SOME POSSIBILITIES OF USING DOE IN SETTING ANN PARAMETERS: AN APPLICATION IN MODELING OF ABRASIVE WATERJET CUTTING

Artificial neural networks (ANNs) have been successfully applied for solving a wide variety of problems. However, determining of ANN architectural and training parameter values still remains a difficult task. This paper is concerned with the usage of design of expe riment (DOE) method in order to determine parameter settin gs of multilayer feedforward (MLFF) ANN trained with backpropagation (BP) algorithm with momentum for modeling purposes. In this paper, a case study of a brasive waterjet (AWJ) cutting was used to find ANN parameters settings in order to develop high performance predi ction model. For evaluating the predictive performance of ANN models, the combined mean absolute percentage error (MAPE comb ) is used as performance criterion. The ANN model was used for prediction of traverse rate of t he separation cut based on material thickness, water p ressure, and abrasive rate as input cutting parameters. The selected 3-8-1 ANN model showed high prediction accuracy with correlation coefficient of 0.999. Finally, the deve loped ANN model is given in the form of mathematical equation. The results indicated that ANN model is able to lea rn the relationships between AWJ process parameters. Also, in searching for ANN model of high performance, DOE method can be efficiently used in setting ANN architectural and training parameters.

[1]  B. S. Lim,et al.  Optimal design of neural networks using the Taguchi method , 1995, Neurocomputing.

[2]  Lionel Tarassenko,et al.  Guide to Neural Computing Applications , 1998 .

[3]  James Tannock,et al.  The optimisation of neural network parameters using Taguchi’s design of experiments approach: an application in manufacturing process modelling , 2005, Neural Computing & Applications.

[4]  T. Y. Lin,et al.  Optimum design for artificial neural networks: an example in a bicycle derailleur system , 2000 .

[5]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[6]  Bernard Widrow,et al.  Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[7]  Michael Sylvester Packianather,et al.  Optimizing the parameters of multilayered feedforward neural networks through Taguchi design of experiments , 2000 .

[8]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[9]  Bong-Jin Yum,et al.  Robust design of multilayer feedforward neural networks: an experimental approach , 2004, Eng. Appl. Artif. Intell..

[10]  Ulaş Çaydaş,et al.  A study on surface roughness in abrasive waterjet machining process using artificial neural networks and regression analysis method , 2008 .

[11]  W Laosiritaworn,et al.  Artificial neural networks parameters optimization design of experiments: An application in materials modeling , 2009 .

[12]  N. Ramesh Babu,et al.  A neuro-genetic approach for selection of process parameters in abrasive waterjet cutting considering variation in diameter of focusing nozzle , 2008, Appl. Soft Comput..

[13]  Yong Liao,et al.  Application of Artificial Neural Networks in Abrasive Waterjet Cutting Process , 2005, ISNN.

[14]  Shih-Ming Yang,et al.  Neural Network Design by Using Taguchi Method , 1999 .

[15]  Margaret J. Robertson,et al.  Design and Analysis of Experiments , 2006, Handbook of statistics.

[16]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[17]  Pratik J. Parikh,et al.  Parameter estimation for abrasive water jet machining process using neural networks , 2009 .

[18]  Jiju Antony,et al.  Design of experiments for engineers and scientists , 2003 .