Comparison of ANN and DoE for the prediction of laser machined micro-channel dimensions
Karazi, ShadiORCID: 0000-0002-8887-0873, Brabazon, DermotORCID: 0000-0003-3214-6381 and Issa, Ahmed A.A.
(2009)
Comparison of ANN and DoE for the prediction of laser machined micro-channel dimensions.
Optics and Lasers in Engineering, 47
(9).
pp. 956-964.
ISSN 0143-8166
This paper presents four models developed for the prediction of the dimensions of laser formed micro-channels. Artificial Neural Networks (ANNs) are often used for the development of predictive models. Three feed-forward, back-propagation ANN models varied in terms of the number and the selection of training data, were developed. These ANN models were constructed in LabVIEW coding. The performance of these ANN models was compared with a 33 statistical design of experiments (DoE) model built with the same input data. When compared with the actual results two of the ANN models showed greater prediction error than the DoE model. The other ANN model showed an improved predictive capability that was approximately twice as good as that provided from the DoE model.