责任编辑：食品科学

中国肉类食品综合研究中心，肉类加工技术北京市重点实验室王守伟教授于11月9日在Food Chemistry上在线发表了文章《Application of artificial neural networks to predict multiple quality of dry-cured ham based on protein degradation》，该文研究了干腌火腿加工过程中蛋白质降解和品质变化，建立了基于蛋白质降解的多品质预测模型。王守伟教授为本文通信作者。

研究亮点：

蛋白质降解参数在整个加工过程中都有显著的变化；

采用电子仿生方法观察质量特性；

开发了基于蛋白质降解的多品质BP预测模型。

中国肉类食品综合研究中心，肉类加工技术北京市重点实验室的Ning Zhu、Shou-wei Wang和军事科学院国防科技创新研究院无人系统技术研究中心的Kai Wang等人研究了干腌火腿加工过程中蛋白质降解和品质变化，建立了基于蛋白质降解的多品质预测模型。从原料到熟化期，外部样品的蛋白质水解指数高于内部样品，但从干燥期到成熟期，差异逐渐减小。蛋白质降解可作为火腿品质控制的指标。以蛋白质降解指数为输入变量，以trainlm为训练函数，输入-隐藏层的传递函数为logsig和隐藏-输出层的传递函数为tansig，以及20个隐藏层神经元，对反向传播人工神经网络（back propagation-artificial neural networks，BP-ANN）模型进行优化。用BP-ANN模型对12个样本的预测数据和实验数据的相对误差均在0左右。结果表明，BP-ANN在基于蛋白质降解的干腌火腿品质预测中具有很大的潜力。

通信作者简介：

王守伟 教授级高级工程师

王守伟，教授级高级工程师，中国肉类食品综合研究中心主任、北京食品科学研究院院长、国家肉类加工工程技术研究中心及国家肉类食品质量监督检验中心主任，兼任国务院食品安全专家委员会委员、中国食品科学技术学会常务理事、肉类加工产业技术创新战略联盟理事长，享受国务院政府特殊津贴，获北京市有突出贡献专家等多项荣誉称号。长期从事肉品科学与技术、食品安全领域研究，致力于肉类产业重大关键共性技术问题研究及科技成果转化与产业化。主持和承担国家重点研发专项、国家“863”计划、国家科技支撑计划、公益性行业专项、国家自然科学基金等项目/课题20余项，发表科技论文130余篇，获授权发明专利10余件，制修订国家/行业标准6 项，出版专著8 部，获国家科技进步二等奖1 项、省部级科技进步一等奖10 项（第一完成人）。

Abstract

Application of artificial neural networks to predict multiple quality of dry-cured ham based on protein degradation

Ning Zhu, Kai Wang, Shun-liang Zhang, Bing Zhao, Jun-na Yang, Shou-wei Wang

Highlight

•Proteins degradation parameters had significant changes throughout the processing.

•Electronic bionic methodologies were used to observe the quality properties.

•A BP model was developed to predict the multi-quality based on protein degradation.

This study investigated protein degradation and quality changes during the processing of dry-cured ham, and then established the multiple quality prediction model based on protein degradation. From the raw material to the curing period, proteolysis index of external samples were higher than that of internal samples, however, the difference gradually decreased from the drying period to the maturing period. Protein degradation can be used as indicators for controlling quality of the hams. With protein degradation index as input variables, the back propagation-artificial neural networks (BP-ANN) models were optimized, with training function of trainlm, transfer function of logsig in input-hidden layer and tansig in hidden-output layer, and 20 hidden layer neurons. Furthermore, the relative errors of predictive data and experimental data of 12 samples were approximately 0 with the BP-ANN model. Results indicated that the BP-ANN has great potential in predicting multiple quality of dry-cured ham based on protein degradation.

该文章《Application of artificial neural networks to predict multiple quality of dry-cured ham based on protein degradation》于《Food Chemistry》2020年11月9日在线发表。