基于BP神经网络对念珠藻摇瓶培养条件的优化

BP Neural Network-based Optimization for Nostoc punctiforme During Flask Cultivation

利用均匀设计就pH、装液量、接种量和光强等影响念珠藻生长的因素进行研究,并以所得的数据为样本建立一个结构为4-6-1的神经网络.当网络的学习速率为0.08,动态参数为0.8,SIGMOID参数为0.8,隐含层神经原数为6时,网络的拟合平均误差为2.24%.在固定装液量为100 mL的条件下,利用该网络优化念珠藻的培养条件,得到最优的培养条件为pH7.4,接种量1.5 g/L,光强5 700 lx,生物量达到1.702 3 g/L.

The culture conditions of Nostoc punctiforme were investigated by a uniform design experiment.A 4-6-1 topology of the BP neural network was constructed.The results showed that the mean calculated error was 2.24% when the learning rate was 0.08,the momentum parameter was 0.8,the SIGMOID parameter was 0.8,the neuron number of the hidden layer was 6.Under a flask contents 100 mL medium,the network was used to look for the optimum conditions,and got the optimization conditions,i.g.pH7.4,inoculation ratio 1.5 g/...