遗传算法在秦皮提取液混批勾兑中的应用

目的：探讨遗传算法用于秦皮提取液多目标混批勾兑的可行性。方法：选择指纹图谱相似度和指标性成分含量的均方根误差为共同优化目标，对10批不同来源、批次的秦皮提取液建立多目标优化模型，运用遗传算法求得勾兑系数，对各批次提取液进行混批勾兑，以相似度和均方根误差评价确定勾兑后提取液的质量。结果：各批次秦皮提取液混批勾兑后，其质量明显改善, 与对照样品间的指纹图谱相似度显著提高, 变异程度降低，指标性成分相对偏差小于10%。结论：遗传算法可用于秦皮提取液多目标的混批勾兑，为中药提取液的质量控制提供新思路。

Application of genetic algorithm in blending technology for extractions of Cortex Fraxini

Objective: To explore the feasibility of genetic algorithm (GA) on multiple objective blending technology for extractions of Cortex Fraxini. Method: According to the optimization objective is the combination of fingerprint similarity and the root-mean-square error of multiple key constituents, a new multiple objective optimization model of 10 batches extractions of Cortex Fraxini is built. The blending coefficient is obtained by genetic algorithm. The quality of 10 batches extractions of Cortex Fraxini that after blending is evaluated by simility and root-mean-square error. Result: The quality of 10 batches extractions of Cortex Fraxini that after blending is well improved. Comparing with the fingerprint of the control sample, the similarity is up, and the degree of variation is down. The relative deviation of the key constituents is less than 10%. Conclusion: It proves to be good in practice that genetic algorithm works on multiple objective blending technology for extractions of Cortex Fraxini. This method can be a reference to control the quality of extractions of Cortex Fraxini. Genetic algorithm in blending technology for extractions of chinese medicine is advisable.