文章基本信息

标题：Adaptive Learning of Hybrid Models for Nonlinear Model Predictive Control of Distillation Columns
本地全文：下载
作者：Jannik T. Lüthje ; Jan C. Schulze ; Adrian Caspari 等
期刊名称：IFAC PapersOnLine
印刷版ISSN：2405-8963
出版年度：2021
卷号：54
期号：3
页码：37-42
DOI：10.1016/j.ifacol.2021.08.215
语种：English
出版社：Elsevier
摘要：AbstractOur previous work has shown that replacing parts of the classical compartmentalization model reduction approach for distillation columns by offline-trained artificial neural networks (ANNs) improves computational performance. In real-life applications, the absence of a high-fidelity model for data generation can, however, prevent the deployment of this approach. Therefore, we propose a method that utilizes solely plant measurement data, starting from a small initial data set and then continuously adapting to newly measured data. We demonstrate the approach in closed-loop simulations and compare to benchmarks using either the high-fidelity model or an offline trained reduced model for control.
关键词：KeywordsNonlinear model reductionModel predictiveoptimization-based controlAdaptive controlReal time optimizationcontrolNeural networks in process control