完全随机型神经网络在1,6-二磷酸果糖制备条件优化上的应用  

Complete Randomization Neural Networks for the Technological Conditions Optimizations of Fructose 1,6-diphosphate

作　　者：郭寅龙[1] 王丁刚[1] 徐晖 相秉仁[1] 安登魁[1] 

机构地区：[1]中国药科大学,南京210009

出　　处：《中国生化药物杂志》1996年第1期12-13,共2页Chinese Journal of Biochemical Pharmaceutics

摘　　要：采用改进模拟退火法作为人工神经网络的学习算法,提出了适用于连续型输入变量、整体优化的完全随机型神经网络,并在1,6-二磷酸果糖制备条件优化中得到了成功应用,单位体积产率显著提高,为工业化生产提供了有利条件。We combined improved simulated annealing method with artificial neural network to develop complete randomization neural networks which algorithm has the power of global optimization to adapt to continuous input variable. By investigating different technological conditions of fructose 1,6-diphosphate, the relationship between its yield per unit volume and technological conditions was found. The yield per unit volume increased by 8 times.

关 键 词：完全随机型 神经网络 1 6-二磷酸果糖 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TQ464.1[自动化与计算机技术—控制科学与工程]