摘要
在传统的机理模型 (三对角矩阵法中的泡点法 )基础上 ,将体系压力 (P) ,平衡液相组成 (x1,x2 ,x3 )为输入节点 ;体系温度 (T) ,平衡汽相氮组成 (y1)及氩、氧的相平衡常数 (k2 ,k3 )为输出节点的神经网络液体空气汽液平衡计算模型 ,取代三对角矩阵法中泡点计算 ,从而建立改进的精馏塔模型。改进模型用于空分塔的模拟计算 ,不仅计算速度快 ,计算结果与机理模型结果非常接近 ,且符合设计要求 ,对实现产品质量的在线监控具有一定的指导意义。
Based on the traditional mechanical model (the buble point method of three diagonal matrix), an neural network model of gas-liquid equilibrium computation for liquid air, which makes system presure (P) and equilibrium component of liquid phrase ( x 1,x 2,x 3) as input nodes; makes system temperature (T), equilibrium component of gas nitrogen (y 1) , equilibrium constant of argon and oxygen (k 2, k 3) as output nodes, insteads of the buble point computation of the three diagonal matrix , thus a improved distillation model is built. The improved model is applied to simulation of the liquid air distillation tower; it not only has rapid compulation speed but computation result is approximate to the mechanical model and meets the demand of the design. The improved model will have some meaning to the realization of line control of product quality.
出处
《计算机与应用化学》
CAS
CSCD
北大核心
2001年第2期147-151,共5页
Computers and Applied Chemistry
