An example of the use of neural computing techniques in materials science - the modelling of fatigue thresholds in Ni-base superalloys

Two adaptive numerical modelling techniques have been applied to prediction of fatigue thresholds in Ni-base superalloys. A Bayesian neural network an d a neurofuzzy network have been compared, both of which have the ability t o automatically adjust the network's complexity to the current dataset. In both cases, despite inevitable data restrictions, threshold values have bee n modelled with some degree of success. However, it is argued in this paper that the neurofuzzy modelling approach offers real benefits over the use o f a classical neural network as the mathematical complexity of the relation ships can be restricted to allow for the paucity of data, and the linguisti c fuzzy rules produced allow assessment of the model without extensive inte rrogation and examination using a hypothetical dataset. The additive neurof uzzy network structure means that redundant inputs can be excluded from the model and simple sub-networks produced which represent global output trend s. Both of these aspects are important for final verification and validatio n of the information extracted from the numerical data. In some situations neurofuzzy networks may require less data to produce a stable solution, and may be easier to verify in the light of existing physical understanding be cause of the production of transparent linguistic rules. (C) 1999 Elsevier Science S.A. All rights reserved.