本文已被:浏览 1112次 下载 412次
投稿时间:2019-04-29
投稿时间:2019-04-29
中文摘要: 以金花茶花为原料,基于单因素试验结果,采用响应曲面法(response surface method,RSM)和人工神经网络模型(artificial neural networks,ANN)对金花茶花多酚氧化酶(polyphenol oxidase,PPO)的提取工艺进行优化。结果表明:RSM 和ANN 两种模型的决定系数R2 分别为0.9922 和0.9362,验证后的相对误差率分别为2.49%、1.14%。对比两种模型,ANN 能够比RSM 更准确地拟合模型和推导提取条件。金花茶花PPO 提取最佳工艺条件为浸提时间45 min,缓冲液pH 6.35,聚乙烯吡咯烷酮(polyvinyl pyrrolidone,PVP)添加量为22%。在此条件下,PPO 提取量为1 805.11 U/(g·min)。该研究为金花茶花PPO 活性与褐变的相关性以及抑制褐变提供基础。
中文关键词: 人工神经网络(ANN) 响应曲面法(RSM) 金花茶花 多酚氧化酶(PPO) 优化
Abstract:Based on the results of single factor experiments,the response surface method(RSM)and artificial neural network(ANN)model were used to optimize the extraction process of polyphenol oxidase (PPO)from Camellia nitidissima flowers.The results showed that the determination coefficients R2 of RSM and ANN models were 0.992 2 and 0.936 2,and the relative error rates after verification were 2.49%and 1.14%,respectively.ANN showed better accuracy and derivative than RSM.The optimal process conditions were extraction time 45 min,buffer pH 6.35,22 % polyvinyl pyrrolidone (PVP)and PPO extraction amount was 1 805.11 U/(g·min)by ANN.This study provided a basis for the inhibition of browning of Camellia nitidissima flowers.
keywords: artificial neural network model(ANN) response surface method(RSM) Camellia nitidissima flowers polyphenol oxidase(PPO) optimization
文章编号:202005010 中图分类号: 文献标志码:
基金项目:中央财政林业改革发展资金项目(2018GDTK-09)
Author Name | Affiliation |
LIU Chang,WU Xue-hui,CHEN Jia-hui | College of Food Science,South China Agricultural University,Guangzhou 510642,Guangdong,China |
引用文本: