earticle

영어

In this paper, we studied the applicability of data driven model, AAKR(Auto-Associative Kernel Regression) for generator power loss estimation. Correlation analysis performed on 39 turbine system variables for dataset construction and then 13 variables were selected as highly correlated with generator power output. For a memory vector, 95~100% thermal power section data were used and data at normal power condition for 3 month were extracted for query vector. Analysis result shows that 9 variables show good prediction between measured and estimated data, 2 variables show good correlation but with small bias and 2 variables show increasing difference and low correlation with the passage of time, which assumed to be cause of electric output loss.