This short article comments on two papers using artificial neural networks published in composites journals. The issues discussed include the predictive capability of the neural networks developed, and the size of the databases for training the neural networks. The article includes criticisms of those previously published papers.
Karnik SR, Gaitonde VN, Mata F. and Davim JPInvestigative study on machinability aspects of unreinforced and reinforced PEEK composite machining using ANN model. J Reinf Plast Compos2008; 27: 751-768.
2.
Gaitonde VN, Karnik SR, Mata F. and Davim JPModeling and analysis of machinability characteristics in PA6 and PA66 GF30 polyamides through artificial neural network. J Therm Compos Mater2010; 23: 313-336.
3.
Sha W.Comment on ‘‘Modeling of tribological properties of alumina fiber reinforced zinc-aluminium composites using artificial neural network’’ by K. Genel et al. [Mater. Sci. Eng. A 363 (2003) 203]. Mater Sci Eng A2004; 372: 334-335.
4.
Sha W.Comment on ‘‘Modeling of the APS plasma spray process using artificial neural networks: basis, requirements and an example’’ by Guessasma et al. [Comput. Mater. Sci. 29 (2004) 315]. Comput Mater Sci2010; 50: 805-809.
5.
Sha W. and Guo Z.Maraging steels: Modelling of microstructure, properties and applications . Cambridge: Woodhead Publishing , 2009.
