NEURAL NETWORK APPLICATION IN ONLINE HEAT FLUX ESTIMATION

Inverse problems are problems of determining cause on the basis of the effects. In this article the artificial neural networks (ANN) is utilized in order to estimate an unknown heat flux in a 1D slab. In developing the training phase of the network inspiration is drawn from the sequential function specification (SFS) method. Obtained results from the ANN method are shown to be more efficient when compared with the results of the SFS method.

Keywords:

Artificial Neural Network , IHCP , SFS , Levenberg Marquardt