dc.contributor.author | Seel, Katrine | |
dc.contributor.author | Grøtli, Esten Ingar | |
dc.contributor.author | Moe, Signe | |
dc.contributor.author | Gravdahl, Jan Tommy | |
dc.contributor.author | Pettersen, Kristin Ytterstad | |
dc.date.accessioned | 2022-08-26T18:05:11Z | |
dc.date.available | 2022-08-26T18:05:11Z | |
dc.date.created | 2021-11-30T13:32:48Z | |
dc.date.issued | 2021 | |
dc.identifier.citation | American Control Conference (ACC). 2021, 3556-3563. | en_US |
dc.identifier.issn | 0743-1619 | |
dc.identifier.uri | https://hdl.handle.net/11250/3013932 | |
dc.description.abstract | Learning-based controllers, and especially learning-based model predictive controllers, have been used for a number of different applications with great success. In spite of good performance, a lot of these cases lack stability guarantees. In this paper we consider a scenario where the dynamics of a nonlinear system are unknown, but where input and output data are available. A prediction model is learned from data using a neural network, which in turn is used in a nonlinear model predictive control scheme. The closed-loop system is shown to be input-to-state stable with respect to the prediction error of the learned model. The approach is tested and verified in simulations, by employing the controller to a benchmark system, namely a continuous stirred tank reactor plant. Simulations show that the proposed controller successfully drives the system from random initial conditions, to a reference equilibrium point, even in the presence of noise. The results also verify the theoretical stability result. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_US |
dc.title | Neural Network-based Model Predictive Control with Input-to-State Stability | en_US |
dc.type | Peer reviewed | en_US |
dc.type | Journal article | en_US |
dc.description.version | acceptedVersion | en_US |
dc.source.pagenumber | 3556-3563 | en_US |
dc.source.journal | American Control Conference (ACC) | en_US |
dc.identifier.doi | 10.23919/ACC50511.2021.9483190 | |
dc.identifier.cristin | 1961732 | |
dc.relation.project | Norges forskningsråd: 223254 | en_US |
dc.relation.project | Norges forskningsråd: 294544 | en_US |
cristin.ispublished | true | |
cristin.fulltext | postprint | |
cristin.qualitycode | 1 | |