Skip to main content
Article
Licensed
Unlicensed Requires Authentication

Prediction of the optimal FSW process parameters for joints using machine learning techniques

  • Furkan Sarsilmaz received his BSc degree in Technical Education Faculty at Firat University, Turkey, in 2000. He received his MSc and PhD degrees in the Department of Metallurgy in 2003 and 2008, respectively. Dr. Sarsılmaz is currently an Associate Professor at the School of Technology Faculty at Firat University in Elazığ,Turkey. Dr. Sarsılmaz’s research interests include solid state welding techniques and materials science.

     EMAIL logo     and

    Gurkan Kavuran is Assistant Professor in the Electrical and Electronics Engineering Department at Malatya Turgut Özal University, Faculty of Engineering and Natural Sciences. He received his B.Sc. degree in Electrical and Electronics Engineering from Firat University in 2008 and Ph.D. degree in Computer Engineering from Inonu University in 2017. His research interests are robotics, fractional calculus, control theory and applications, modeling and simulation, signal processing, embedded systems and artificial intelligence.
Published/Copyright: December 30, 2021
Become an author with De Gruyter Brill
Submit Manuscript Author Information
Materials Testing
From the journal Materials Testing Volume 63 Issue 12

Abstract

In this work, a couple of dissimilar AA2024/AA7075 plates were experimentally welded for the purpose of considering the effect of friction-stir welding (FSW) parameters on mechanical properties. First, the main mechanical properties such as ultimate tensile strength (UTS) and hardness of welded joints were determined experimentally. Secondly, these data were evaluated through modeling and the optimization of the FSW process as well as an optimal parametric combination to affirm tensile strength and hardness using a support vector machine (SVM) and an artificial neural network (ANN). In this study, a new ANN model, including the Nelder-Mead algorithm, was first used and compared with the SVM model in the FSW process. It was concluded that the ANN approach works better than SVM techniques. The validity and accuracy of the proposed method were proved by simulation studies.

Keywords: Friction-stir welding; ANN; SVM; aluminum alloys; nelder-mead nonlinear optimization algorithm
Associate Prof. Dr. Furkan Sarsilmaz Firat University, Faculty of Technology Department of Mechatronics Engineering, 23119, Elazığ, Turkey

About the authors

Associate Prof. Dr. Furkan Sarsilmaz

Furkan Sarsilmaz received his BSc degree in Technical Education Faculty at Firat University, Turkey, in 2000. He received his MSc and PhD degrees in the Department of Metallurgy in 2003 and 2008, respectively. Dr. Sarsılmaz is currently an Associate Professor at the School of Technology Faculty at Firat University in Elazığ,Turkey. Dr. Sarsılmaz’s research interests include solid state welding techniques and materials science.

Gürkan Kavuran

Gurkan Kavuran is Assistant Professor in the Electrical and Electronics Engineering Department at Malatya Turgut Özal University, Faculty of Engineering and Natural Sciences. He received his B.Sc. degree in Electrical and Electronics Engineering from Firat University in 2008 and Ph.D. degree in Computer Engineering from Inonu University in 2017. His research interests are robotics, fractional calculus, control theory and applications, modeling and simulation, signal processing, embedded systems and artificial intelligence.

References

1 F. Sarsilmaz: Weldability characteristics of dissimilar Al Cu friction stir weld joints, Materials Testing 54 (2012), No. 2, pp. 85-92 DOI:10.3139/120.11030010.3139/120.110300Search in Google Scholar

2 H. W. Zhang, Z. Zhang, J. T. Chen: 3D modeling of material flow in friction stir welding underdifferent process parameters, Journal of Materials Processing Technology 183 (2007), No. 1, pp. 62-70 DOI:10.1016/j.jmatprotec.2006.09.02710.1016/j.jmatprotec.2006.09.027Search in Google Scholar

3 F. Sarsilmaz, U. Çaydaş, A. Hasçalik, L. Tanriover: The joint properties of dissimilar aluminum plates joined by friction stir welding, International Journal of Materials Research 101 (2010), No. 5, pp. 692-699 DOI:10.3139/146.11032910.3139/146.110329Search in Google Scholar

