Forecasting the eddy current loss of a large turbo generator using hybrid ensemble Gaussian process regression

For the issue that the sample space of wedge winding eddy current losses of large generator does not obey Gaussian distribution, a hybrid ensemble Gaussian process regression (HEGPR) model is proposed in this paper. The HEGPR contains three layers. First, four tree regression models (XGBoost, CatBoost, LGBM and NGBoost) are built. Then, the output of the first layer is taken as the input of multiple Gaussian regression models, so that the input samples of the second layer obey Gaussian distribution, which can effectively improve the generalization ability of Gaussian process regression. The results show that the root mean squared error (RMSE) is 0.0282 and the goodness of fit (R2) is 0.9973. The model has good prediction performance for the eddy current loss of large turbo generator. Compared with kinds of Gaussian process models and traditional ensemble learning models, the prediction accuracy of this model is higher, and it is more suitable for forecasting eddy current loss of the large generator. HEGPR model can effectively solve the problem of insufficient regression accuracy of Gaussian process when sample space does not obey Gaussian distribution.

Automated summary

A hybrid ensemble Gaussian process regression (HEGPR) model is proposed in this paper to address the issue of non-Gaussian distribution in the sample space of wedge winding eddy current losses of large generators. The HEGPR model consists of three layers, with four tree regression models in the first layer and multiple Gaussian regression models in the second layer. The results demonstrate that the HEGPR model has good prediction performance, with a root mean squared error (RMSE) of 0.0282 and a goodness of fit (R2) of 0.9973. Compared to other Gaussian process models and traditional ensemble learning models, the HEGPR model has higher prediction accuracy and is more suitable for forecasting eddy current loss in large generators. It effectively addresses the issue of insufficient regression accuracy in Gaussian process when the sample space does not follow a Gaussian distribution.