中文摘要：

基于[C4mim]Br/K3C6H5O7离子液体双水相体系相平衡的特征,提出了＂子网络＂的概念和＂实验数据放大适当倍数＂的策略,将体系在278.15 K、298.15 K和318.15 K温度下的相平衡数据分为训练和检验样本,建立了相应的神经网络数据模型.模型对实验测量的依赖性较低,且计算精度优于文献中的Setschenowtype方程,有助于更好地了解该体系的相行为.

英文摘要：

The concept of subnetwork and the strategy to magnify experiment data with an appropriate multiple were proposed based on the characteristic of the phase equilibrium data of the aqueous two-phase system formed by[C4mim]Br / K3C6H5O7. Then the neural network model was established by dividing the collected data at 278. 15 K,298. 15 K and 318. 15 K into training and validation samples. The suggested model was slightly dependent on experiment and outperformed the Setschenow-type equation in terms of calculation accuracy.