Full-process modeling method for oil refining process

Abstract

The invention discloses a full-process modeling method for an oil refining process. Based on the mechanisms and running characteristics of all production devices in the oil refining process and a corrected model, the influence of key operation / process conditions of all the devices on the product yield is analyzed. Piecewise linearization is carried out according to the influence trend, a linear equation is solved, corresponding Delta-Base yield data are obtained, a neural network modeling technology is combined, operation conditions and the Delta-Base data are related, a yield surrogate model is built, the yield data calculating speed is improved, real-time prediction on the product yield in the oil refining process is achieved, and theoretical supports are provided for building a precise plan optimized PIMS model.

Description

technical field [0001] The invention relates to a method for modeling the whole process of oil refining process based on mechanism and operating characteristics. The method can be used for modeling simulation of oil refining process, real-time model correction and real-time construction of PIMS production plan optimization model. Background technique [0002] Oil refining industry is an important part of my country's petroleum industry. Crude oil can be refined and processed to produce gasoline, kerosene, diesel and other liquid vehicle fuels that cannot be replaced by other energy sources; it can also produce nearly a thousand kinds of lubricants, paraffin, asphalt, oil coke and other petroleum products; it can also be used for plastics, The production of three major synthetic materials such as synthetic rubber and synthetic fiber and other important organic raw materials provides chemical raw materials. Therefore, the oil refining industry is the lifeline of our national ...

AI Technical Summary

Problems solved by technology

However, the optimization of a single device also has its limitations. Its optimal solution is not necessarily the optimal solution of the whole plant. The reason is that the optimization of a single device requires correct price information of intermediate products, and some intermediate products are not sold in the market. Therefore, it is necessary to establish a full-process model of the whole plant to implement full-process optimization of the refining process

However, the informatization of the oil refining industry has always lacked a complete simulation and optimization plan. The difficulty lies in the huge amount of data generated by the production equipment, the variety of databases, the complex mechanism of the equipment model, and the current simulation software in the whole process simulation and optimization. There are defects in the above: most of the software is difficult to achieve high precision, and some reactor models based on molecular structure lumping are incompatible with the distillation range lumping used in the fractionation part; the operation of the refining process simulation software is complicated and does not rely on external calculations It is difficult to support the optimization of the whole process alone, and it is impossible to provide rational production guidance for refining production

Images