摘要
超微粉体技术是21世纪食品工程学科一项先进的加工技术,在日本及韩国的杂粮粉生产加工方面广泛应用。基于径向基函数(radial basis function,RBF)神经网络分别利用MATLAB软件构建杂粮粉超微粉体加工粒径占比预测模型以及使用SPSS Modeler软件构建杂粮粉超微粉体加工影响因素重要性预测模型,综合预测在固定杂粮原料配比及粉碎机运行频率恒定的情况下的杂粮粉体颗粒平均分布特性具有良好的精确度,试验证明,杂粮粉超微粉体加工粒径占比预测模型预测相对误差小于1%的约占35%,误差在1%和3%之间的约占32%,误差在3%和5%之间的约占17.5%,杂粮粉超微粉体加工影响因素重要性预测模型的准确程度达80.5%。
Ultra-fine pulverization is an advanced processing technology of food engineering in the 21st century,widely used in Japan,South Koreans grain powder production and processing.This article was about how to setting up the prediction model of particle size ratio and the prediction model of mixed grain ultrafine powder influence factor by using the MATLAB software and SPSS Modeler software based on Radial basis function(RBF)neural network.In condition of the ratio of raw material and the constant frequency of the machine,grains powder particle average distribution characteristics comprehensive prediction showed good accuracy.Experiment proved that the relative error of ultrafine powder particle size ratio prediction model was very small,the error less than 1%was about 35%,the error between 1%and 3%was about 32%,and the error between 3%and 5%was about 17.5%.The accuracy of the important influencing factors prediction model was 80.5%.
作者
王萍
郭嘉成
WANG Ping;GUO Jia-cheng(School of Electrical Engineering and Automation,Tianjin Polytechnic University,Tianjin 300387,China;Key Laboratory of Advanced Electrical Engineering and Energy Technology,Tianjin Polytechnic University,Tianjin 300387,China)
出处
《食品研究与开发》
CAS
北大核心
2018年第19期1-6,共6页
Food Research and Development
基金
国家自然科学基金面上项目(61372011)
天津市高等学校创新团队培养计划(TD13-5036)
