# (Mathematic Model by Response Surface Methodology and Artificial Neural Network for Predict Result of Tensile Shear and Nugget Size of Zinc Coated Steel JIS G3313 Welded by Resistance Spot Welding)

## Authors

• ปรัชญา เพียสุระ Department of Production Technology Education, Faculty of Industrial Education and Technology, King Mongkut University of Technology Thonburi
• พีรวุฒิ เล้าภาษิต Department of Production Technology Education, Faculty of Industrial Education and Technology, King Mongkut University of Technology Thonburi

## Keywords:

Mathematic Model, Response Surface Methodology, Artificial Neural Network, Resistance Spot Welding, Zinc Coated Steel

## Abstract

Abstract

This research described to the determine an optimization mathematic model using response surface methodology in central composite design method and artificial neural network (ANN) for predicting the of tensile shear and nugget size in the zinc coated steel JIS G3313. The following resistance spot welding (RSW) parameters were studied: the welding current, welding time, and electrode force. The resulting materials were examined using tensile shear tests which were observed nugget size and microstructure with scanning electron microscopy (SEM). The microstructure phenomenon could be explained by the welding optimum condition that fine pearlite and intensity in heat affected zone. The research results reveal that an optimum RSW parameters were welding current of 12 kilo amperes, welding time of 9 cycle and 1.5 kilo newton electrode force. The fine acicular ferrite occurred in the nugget size, which results in increased welding material high mechanical property. The ANN model with the proposed mathematical model, which tensile shear represents 3 neurons for the input 10 neurons for 1 hidden layer and 1 output neurons (3-10-1). The ANN model was developed to establish of the nugget predict represents 3 neurons for the input 5 neurons for 1 hidden layer and 1 output neurons (3-5-1). The mean square error (MSE) and coefficient of determination (R2) for tensile shear predict was showed that of 0.0026 and 0.956 respectively, which nugget size predicted MSE of 0.0004 and R2 of 0.958. This research, the related manufacturing sector can use research data and mathematical models was used to predict and quality control of the RSW processes to obtain tensile shear and the nugget size according to the acceptance criteria.

## Author Biographies

### ปรัชญา เพียสุระ, Department of Production Technology Education, Faculty of Industrial Education and Technology, King Mongkut University of Technology Thonburi

Abstract

This research described to the determine an optimization mathematic model using response surface methodology in central composite design method and artificial neural network (ANN) for predicting the of tensile shear and nugget size in the zinc coated steel JIS G3313. The following resistance spot welding (RSW) parameters were studied: the welding current, welding time, and electrode force. The resulting materials were examined using tensile shear tests which were observed nugget size and microstructure with scanning electron microscopy (SEM). The microstructure phenomenon could be explained by the welding optimum condition that fine pearlite and intensity in heat affected zone. The research results reveal that an optimum RSW parameters were welding current of 12 kilo amperes, welding time of 9 cycle and 1.5 kilo newton electrode force. The fine acicular ferrite occurred in the nugget size, which results in increased welding material high mechanical property. The ANN model with the proposed mathematical model, which tensile shear represents 3 neurons for the input 10 neurons for 1 hidden layer and 1 output neurons (3-10-1). The ANN model was developed to establish of the nugget predict represents 3 neurons for the input 5 neurons for 1 hidden layer and 1 output neurons (3-5-1). The mean square error (MSE) and coefficient of determination (R2) for tensile shear predict was showed that of 0.0026 and 0.956 respectively, which nugget size predicted MSE of 0.0004 and R2 of 0.958. This research, the related manufacturing sector can use research data and mathematical models was used to predict and quality control of the RSW processes to obtain tensile shear and the nugget size according to the acceptance criteria.

### พีรวุฒิ เล้าภาษิต, Department of Production Technology Education, Faculty of Industrial Education and Technology, King Mongkut University of Technology Thonburi

Abstract

This research described to the determine an optimization mathematic model using response surface methodology in central composite design method and artificial neural network (ANN) for predicting the of tensile shear and nugget size in the zinc coated steel JIS G3313. The following resistance spot welding (RSW) parameters were studied: the welding current, welding time, and electrode force. The resulting materials were examined using tensile shear tests which were observed nugget size and microstructure with scanning electron microscopy (SEM). The microstructure phenomenon could be explained by the welding optimum condition that fine pearlite and intensity in heat affected zone. The research results reveal that an optimum RSW parameters were welding current of 12 kilo amperes, welding time of 9 cycle and 1.5 kilo newton electrode force. The fine acicular ferrite occurred in the nugget size, which results in increased welding material high mechanical property. The ANN model with the proposed mathematical model, which tensile shear represents 3 neurons for the input 10 neurons for 1 hidden layer and 1 output neurons (3-10-1). The ANN model was developed to establish of the nugget predict represents 3 neurons for the input 5 neurons for 1 hidden layer and 1 output neurons (3-5-1). The mean square error (MSE) and coefficient of determination (R2) for tensile shear predict was showed that of 0.0026 and 0.956 respectively, which nugget size predicted MSE of 0.0004 and R2 of 0.958. This research, the related manufacturing sector can use research data and mathematical models was used to predict and quality control of the RSW processes to obtain tensile shear and the nugget size according to the acceptance criteria.

