基于RBFN-PLSR方法的CO2提纯塔模型

CO2提纯塔出口浓度与其影响因素之间存在复杂的非线性关系，传统的线性回归和非线性回归方法难以建立起它们之间准确的关系模型。本文运用RBFN的最佳函数逼近性能，结合PLSR的空间变换方法，建立了CO2提纯塔模型。交叉验证表明，所建模型平均拟合相对误差为0．0063%，平均预报相对误差为0．1210％，该模型可用于提纯塔出口CO2浓度的预测。

Model of Purifying Column of Carbon Dioxide Based on RBFN-PLSR Approach

There was complex nonlinear relation between the concentration of carbon dioxide in the exit of purifying column and the factors affecting it. It is difficult to set up a model of purifying column with conventional methods, for instance linear regression and nonlinear regression. A model of CO_2 purifying column was set up by RBFN-PLSR method. RBFN-PLSR method took advantage of the optimal approximation of radial basis function networks (RBFN) and the space-transform technology of partial least square regression (PLSR), and combined RBFN with PLSR. The cross experiments indicated that the average matching relative error and the average prediction relative error of this model, was 0.0063% and 0.1210% respectively. The model was applied to predict the concentration of CO_2 in the exit of purifying column.