微孔晶体合成反应数据库的数据挖掘研究

Data Mining Research in the Synthesis Database of Microporous Crystals

采用数据挖掘中的查询和决策树技术对吉林大学无机合成与制备化学国家重点实验室建立的微孔晶体合成反应数据库进行了数据挖掘研究.针对微孔磷酸铝和硅铝酸盐两类合成反应体系,通过数据挖掘找出模板剂的参数特征,预测出适用于合成十二元环和十元环微孔磷酸铝和硅铝酸盐的分子筛一系列新的有机胺模板剂.采用分子力学方法计算了预测的有机胺模板剂与分子筛骨架的作用能,根据计算结果,最后确定有望成为合成这些特定结构分子筛的新模板剂,针对十二元环磷酸铝AlPO4 5的合成,根据数据挖掘的结果,安排了合成实验,结果采用预测的二乙醇胺作新的模板剂首次合成出了很好的AlPO4 5晶体,为定向合成研究探索了新的途径.

It presents data mining research in the synthesis database of microporous crystals built up by the State Key Laboratory of Inorganic Synthesis and Preparative Chemistry of Jilin University through query and decision tree. Some suitable templates are predicted for the formation of microporous aluminophosphates and aluminosilicates molecular sieves with 12-membered ring or 10-membered ring channel structures by analyzing the character of template parameters. These templates are further evaluated by computational simulations. Diethanolamine, one of the predictive templates for the formation of microporous aluminophosphates with 12-membered ring channel structure, is used to synthesize AlPO_4-5 crystals firstly in the experiment. This is a new approach in the research of rational design and synthesis.