J].Spectrochimica Acta Part B:Atomic Spectroscopy,2005,60(7-8):920-925. [3] Kurihara M,Ikeda K,Izawa Y,et al.Optimal boiler control through real-time monitoring of unburned carbon in fly ash by laser-induced breakdown spectroscopy[J].Applied Optics,2003,42(30):6159-6165. [4] Li W,Lu J,Dong M,et al.Quantitative analysis of calorific value of coal based on spectral preprocessing by laser-induced breakdown spectroscopy (LIBS)[J].Energy & Fuels,2018,32(1):24-32. [5] Mishra P,Rai P K,Kumar R,et al.Monitoring of minerals level in dialysate during hemodialysis treatment of kidney patients using LIBS technique[J].Lasers in Medical Science,2023,38(7):165. [6] Yahiaoui K,Aberkane S M,Naitbouda A.Correlation between surface hardness of α-alumina samples and their spectroscopic parameters[J].Materials Chemistry and Physics,2021,259(2):124045 [7] Lu S,Dong M,Chen Q,et al.Temporal-spatial resolved laser-induced breakdown spectroscopy of T91 steel of different aging grades[J].Spectrochimica Acta Part B:Atomic Spectroscopy,2019,151(9):1-11. [8] Lu S,Dong M,Huang J,et al.Estimation of the aging grade of T91 steel by laser-induced breakdown spectroscopy coupled with support vector machines[J].Spectrochimica Acta Part B:Atomic Spectroscopy,2018,140(2):35-43. [9] Pořízka P,Klus J,Hrdlička A,et al.Impact of laser-induced breakdown spectroscopy data normalization on multivariate classification accuracy[J].Journal of Analytical Atomic Spectrometry,2017,32(2):277-288. [10] 卢伟业,董美蓉,白凯杰,等.基于便携式LIBS的T91金属老化等级评估[J/OL].激光与光电子学进展. https://kns.cnki.net/kcms/detail/31.1690.TN.20230309.2156.140.html. [11] 白凯杰,董美蓉,尚子瀚,等.基于特征谱线比与时间分辨激光诱导击穿光谱的金属老化等级评估[J].冶金分析,2023,43(7):29-36. BAI Kaijie,DONG Meirong,SHANG Zihan,et al.Evaluation of metal aging grade based on characteristic spectral line ratio and time-resolved laser-induced breakdown spectroscopy[J].Metallurgical Analysis,2023,43(7):29-36. [12] 王贞,刘静,鲁修宇,等.热处理工艺对 12Cr1MoV 钢组织性能的影响[J].热处理技术与装备,2012,33(2):10-14. WANG Zhen,LIU Jing,LU Xiuyu,et al.Effect of heat treatment process on microstructure properties of 12Cr1MoV steel[J].Heat Treatment Technology and Equipment,2012,33(2):10-14. [13] 李雪峰,王春芬,王嘉敏.回火马氏体与回火索氏体辨析[J].热处理,2012,27(4):12-16. LI Xuefeng,WANG Chunfen,WANG Jiamin.Discrimination of tempered martensite from tempered sorbite[J].Heat Treatment,2012,27(4):12-16. [14] 陆盛资.基于机器学习的激光诱导击穿光谱应用于金属受热面失效检测的研究[D].广州:华南理工大学,2019. [15] 戴沅,李军,钟万里,等.不同金相组织12Cr1MoV的等离子体特性[J].光学学报,2014,34(3):317-322. DAI Yuan,LI Jun,ZHONG Wanli,et al.Plasma characteristics of different metallographic of steel 12Cr1MoV[J].Acta Optica Sinica,2014,34(3):317-322. [16] Raymond V J,Raj R J R,Retna J.Investigation of android malware with machine learning classifiers using enhanced PCA algorithm[J].Comput. Syst. Sci. Eng.,2023,44(3):2147-2163. [17] Lee J W,Han D H.Data analysis of psychological approaches to soccer research:Using LDA topic modeling[J].Behavioral Sciences,2023,13(10):787. [18] Nakao H,Imaoka M,Hida M,et al.Determination of individual factors associated with hallux valgus using SVM-RFE[J].BMC Musculoskeletal Disorders,2023,24(1):534. [19] Vapnik V N.An overview of statistical learning theory[J].IEEE Transactions on Neural Networks,1999,10(5):988-999. [20] Ali H,Muthudoss P,Chauhan C,et al.Machine learning-enabled NIR spectroscopy.Part 3:Hyperparameter by design (HyD) based ANN-MLP optimization,model generalizability,and model transferability[J].AAPS PharmSciTech,2023,24(8):254.
