The study of neural estimator structure influence on the estimation quality of selected state variables of the complex mechanical part of electrical drive

摘要

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.