An Approach for DC Motor Speed Control with Off-Policy Reinforcement Learning Method

Basit Öğe Kaydı
dc.contributor.authorTufenkci, Sevilay
dc.contributor.authorKavuran, Gürkan
dc.contributor.authorYeroglu, Celaleddin
dc.date.accessioned2025-10-24T18:03:28Z
dc.date.available2025-10-24T18:03:28Z
dc.date.issued2023
dc.departmentMalatya Turgut Özal Üniversitesi
dc.description.abstractIntegration of self-learning mechanisms with control systems is frequently encountered in the literature due to the development of autonomous systems. This paper proposes a tuning method of PI controllers using a deep reinforcement learning algorithm, which is known as self-learning structure. The coefficients of the PI controller, which is used to control a DC motors, are determined. The proposed method aims to adjust the voltage value applied to the input of the DC motor to reach the desired speed with the tuned PI controller using the twin- delayed deep deterministic policy gradient (TD3) reinforcement learning algorithm. The Kp and Ki coefficients of the PI controller are taken as the absolute values of the neural network weights, which are driven by Gradient descent optimization to positive values with a fully connected layer. The proposed tuning method has been shown to provide a higher gain margin and a more optimal solution.
dc.identifier.doi10.17694/bajece.1114868
dc.identifier.endpage189
dc.identifier.issn2147-284X
dc.identifier.issue2
dc.identifier.startpage184
dc.identifier.trdizinid1263141
dc.identifier.urihttps://doi.org/10.17694/bajece.1114868
dc.identifier.urihttps://search.trdizin.gov.tr/tr/yayin/detay/1263141
dc.identifier.urihttps://hdl.handle.net/20.500.12899/2268
dc.identifier.volume11
dc.indekslendigikaynakTR-Dizin
dc.language.isoen
dc.relation.ispartofBalkan Journal of Electrical and Computer Engineering
dc.relation.publicationcategoryMakale - Ulusal Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzTR-Dizin_20251023
dc.subjectPI controller
dc.subjectDeep reinforcement learning
dc.subjectDC motor
dc.subjectTwin-delayed deep deterministic policy gradient
dc.titleAn Approach for DC Motor Speed Control with Off-Policy Reinforcement Learning Method
dc.typeArticle

Dosyalar

Koleksiyon

TR-Dizin İndeksli Yayınlar Koleksiyonu