Accuracy Improvement of Mn Element in Aluminum Alloy by the
Combination of LASSO-LSSVM and Laser-Induced Breakdown
Spectroscopy
DAI Yu-jia1, GAO Xun2*, LIU Zi-yuan1*
1. College of Optical, Mechanical and Electrical Engineering, Zhejiang A&F University, Hangzhou 311300, China
2. School of Physics Science, Changchun University of Science and Technology, Changchun 130022, China
Abstract:Aluminum alloy is an important aerospace equipment material, and its element content is an important factor determining the quality and performance of aluminum alloy materials. The Mn is an important element in aluminum alloy, which can stop the recrystallization process of aluminum alloy and increase the recrystallization temperature. Quantitative determination of aluminum alloy composition is an important part of on-line detection of alloy composition. The signal fluctuation (laser energy fluctuation, plasma instability, sample inhomogeneity, etc.) and self-absorption effect influence the determination of trace elements in aluminum alloys by laser-induced breakdown spectroscopy (LIBS). In order to eliminate the bias caused by the self-absorption effect and signal fluctuation, a new method for detecting alloy content using LIBS technology combined with the LASSO-LSSVM machine learning method is proposed. The Least Absolute Shrinkage and Selection Operator (LASSO) model is used to select the spectral eigenvectors, reducing the dimension of the spectral data to match the training samples, reducing the risk of overfitting, and effectively extracting the most important features that characterize LIBS spectra. The Least squares support vector machine regression (LSSVM) model is used to train the characteristic spectra selected by LASSO. Compared with the internal standard method and partial least squares regression (PLSR), the analysis results show that the model accuracy and accuracy of LASSO-LSSVM were improved. The Mn element regression curve's correlation coefficient (R2) of Mn element regression curve increased from 74.62% to 99.29%. The mean relative error (ARE) decreased from 22.38% to 3.56%, the root mean square error (RMSEC) of the training set decreased from 0.66 wt% to 0.040 wt%, and the root mean square error (RMSEP) of the test set decreased from 0.58 wt% to 0.042 wt%. The LASSO-LSSVM regression model is suitable for complex and high-dimensional spectral data with high uncertainty, and can greatly reduce input spectral data's dimension and redundant information. Therefore, the model reduces the overfitting problem of LSSVM. The results show that LIBS technology and the LASSO-LSSVM regression model can effectively improve the quantitative analysis performance of aluminum alloy materials by LIBS technology, which is a simple, reliable and high-precision method to detect alloy content.
戴宇佳,高 勋,刘子源. LASSO-LSSVM与激光诱导击穿光谱技术结合提高铝合金中Mn成分检测精度研究[J]. 光谱学与光谱分析, 2024, 44(04): 977-982.
DAI Yu-jia, GAO Xun, LIU Zi-yuan. Accuracy Improvement of Mn Element in Aluminum Alloy by the
Combination of LASSO-LSSVM and Laser-Induced Breakdown
Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(04): 977-982.
[1] GAO An-jiang, WANG Gang, QU Xin-lei, et al(高安江,王 刚,曲信磊,等). Recyclable Resources and Circular Economy(再生资源与循环经济), 2015, 8(2): 33.
[2] Xiong H Y, Tan Z R, Zhang R H, et al. Nanotechnology Reviews, 2019, 8(1): 370.
[3] Hong K, Park H, Kim Y, et al. Journal of the Mechanical Behavior of Biomedical Materials, 2019, 98: 213.
[4] Petráčková K, Kondás J, Guagliano M. Journal of Thermal Spray Technology,2017, 26(8): 1888.
[5] YE Mu-zhou(叶慕舟). Metallurgical Analysis(冶金分析), 2015, 35(4): 13.
[6] Cheng A, Yu J, Gao C, et al. IOP Conference Series Materials Science and Engineering, 2020, 780: 062059.
[7] Lahmar L, Benamar M, Melzi M A, et al. X-Ray Spectrometry, 2020, 49(2): 313.
[8] Guo Y M, Guo L B, Li J M, et al. Frontiers of Physics, 2016, 11(5): 114212.
[9] Winefordner J D, Gornushkin I B, Correll T, et al. Journal of Analytical Atomic Spectrometry, 2004, 19(9): 1061.
[10] Naes B E, Umpierrez S, Ryland S, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2008, 63(10): 1145.
[11] Guo L B, Zhang D, Sun L X, et al. Frontiers of Physics, 2021, 16(2): 22500.
[12] Gudmundsson S H, Matthiasson J, Björnsson B M, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2019,158: 105646.
[13] Hou Z, Wang Z, Yuan T, et al. Journal of Analytical Atomic Spectrometry, 2016, 31(3): 722.
[14] Yin H, Hou Z, Zhang L, et al. Journal of Analytical Atomic Spectrometry, 2016, 31: 2384.
[15] Wang Z, Afgan M S, Gu W, et al. TrAC Trends in Analytical Chemistry, 2021, 143: 116385.
[16] LI Ming-liang, DAI Yu-jia, QIN Shuang, et al(李明亮,戴宇佳,秦 爽,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2022, 42(2): 587.
[17] Song X Y, Li K H, Dai K J, et al. Optik, 2022, 249: 168214.
[18] Lü Z J, Yu H X, Sun L X, et al. Analytical Methods, 2022, 14: 1320.
[19] Deng F, Ding Y, Chen Y, et al. Plasma Science and Technology, 2020, 22(7): 074005.
[20] YANG Lin-yu, DING Yu, ZHAN Ye, et al(杨淋玉,丁 宇,战 晔,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2022, 42(6): 1804.
[21] Hastie T J, Tibshirani R J, Friedman J H. Journal of the Royal Statistical Society, 2004, 167(1): 192.