BP神经网络结合遗传算法优化灰树花多糖提取工艺

Optimization of Extraction Process of Polysaccharides from Grifola frondosa by BP Neural Network Combined with Genetic Algorithm

关键词:  灰树花  多糖  工艺优化  BP神经网络  遗传算法

Key words:  Grifola frondosa  polysaccharides  process optimization  BP neural network  genetic algorithm

摘要:

目的 通过BP神经网络结合遗传算法，对灰树花多糖提取工艺进行优化，以探讨最佳提取工艺。方法 采用水提醇沉法，以多糖提取率为检测指标，采用3因素（提取温度、提取时间、液料比）4水平正交试验对多糖提取工艺进行考察。用BP神经网络模型结合遗传算法对试验结果进行目标寻优，并通过正交分析法进行验证，获得灰树花多糖的最佳提取工艺。结果 BP神经网络结合遗传算法处理分析得到优化结果为提取温度79.6℃，提取时间3.4 h，液料比50：1，此方法下多糖提取率为6.754%。结论 BP神经网络结合遗传算法优化灰树花多糖提取工艺的方法有效可靠，可为同类提取工艺的优化提供新思路。

Abstract:

OBJECTIVE To optimize the extraction process of polysaccharides from Grifola frondosa by BP neural network combined with genetic algorithm, and obtain an optimum extraction process. METHODS Using water extract-alcohol precipitation method, and the extraction rate of polysaccharides was used as the detection index, the extraction technology was investigated by 3 factors (extraction temperature, extraction time and liquid material ratio) 4 levels orthogonal test. BP neural network combined with genetic algorithm was used to optimize the experiment results, and the optimum extraction process of polysaccharide from Grifola frondosa was obtained. RESULTS Through BP neural network combined with genetic algorithm, the optimization results were as follows:the extraction temperature was 79.6℃, the extraction time was 3.4 h, and the liquid ratio was 50:1, the extraction rate of polysaccharide was 6.754%. CONCLUSION BP neural network combined with genetic algorithm to optimize the extraction process of Grifola frondosa polysaccharide is effective and reliable, and can provide a new idea for the optimization of similar extraction process.