A CASCADE CORRELATION NEURAL NETWORKS FOR THE PREDICTION OF SURFACE FINISH IN DRY TURNING OF SS 420 MATERIALS
Keywords:
Cascaded Correlation Neural Network, Taguchi Methods, Surface RoughnessAbstract
In the contribution, a cascaded correlation neural network optimization technique for optimization of cutting parameters for predicting the surface roughness is proposed. The cascaded correlation neural network algorithm has the powerful capabilities of learning and adaptation. Cascade-Correlation is a new architecture and supervised learning algorithm for artificial neural networks. Instead of just adjusting the weights in a network of fixed topology, Cascade-Correlation begins with a minimal network, then automatically trains and adds new hidden units one by one and creating a multi-layer structure. The Cascade-Correlation architecture has several advantages over existing algorithms: it learns very quickly, the network determines its own size and topology and it retains the structures it has built even if the training set changes. The validation of the methodology is carried out for dry turning of SS420 steel using uncoated tungsten carbide tools. It is observed that the present methodology is able to make accurate prediction of surface roughness by utilizing small sized training and testing datasets.
Downloads
References
Suresh Kumar Reddy N and Venkadeswara Rao P (2006), “Selection of an Optimal Parametric Combination for Achieving a Better Surface Finish in Dry Milling Using Genetic Algorithms”, International Journal of Advanced Manufacturing Technology, Vol. 28, 463- 473.
Sander M (1991), “A Practical Guide to Assessment of Surface Texture”, Mahr Perthen, Gottingen, Germany.
Majidi A P and Streicher M A (1984), “The Effect of Methods of Cutting and Grinding on Sensitization in Surface Layers on AISI 304 Stainless Steel”, National Association of Corrosion Engineers, Vol. 40(9), 445−458.
Ben Rhouma A, Braham C, Fitzpatrick M E, Lédion J and Sidhom H (2001), “Effects of Surface Preparation on Pitting Resistance, Residual Stress and Stress Corrosion Cracking in Austenitic Stainless Steels”, Journal of Materials Engineering and Performance, Vol. 10(5), 507−514
“Albrecht A B (1956), “How to Secure Desired Surface Finish in Turning Operations”, Am. Mach., 133–136.
Ansell C T and Taylor J (1962), “The Surface Finishing Properties of a Carbide and Ceramic Cutting Tool”, Proceedings of the Third International MTDR Conference, 25.
Chandiramani K L and Cook N H (1964), “Investigations into the Nature of Surface Finish and its Variation with Cutting Speed”, Journal of Engineering Industry, Vol. 80, 134–140.
Karmakar A (1970), “Factors Influencing Surface Finish During Fine Turning: Proceedings of the Fourth All India Machine Tool Design and Research Conference”, 123–125.
Dixit U S and Chandra S (2003), “A Neural Network Based Methodology for the Prediction of Roll Force and Roll Torque in Fuzzy Form for Cold Rolling Process”, International Journal of Advanced Manufacturing Technology, Vol. 22, 883–889.
Feng C X and Wang X F (2003), “Surface Roughness Prediction Modeling: Neural Networks versus Regression”, Vol. 35(1), 11–27.
Chryssolouris G and Guillot M (1990), “A Comparison of Statistical and AI Approaches to the Selection of Process Parameters in Intelligent Machining”, Journal of Engineering Industry, Vol. 112, 112–131.
Bogdon M Wilamoski et al (2001), “An Algorithm for Fast Convergence in Training Neural Networks”, IEEE Transaction of Neural Networks, Vol. 3, 1778-1782
Kosko B (1997), “Neural Networks and Fuzzy Systems: A Dynamic approach to Machine Intelligence”, Prentice Hall International, London.
Jang J S R, Sun C T and Mizutani E (1997), “Neuro Fuzzy and soft Computing”, Prentice Hall International, London
Jan Depenau (1995), “Automated Design of Neural Network Architecture for Classification”, Danish Academy of Technical Sciences Industrial Research Education Ph.D. Thesis EF-448, Aarhus University, August.
Fogel D B (1991), "An Information Criterion for Optimal Neural Network Selection", IEEE Trans. on Neural Networks, Vol. 2, 490-497.
Sivanandam S N et al (2006), “Introduction to Neural Networks using MATLAB 6.0”, Tata McGraw Hill.
Fahlman S E and Lebiere C (1990), “The Cascade-Correlation Learning Architecture, in Neural Information Processing Systems”, Editors D. Touretzky, Morgan Kaufmann Publishers, Inc., Denver, Colorado, 524-532.
Haward Demuth and Mark Beale (2000), “Neural Network Tool Box for use with MATLAB, User's Guide”, The Math Works Inc,.