## References

เอกสารอ้างอิง
[1] R.L. O’Brien. “Welding Handbook” (8th ed.), American Welding Society, 1992.
[2] Toyota Motor Corporation, “Toyota New Global Architecture”, Available: http://www.toyota.co.th/ TNGA, 5 August 2018.
[3] W.H. Kearns, “Welding Handbook” (7th ed), American Welding Society,1982.
[4] L.F. Jeffus, “Welding Principles and Applications” Cengage Learning, 2014.
[5] R.L. O’Brien, “Welding Hand Book Test Methods for Evaluating Welded Joints”, (9th ed), American Welding Society, 2001.
[6] Japanese Industrial Standard, “JIS Z 3140-2017 Method of Inspection for Spot Welding”, Japanese Standard Association, 2017.
[7] C. Summerville, P. Compston and M. Doolan, “A Comparison of Resistance Spot Weld Quality Assessment Techniques”, Procedia Manufacturing 29, 2019, pp. 305-312.
[8] Aravinthan A. and Mohd A.N., “Spot Welding Parameter Optimization to Improve Weld Characteristics for Dissimilar Metals”, International Journal of Scientific & Technology Research 4, 2015, pp. 75-80.
[9] H. Long, Y. Hu, X. Jin, H. Yu and H. Zhu, “An Optimization Procedure for Spot-Welded Structures Based on SIMP Method”, Computational Materials Science 117, 2016, pp. 602-607.
[10] K. Zhou and P. Yao, “Overview of Recent Advances of Process Analysis and Quality Control in Resistance Spot Welding” Mechanical Systems and Signal Processing 124, 2019, pp.170-198.
[11] T. Arunchai, K. Sonthipermpoon, P. Apichayakul and K. Tamee, “Resistance Spot Welding Optimization Based on Artificial Neural Network”, International Journal of Manufacturing Engineering 54784, 2014, pp.1-6.
[12] D. Shah and D.P. Patel, “Prediction of Weld Strength of Resistance Spot Welding Using Artificial Neural Network” Journal of Engineering Research and Applications3, 2013, pp.1486-1491.
[13] H. Pashazadeh, Y. Gheisari, and M. Hamedi. "Statistical Modeling and Optimization of Resistance Spot Welding Process Parameters using Neural Networks and Multi-Objective Genetic Algorithm." Journal of Intelligent Manufacturing 27, 2016, pp. 549-559.
[14] F. Ahmed and K.Y. Kim, “Data-driven Weld Nugget Width Prediction with Decision Tree Algorithm” Procedia Manufacturing 10, 2017, pp. 1009-1019.
[15] K. He and X. Li. "A Quantitative Estimation Technique for Welding Quality using Local Mean Decomposition and Support Vector Machine." Journal of Intelligent Manufacturing 27, 2016, pp.525-533.
[16] B.S. Gawai, R.L. Karwande, M.D. Irfan and P.S. Thakare, “Mathematical Modeling and Optimization of Process Parameters for Tensile Strength and Nugget Diameter in Resistance Spot Welding of HR E-34 Steel Sheet Joint”, Proceedings of International Conference on Intelligent Manufacturing and Automation, Mumbai, India, 2018, pp. 3-13.
[17] F. A. Ghazali, Z. S. Yupiter, H. P. Manurung, Y. M. Taib, K. M. Hyie, M. A. Ahamat and S. H. A. Hamidi, Three Response Optimization of Spot-Welded Joint using Taguchi Design and Response Surface Methodology Techniques, The Advances in Joining Technology, 2018, pp. 85-95.
[18] F. Mirzaei, H. Ghorbani and F. Kolahan, Numerical Modeling and Optimization of Joint Strength in Resistance Spot Welding of Galvanized Steel Sheets, The International Journal of Advanced Manufacturing Technology, 92, 2017, pp. 3489–3501.
[19] Japanese Industrial Standard, “JIS Z 3136-1999 Specimen Dimensions and Procedure for Shear Testing Resistance Spot and Embossed Projection Welded Joints”, Japanese Standard Association, Japan, 1999.
[20] Mohammad D., Ahmed H. E., Othman J., Othman A. K. and Sharifah M., Comparison of Artificial Neural Network Transfer Functions Abilities to Simulate Extreme Runoff Data, 2012 International Conference on Environment, Energy and Biotechnology, Singapore, 2012, pp.39-44.
[21] Yixi Z., Yansong Z. and Xinmin L., Analysis of Fracture Modes of Resistance Spot Welded Hot-Stamped Boron Steel Metals, 764, 2018 pp.1-15.
[22] Chapple S.C., Temple P.I., Senatore D.A., Barras K. and Mccoy, R., “Welding Hand Book Weld Quality (9th ed., Vol.1)” American Welding Society, Miami, 2001.
[23] L. Kaščák, J. Viňáš and R. Mišičko, Influence of Welding Current in Resistance Spot Welding on the Properties of Zn Coated Steel DX51D, Songklanakarin Journal of Science and Technology 38, 2016, pp. 237-242.
[24] Lin H.C., Hsu C.A., Lee C.S., Kuo T.Y. and Jeng S.L., Effects of Zinc Layer Thickness on Resistance Spot Welding of Galvanized Mild Steel, Journal of Materials Processing Technology., 251, 2018, pp. 205-213
[25] Myers R.H., “Montgomery DC., Response Surface Methodology Process and Product Optimization using Designed Experiments”, 2 ed., John Wiley and Sons, New York, 2002.
[26] W.B. Oha, T.J. Yun, B.R. Lee, C.G. Kim, Z.L. Liang and I.S. Kim, A Study on Intelligent Algorithm to Control Welding Parameters for Lap-joint, Procedia Manufacturing,30, 2019, pp. 48-55.