基于三维荧光光谱预测大豆油掺假花生油含量的建模效果研究

doi:10.3964/j.issn.1000-0593(2025)07-1906-10

Abstract
References
Related Citation (15)

Download: PDF (13303 KB)
Export: BibTeX | EndNote (RIS)

Abstract To determine the content of adulterated peanut oil in soybean oil, the three-dimensional fluorescence spectrum data of soybean oil and peanut oil counterfeit were collected. Rayleigh scattering and Raman scattering were removed using the triangular internal interpolation method. Then the fluorescence spectra were processed using Savitzky-Golay. The Alternating trilinear decomposition (ATLD) and Parallel factor (PARAFAC) algorithms were used to predict peanut oil content. Meanwhile, after scattering and smoothing the three-dimensional fluorescence data of the different contents of counterfeit peanut oil. The emission spectrum corresponding to each excitation wavelength is decomposed by wavelet packet decomposition (WPD), and the wave packet coefficient of the lowest frequency band is used as the characteristic amount of fluorescence emission spectrum data. All the emission wavelengths were reconstructed according to the sequence number of excitation wavelengths, and the data were reconstructed into a first-order fluorescence spectrum data vector. Partial least squares (PLS) and artificial neural network (ANN) data models were constructed to predict the content of peanut oil in counterfeit products. The results indicated the regression coefficients R² of PARAFAC, ATLD, WPD-PLS, and WPD-ANN were 0.898, 0.941, 0.961, and 0.981, respectively. Mean absolute deviation (MAD), mean squared error (MSE), and root mean squared error (RMSE) of the training set, verification set, test set, and all data of the WPD-ANN algorithm model were all small. The peanut oil content in counterfeit products was predicted using the WPD-ANN model. The percentage of samples with prediction deviation within ±5% was 82.5%. The peanut oil content prediction results by WPD-ANN, WPD-PLS, ATLD, and PARAFAC were compared and analyzed. The mean and median deviations of WPD-ANN and WPD-PLS models are near 0%, while the mean and median deviations of ATLD and PARAFAC models are far from 0%. Compared with the PARAFAC model, the ATLD model has faster convergence and smaller deviation. ATLD and PARAFAC models may be affected by nonlinear factors, and their prediction effect was inferior to that of WPD-ANN and WPD-PLS, while ANN and PLS were based on first-order data regression modeling after WPD and data reconstruction. ANN was a nonlinear model. Therefore, the WPD-ANN model has stronger prediction ability and smaller deviation for peanut oil content in counterfeit peanut oil. The WPD-ANN model was the best algorithm among the four algorithms for predicting peanut oil content in counterfeit peanut oil. This provides a research basis for quantitative analysis of adulterated edible oil.

Key words：Edible oil adulteration; Wavelet packet decomposition; Artificial neural network; Partial least squares, Alternating trilinear decomposition; Parallel factor

Received: 2024-07-31 Accepted: 2025-01-23

ZTFLH:

O657.3

Cite this article:

WEI Quan-zeng,LIU Xue-ying,WANG Zhi-jie, et al. Study on Modeling the Effect of Three-Dimensional Fluorescence Spectrum of Predicting the Content of Peanut Oil Adulterated Soybean Oil[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(07): 1906-1915.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2025)07-1906-10 OR https://www.gpxygpfx.com/EN/Y2025/V45/I07/1906

