Abstract: Two different artificial neural networks (NN) are used for estimating a time dependent boundary condition ($x=0$) in a slab: multilayer perceptron (MP) and radial base function (RBF). The input for the NN is the temperature time-series obtained from a probe next to boundary of interest. Our numerical experiments follow the work of Kreja et al (1999). The NNs were trainned considering a 5% of noise in the experimental data. The training was performed considering 500 similar test-functions and 500 different test-functions. Inversions with NNs trained with different test-functions were better. The RBF-NN presented results a little bit better than MP-NN.

Refences:

1. J. Krejsa, K.A. Woodbury, J.D. Ratliff, M. Raudensky (1999): Assessment of Strategies and Potential for Neural Networks in Inverse Heat Conduction Problem, Inverse Problem in Engineering, 7, 197-214.