Lactic acid polymerization process based on neural network prediction

The invention discloses a lactic acid polymerization process based on neural network prediction, which relates to prediction of lactic acid polymerization conditions, adopts a foldover sampling uniform design method, and obtains lactic acid polymers with different molecular weights by controlling lactic acid polymerization reaction time, catalyst content and reaction temperature. The neural network is trained and predicted by using the obtained test data, and the predicted data is well matched with the test data. According to the method, the polymerization reaction conditions are predicted by using the neural network, the exploration process of the test is greatly simplified, the test time and cost are saved, and the method has a wide application prospect in exploration of chemical reaction conditions in the field of biochemical synthesis. 本发明公开一种基于神经网络预测的乳酸聚合工艺，所述工艺涉及乳酸聚合条件的预测，采用叠影取样均匀设计法，通过控制乳酸聚合反应时间、催化剂含量以及反应温度，得到不同分子量的乳酸聚合物，利用得到的试验数据对神经网络进行训练和预测，预测数据与试验数据吻合良好。本发明利用神经网络预测聚合反应条件，大大简化了试验的探究过程，节省了试验时间和成本，在生物化