Loading...

An artificial neural network approach to compressor performance prediction

Ghorbanian, K ; Sharif University of Technology | 2009

775 Viewed
  1. Type of Document: Article
  2. DOI: 10.1016/j.apenergy.2008.06.006
  3. Publisher: Elsevier Ltd , 2009
  4. Abstract:
  5. The application of artificial neural network to compressor performance map prediction is investigated. Different types of artificial neural networks such as general regression neural network, rotated general regression neural network proposed by the authors, radial basis function network, and multilayer perceptron network are considered. Two different models are utilized in simulating the performance map. The results indicate that while the rotated general regression neural network has the least mean error and best agreement to the experimental data; it is however, limited to interpolation application. On the other hand, if one considers a tool for interpolation as well as extrapolation applications, multilayer perceptron network technique is the most powerful candidate. Further, the compressor efficiency based on the multilayer perceptron network technique is determined. Excellent agreement between the predictions and the experimental data is obtained. © 2008 Elsevier Ltd. All rights reserved
  6. Keywords:
  7. Axial compressor ; Neural networks ; Performance map ; Compressors ; Deep neural networks ; Forecasting ; Interpolation ; Multilayers ; Radial basis function networks ; Regression analysis ; Artificial neural network approach ; Axial compressors ; Compressor efficiency ; Compressor performance ; General regression neural network ; Mean errors ; Multi-layer perceptron networks ; Performance maps ; Multilayer neural networks ; Artificial neural network ; Modeling ; Performance assessment
  8. Source: Applied Energy ; Volume 86, Issue 7-8 , 2009 , Pages 1210-1221 ; 03062619 (ISSN)
  9. URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-61849184066&doi=10.1016%2fj.apenergy.2008.06.006&partnerID=40&md5=edbeb7e944f1db94699fbfd66166c3f2