基于全透射可见-近红外光谱的西瓜糖度在线检测研究

doi:10.3964/j.issn.1000-0593(2024)06-1710-08

摘要
参考文献
相关文章 (15)

全文: PDF (9044 KB)
输出: BibTeX | EndNote (RIS)

摘要：糖度是评价西瓜品质的重要指标之一，影响着西瓜的受欢迎程度和销售价格。但体积大、皮厚的自然生物特征为西瓜糖度的快速、无损评估带来了挑战。为探索西瓜糖度快速无损检测，选择230个西瓜作为试验样本，使用自行研制的全透射可见-近红外光谱系统在线采集西瓜光谱数据，在线检测过程中保持光谱连续检测点在西瓜的赤道部位，并分别测量西瓜整果糖度和中心糖度作为理化糖度参考值。首先对样本在线检测过程中产生的多条光谱数据进行均值化处理，并选取波长范围690～1 100 nm的光谱数据，使用蒙特卡洛方法剔除其中的异常样本，使用多种预处理方法（SNV、SG平滑等）对光谱数据优化，并采用SPXY算法划分样本校正集和预测集以减小因西瓜内部糖度分布差异造成的影响；基于优化的光谱数据构建了线性PLSR模型和非线性LS-SVM模型预测西瓜中心糖度和整果糖度。结果表明，基于SNV和SG组合法预处理光谱构建的LS-SVM模型预测西瓜整果糖度效果最好，其校正集相关系数R_C=0.92，建模均方根误差RMSEC=0.37°Brix；预测集相关系数R_P=0.88，预测均方根误差RMSEP=0.40°Brix。进一步使用特征波段挑选算法（CARS、UVE、SPA等）对光谱数据优化，结果显示构建的模型效果更好，其中使用CARS和UVE组合算法选取的特征波长构建LS-SVM模型预测西瓜整果糖度时效果最好，其校正集相关系数R_C=0.94，校正均方根误差RMSEC=0.31°Brix；预测集相关系数R_P=0.91，预测均方根误差RMSEP=0.37°Brix，且建模变量从1524个特征变量缩减到39个特征变量。该研究为实际生产中西瓜糖度快速无损检测应用提供了参考。

关键词：全透射光谱；在线检测；西瓜；糖度；模型构建

Abstract：Sugar content is a crucial parameter for assessing watermelon quality, influencing watermelon's marketability and commercial value. However, the natural biological characteristics of large volume and thick skin pose challenges for rapid and non-destructive evaluation of the sugar content of watermelon. In this study, 230 watermelons were selected for investigation. A custom-designed full-transmission visible-near-infrared detection system was developed. Spectral data of all samples were acquired online. Each sample spectral data comes from the equatorial part of the watermelon. The overall watermelon sugar content and the central sugar content were measured separately to provide reference values for the assessment of sugar content. In the data processing phase, the spectral data of each sample was averaged, and spectral data in the 690～1 100 nm was selected. The Monte Carlo method was implemented to remove abnormal samples, and preprocessing, such as Standard Normal Variate correction and Savitzky-Golay smoothing, was applied to optimize the spectral data. The SPXY algorithm was used to divide the calibration and prediction sets. Utilizing the optimized spectral data, linear Partial Least Squares Regression (PLSR) and non-linear Least Squares Support Vector Machine (LS-SVM) models were developed to forecast each sample's center sugar content and overall sugar content. The results revealed that, Combined with standard normal variate correction and Savitzky-golay smoothing, the LS-SVM model yielded the most favorable results in predicting the overall watermelon sugar content. The calibration correlation coefficient (R_C) of 0.92 and root mean square error of calibration (RMSEC) of 0.37°Brix were obtained for the calibration set. Correspondingly, the prediction correlation coefficient (R_P) of 0.88 and root mean square error of prediction (RMSEP) of 0.40°Brix were obtained for the prediction set. Furthermore, feature wavelength selection algorithms (e.g., Competitive Adaptive Reweighted Sampling, Uninformative Variable Elimination, Successive Projections Algorithm) were used for variable selection. Study found that the LS-SVM model combined with Competitive Adaptive Reweighted Sampling and Uninformative Variable Elimination methods has the optimal performance in predicting the overall watermelon sugar content with a calibration correlation coefficient (R_C) of 0.94 and a calibration root mean square error of 0.31°Brix. Correspondingly, the prediction correlation coefficient (R_P) and the root mean square error of prediction (RMSEP) were 0.91 and 0.37 °Brix, respectively. Additionally, the number of variables was significantly reduced from 1 524 to 39. This study provides a reference for the practical application of rapid and non-destructive testing of sugar content in watermelon.

