COMPARISON OF PARAMETER ESTIMATION ALGORITHMS FOR CONTINUOUS TIME MODELS APPLIED TO D.C. MOTOR THERMAL SUPERVISION
- 1 October 1998
- journal article
- research article
- Published by Taylor & Francis in Electric Machines & Power Systems
- Vol. 26 (8) , 839-853
Abstract
This paper deals with the thermal supervision of a D.C. motor process by means of parameter estimation. Identification is realized by applying two classes of algorithm to the measurable inputs/outputs of the process: The first deals with Reinitialized Partial time Moment modeling, which can be interpreted as an equation error method. The model parameters are computed by means of Least Square or Instrumental Variable algorithms. The second is based on the output error method. The model parameters are estimated by minimizing the output error by means of a Non Linear Programming according to the Marquardt algorithm.Keywords
This publication has 3 references indexed in Scilit:
- Process fault detection based on modeling and estimation methods—A surveyAutomatica, 1984
- Parameter estimation for continuous-time models—A surveyAutomatica, 1981
- An Algorithm for Least-Squares Estimation of Nonlinear ParametersJournal of the Society for Industrial and Applied Mathematics, 1963