A method and system for molecular level prediction of quality of any stream in petrochemical production

By combining online spectral analysis and dynamic molecular libraries with genetic algorithms and neural network models, the molecular-level reaction network is updated in real time, solving the problems of lag and low accuracy in stream quality prediction in oil refining and chemical production, and realizing timely response and high-precision prediction of feed fluctuations.

CN121034458BActive Publication Date: 2026-03-03BEIJING PROFESSIONAL DIGITIZE& INTELLIGENTIZE TECH CO LTD
3 Cites 0 Cited by

Patent Information

Application Number
CN202511564256.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-10-30
Publication Date
2026-03-03
Estimated Expiration
2045-10-30

AI Technical Summary

Technical Problem

In oil refining and chemical production, the prediction of feed quality is lagging and has low accuracy. It cannot adapt to feed fluctuations in real time and lacks real-time and in-depth understanding of key locations, resulting in inaccurate operation adjustments and poor product quality uniformity.

Method used

Carbon number distribution data and hydrocarbon composition data are obtained through online spectral analysis. A dynamic molecular library is established, and reaction kinetic parameters and neural network models are optimized by combining genetic algorithms. The molecular-level reaction network is updated in real time, gas-liquid phase equilibrium calculations are performed, and the flow stream quality is predicted.

Benefits of technology

It enables real-time capture of changes in feed composition, accurately describes all molecular types and reaction pathways, dynamically adjusts kinetic parameters, improves the prediction accuracy of nonlinear properties such as octane number, and solves the problems of lag and insufficient accuracy of traditional methods.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application relates to the technical field of petrochemical production, and discloses a method and system for molecular-level prediction of the quality of any flow in petrochemical production. The method comprises the following steps: performing online spectrum analysis on a feed flow to obtain carbon number distribution and hydrocarbon composition data, and establishing a dynamic molecular library through structural unit coding; establishing a reaction rule library according to a reaction mechanism, and matching the reaction rule library with the molecular library to generate a reaction network; establishing a reaction kinetics equation group with an introduced feed composition correction factor and optimizing parameters; performing gas-liquid phase equilibrium calculation on reaction products to obtain flow molecular composition, inputting structural descriptors into a neural network model to introduce component interaction terms, and outputting flow quality prediction results. The application solves the problems of lagging flow quality prediction, low precision and incapability of real-time adaptation to feed fluctuations in the prior art.
Need to check novelty before this filing date? Find Prior Art