Abstract：It takes a plenty of time for model updating and maintenance when use visible near infrared spectroscopy to measure the soluble solids contents(SSC)of fruits online and each of the fruit varieties need to be modeled separately. This paper aimed to explore the feasibility of establishing the online detection universal mathematical models of thin skinned fruits such as the apples and pears . The online visible near infrared spectroscopy diffuse transmission spectra detection system which was designed by ourselves was applied. Under the condition of integral time 80 ms, single speed 5 s-1 collecting visible near infrared spectroscopy diffuse transmission spectra of Xinli No. 7, Dangshan pear, Yulu pear and Fuji apple. The spectra response characteristics of near infrared diffuse transmission of four kinds of fruit were analyzed by using the variation coefficient method and continuous projection algorithm screened the modeling spectral variables of the universal mathematical mode and establish partial least squares and least squares support vector machine universal mathematical models of apple and pears finally. New samples were used to evaluation the predictive ability of the universal model. The coefficient variation method by screening similar band to established the universal mathematical model of partial least squares spectral had the highest prediction accuracy. Pear and apple pear universal models correlation coefficient (rp) of prediction are 0.88 and 0.93 and the root mean square error of prediction (RMSEP) are 0.49% and 0.55% respectively; the correlation coefficient of independent model for predict Xinli No.7, Yulu pear, Dangshan pear and Fuji apple were 0.93, 0.91, 0.88 and 0.95, and the root mean square error of prediction are 0.40%, 0.42%, 0.41% and 0.46% respectively. The prediction accuracy of the universal mathematical model is slightly lower than the independent mathematical model prediction accuracy of each variety, but the generality of universal model is higher than the single model. The experiment results shows that using coefficient variation method combined with partial least squares method to establish the online detection general mathematical model of thin skinned fruit is feasible in achieving four kinds of fruit sugar online detection .
Key words：Detection online; Soluble solids; General model; Coefficient variation; Partial least squares; Least square support vector machine
[1] Li Jiangbo, Huang Wenqian, Zhao Chunjiang, et al. Postharvest Biology and Technology, 2013, 116(2): 324.
[2] WANG Ming-hai, GUO Wen-chuan, GU Jing-si, et al(王铭海，郭文川，谷静思，等). Journal of Northwest A & F University(西北农林科技大学学报)，2013, 41(12): 113.
[3] WANG Meng, FENG Xiao-yuan(王 蒙, 冯晓元). Journal of Food Safety and Quality(食品质量安全检测学报), 2014, 5(3): 681.
[4] Magwaza L S，Opara U L, Nieuwoudt H, et al. Food and Bioprocess Technology, 2012, 5: 425.
[5] Acharya K B Walsh，Subedi P P. J. Near Infrared Spectrosc, 2014, 22: 287.
[6] A Wang，L Xie. Journal of Food Engineering, 2014, 143: 17.
[7] Narsaiah Jha K，Jaiswal P, Bhardwaj R, et al. J. Food Eng.，2014，124：152.
[8] LIU Yan-de, ZHOU Yan-rui, PAN Yuan-yuan(刘燕德，周延睿，潘圆媛). Optics and Precision Engineering(光学精密工程)，2014, 2: 281.
[9] Liu Cong, Yang Simon X, Deng Lie. Journal of Food Engineering，2015, 161: 16.
[10] Sánchez M T, Dela Haba M J, Pérez-Marín D. Computers and Electronics in Agriculture, 2013, 92: 66.
[11] Schmutzler M, Huck C W. Food Control, 2016, 66: 27.
[12] SUN Tong, HU Tao, DUAN Wu-mao，et al(孙 通，胡 涛，段武茂，等). Acta Agriculturae Universitatis Jiangxiensis(江西农业大学报)，2013, 35(6): 1162.
[13] Yuan L, Cai J, Sun L, et al. Food Analytical Methods, 2016, 9(3): 785.
[14] Viegas T R, Mata A L M L, Duarte M M L, et al. Food Chemistry, 2016, 190: 1.
[15] Jannok P, Kamitani Y, Kawano S. J. Near Infrared Spectrosc., 2014, 22: 367.
[16] Liu R, Qi S, Han D. Journal of Near Infrared Spectroscopy, 2015, 23(5): 301.
[17] Fernández-Espinosa A J. Talanta, 2016, 148: 216.
