近红外光谱的小麦粉粉质特性预测模型研究

doi:10.3964/j.issn.1000-0593(2023)10-3089-09

Abstract
References
Related Citation (15)

Download: PDF (6168 KB)
Export: BibTeX | EndNote (RIS)

Abstract The farinograph characteristics of wheat flour determine the quality and the end use of wheat flour. The farinograph characteristics of wheat flour are influenced by wheat variety, origin, and milling process technology. There are four important farinograph parameters: water absorption, development time, stability time and degree of softening. Near-infrared spectroscopy (NIR) is widely used to determine wheat flour composition parameters, such as moisture, protein, ash and wet gluten content. Most of them directly use linear regression algorithms to establish models, which has low prediction accuracy, and there are few studies on detecting farinograph characteristics, and the results are also affected by the lack of sample richness. In this study, 968 samples of wheat flour from different countries and regions were collected, and an ensemble method of classification model and a regression model was proposed to improve the prediction accuracy of farinograph characteristics. Spectral preprocessing methods, including standard normal variation (SNV), linear detrending, multiplicative scatter correction (MSC) and Savitzky-Golay first-order derivative, were applied to the spectral data, and the best preprocessing method was selected with cross-validation. As for the modeling methods, the classical linear regression methods, i.e., partial least squares regression (PLSR) and principal component regression (PCR), were explored. The accuracies of the two methods are approximately equivalent. The root mean squared error of calibration (RMSEC) on farinograph parameters (i.e. water absorption, development time, stability time, and degree of softening) of the PCA model were 2.186, 1.838, 4.037, 21.693 and 2.039, 1.837, 3.968, 21.252 for PLSR correspondingly. The PLSR model requires fewer factors than PCR. Secondly, the two-stage regression model proposed in this paper was explored. Gaussian process regression (GPR) results were used as the classifier to cluster the samples, PLSR models were established in different clusters to predict the farinograph characteristics, and the sigmoid function was used to fuse the PLSR models. This modeling method can significantly improve the prediction accuracy of farinograph characteristics. The RMSEC on the predictions of farinograph parameters is 1.876, 1.160, 2.459 and 14.449 correspondingly.

Key words：Farinograph characteristics; Near-infrared spectroscopy; Preprocessing; Partial least square regression; Principal component analysis; Gaussian process regression

Received: 2022-07-01 Accepted: 2022-09-20

ZTFLH:

O657.3

Corresponding Authors: ZHOU De-qiang E-mail: zhoudeqiang@jiangnan.edu.cn

Cite this article:

CHEN Jia-wei,ZHOU De-qiang,CUI Chen-hao, et al. Prediction Model of Farinograph Characteristics of Wheat Flour Based on Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3089-3097.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2023)10-3089-09 OR https://www.gpxygpfx.com/EN/Y2023/V43/I10/3089

[1] ZHANG Ying-quan, SHI Zhen-qiang, ZHAO Bo, et al(张影全, 师振强, 赵博, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2020, 36(15): 299.
[2] PAN Zhi-li, TIAN Ping-ping, HUANG Zhong-min, et al(潘治利, 田萍萍, 黄忠民, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2017, 33(3): 307.
[3] Cao Yanfei, Zhang Fengjie, Guo Peng, et al. LWT-Food Science and Technology, 2019, 111: 527.
[4] Bueno Micheli Maria, Thys Roberta Cruz Silveira, Rodrigues Rafael C. Food and Bioprocess Technology, 2016, 9(9): 1598.
[5] LUO Xian-hua(罗先华). Cereal & Feed Industry(粮食与饲料工业), 2004，(12): 15.
[6] Jirsa O, Hruskova M, Svec I. Czech Journal of Food Sciences, 2007, 36(5): 243.
[7] Moroi Alina, Vartolomei Nicoleta, Arus Alisa-Vasilica, et al. Annals of the University Dunarea de Jos of Galati. Fascicle VI: Food Technology, 2011, 35(2): 33.
[8] Daba Sintayehu D, Simsek Senay, Green Andrew J. Cereal Chemistry, 2021, 98(3): 660.
[9] Jirsa Ondrej, Hruskova Marie, Svec Ivan. Journal of Food Engineering, 2007, 87(1): 21.
[10] LI Hong-zhong, LIANG Chun-ling, SHI Ben-lin(李红忠, 梁春玲, 史本林). Resources Science(资源科学), 2012, 34(11): 2146.
[11] Chen Xinyu, Siesler H W, Yan Hui. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2021, 252: 119504.
[12] Yu Liwei, Ma Yanrong, Zhao Yiyue, et al. Frontiers in Nutrition, 2021, 8: 785847.
[13] Melaku Tafese Awulachew. International Journal of Food Science and Biotechnology, 2021, 6(4): 115.
[14] An Changqing, Yan Xin, Lu Chang. Infrared Physics & Technology, 2021, 8: 103869.
[15] CHEN Jia, YE Fa-yin, ZHAO Guo-hua(陈嘉, 叶发银, 赵国华). Food and Fermentation Industries(食品与发酵工业), 2019, 45(15): 243.
[16] Amigo Jose Manuel, del Olmo Arantxa, Engelsen Merete Moller, et al. Food Chemistry, 2019, 297: 124946.
[17] Cui Chenhao, Fearn Tom. Journal of Near Infrared Spectroscopy, 2017, 25(1): 5.
[18] Chen Zexun, Wang Bo, Gorban Alexander N. Neural Computing and Applications, 2020, 32(8): 11963.
[19] LIU Cui-ling, YANG Yu-fei, TIAN Fang, et al(刘翠玲, 杨雨菲, 田芳, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2021, 41(5): 1387.
[20] NGUYEN Van-Truong, CAI Jue-ping, WEI Lin-yu, et al(NGUYEN Van-Truong, 蔡觉平, 魏琳育, 等). Journal of Xidian University(西安电子科技大学学报), 2020, 47(3): 58.