Application of evolutionary programming to transient and subtransient parameter estimation

This paper presents an artificial intelligence approach of using evolutionary programming to estimate the transient and subtransient parameters of a generator under normal operation. The estimation using evolutionary programming is compared with that using a corrected extended Kalman filter. The comparisons with both simulation and micromachine test results show that evolutionary programming is robust to search the real values of parameters even when the data are highly contaminated by noise, while with the extended Kalman filter, the estimation tends to diverge with such data.