摘要
该文采用BP神经网络对脂肪酶催化酯化菜籽油脱臭馏出物的工艺条件进行了仿真研究。将中心组合试验和神经网络相结合,采用动量梯度下降法对网络进行训练仿真,并利用训练好的网络对催化酯化工艺条件进行预测。结果表明:经过训练的网络可以很好的模拟反应条件,得到了脂肪酶催化反应的最佳工艺参数,此时脂肪酸甲酯的含量为55.2%,维生素E保留率达到90%,为脱臭馏出物的酯化催化效果的预测提供了一条可行的途径。
The Emulation of rapeseed oil deodorizer distillate esterification by lipase reaction based on artificial neural network and central composite experiment was carried out. Back-Propagation algorithm with momentous factor was adopted to train the neural network followed by the prediction of esterifieation reaction. Results show that lipase reaction is well simulated and the optimal technological conditions of lipase reaction can be obtained by the trained neural network. Under these conditions, the content of fatty acid methyl ester and the recovery of vitamin E reaches 55.2% and 90%, respectively. It provids a significant approach for the prediction of esterification of deodorizer distillate.
出处
《农业工程学报》
EI
CAS
CSCD
北大核心
2006年第10期198-202,共5页
Transactions of the Chinese Society of Agricultural Engineering
基金
安徽省自然科学基金(03041302)
安徽省十一五攻关项目(06013046A)
关键词
神经网络
脂肪酶
酯化
菜籽油脱臭馏出物
neural network
lipase
esterification
rapeseed oil deodorizer distillate
