METHOD FOR OPERATING A PROCESS PLANT, CONTROL SYSTEM AND PROCESS PLANT
Abstract
[0001] The invention relates to a method for operating a process plant, wherein the process plant is configured to perform at least one of substance modifications and substance conversions, with the aid of at least one of physical, chemical, biological, and nuclear effects, preferably, separation of air into nitrogen and/or oxygen and/or argon and/or other components included in air, said method comprising the following steps, performed by a control system comprising a model predictive controller having a control model (320), wherein the model predictive controller is a nonlinear model predictive controller, and wherein the control model (320) is a hybrid model, wherein the hybrid model comprises at least one data-based component (324, 326, 424) and at least one dynamic component (322): initialising the control model; determining (230), based on the initialised control model, one or more setpoints for one or more parameters of one or more process components and/or units of the process plant; and providing the one or more setpoints to control the process plant.
Inventors 4
- Andreas Peschel Aachen author as filed: Peschel, Andreas
- Ecker, Anna-Maria
- Alexander Mitsos Aachen author as filed: Mitsos, Alexander
- Jan C. Schulze Aachen author as filed: Schulze, Jan
Inventors are linked to an Aachen author when surname and first name match exactly one author.
Applicants
- Linde GmbH
- Rheinisch-Westfälische Technische Hochschule (RWTH) Aachen RWTH Aachen University
Cited papers 1 in the database
Non-patent literature as cited (1)
- - PICHÉ STEPHEN ET AL: "SPECIAL SECTION Industrial Process Control I Non linear Model PRedictive Control using neural networks", IEEE CONTROL SYSTEMS MAGAZINE, 30 June 2000 (2000-06-30), pages 53 - 62, XP093050909, Retrieved from the Internet <URL:https://doi.org/10.1109/37.845038> [retrieved on 20230531]