Details

Title

Determination of synchronous generator nonlinear model parameters based on power rejection tests using a gradient optimization algorithm

Journal title

Bulletin of the Polish Academy of Sciences: Technical Sciences

Yearbook

2017

Numer

No 4

Keywords

General Engineering ; Computer Networks and Communications ; Atomic and Molecular Physics, and Optics ; Artificial Intelligence ; Information Systems

Divisions of PAS

Nauki Techniczne

Abstract

<jats:title>Abstract</jats:title><jats:p>The paper presents a method for determining electromagnetic parameters of different synchronous generator models based on dynamic waveforms measured at power rejection. Such a test can be performed safely under normal operating conditions of a generator working in a power plant. A generator model was investigated, expressed by reactances and time constants of steady, transient, and subtransient state in the d and q axes, as well as the circuit models (type (3,3) and (2,2)) expressed by resistances and inductances of stator, excitation, and equivalent rotor damping circuits windings. All these models approximately take into account the influence of magnetic core saturation. The least squares method was used for parameter estimation. There was minimized the objective function defined as the mean square error between the measured waveforms and the waveforms calculated based on the mathematical models. A method of determining the initial values of those state variables which also depend on the searched parameters is presented. To minimize the objective function, a gradient optimization algorithm finding local minima for a selected starting point was used. To get closer to the global minimum, calculations were repeated many times, taking into account the inequality constraints for the searched parameters. The paper presents the parameter estimation results and a comparison of the waveforms measured and calculated based on the final parameters for 200 MW and 50 MW turbogenerators.</jats:p>

Publisher

Polish Academy of Sciences

Date

2017

Identifier

ISSN 0239-7528, eISSN 2300-1917

DOI

10.1515/bpasts-2017-0053

×