OPTIMAL BRAIN SURGEON PRUNING OF NEURAL NETWORK MODELS OF MANUFACTURING PROCESSES
Main Article Content
Abstract
In this paper, Optimal Brain Surgeon (OBS) pruning algorithm is proposed to optimize network architecture with respect to testing patterns error and overcoming the overlitting problem. Turning process is used as case study to improve the performance of the neural network-surface roughness model. Using the proposed algorithm reduced the prediction error on testing patterns from 0.6237 to 0.2854 based on the absolute percent error estimate. Also, a noticeable improvement is made in correlation coefficient from 0.8656 to 0.9807 making the network more reliable for new operating conditions.
Article Details
How to Cite
Publication Dates
References
Bauer, B., D.Georges,: B.Geropp and M.Poschmann, (2002), Lathe Tool Wear Monitoring With Neural Networks, www.formikrosys.de/veroeffentlichungen.html
Demuth H.B.and M.Beala. (1998), Neural Network Toolboxa: User's Guide. Ver, 3, The Mathworks. Inc., Natik, MA
Hasegawa M.. A.Seireg, and R.A.Lindberg, (1976), Surface Roughness Model For Turning. Tripology International.
Hintz-Madsen M., 1K.Hansen, JLarsen. M.W.Pedersen and M.Larsen. 1998), Neural Classifier Construction Using Roularivion. Prusin and Test Error Estimation, Neual Networks. Vol. 11 Pp.1659-1670
Kazem B.L,( 2004), A Neural Network Prediction Model For Surface Finish In Turning process. Acccepted at the 5th Jordanian International Mechanical Engineering Conference.
Markos S., Z.J.Viharos and L.Monostori. Quality-Oriented Comprehensive Modelling Of Machining Processes www.sztaki.hu²-viharos/homepage/Publications/1998 IMEKO/QUALITY%200RIENTED%20CO MPREHENSIVE.pdf
Nadgir A, and T,Özel (2000), Neural Network Modeling Of Flank Wear For Tool Condition Monitoring In Orthogonal Cutting, 4th International Conference on Engineering Design and Automation. Orlando. Florida. USA. July 30-August 2.
Ozel T. and A.Nadgir, (2002. Predictien Of Mank Wear By Using Backpropapation Neural Network Modeling When Cutting Hardened 1-11 Steel With Chanfered and Honed CBN Tools Intermational Journai of Machine Tools and Manulacturing, Vol. 42. pp. 287-297
Principe J.C, N.R.Euliano and W.C.Lefebvre,( 2000), Neural and Adaptive Systems: Fundamentals Through Simulations, JOHN WILEY &SONS, INC
Scheffer C.and P.S.Heyns,( 2001), Wear Monitoring In Tuming Operations Using Vibration and Strain Measurements, Mechanical Systems and Signal Processing, Vol. 15,No. 6.pp. 1185-1202
Silva RG., R.L Reuben, K.JBaker and S.J.Wileox( 1998), Tool Wear Monitoring Of Tuming Operations By Neural Network and Expert System Classification Of a Feature Set Generated From Moltiple Sensors, Mechanical Systems and Signal Processing, Vol. 12. No 2
Silva R G. R.L Reuben, KJBaker and S.J Wilcox.( 2003). A Neural Network Apprach Fo Togt Wear Monioring,www.glam.ac.uk/sot/resenrch/MechMan/index