Quantitative Analysis of Polycyclic Aromatic Hydrocarbons by Raman Spectroscopy Based on ML-PCA-BP Model
YIN Xiong-yi1, SHI Yuan-bo1*, WANG Sheng-jun2, JIAO Xian-he2, KONG Xian-ming2
1. College of Artificial Intelligence and Software, Liaoning Petrochemical University, Fushun 113001, China
2. College of Petroleum and Chemical Engineering, Liaoning Petrochemical University, Fushun 113001, China
Abstract:Pyrene, a kind of polycyclic aromatic hydrocarbons (PAHs), widely exists in the natural environment. It has strong lipophilicity and carcinogenic effect on the human body. Therefore, the rapid analysis of pyrene content in edible oil has far-reaching significance for quality control. The quantitative analysis of polycyclic aromatic hydrocarbons using Raman spectroscopy and artificial intelligence algorithm is a current research hotspot. One milliliter of edible oil is mixed with pyrene liquid with different fixed concentrations to make samples, and then a thin-layer chromatography plate and gold particles are made. The experiment is carried out by combining thin-layer chromatography, and surface-enhanced Raman scattering (SERS) spectrum to obtain the spectral data. The adaptive iterative weighted penalty least square algorithm is selected for preprocessing, Then the Multi parameter-Principal Component Analysis- Back Propagation Neural Network model was used for quantitative analysis. Firstly, two characteristic peaks are selected in the preprocessed spectrum for peak fitting, and the parameters such as height, half-width, height and area of characteristic peaks are obtained. Normalized the Raman data of the two characteristic peaks and the parameters obtained by fitting, and then use the principal component analysis to obtain the key parameters. The obtained key parameters are input into the BP neural network based on L2 regularization as the input layer to output the predicted concentration. The experimental results show that the R2 determination coefficient of the test set is 0.58 and the root mean square error (RMSEC) is 1.85; The linear regression is used to fit the law between the characteristic peak area and pyrene concentration. The final predicted pyrene concentration has an R2 determination coefficient of 0.26, and a root mean square error (RMSEC) of 2.28; For the pyrene concentration predicted by the Multi parameter-Principal Component Analysis-Back Propagation Neural Network model, the R2 determination coefficient of the test set is 0.99, and the root mean square error (RMSEC) is 0.31. The multi-parameter principal component analysis-back propagation neural network model has higher measurement accuracy and less error. The model is aimed at the nonlinear and high-dimensional relationship between spectral data information and sample concentration. The prediction accuracy and modeling efficiency are higher than similar comparison algorithms. The model fits the characteristic peak to obtain the key variables and takes the Raman displacement of the variable and the characteristic peak as the characteristic vector, so the characteristic vector is sufficient. The model uses PCA to extract the nonlinear characteristics of the Raman spectrum and adopts the advantages of strong generalization based on L2 regularization BP neural network to prevent overfitting, so that it can predict the concentration of naphthalene more accurately and quickly.
尹雄翼,石元博,王胜君,焦仙鹤,孔宪明. 基于ML-PCA-BP模型的多环芳烃拉曼光谱定量分析[J]. 光谱学与光谱分析, 2023, 43(03): 861-866.
YIN Xiong-yi, SHI Yuan-bo, WANG Sheng-jun, JIAO Xian-he, KONG Xian-ming. Quantitative Analysis of Polycyclic Aromatic Hydrocarbons by Raman Spectroscopy Based on ML-PCA-BP Model. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 861-866.
[1] ZHANG Ting-hui,YU Jie,YE Zhang-lin,等(张婷慧, 宇 洁, 叶张林, 等). Journal of Geomatics Science and Technology(测绘科学技术学报), 2019, 36(1): 56.
[2] RAO Li-bo,PANG Tao,JI Ran-shi, et al(饶利波, 庞 涛, 纪然仕, 等). Laser & Optoelectronics Progress(激光与光电子学进展), 2019, 56(11): 113001.
[3] Fadillah G, Saputra O A, Saleh T A. Trends in Environmental Analytical Chemistry, 2020, 26: e00084.
[4] Kamran M, Haroon M, Popoola S A, et al. Journal of Molecular Liquids, 2019, 273: 536.
[5] Onawole A T, Popoola S A, Saleh T A, et al. Spectrochimica Acta Part A:Molecular & Biomolecular Spectroscopy, 2018, 201: 354.
[6] Saleh T A, Al-Shalalfeh M M, Al-Saadi A A. Sensors and Actuators B:Chemical, 2018, 254:1110.
[7] Mutasem M Al-Shalalfeh, Onawole A T, Saleh T A, et al. Materials Science and Engineering: C, 2017, 76: 356.
[8] Ji W, Li L, Song W, et al. Angewandte Chemie International Edition, 2019, 58: 14452.
[9] Lin X, Fang G, Liu Y, et al. Journal of Physical Chemistry Letters, 2020, 11(9): 3573.
[10] Yue S, Sun X, Wang N, et al. ACS Appl. Mater. Interfaces, 2017, 9(45): 39699.
[11] LI Ai-min, LIAN Zeng-yan, YANG Ren-jie, et al(李爱民, 连增艳, 杨仁杰, 等). Environmental Chemistry(环境化学), 2018, 37(4): 910.
[12] Shen Z, Wang H, Yu Q, et al. Microchemical Journal, 2021, 160: 105672.
[13] CHEN Xin-gang,FENG Yu-xuan,LI Chang-xin, et al(陈新岗, 冯煜轩, 李昌鑫, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(6): 1916.
[14] WANG Cong, ZHANG Jia-yi, SONG Shi-jie,et al(王 聪, 张嘉益, 宋仕杰, 等). The Journal of Light Scattering(光散射学报), 2020, 32(2): 148.