中文摘要：

以膜孔径、操作压力、滤过温度为输入变量,以红芪酶解提取液在不同超滤条件下的芒柄花素保留率为输出变量,采用L-M算法优化网络参数,建立适用于纤维性根茎药材超滤的芒柄花素保留率BP神经网络预测模型,并对模型的预测性能和适用性及最优工艺条件和各条件对芒柄花素保留率的影响进行考察。该模型对红芪和黄芪酶解提取液超滤后的芒柄花素保留率预测的平均误差率分别为1.78%和1.92%。最优超滤工艺条件为：膜孔径100 nm,操作压力0.15 Mpa,滤过温度45℃。各条件对芒柄花素保留率的影响大小为：滤过温度〉膜孔径〉操作压力。结果表明,所建神经网络预测精度较高,适用性较好,具有很好的实用价值,可避免对成分相近纤维性根茎药材的超滤工艺重复优化的问题。

英文摘要：

The objective of this study was to establish a BP neural network to predict formononetin retention rate in the process of ultraflltration for fibrillary rhizome herbs. Using the membrane pore size,operating pressure and temperature as input variables, formononetin retention rate as output variable, the BP neural network was established after network pa- rameters optimized using L-M method. Furthermore ,the performance and applicability of model were evaluated. The opti- mal process condition and the effects of different u]trafiltration conditions on formononetin retention rate was then investi- gated. The average error rate of Hedysari Radix and Astragali Radix was 1.78% and 1.92% ,respectively. The optimal ultrafiltration process was as follows：membrane pore size 100 nm,operating pressure 0.15 Mpa,temperature 45 ℃. The influence of formononetin retention rate was temperature 〉 membrane pore size 〉 operating pressure. The results showed that the BP neural network had good practical value because of higher accuracy and better applicability. The established prediction model can avoid optimizing ultrafiltration technology of similar fibrillary rhizome herbs repeatedly.