de
en
Schliessen
Detailsuche
Bibliotheken
Projekt
Impressum
Datenschutz
Schliessen
Publizieren
Besondere Sammlungen
Digitalisierungsservice
Hilfe
Impressum
Datenschutz
zum Inhalt
Detailsuche
Schnellsuche:
OK
Ergebnisliste
Titel
Titel
Inhalt
Inhalt
Seite
Seite
Im Werk suchen
Combined current control and system identification of a PMSM with neural ordinary differential equations / by Marvin Meyer ; Supervisor: Wilhelm Kirchgässner and Maximilian Schenke. Paderborn, 2022
Inhalt
Introduction
Theoretical Fundamentals
Electric Drive
Inverter
Pulse Centering
Permanent Magnet Synchronous Machine
Modeling
Field-Oriented Control with PI-Controller
Simulation Environment
System Identification
Machine Learning
Neural Networks
Reinforcement Learning
Modeling
Neural Ordinary Differential Equations
Internal Plant Model with Neural Controller
Structure
Current Control via Neural Controller
Current Control and System Identification
Data Generation
Hyperparameter Optimization
Experimental Evaluation
GEM Drive Simulation
Current Control of a PMSM
Baselines
Neural Controller
Results
Discussion
HPO of the Neural Controller
Setup
Results
Discussion
Current Control and System Identification
Setup
Training
Results
Discussion
Summary
Summary
Outlook
Appendix
Dynamical Systems
Derivation of NODE
Equations
Ornstein-Uhlenbeck Prozess
Approximation Error
Plots
Sigmoid
HPO
Algorithms
DDPG Algorithm
Current Control and System Identification Algorithm
Lists
List of Tables
List of Figures
Acronyms
Glossary
Nomenclature
References
Die detaillierte Suchanfrage erfordert aktiviertes Javascript.