Prediction of mechanical properties as a function of welding variables in robotic gas metal arc welding of duplex stainless steels SAF 2205 welds through artificial neural networks

• Autorzy: Payares-Asprino, Carolina
• Języki publikacji: EN

Abstrakty

EN

Dual-phase duplex stainless steel (DSS) has shown outstanding strength. Joining DSS alloy is challenging due to the formation of embrittling precipitates and metallurgical changes during the welding process. Generally, the quality of a weld joint is strongly influenced by the welding conditions. Mathematical models were developed to achieve high-quality welds and predict the ideal bead geometry to achieve optimal mechanical properties. Artificial neural networks are computational models used to address complex nonlinear relationships between input and output variables. It is one of the powerful modeling techniques, based on a statistical approach, presently practiced in engineering for complex relationships that are difficult to explain with physical models. For this study robotic GMAW welding process manufactured the duplex stainless steel welds at different welding conditions. Two tensile specimens were manufactured from each welded plate, resulting in 14 tensile specimens. This research focuses on predicting the yield strength, tensile stress, elongation, and fracture location of duplex stainless steel SAF 2205 welds using back-propagation neural networks. The predicted values of tensile strength were later on compared with experimental values obtained through the tensile test. The results indicate <2% of error between observed and predicted values of mechanical properties when using the neural network model. In addition, it was observed that the tensile strength values of the welds were higher than the base metal and that this increased when increasing the arc current. The welds' yield strength and elongation values are lower than the base metal by 6%, ~ 9.75%, respectively. The yield strength and elongation decrease might be due to microstructural changes when arc energy increases during the welding.

Słowa kluczowe

PL

sieci neuronowe; spawanie; właściwości mechaniczne

EN

neural network; welding; mechanical properties

• Czasopismo: Advances in Materials Science
• Rocznik: 2021
• Tom: Vol. 21, nr 3(69)
• Strony: 75--90
• Opis fizyczny: Bibliogr. 37 poz., tab., wykr., il. zdj.

