摘要
利用误差逆向传播人工神经网络(BPANN)模型对文献已发表的24种固体在超临界流体(SCF)中的溶解度数据分别进行了模拟及预测,结果表明该模型具有较好的模拟及内推功能,可作为模拟和内推固体溶质在超临界流体中溶解度的一种较好手段,但外推效果较差.
The published solubilities data of 24 solids in supercritical fluid (SCF) were simulated and predicted by back-propagation artificial neural networks (BPANN) model. The results show that the model can simulate and interpolate the solubility of solids in SCF well, and it is a better way to simulate and interpolate the solubility of the most solids in SCF, but having the worse extrapolative effect.
出处
《山东大学学报(工学版)》
CAS
2006年第2期8-11,共4页
Journal of Shandong University(Engineering Science)
关键词
溶解度
模拟
固体
超临界流体
solubility
simulation
solid
supercritical fluid