[1] Feng Liang, Wang Shuqi, Chen Haitao, et al. Journal of Food Composition and Analysis, 2025, 139: 107143.
[2] LÜ Zhuang, HUANG Jin, LAN Zi-rong, et al(吕壮, 黄金, 兰梓溶, 等). China Oils and Fats（中国油脂）, 2024, https://link.cnki.net/urlid/61.1099.ts.20240607.1603.002.
[3] CHANG Ming, JIN Qing-zhe, WANG Xing-guo, et al(常明, 金青哲, 王兴国, 等). China Oils and Fats(中国油脂), 2020, 45(7): 10.
[4] JIANG Wan-feng, YANG Zhao, ZHANG Feng-yan, et al（蒋万枫, 杨钊, 张凤艳, 等）. Chinese Journal of Analysis Laboratory(分析试验室), 2017, 36(6): 732.
[5] Shi Ting, Wu Gangcheng, Jin Qingzhe, et al. Food Chemistry, 2021, 352：129422.
[6] Andreas N Schwarz, Thomas Züllig, Maximilian Schicher, et al. Food Chemistry, 2025, 463: 141467.
[7] Diego G Much, Mirta R Alcaraz, José M Camiña, et al. Talanta Open, 2024, 9: 100313.
[8] SUN Yong-rong, QUAN Zhi-xi, DING Lin-zhi et al(孙雍荣, 权志熙, 丁林志, 等). Spectroscopy and Spectral Analysis（光谱学与光谱分析), 2024, 44(12): 3391.
[9] JIANG Hai-yang, CUI Yao-yao, JIA Yan-guo, et al(姜海洋, 崔耀耀, 贾彦国, 等). Spectroscopy and Spectral Analysis（光谱学与光谱分析), 2024, 44(11): 3179.
[10] Hu Yating, Wei Chaojie, Wang Xiaorong, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2025, 329：125524.
[11] HUANG Xiu-li, HUANG Fei, CHEN Jia-cong, et al（黄秀丽，黄飞，陈嘉聪，等). Science and Technology of Food Industry(食品工业科技), 2014, 35(14): 64.
[12] CHEN Wei, WU Hai-long, WANG Tong, et al(陈伟, 吴海龙, 王童，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2022, 42(9): 2875.
[13] Larissa Naida Rosa, Aline Coqueiro, Paulo Henrique Março, et al. Food Chemistry, 2019, 273: 52.
[14] Chen Hengye, Ren Lixue, Yang Yinan, et al. Food Chemistry, 2024, 444: 138603.
[15] Yan Xiaoqin, Wu Hailong, Wang Bin, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2023, 295: 122617.
[16] REN Yong-jie, YIN Yong, YU Hui-chun，et al(任永杰, 殷勇, 于慧春, 等). Food Science(食品科学), 2024, 45(1): 198.
[17] XU Sheng, QU Zeng-yi, BI Jian-li，et al(徐胜, 屈曾义, 毕健丽, 等). Science and Technology of Food Industry(食品工业科技), 2021, 42(5): 257.
[18] Zhang Yu, Sun Yuwei, Song Huanlu. Foods, 2021, 10(10): 2430.
[19] CHEN Si-yu, PEI Ying, GU Hai-yang(陈思雨，裴颍，顾海洋). Food Science(食品科学), 2024, 45(20): 256.
[20] YU Hui-chun, LI Ying, YIN Yong，et al(于慧春, 李迎, 殷勇, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2022, 53(5): 392.
[21] Dong Mingyue, Wu Hailong, Wang Tong, et al. Chemometrics and Intelligent Laboratory Systems, 2023, 237: 104823.
[22] Matan Birenboim, Åsmund Rinnan, David Kengisbuch, et al. Chemometrics and Intelligent Laboratory Systems, 2023, 232: 104717.
[23] Bhumi K Sachaniya, Haren B Gosai, Haresh Z Panseriya, et al. Chemometrics and Intelligent Laboratory Systems, 2020, 202: 104033.
[24] LIU Wen-ya, TIAN Zhao-shuo, CUI Zi-hao, et al(刘文雅, 田兆硕, 崔子浩, 等). Infrared and Laser Engineering(红外与激光工程), 2021, 50(S2): 20210362.
[25] WU Hai-long, LONG Wan-jun, GU Hui-wen，et al(吴海龙, 龙婉君, 谷惠文, 等). Journal of Yangtze University(Natural Science Edition)[长江大学学报(自然科学版)], 2021, 18(3): 74.
[26] Yu Peigen, Mei Yin Low, Zhou Weibiao. Trends in Food Science & Technology, 2018, 71(1): 202.
[27] Afanador N L, Tran T N, Buydens L M C. Analytica Chimica Acta, 2013, 768: 49.