4 Y. S. Sato, H. Kokawa, M. Enomoto, S. Jogan: Microstructural evolution of 6063 aluminum during friction-stir welding, Metallurgical and Materials Transactions A 30 (1999), pp. 2429-2437 DOI:10.1007/s11661-999-0251-110.1007/s11661-999-0251-1Search in Google Scholar

5 B. Das, S. Pal, S. Bag: Torque based defect detection and weld quality modelling in friction stir welding process, Journal of Materials Processing Technology 27 (2017), pp. 8-17 DOI:10.1016/j.jmapro.2017.03.01210.1016/j.jmapro.2017.03.012Search in Google Scholar

6 Y. Li, T. H. Lee, C. Wang, K. Wang, C. Tan: An artificial neural network model for predicting joint performance in ultrasonic welding of composites, Procedia CIRP 76 (2018), pp. 85-88 DOI:10.1016/j.procir.2018.01.01010.1016/j.procir.2018.01.010Search in Google Scholar

7 M. M. Krishnan, J. Maniraj, R. Deepak, K. Anganan: Prediction of optimum welding parameters for FSW of aluminium alloys AA6063 and A319 using RSM and ANN, Materials Today: Proceedings 5 (2018), No. 1, pp. 716-723 DOI:10.1016/j.matpr.2017.11.13810.1016/j.matpr.2017.11.138Search in Google Scholar

8 R. Padmanaban, R. V. Vignesh, A. P. Povendhan, A. P. Balakumharen: Optimizing the tensile strength of friction stir welded dissimilar aluminium alloy joints using particle swarm optimization, MaterialsToday: Proceedings 5 (2018), No. 11, pp. 24820-24826 DOI:10.1016/j.matpr.2018.10.28010.1016/j.matpr.2018.10.280Search in Google Scholar

9 H. Fathabadi: Novel filter based ANN approach for short-circuit faults detection, classification and location in power transmission lines, International Journal of Electrical Power & Energy Systems 74 (2016), pp. 374-383 DOI:10.1016/J.IJEPES.2015.08.00510.1016/J.IJEPES.2015.08.005Search in Google Scholar

10 B. Naik, J. Nayak, H. S. Behera, A. Abraham A self adaptive harmony search based functional link higher order ANN for nonlinear data classification. Neurocomputing 179 (2016), pp. 69-87 DOI:10.1016/J.NEUCOM.2015.11.05110.1016/J.NEUCOM.2015.11.051Search in Google Scholar

11 C. C. Nwobi, B. Q. Ochieze, S. Okiy Multi-objective optimization and modeling of age hardening process using ANN, ANFIS and genetic algorithm: Results from aluminum alloy A356/cow horn particulate composite, Journal of Materials Research and Technology 8 (2019), pp. 3054-3075 DOI:10.1016/J.JMRT.2019.01.03110.1016/J.JMRT.2019.01.031Search in Google Scholar

12 P. K. Freire, C. A. G. Santos, G. B. L. Silva: Analysis of the use of discrete wavelet transforms coupled with ANN for short-term streamflow forecasting, Applied Soft Computing 80 (2019), pp. 494-505 DOI:10.1016/J.ASOC.2019.04.02410.1016/J.ASOC.2019.04.024Search in Google Scholar

13 B. Sivaneasan, C. Y. Yu, K. P. Goh: Solar Forecasting using ANN with Fuzzy Logic Pre-processing, Energy Procedia 143 (2017), pp. 727-732 DOI:10.1016/J.EGYPRO.2017.12.75310.1016/J.EGYPRO.2017.12.753Search in Google Scholar

14 M. G. Na, J. W. Kim, D. H. Lim, Y. Kang: Residual stress prediction of dissimilar metals welding at NPPs using support vector regression, Nuclear Engineering and Design 238 (2008), pp. 1503-1510 DOI:10.1016/J.NUCENGDES.2007.12.00310.1016/J.NUCENGDES.2007.12.003Search in Google Scholar

15 S. Verma, M. Gupta, J. P. Misra: Performance evaluation of friction stir welding using machine learning approaches, MethodsX 5 (2018), pp. 1048-1058 DOI:10.1016/J.MEX.2018.09.00210.1016/J.MEX.2018.09.002Search in Google Scholar PubMed PubMed Central

