基于均匀设计和BP神经网络的花生油SFE-CO2萃取预测  

Prediction of Peanut Oil SFE-CO_2 Extraction Based on Uniform Design and BP Neural Network

作　　者：郭建章[1] 陈博文 王威强[2] GUO Jianzhang;CHEN Bowen;WANG Weiqiang(College of Electromechanical Engineering, Qingdao University of Science and Technology,Qingdao 266061, China;School of Mechanical Engineering, Shan Dong University, Jinan 250061, China)

机构地区：[1]青岛科技大学机电工程学院,山东青岛266061 [2]山东大学机械工程学院,山东济南250061

出　　处：《食品科学技术学报》2018年第3期78-82,共5页Journal of Food Science and Technology

基　　金：国家自然科学基金资助项目(2167060371)

摘　　要：利用均匀设计和BP神经网络相结合的方法,研究了SFE-CO_2萃取花生油工艺。以半烘烤并粉碎之后的花生为原料,针对萃取压力、温度、时间和CO_2流量4个因素,每个因素10个水平安排实验,利用均匀设计的实验数据作为网络训练样本,构造花生油SFE-CO_2萃取的BP神经网络预测模型,对萃取过程进行预测,分析各实验因素与出油率之间的关系,确定较优的工艺条件。最后确定4-9-1的BP神经网络模型,利用该模型所得出油率的预测值与实验值相接近,相对误差(绝对值)小于2%;构造的BP神经网络模型能较好地预测萃取过程中各参数影响下花生出油率的变化趋势。结果显示,当萃取压力30 MPa,温度40.5℃,时间125 min,CO_2流量187 L/(h·kg)时花生出油率可达期望值47.5%。该方法为实现预测与控制SFE-CO_2萃取花生油过程奠定了可靠的理论基础。Extraction of peanut oil with SFE-CO2 was studied by combining methods of uniform design and BP neural network. Taking peanut after being semi-baked and crushed as raw materials, four factors, including extraction pressure, temperature, time, and CO2 flow rate, were tested at ten levels of each factor. Using the experimental data of uniform design as training samples, a neural network prediction model for SFE-CO2 extraction of peanut oil was established. The extraction process was predicted, and the relationship between the experimental factors and the oil yield rate was analyzed. Therefore, the better technological condiitions were determined. A 4-9-1 neural network model was established. The prediction value of the oil yield was close to the experimental value, and the relative error （absolute value） was less than 2%. The neural network model could predict the trend of peanut oil yield under the influence of various parameters. Under the conditions of the extraction pressure 30 MPa, temperature 40.5 ℃, time 125 min, and the CO2 flow rate 187 L/（h ·kg）, the expected value of peanut oil yield was 47.5%. The method provides a reliable theoretical basis for the prediction and control of SFE-CO2 extraction of peanut oil.

关 键 词：花生油 萃取 BP神经网络 SFE-CO2 均匀设计 

分 类 号：TS225.1[轻工技术与工程—粮食、油脂及植物蛋白工程] TS224.4[轻工技术与工程—食品科学与工程]