基于PLS-GRNN的豆粕品质近红外光谱检测研究

doi:10.3964/j.issn.1000-0593(2022)05-1433-06

Abstract
References
Related Citation (15)

Download: PDF (3022 KB)
Export: BibTeX | EndNote (RIS)

Abstract Soybean meal is a by-product of soybean oil extracted from soybean after proper drying and heat treatment. It is the main raw material for making livestock feed, and its quality determines the nutritional value. There are many problems with existing soybean meal quality detection methods, such as the use of toxic chemical reagents, complex operation, long analysis time, so they cannot meet the needs of rapid detection and control in the production process. This paper proposes a multi-component detection method of soybean meal quality based on near infrared spectroscopy for on-line detection and control of product quality. 449 soybean meal samples were collected from the soybean oil processing line. The chemical values of moisture, protein and fat were determined by 105 ℃ oven method, Kjeldahl nitrogen determination method and Soxhlet extraction method, respectively. The diffuse reflectance spectra of samples were collected by the Swiss Buchi NIRMaster Fourier Transform near-infrared spectrometer. Firstly, the Mahalanobis distance method was used to remove abnormal samples, and then the spectral denoising was processed by various methods. The results show that the wavelet denoising effect is the best. KS and SPXY algorithms were used to determine the optimal sample partition of different components. In order to investigate the NIR absorption characteristics of soybean meal components, eliminate spectral redundancy and reduce the computational complexity of the model, interval Partial Least Squares (iPLS) was used to extract the features from the whole spectrum of 4 000～10 000 cm^-1. The optimized characteristic absorption bands of moisture, protein and fat were 4 904～5 200, 4 304～4 600 and 4 304～4 600 cm^-1, respectively. Finally, a Generalized Regression Neural Network (GRNN) model was established to predict the component contents of soybean meal. In order to reduce the input variables and the network scale improve the operation speed, PLS was used to reduce the dimension of spectral data, and the principal factor score was extracted as the input variable of GRNN. The PLS-GRNN prediction models of soybean meal multi-component contents were established by optimizing the smooth factor spread through the cross-validation and compared with the classical PLS and BP models. The results show that the PLS-GRNN models are good, the prediction determination coefficients (R²) of moisture, protein and fat are 0.976 9, 0.940 2 and 0.911 1, the Root-Mean-Square Errors of Prediction (RMSEP) are 0.091 2, 0.383 4 and 0.113 4, the Relative Standard Deviations (RSD) of prediction are 0.79 %, 0.83 % and 8.53 %, respectively. Although the prediction error for fat is relatively large, it is also within the available range of the model evaluation criteria. The results show that the near infrared spectroscopy analysis based on PLS-GRNN is feasible to detect soybean meal quality and can be used for quality monitoring in the actual production process.

Key words：Soybean meal quality; Near-infrared spectroscopy (NIR); Interval partial least squares (iPLS); Generalized regression neural network (GRNN)

Received: 2021-04-14 Accepted: 2021-10-14

ZTFLH:

O657.3

Corresponding Authors: ZHANG Yan-rong E-mail: zhangyanrong_5@163.com

Cite this article:

WANG Li-qi,YAO Jing,WANG Rui-ying, et al. Research on Detection of Soybean Meal Quality by NIR Based on PLS-GRNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1433-1438.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2022)05-1433-06 OR https://www.gpxygpfx.com/EN/Y2022/V42/I05/1433

[1] GUO Zhong-yuan，SHEN Shi-lei，ZHOU Xin-qi，et al(郭中原，慎石磊，周新奇，等). Cereal & Feed Industry(粮食与饲料工业)，2020，(4)：46.
[2] Wei Z，Lin M. Journal of Applied Spectroscopy，2021，88(3)：681.
[3] ZHUANG Shu-hua，ZHANG Guang-li，LU Li-jun(庄树华，张广利，卢利军). Oil Crops of China(中国油料)，1991，(2)：77.
[4] NA Rong(纳嵘). Animal Husbandry and Feed Science(畜牧与饲料科学)，2017，38(8)：14.
[5] Lesson S. Journal of Applied Poultry Research，1997，(6)：501.
[6] Fontaine J，Horr J，Schirmer B. Journal of Agricultural and Food Chemistry，2001，49：57.
[7] WANG Hong-mei，PENG Hai-hong，LIU Jia(王红梅，彭海宏，刘佳). Feed and Animal Husbandry(饲料与畜牧)，2009，(5)：40.
[8] YANG Zeng-ling，YANG Qin-kai，SHEN Guang-hui，et al(杨增玲，杨钦楷，沈广辉，等). Transactions of the Chinese Society for Agricultural Machinery (农业机械学报)，2019，50(8)：358.
[9] Bayer F M，Kozakevicius A J，Cintra R J. Signal Processing，2019，162：10.
[10] Morais Camilo L M，Santos Marfran C D，Lima Kássio M G，et al. Bioinformatics (Oxford，England)，2019，35(24)：5257.
[11] Tian Han，Zhang Linna，Li Ming，et al. Infrared Physics and Technology，2018，95：88.
[12] Wei Xiao，Zheng Wanqin，Zhu Shiping，et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy，2020，238：118453.
[13] Ju Wei，Lu Changhua，Zhang Yujun，et al. Journal of Innovative Optical Health Sciences，2019，12(2)：1950005.
[14] Specht D F. IEEE Transactions on Neural Networks，1991，2(6)：568.
[15] Kamel A H，Afan H A，Sherif M，et al. Sustainable Computing：Informatics and Systems，2021，30：100514.
[16] Xu Hanxiao，Xu Da，Zhang Naiqian，et al. Journal of Proteome Research，2021，20(3)：1657.
[17] Huang Yicheng，Liao Hsienshu. Journal of Intelligent & Fuzzy Systems，2020，38(2)：2347.