16 S. Haykin: Neural Networks and Learning Machines, 3rd Ed., Pearson, Ontario, Canada (2009)Search in Google Scholar

17 I. Kırık, N. Özdemir, F.Sarsilmaz: Microstructure and Mechanical Behaviour of Friction Welded AISI 2205 AISI 1040 Steel Joints, Materials Testing 54 (2012), No. 10, pp. 683-687 DOI:10.3139/120.11037910.3139/120.110379Search in Google Scholar
Published Online: 2021-12-30

© 2021 Walter de Gruyter GmbH, Berlin/Boston

Articles in the same Issue

  1. Contents
  2. Fatigue testing
  3. Near-component testing of materials for cylinder heads to determine thermomechanical fatigue under superimposed high-frequency mechanical loads
  4. Dynamic mechanical behavior of composite materials reinforced by graphene and huntite minerals
  5. Materials testing for joining and additive manufacturing applications
  6. Effect of friction time on tensile strength and metallurgical properties of friction welded dissimilar aluminum alloy joints
  7. Prediction of the optimal FSW process parameters for joints using machine learning techniques
  8. Mechanical testing
  9. Effect of steel forming on vehicle side impact behavior
  10. Potentiodynamic corrosion behavior and microstructural features of gas tungsten constricted arc (GTCA)-welded superalloy 718 joints
  11. Improvement of the mechanical and damping behavior of nylon by integration of nanoclay platelets
  12. Numerical simulations/materialography
  13. Computer simulation of boronizing kinetics for a TB2 alloy
  14. Experimental evaluation and modelling of the boronizing kinetics of AISI H13 hot work tool steel
  15. Production-Oriented testing
  16. Determination of plastic deformation rate after solid particle erosion in ductile materials
  17. Production-Oriented testing/wear testing
  18. Hot press sintering effects and wear resistance of the Al-B4C composite coatings of an AA-2024 alloy
  19. Corrosion testing
  20. Corrosion behavior of particle reinforced aluminum composites
  21. Ultra-sonics
  22. Concrete anisotropy estimated from ultrasonic signal amplitudes
  23. Materials testing for civil engineering applications
  24. Application of ultra-high-performance concrete in prefabricated buildings
  25. Analysis of physical and chemical properties
  26. Comparison of reduced graphene oxides synthesized chemically with different reducing agents for supercapacitors
https://doi.org/10.1515/mt-2021-0058
Keywords for this article
Friction-stir welding; ANN; SVM; aluminum alloys; nelder-mead nonlinear optimization algorithm

Articles in the same Issue

  1. Contents
  2. Fatigue testing
  3. Near-component testing of materials for cylinder heads to determine thermomechanical fatigue under superimposed high-frequency mechanical loads
  4. Dynamic mechanical behavior of composite materials reinforced by graphene and huntite minerals
  5. Materials testing for joining and additive manufacturing applications
  6. Effect of friction time on tensile strength and metallurgical properties of friction welded dissimilar aluminum alloy joints
  7. Prediction of the optimal FSW process parameters for joints using machine learning techniques
  8. Mechanical testing
  9. Effect of steel forming on vehicle side impact behavior
  10. Potentiodynamic corrosion behavior and microstructural features of gas tungsten constricted arc (GTCA)-welded superalloy 718 joints
  11. Improvement of the mechanical and damping behavior of nylon by integration of nanoclay platelets
  12. Numerical simulations/materialography
  13. Computer simulation of boronizing kinetics for a TB2 alloy
  14. Experimental evaluation and modelling of the boronizing kinetics of AISI H13 hot work tool steel
  15. Production-Oriented testing
  16. Determination of plastic deformation rate after solid particle erosion in ductile materials
  17. Production-Oriented testing/wear testing
  18. Hot press sintering effects and wear resistance of the Al-B4C composite coatings of an AA-2024 alloy
  19. Corrosion testing
  20. Corrosion behavior of particle reinforced aluminum composites
  21. Ultra-sonics
  22. Concrete anisotropy estimated from ultrasonic signal amplitudes
  23. Materials testing for civil engineering applications
  24. Application of ultra-high-performance concrete in prefabricated buildings
  25. Analysis of physical and chemical properties
  26. Comparison of reduced graphene oxides synthesized chemically with different reducing agents for supercapacitors
Downloaded on 30.4.2026 from https://www.degruyterbrill.com/document/doi/10.1515/mt-2021-0058/html?lang=en
Scroll to top button