基于BP神经网络和改进遗传算法的钩藤碱提取工艺优化研究

摘要

钩藤是一种比较常用的中药,具有清热解毒、清肝明目等作用,其主要有效成分是钩藤碱和异钩藤碱.为了有效地提高钩藤碱的提取含量和质量,本文提出BP神经网络结合改进遗传算法,使用遗传算法对影响BP神经网络性能的初始权值和阈值进行寻优,再通过BP神经网络建立和优化模型.测试结果说明本文提出的方法是解决钩藤碱提取工艺优化的有效途径,并且表明自适应交叉和变异概率的寻优能力要优于固定交叉和变异概率.%Ramulus uncariae cum uncis, which is a common kind of tradition Chinese medicine, can clear away the heat evil and expel superficial evils, and can clear liver and improve vision. Its constituent is mainly rhynchophylline and isorhynchophylline. In order to increase the quantity and improve the quality of the extraction of the rhynchophylline, this paper proposes an improved genetic algorithm integrated with a BP neural network. This paper uses the genetic algorithm to optimize the initial weights and thresholds which impact the performance of the BP neural network, and then establishes and optimizes the model by the BP neural network. The test results indicate that the proposed approach provides an effect way for optimizing the parameters of the extraction process of rhynchophylline, and that the optimizing capability of the self-adapting crossover probability outperforms the fixed crossover probability.