中文摘要：

目的采用反向传播人工神经网络（BP-ANN）结合正交试验法优化白附子多糖提取工艺。方法水提醇沉法提取多糖后,苯酚-硫酸法测定含有量。基于单因素试验的基础上,按照L9（3^4）正交表安排进行试验,考察提取温度、提取时间、料液比对多糖得率的影响,BP-ANN技术优化提取工艺。结果最佳条件为提取时间3.5 h,提取温度90℃,料液比1∶20,多糖得率达5.20%。结论该方法重复性良好,而且试验次数少。

英文摘要：

AIM To optimize the extraction of polysaccharides from Typhonii Rhizoma by back-propagation artificial neural network（BP-ANN） combined with orthogonal test.METHODS For polysaccharides extracted by aqueous extraction-alcohol precipitation technology,the content was determined by phenol-sulfuric acid method.Based on single factors experiments,the L9（3^4） orthogonal test was conducted to investigate the effects of extraction temperature,extraction time,and solid-liquid ratio on polysaccharides extraction yield.Subsequently,the extraction was optimized by BP-ANN.RESULTS Provided at a 5.20% high yield of polysaccharides,the best conditions were thus determined to be 90 ℃ for extraction temperature,3.5 h for extraction time,and 1 ∶ 20 for solid-liquid ratio.CONCLUSION The work proves that this method has good reproducibility and the advantage with fewer test times.