苹果渣多酚提取工艺的神经网络建模与遗传算法优化  

Modeling and Optimization of Polyphenol Extraction Process from Apple Pomace Based on Artificial Neural Network and Genetic Algorithm

作　　者：赵武奇[1] 仇农学[1] 王宏[1] 

机构地区：[1]陕西师范大学食品工程系,陕西西安7100621

出　　处：《食品科学》2007年第12期138-142,共5页Food Science

基　　金：国家"十五"重大专项(2001BA501A21)

摘　　要：本实验建立了苹果渣多酚提取工艺的人工神经网络模型,研究了提取工艺神经网络模型的遗传算法优化技术。结果表明,结构为4-9-1的神经网络能较为精确的拟合输入的样本数据,其对测试样本的输出与实验结果的相关系数为0.985;遗传算法优化出的最佳提取工艺参数为乙醇浓度为62%、乙醇溶液的体积与苹果渣的质量之比为14:1,温度为69.7℃,提取时间为5.9h,该工艺参数下的提取率明显大于单因素试验和二次组合试验的结果,比最好的大16.9%。用神经网络模型描述提取工艺参数与提取率之间的关系,用遗传算法优化工艺参数,能设计出最佳的提取工艺参数。The artificial neural network （ANN）model for polyphenol extraction from apple pomace was studied and ANN model was optimized by using genetic algorithm （GA） in this paper. Results showed that the structure of network is of four neurons of input layer with one neuron of output layer, one hidden layer and nine neurons. The trained network has a high generalization and the correlation coefficient between simulating outputs of the BP network and the experiments result is 0.985. The optimum performance, 16.9% greater than the greatest value in experiments, is obtained when alcohol concentration is 62% while ratio of alcohol solution volume to apple pomace weight is 14：1, temperature was 69.7 ~C, and treatment time 5.9 hours. The optimial process parameters can be obtained with ANN model to describe the relationship between process parameters and target and GA so as to optimize process parameters.

关 键 词：神经网络 遗传算法 苹果渣多酚 优化 模型 

分 类 号：R943.41[医药卫生—药剂学]