Modeling of the contact resistances in resistance spot welding (RSW) process

Bu çalışmada, nokta direnç kaynağında oluşan temas dirençleri yapay sinir ağları uygulaması kullanılarak modellenmiştir. Üst elektrot-iş parçası, iş parçası ara yüzey dirençleri ve alt elektrot-iş parçası arasındaki ilişkilerin modellenmesi için yapay sinir ağları yöntemi kullanılmıştır. Bu amaçla, SAE 1010 çeliği üzerinde çok sayıda deneyler yapılmıştır. Yapay sinir ağları metodunda sistemi tanıtma işlemi deney sonuçları kullanılarak gerçekleştirilmiştir. Sonuç olarak, bu çalışma temas dirençlerinin modellenmesinde yapay sinir ağları yönteminin etkili bir metot olduğunu göstermiştir.

Direnç nokta kaynağında temas dirençlerinin modellenmesi

This paper describes an application of neural network (NN) technologies with back propagation method (BPM) for modeling of the contact resistance in resistance spot welding (RSW) process. A neural network is used to construct the relationships between electrode force, tip geometry and contact resistances (upper electrode-workpiece, workpiece-workpiece and lower electrode-workpiece). A series of experiments were carried out using 1.5 mm SAE 1010 steel specimens to measure the contact resistances. Then, the neural network is trained with contact resistance experimental data, tested and compared in experimental data in terms of its ability to determine contact resistances. The results show that the proposed neural network is capable of mapping the complex relationships between the contact resistances and welding parameters.

___

1. James,P.S., Chandler,H.W., Evans,J.T., Wen,J., Browne,D.J., Newton,C.J., The Effect of Mechanical Loading on the Contact Resistance of Coated Aluminum , Materials Science & Engineering, A230, pp. 194-201, 1997.
2. Eşme,U., The Effect of Welding and Design Parameters on the Quality of the Resistance Spot Welding (RSW) Joints , MSc Thesis, Cukurova University Institue of Natural and Applied Sciences, Turkey, 2002.
3. Degarmo,E.P., Black,J.T., Kohser,R.A.,Materials and Processes in Manufacturing , Macmillan Publishing Company, New York, 1988.
4. Lantz,J., Principles of Resistance Welding-Weld Heads, Electrodes and Quality, Welding Design and Fabrication , pp. 46-49, April 2000.
5. Yeung,K.S., Thornton,P.H., Transient Thermal Analysis of Spot Welding Electrodes, AWS Welding Research , pp. 1-6, January 1999.
6. Hirsch,R.B., The Effect of Tip Force on Weld Quality and Electrode Life , Leibovitz V.P. Manufacturing Unitrol Electronics Inc, pp. 1-12, USA, 1998.
7. Bayramoglu,M., Esme,U. and Geren,N., Effects of welding parameters on the quality of resistance spot welded SAE 1010 steel sheet", International Journal of Materials and Product Technology, 19(5), 2003.
8. Nagesh,D.S. and Data,G.L., Prediction of weld bead geometry and penetration in shielded metal-arc welding using artificial Neural Networks , Journal of Materials Processing Technology, 123, 303-312, 2002.
9. Tarng,Y.S., Tsai,H.L. and Yeh,S.S., Modeling, optimization and classification of weld quality in tungsten inert gas welding , International Journal of Machine Tools & Manufacture 39, 1427 1438, 1999.
10. Aravinthan,A. and et al., A Neural Network System for Spot Weld Strength Prediction , Systems Engineering Research Group, Department of Mechanical and Manufacturing Engineering, 1999.
11. Brown,J.D and Rodd,M.G, Application of artificial intelligence techniques to resistance spot welding", Ironmaking & Steelmaking, 199-204, 1998.