Wyniki wyszukiwania - Biblioteka Nauki

Ten serwis zostanie wyłączony 2025-02-11.

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Cyfrowy bliźniak siłownika elektrycznego

100%

Terczyński S. , Stebel K.

Przegląd Elektrotechniczny

2023

tom R. 99, nr 8

200--203

W artykule przedstawiona została adaptacja koncepcji cyfrowego bliźniaka na potrzeby stworzenia hybrydowego symulatora siłownika elektrycznego sterującego pracą zaworu regulacyjnego. Dokonano opisu, w jaki sposób został on zaimplementowany oraz zaproponowana została metoda pozwalająca uzyskać dokładniejsze wyniki symulacji. Część badawcza poświęcona jest układowi regulacji przepływu – parametrom regulatora krokowego i ich wpływu na zachowanie się całego układu.

The article presents an adaptation of the digital twin concept to create a hybrid simulator of an electric actuator that controls the operation of a control valve. A description was given on how it was implemented and a method was proposed to obtain more accurate simulation results. The research part is focused on the flow control system - the parameters of the step controller and their influence on the behavior of the whole system.

Self-improving Q-learning based controller for a class of dynamical processes

80%

Musial J. , Stebel K. , Czeczot J.

Archives of Control Sciences

2021

tom Vol. 31, No. 3

527--551

This paper presents how Q-learning algorithm can be applied as a general-purpose self-improving controller for use in industrial automation as a substitute for conventional PI controller implemented without proper tuning. Traditional Q-learning approach is redefined to better fit the applications in practical control loops, including new definition of the goal state by the closed loop reference trajectory and discretization of state space and accessible actions (manipulating variables). Properties of Q-learning algorithm are investigated in terms of practical applicability with a special emphasis on initializing of Q-matrix based only on preliminary PI tunings to ensure bumpless switching between existing controller and replacing Q-learning algorithm. A general approach for design of Q-matrix and learning policy is suggested and the concept is systematically validated by simulation in the application to control two examples of processes exhibiting first order dynamics and oscillatory second order dynamics. Results show that online learning using interaction with controlled process is possible and it ensures significant improvement in control performance compared to arbitrarily tuned PI controller.

Agent-based system for continuous control and its application to activated sludge process

80%

Pośpiech J. , Nocoń W. , Stebel K.

Bulletin of the Polish Academy of Sciences. Technical Sciences

2024

tom Vol. 72, nr 4

art. no. e150114

This paper presents a concept of architecture and ontology layouts for the development of multiagent model-based predictive control systems. The presented architecture provides guidelines to simplify the development of agent-based systems and improve their maintainability. The proposed multiagent system (MAS) layout is split into multiple subsystems that include agents dedicated to performing assigned tasks. MAS implementation was prepared which can use provided algorithms and actuators and can react to changes in its environment to reach the best available control quality. An example of MAS based on the proposed architecture is shown in the application of dissolved oxygen (DO) concentration control in a laboratory-activated sludge setup with a biological reactor. For that application, MAS incorporates agent-based controllers from the boundary-based predictive controllers (BBPC) family. Presented experiments prove the flexibility, resilience, and online reconfiguration ability of the proposed multiagent system.