基于BP神经网络研究儿茶素在ADS-8树脂固定床中的洗脱过程

以信阳毛尖茶叶浸提液为原料,研究ADS-8树脂固定床吸附儿茶素后的洗脱过程,建立模型并优化工艺。基于BP神经网络建立洗脱模型,利用模型对因素进行仿真分析。模型误差为0.00108523,测试样本的试验值和模拟值的相关系数r=0.984,最佳工艺条件是温度20℃、流速1.0mL/min、乙醇浓度30%。基于BP神经网络建立的模型具有很强的逼近能力,为儿茶素在ADS-8树脂固定床中洗脱过程的预测、控制提供一定参考。

Studies on The Elution of Catechin in a Fixed Bed Packed With Macroporous Resin ADS-8 Based on BP Neural Network

Catechin from Xinyang tea extracts was as raw material. The experiments were carried out to study the elution of catechin in a fixed bed packed with resin ADS-8. The BP neural network was used to simulate the process of elution. The factors were predicted and analyzed by the model which based on BP neural network. The optimal conditions were temperature 20℃, flow rate 1.0mL/min, ethanol concentration 30%. Error of the model was 0.00108523 and the correlation coefficient of experimental data and simulated data was 0.984. The model based on BP neural network was feasible.