论文部分内容阅读
在常减压装置中,影响初馏塔顶石脑油干点的因素很多,反应十分复杂,故难以建立准确的机理模型。针对传统的主元分析法(PCA)或自适应模糊推理系统(ANFIS)建立软测模型中的缺点,本文提出采用主元分析法预处理输入变量,再结合自适应模糊推理系统,进行常减压装置初馏塔顶石脑油干点的软测量模型的改进,能及时测定化工过程的变量,对稳定生产过程,有效控制产品质量具有重要意义。通过MATLAB仿真,表明该改进型方法的软测建模效果较好,建模的训练时间大大节省了,且泛化能力和拟合精度很好。
In the atmospheric and vacuum unit, there are many factors that affect the top-of-tower naphtha dry point, the reaction is very complicated, so it is difficult to establish an accurate mechanism model. In this paper, the principal component analysis (PCA) method is used to preprocess the input variables, and then combined with adaptive fuzzy inference system, Improvement of the soft measuring model of the naphtha dry point in the prefractionating distillation tower, which can measure the chemical process variables in time, is of great significance to stabilizing the production process and effectively controlling the product quality. Through MATLAB simulation, it shows that the improved method has better effect of soft-sensing modeling, saving training time greatly and generalization ability and fitting precision are very good.