Neural state estimator for complex mechanical part of electrical drive - neural network size and state estimation performance
Journal Title: Power Electronics and Drives - Year 2018, Vol 2018, Issue 1
Abstract
This paper presents results of simulation research of off-line trained, feedforward neural-network-based state estimator. The investigated system is the mechanical part of electrical drive characterized by elastic coupling with working machine, modeled as dual-mass system. The aim of the research was to find a set of neural networks structures giving useful and repeatable results of the estimation. Mechanical resonance frequency of the system has been adopted at the level of 9.3 Hz to 10.3 Hz. Selected state variables of the mechanical system are load speed and stiffness torque of the shaft.
Authors and Affiliations
Adrian Wójcik, Dominik Łuczak
Keywords
Related Articles
- EP ID EP408063
- DOI 10.2478/pead-2018-0017
- Views 85
- Downloads 0
Fuzzy adaptive control of nonlinear two-mass system
Background: In the paper the adaptive control MRAS-based structure for nonlinear two-mass system is proposed. Material and methods: The structure of fuzzy adaptive control of nonlinear two-mass system is presented. Contr...
DIAGNOSTIC SYSTEM FOR INDUCTION MOTOR STATOR WINDING FAULTS BASED ON AXIAL FLUX
The article presents the results of research on the use of an axial flux in the diagnostics of induction motor stator winding fed by a frequency converter. Voltage signal waveforms proportional to the axial flux were reg...
PERFORMANCE OF SENSORLESS CONTROL OF PERMANENT MAGNET SYNCHRONOUS GENERATOR IN WIND TURBINE SYSTEM
Background: The article presents the sensorless control of permanent magnet synchronous generator (PMSG) in the variable speed wind energy conversion system. The considered system of wind turbine consists of PMSG and bac...
Synchrogenverter - parallel connection of synchronous generator and power converter with energy storage
Background: The paper describes novel power generation topology wherein synchronous generator have a parallel connected power electronic converter. In this arrangement synchronous generator is only source of active power...
APPLICATION OF ARTIFICIAL BEE COLONY ALGORITHM TO AUTO-TUNING OF STATE FEEDBACK CONTROLLER FOR DC-DC POWER CONVERTER
Background: The article presents auto-tuning method of state feedback voltage controller for DC-DC power converter. Material and methods: Simulation and experimental tests prove proper operation of proposed auto-tuning m...