Assessment of strategies and potential for neural networks in the inverse heat conduction problem

Estimation of Boundary Conditions in Conduction Heat Transfer by Neural Networks

“…However, two new features are studied here: different training data sets for learning step, considering similar and nonsimilar data sets; also, several learning strategies for RBF-NN are studied. These purposes distinguish our research from previous ones [4,13].…”

“…In recent works [6,7] initial conditions are estimated by classical inverse techniques, such as Tikhonov regularization, maximum entropy principle, and truncated singular value decomposition. Reference [4] deals (see also [13]) with reconstruction of boundary condition using neural networks: multilayer perpectron (MP), radial base function (RBF), cascade-correlation (CC) and cascade-correlation with genetic algorithm (CCGA). The main conclusion is that NNs are effective tools as alternative techniques for solving inverse problems and they deserve investigation.…”

“…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 Krejsa et al [4]. The NNs were trainned considering 5 per cent of noise in the experimental data.…”

Assessment of Various Methods in Solving Inverse Heat Conduction Problems

“…Artificial neural networks can be successfully applied in the solution of inverse heat conduction problems (Krejsa et al, 1999;Shiguemori et al, 2004;Lecoeuche et al, 2006). They are capable of dealing with significant non-linearities and are known to be effective in damping the measurement errors.…”

Thermophysical properties of porous mineral-resin composites determined by a transient measurement technique

“…There are two main methods: neural networks [7,10,14,16] and genetic algorithms [3,5,11,15,17]. In the literature sources mentioned above, the unknown parameter or unknown function sought for by the inverse problem is the boundary or the initial condition of a heat conduction problem, mostly in one dimension.…”