Optimization of Theanine-Glucose Maillard Reaction Conditions Based on Artificial Neural Network Coupled Genetic Algorithm (BP-GA)

被引：0
作者：
Qu Y. [1 ,2 ]
Zhang S. [1 ,2 ]
Luo L. [1 ,2 ,3 ]
Zeng L. [1 ,2 ,3 ]
机构：
[1] College of Food Science, Southwest University, Chongqing
[2] Chongqing Key Laboratory of Speciality Food Co-Built by Sichuan and Chongqing, Chongqing
[3] Tea Research Institute, Southwest University, Chongqing
来源：
Science and Technology of Food Industry | 2023年 / 44卷 / 24期
关键词：
artificial neural network; entropy method; genetic algorithm; glucose; Maillard reaction; optimization; theanine;
D O I：
10.13386/j.issn1002-0306.2023020165
中图分类号：
学科分类号：
摘要：
In order to comprehensively evaluate the Maillard reaction system and optimize the conditions of theanine-glucose Maillard reaction, an artificial neural network coupled genetic algorithm (BP-GA) model for the comprehensive evaluation value of theamine-glucose Maillard reaction was herein constructed, and the best reaction conditions were optimized. Firstly, the weight among five evaluation indexes, fluorescence value, A294, A420, glucose and theanine residue were obtained by entropy method. Next, a BP-GA artificial neural network model with experimental factor parameter as the input and the comprehensive evaluation value of Maillard reaction as output was established in combination with the results of the single factor experiment and orthogonal experiment. Finally, the optimal condition for the theanine-glucose Maillard reaction and the corresponding comprehensive evaluation value of the Maillard reaction were obtained with the established model. The results showed that the optimal conditions for the theanine-glucose Maillard reaction obtained through the global optimization by the established BP-GA model were: Reaction temperature 117.6 ℃, reaction time 1.8 h, pH7.3, and carbonyl ammonia ratio 1:2. In such case, the comprehensive evaluation value of Maillard reaction was 93.22. Compared with the results obtained by the orthogonal experiment, it was found that the BP-GA model had good predictive performance. In this study, the optimum conditions for the model Maillard reaction was obtained by the BP-GA model, which would provide a reference for the establishment of the Maillard reaction simulation system and prediction of the reaction. © The Author(s), 2023.
引用
收藏
页码：183 / 192
页数：9
相关论文
共 34 条
  • [1] DENG S B, CUI H P, HAYAT K, Et al., Comparison of pyrazines formation in methionine/glucose and corresponding Amadori rearrangement product model[J], Food Chemistry, 382, (2022)
  • [2] YE Y K, YE S S, WANYAN Z X, Et al., Producing beef flavors in hydrolyzed soybean meal-based Maillard reaction products participated with beef tallow hydrolysates[J], Food Chemistry, 378, (2022)
  • [3] QIU T T, TAN X, LI R N, Et al., Research progress in preparation of chitosan-monosaccharide Maillard reaction products and their applications in antibacterial and antioxidant activities[J], Food Science, 41, 19, pp. 327-333, (2020)
  • [4] GULLoN B, MONTENEGRO M I, RUIZ-MATUTE A I, Et al., Synthesis, optimization and structural characterization of a chitosanglucose derivative obtained by the Maillard reaction[J], Carbohydrate Polymers, 137, pp. 382-389, (2016)
  • [5] LIN P X, ZHANG H J, CHEN J J, Et al., Kinetic analysis of alkylpyrazine compound formed by Maillard reaction between alanine and butanedione[J], Food Science, 43, 2, (2022)
  • [6] HAN Z S, JIANG Z D, ZHANG H, Et al., Amadori reaction products of theanine and glucose：Formation, structure, and analysis in tea[J], Journal of Agricultural and Food Chemistry, 70, 37, pp. 11727-11737, (2022)
  • [7] MU W M, ZHANG T, JIANG B., An overview of biological production of L-theanine[J], Biotechnol Advance, 33, 3-4, (2015)
  • [8] JIANG P F, YU W J, SUN N, Et al., Application of artificial neural network in food industry[J], Food Research and Development, 42, 13, pp. 188-196, (2021)
  • [9] WANG S., Research on digital simulation and simulation of salmon baking process based on artificial neural network, (2020)
  • [10] PAN H B, QIN L Q, HUANG Y T, Et al., Artificial neural network combined with genetic algorithm to optimize the protective agent to improve the frost resistance of Lactobacillus reuteri[J], Food Science, 42, 14, pp. 70-77, (2021)
1234