Refine
Year of publication
Institute
- Fachbereich Elektrotechnik und Informationstechnik (1183) (remove)
Language
- English (717)
- German (465)
- Multiple languages (1)
Document Type
- Article (637)
- Conference Proceeding (302)
- Book (114)
- Part of a Book (64)
- Patent (17)
- Report (9)
- Other (8)
- Contribution to a Periodical (6)
- Course Material (6)
- Doctoral Thesis (6)
Keywords
- Multimediamarkt (7)
- Enterprise Architecture (5)
- MINLP (5)
- Engineering optimization (4)
- Gamification (4)
- Serious Game (4)
- Auslenkung (3)
- Digitale Transformation (3)
- Digitalisierung (3)
- Education (3)
In this paper, the use of reinforcement learning (RL) in control systems is investigated using a rotatory inverted pendulum as an example. The control behavior of an RL controller is compared to that of traditional LQR and MPC controllers. This is done by evaluating their behavior under optimal conditions, their disturbance behavior, their robustness and their development process. All the investigated controllers are developed using MATLAB and the Simulink simulation environment and later deployed to a real pendulum model powered by a Raspberry Pi. The RL algorithm used is Proximal Policy Optimization (PPO). The LQR controller exhibits an easy development process, an average to good control behavior and average to good robustness. A linear MPC controller could show excellent results under optimal operating conditions. However, when subjected to disturbances or deviations from the equilibrium point, it showed poor performance and sometimes instable behavior. Employing a nonlinear MPC Controller in real time was not possible due to the high computational effort involved. The RL controller exhibits by far the most versatile and robust control behavior. When operated in the simulation environment, it achieved a high control accuracy. When employed in the real system, however, it only shows average accuracy and a significantly greater performance loss compared to the simulation than the traditional controllers. With MATLAB, it is not yet possible to directly post-train the RL controller on the Raspberry Pi, which is an obstacle to the practical application of RL in a prototyping or teaching setting. Nevertheless, RL in general proves to be a flexible and powerful control method, which is well suited for complex or nonlinear systems where traditional controllers struggle.
Positionssensorvorrichtung
(2024)
Die Erfindung betrifft eine Positionssensorvorrichtung zur Bestimmung einer Absolutposition eines beweglichen ersten Teils relativ zu einem ortsfesten zweiten Teil mit einem mit dem beweglichen ersten Teil gekoppelter Codekörper, der dazu eingerichtet ist, eine Codespur mit einer Mehrzahl von in Spurrichtung aufeinanderfolgenden Codeelementen zu enthalten zur Bildung eines Codewortes, mit einer magnetischen Detektionseinrichtung zur Detektion der Codespur, wobei die Detektionseinrichtung zum einen an dem Codekörper befestigte und entlang der Spurrichtung in einem solchen Abstand gegenpolig zueinander angeordnete Permanentmagneten aufweist, dass der Abstand mit einer vorgegebenen Länge der jeweiligen Codeelemente übereinstimmt, und zum anderen eine Anzahl von ortsfest und quer zu dem Codekörper versetzt
angeordnete Wiegandsensoren aufweist, wobei der Abstand des Wiegandsensors zu einer Erstreckungsebene der Permanentmagneten derart gewählt ist, dass bei Überdeckung des Wiegandsensors durch den Permanentmagneten ein Wiegandpuls in dem Wiegandsensor induziert wird.
This paper serves as an introduction to the ECTS monitoring system and its potential applications in higher education. It also emphasizes the potential for ECTS monitoring to become a proactive system, supporting students by predicting academic success and identifying groups of potential dropouts for tailored support services. The use of the nearest neighbor analysis is suggested for improving data analysis and prediction accuracy.