Comparison of various regression models for predicting compressor and turbine performance parameters


YAZAR I., YAVUZ H. S., ALTIN YAVUZ A.

ENERGY, cilt.140, ss.1398-1406, 2017 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 140
  • Basım Tarihi: 2017
  • Doi Numarası: 10.1016/j.energy.2017.05.061
  • Dergi Adı: ENERGY
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.1398-1406
  • Anahtar Kelimeler: Performance map prediction, Regression models, ANFIS, Model selection, AIC value, NONLINEAR-REGRESSION
  • Eskişehir Osmangazi Üniversitesi Adresli: Evet

Özet

This paper investigates various regression models to predict the compressor and turbine map parameters. To this end, we used the data measured from two different types of compressors and turbines. The compressor is basically a single stage radial machine, whereas, the turbine is formed of high pressure and low pressure parts. The emphasis of this study is to construct various models for prediction of corrected mass flow rate and isentropic efficiency. Except for prediction capabilities, the study also compares the regression model's performances. Results show that the designed models can be used for the development of dynamic mathematical model of a gas turbine engine. (C) 2017 Elsevier Ltd. All rights reserved.