Twórcy

autor

Payares-Asprino, Carolina

• Mechanical Engineering Department Norwich University, Northfield, USA,

Bibliografia

• 1. Ma M., Shrikrishna K.A., Sathiya P.: The impact of heat input on the strength, toughness, microhardness, microstructure and corrosion aspect of friction welded duplex stainless steel joints. Journal of Manufacturing Process 18 (2015) 92-106.
• 2. Zou Y., Ueji R., Fujii H.: Mechanical Properties of advanced active-TIG welded duplex stainless steel and ferrite steel. Materials Science and Engineering A 620 (2015) 140-148
• 3. Palanivel R., Mathews P.K., Murugan N.: Development of mathematical model to predict the mechanical properties of friction stir welded AA6351 aluminum alloy. Journal of Engineering Science and Technology Review 4 (1) (2011) 25-31.
• 4. Verma R. P., Pandey K.N.: Multi-response optimization of process parameters of GMA welding of dissimilar AA 6061-T6 and AA 5083-O aluminium alloy for optimal mechanical properties. Materials Today: Proceedings (2021) in Press.
• 5. Heidarzadeh A., Saeid T.: Prediction of mechanical properties in friction stir welds of pure copper. Materials and Design 52 (2013) 1077–1087.
• 6. Luo Y., Liu J., Xu H., Xiong C., Liu L.: Regression modeling and process analysis of resistance spot welding on galvanized steel sheet. Materials and Design 30 (2009) 2547–2555.
• 7. Marichamy M., Babu S.: Experimental study and Taguchi optimization of process parameter on mechanical properties of A319 aluminum alloy using friction stir welding. Materials Today: Proceedings 39 (2021) 1527–1531
• 8. Rao S.P., Gupta O.P., Murty S.S.N., Rao A.K.: Effect of process parameters and mathematical model for the prediction of bead geometry in pulsed GMA welding. International Journal Advanced Manufacturing Technology 45 (2009) 45 496 –505.
• 9. Kumar S., Singh, R.: Optimization of process parameters of Metal Inert Gas welding with preheating on AISI 1018 mild steel using grey based Taguchi method. Measurement 148 (2019) 106924.
• 10. Vakili-Tahami F., Majnoun P., Ziaei-Asl A.: Controlling the in-service welding parameters for T-shape steel pipes using neural network. International Journal of Pressure Vessels and Piping 175 (2019) 103937.
• 11. Pal S., Pal S.K, Samantaray A.K.: Artificial neural network modeling of weld joint strength prediction of a pulsed Metal Inert Gas welding process using arc signals. Journal of Materials Processing Technology 202 (2008) 464-474.
• 12. Atharifar H.: Optimum parameters design for friction stir spot welding using a genetically optimized neural network system. Proceedings of the Institution of Mechanical Engineer Part B: Journal of Engineering Manufacture 224 (2009) 403-418.
• 13. Saoudi A., Fellah M., Hezil N., Lerari D., Khamouli F., Atoui L., Bachari K., Morozova J., Obrosov A., Samad M.A.: Prediction of mechanical properties of welded steel X70 pipeline using neural network modelling. International Journal of Pressure Vessels and Piping 186 (2020) 104153.
• 14. Sivagurumanikandan N., Saravanan S., Kumar G.S., Raju S., Raghukandan K.: Prediction and optimization of process parameters to enhance the tensile strength of Nd: YAG laser welded super duplex stainless steel. Optik 157 (2018) 833-840.
• 15. Chaki S.: Neural networks based prediction modelling of hybrid laser beam welding process parameters with sensitivity analysis. SN Applied Sciences 1(10) (2019) 1-11.
• 16. Cortéz V.H.L, Valdés F.A.R, Treviño L.T.: Weldability of martensitic steel by resistance spot welding a neural network optimization in the automotive industry. Materials and Manufacturing Processes 24 (12) 1412-1417.
• 17. Thekkuden D.T., Mourad A-H.I.: Investigation of feed-forward back propagation ANN using voltage signals for the early prediction of the welding defect. SN Applied Sciences 1 (2019) 1615.
• 18. Kim I.S., Son J.S., Park C.E., Lee C.W., Yarlagadda K.D.V Prasad.: A study on prediction of bead height in robotic arc welding using neural network. Journal of Materials Processing Technology 130-131 (2002) 229-234.
• 19. Payares-Asprino C., Steele J.P.H.: Optimization of GMAW welding parameters in duplex stainless steel welds mechanical properties. Procedures of the ASME 2009 Pressure Vessels and Piping Division Conference; Prague, Czech Republic; PVP2009:77203.
• 20. ASTM A789/A789M-18 Standard Specification for Seamless and Welded Ferritic/Austenitic Stainless Steel Tubing for General Service; 2018.
• 21. ASTM A815/A815M-18 Standard Stainless Steel Specification for Wrought Ferritic, Ferritic/ Austenitic, and Martensitic Stainless Steel Piping Fittings; 2018.
• 22. AVESTA WELDING. How to Weld AVESTA SHEFFIELD. Sweden, Trade Literature, 2005.
• 23. Payares-Asprino C, Patricia Muñoz-Escalona P.: Modeling to predict the percentage of ferrite as a function of heat input in Gas Metal Arc Welding of duplex stainless steel SAF2205 weldment. Proceedings of ESSC & DUPLEX 2019 Conference 285-294.
• 24. ASTM A370.: Standard Test Methods and Definitions for Mechanical Testing of Steel Products, Edition 2019.
• 25. ASTM E8/E8M.: Standard Methods for Tension Testing of Metallic Materials, Edition 2018.
• 26. Muthupandi V., Srinivassa P.B., Asehadri S.K, Sundaresam S.: Effect of weld metal chemistry and heat input of the structure and properties of duplex stainless steel welds, Materials Science and Engineering A 358 (1-2) (2003) 9-16.
• 27. Vahman M., Shamanian M., Golozar M.A., Jalali A., Ahl Sarmadi M., Kangazian J.: The effect of welding heat input on the structure– property relationship of a new grade super duplex stainless steel. Steel Research International 91(1) (2020) 1900347.
• 28. Lee C-H., Chang K-Ho: Comparative study on girth weld-induced residual stresses between austenitic and duplex stainless steel pipe welds. Applied Thermal Engineering 63 (2014) 140-150.
• 29. Wu T., Wang J., Li H., Jiang Z., Liu C., Zhang H.: Reformation behavior of austenite in duplex stainless steel with rapid heat treatment. Steel Research International (90)2 (2018) 1800305.
• 30. Varbai B., Pickle T., Májlinger K.: Effect of heat input and role of nitrogen on the phase evolution of 2205 duplex stainless steel weldment. International Journal of Pressure Vessels and Piping 176 (2019) 103952.
• 31. Baghdadchi A., Hosseini A. V., Hurtig K., Karlsson L.: Promoting austenite formation in laser welding of duplex stainless steel-impact of shielding gas and laser reheation. Welding in the World 65 (2021) 499-511.
• 32. El-Batahgy A.M., Khourshid A.F., Sharef T.: Effect of laser beam welding parameters on microstructure and properties of duplex stainless steel. Material Science and Applications 2(10) (2011) 1443.
• 33. Haykin S.S.: Neural Networks: A Comprehensive Foundation, Macmillan College Publishing Company, New York, (1994) 138-229.
• 34. Beale M.H., Haga H.B., Demuth H.B.: Neural Network ToolboxTM user’s guide. R22012a, the MathWorks, Inc., Apple Hill Drive Natick, 2012 MA 01760-2098.
• 35. Freeman J.A., Skapura D.M.: Algorithms, Applications, and Programming Techniques, Addison-Wesley Publishing Company, USA, 1991.
• 36. Kanzow C., Yamashita N., Fukushima M.: Levenberg-Marquardt methods with strong local convergence properties for solving nonlinear equations with convex constraints. Journal of Computational Applied Mathematics 172 (2) (2004) 375-397.
• 37. Nagesh D.S., Datta G.L.: Prediction of weld bead geometry and penetration in shielded metal-arc welding using artificial neural networks. Journal of Materials Processing Technology 123 (2002) 303–312.

Uwagi

1. Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).

2. The author would like to thank the Norwich University Faculty Development Funding for the Charles A. Dana Research Fellowship AY19-20 and the resourceful contribution of the Kreitzberg Library. The author is also grateful to the Colorado School of Mines for the support of this research, allowing use of the GMA welding FANUC 100iB® Robot.

Identyfikatory

DOI

10.2478/adms-2021-0019