论文部分内容阅读
该文优化了复方威灵仙喷雾剂的水提工艺。实验采用L_9(3~4)正交试验设计复方威灵仙喷雾剂的水提工艺;熵值法求解各有效成分及出膏率的权重系数;再利用支持向量机结合遗传算法参数寻优建立模型,网格搜索优化复方威灵仙喷雾剂的工艺条件。结果显示经过新方法优化后的工艺条件为水提3次,每次2 h,加水倍数为6。支持向量机在此条件下的预测值与验证的实际值相比,相对误差为1.23%。将支持向量机法与传统的正交直观分析方法进行对比,结果表明这种新方法用于优化复方威灵仙喷雾剂水提工艺更精确,可靠。
The paper optimizes the water extraction process of compound clematis spray. In the experiment, the orthogonal design of L_9 (3-4) was used to design the water extraction process of the compound Clematis Spray; the entropy method was used to solve the weight coefficient of each active ingredient and the rate of the ointment; then, the support vector machine was used to optimize the parameter of genetic algorithm Model, Grid Search Optimized Process Conditions for Compound Clematis Spray. The results show that after the new method is optimized, the process conditions are three times with water, each time being 2 h, the water multiple is 6. Compared with the actual value of verification, the prediction error of SVM in this condition is 1.23%. Comparing the SVM with the traditional orthogonal visual analysis method, the results show that this new method is more accurate and reliable for optimizing the water extraction process of Compound Clematis Spray.