Cascaded Neural Network for Internal TemperatureForecasting in Induction Motor

Creative Commons License

Noğay H. S.

ICIMSET 2017, London, England, 16 - 17 February 2017, pp.1769-1775

  • Publication Type: Conference Paper / Full Text
  • City: London
  • Country: England
  • Page Numbers: pp.1769-1775
  • Bursa Uludag University Affiliated: No


Abstract— In this study two systems were created to prediction of interior temperature in induction motor. One of them consisted of a simple ANN model which has two layers, ten input parameters and one output parameter. The other one is consisted of eight ANN models connected each other as cascaded. Cascaded ANN system has seventeen inputs. Main reason of cascaded system being used in this study is to accomplish more accurate estimation by increasing inputs in the ANN system. The other reason of this system is being completely different and simpler approach from other conventional methods. Cascaded ANN system compared with simple conventional ANN model to prove mentioned advantages. Data set was obtained from experiments using by experimental set up. Small part of the data set was used to obtain more understandable graphs. Number of data is 329. 30 % of this data was used for testing and validation. Test data and validation data were determined for each ANN model separately and reliability of each model was tested. As a result of this study, it has been understood that the cascaded ANN system produced more accurate estimates than conventional ANN model.

Keywords— Cascaded Neural Network, Internal temperature; Three-phase induction motor; Inverter.