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

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.