Key words：Full-transmittance spectrum; Online detection; Watermelon; Sugar content; Modeling

收稿日期: 2023-05-05 修订日期: 2023-08-07

中图分类号:

S24

基金资助: 国家重点研发计划子课题（2022YFD2002202-01），国家自然科学基金项目（31972152）资助

通讯作者: 李江波 E-mail: jbli2011@163.com; lijb@nercita.org.cn

作者简介: 王贺功，1998年生，新疆农业大学机电工程学院硕士研究生 e-mail: whg202300@163.com

引用本文:

王贺功，黄文倩，蔡仲磊，严忠伟，黎胜，李江波. 基于全透射可见-近红外光谱的西瓜糖度在线检测研究[J]. 光谱学与光谱分析, 2024, 44(06): 1710-1717.
WANG He-gong, HUANG Wen-qian, CAI Zhong-lei, YAN Zhong-wei, LI Sheng, LI Jiang-bo. Online Detection of Sugar Content in Watermelon Based on Full-Transmission Visible and Near-Infrared Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(06): 1710-1717.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2024)06-1710-08 或 https://www.gpxygpfx.com/CN/Y2024/V44/I06/1710

[1] ZHANG Lin, YAN Shen, LI Qiong-hua, et al（张琳, 闫燊, 李琼华, 等）. Chinese Scientific Data（中国科学数据)，2021, 6(4): 8.
[2] ZUO Jie-wen, PENG Yan-kun, LI Yong-yu, et al（左杰文, 彭彦昆, 李永玉, 等）. Transactions of the Chinese Society for Agricultural Machinery（农业机械学报）, 2022, 53(S1): 316.
[3] Jie D, Xie L, Rao X, et al. Postharvest Biology and Technology, 2014, 90: 1.
[4] Chen Y, Xu Z, Tang W, et al. Artificial Intelligence in Agriculture, 2021, 5: 125.
[5] Raghavendra A, Guru D S, Rao M K. Aritificial Intelligence in Agriculture, 2021, 5: 43.
[6] Rejeb A, Rejeb K, Zailani S, et al. Artificial Intelligence in Agriculture，2022, 6: 111.
[7] LU Yong, LI Zhen-feng, LI Jing, et al（陆勇, 李臻峰, 李静, 等）. Fujian Agricultural Science and Technology（福建农业科技）, 2014，(10): 77.
[8] Liu D, Wang E, Wang G, et al. Journal of the Science of Food and Agriculture, 2021, 101(10): 4308.
[9] Jie D F, Wei X. Computers and Electronics in Agriculutre, 2018, 151: 156.
[10] Phuangsombut K, Phuangsombut A, Talabnark A, et al. Postharvest Biology and Technology, 2018, 142: 55.
[11] Jie D, Zhou W, Wei X. Scientia Horticulturae, 2019, 257: 108718.
[12] Zhang D Y, Xu L, Wang Q Y, et al. Food Analytical Methods, 2019, 12: 136.
[13] Jie D, Xie L, Fu X, et al. Journal of Food Engineering, 2013, 118(4): 387.
[14] Onsawai P, Phetpan K, Khurnpoon L, et al. Measurement, 2021，174: 108684.
[15] Olarewaju O O, Magwaza L S, Nieuwoudt H, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2019, 209: 62.
[16] WANG Shi-fang, HAN Ping, CUI Guang-lu, et al（王世芳, 韩平, 崔广禄, 等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析）, 2019, 39(3): 738.
[17] Hu R, Zhang L X, Yu Z Y, et al. Infrared Physics & Technology, 2019, 102: 102999.
[18] Li M, Han D, Liu W. Biosystems Engineering, 2019, 188: 31.
[19] JIE Deng-fei, XIE Li-juan, RAO Xiu-qin, et al（介邓飞, 谢丽娟, 饶秀勤, 等）. Transactions of the Chinese Society of Agricultural Engineering（农业工程学报）, 2013, 29(12): 264.
[20] GUO Yang, SHI Yong, GUO Jun-xian, et al（郭阳, 史勇, 郭俊先, 等）. Food and Fermentation Industries（食品与发酵工业）, 2022, 48(2): 248.
[21] GUO Yang, GUO Jun-xian, SHI Yong, et al（郭阳, 郭俊先, 史勇, 等）. Food & Machinery（食品与机械）, 2021, 37(6): 81.
[22] Zhang Y, Wang Z, Tian X, et al. Infrared Physics and Technology, 2022, 122: 104090.
[23] Song J, Li G, Yang X. Journal of the Science of Food and Agriculture, 2019, 99(11): 4898.
[24] LONG Fei, YU Zheng, LIU Fen, et al(龙霏, 余铮, 刘芬, 等). Computer Systems & Applications(计算机系统应用), 2021, 30(7): 283.
[25] Tamburini E, Costa S, Rugiero I, et al. Sensors, 2017, 17(4): 746.
[26] Qi S, Song S, Jiang S, et al. Journal of Innovative Optical Health Sciences, 2014, 7(4): 1350034.