Artificial intelligence-based fluid chemical reaction process prediction and optimization method and system
By constructing a hierarchical hybrid modeling system that combines mechanism delimitation, data optimization, and constraint guarantees, the problems of difficult model parameter identification and poor real-time performance in chemical processes are solved. This enables high-precision and robust prediction and optimization of fluid chemical reaction processes, and is applicable to multiphase flow, transient heat and mass transfer, and heterogeneous catalytic reactions.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHANGHAI INST OF TECH
- Filing Date
- 2026-04-22
- Publication Date
- 2026-06-16
AI Technical Summary
Existing technologies in the chemical, petrochemical, and fine chemical industries suffer from difficulties in identifying model parameters for fluid chemical reaction processes, poor real-time performance, weak generalization ability, lack of complete solutions for collaborative work with DCS/PLC, and insufficient accuracy and stability in modeling multiphase flow, transient heat and mass transfer, and heterogeneous catalytic reactions.
An AI-based method for predicting and optimizing fluid chemical reaction processes is adopted. By constructing a hierarchical hybrid modeling system that combines mechanism delimitation, data supplementation, constraint guarantee, and real-time optimization, and combining multimodal data acquisition, preprocessing, online identification, and dynamic updating, integrated multi-objective and strongly constrained optimization control is executed to achieve linkage with the field control system.
It improves prediction accuracy and generalization ability, enhances robustness and online executability, ensures the safety of process operation and industrial adaptability, and is suitable for complex chemical reaction systems with multiphase coexistence and multi-scale coupling.
Smart Images

Figure CN122224378A_ABST