A Comparative Study between Linear and Nonlinear Regression Analysis for Prediction of Weld Penetration Profile in AC Waveform Submerged Arc Welding of Heat Resistant Steel
Authors
-
Department of Mechanical & Aerospace Engineering, IIT Hyderabad, Sangareddy ,IN
Uttam Kumar Mohanty -
Department of Mechanical & Aerospace Engineering, IIT Hyderabad, Sangareddy ,INAbhay Sharma
-
Technical Research Institute, Hitachi Zosen Corporation, Osaka ,JPMitsuyoshi Nakatani
-
Technical Research Institute, Hitachi Zosen Corporation, Osaka ,JPAkikazu Kitagawa
-
Joining & Welding Research Institute, Osaka University ,JPManabu Tanaka
-
Joining & Welding Research Institute, Osaka University ,JPTetsuo Suga
DOI:
https://doi.org/10.22486/iwj/2019/v52/i1/178187Keywords:
Weld Bead Geometry, Linear Regression, Process Variable, Nonlinear Regression, Model Adequacy.Abstract
Alternating current with square waveform provides better control of weld quality and reduces the effect of the arc-blow in the submerged arc welding process. This paper presents a comparative study in between conventionally used linear regression and newly proposed nonlinear regression analysis for prediction of weld penetration profile, i.e. weld width, penetration and penetration shape factor in the AC waveform welding of heat resistant steel. The comparison is based on second order linear regression and nonlinear regression analysis using Levenberg-Marquardt method. The frequency, electrode negative ratio, welding current, and welding speed are used as input parameters to obtain the models for penetration and width. The models are developed following a design of experiment and extra experiments are conducted to check the adequacy of the models. The results show that the Levenberg-Marquardt method associated with exponential function without considering constant term is more effective as compared to second order linear regression in terms of predictability and accuracy. The significant effect of process variables on the outcomes is analyzed. The investigation shows a new approach to weld penetration profile prediction that can be horizontally deployed to other welding process where predication is difficult because of the complex shape of the weld bead.
References
Monteiro LS and Scotti A (2013); A methodology for parameterization of the MIG/MAG CA and its application in service repair of pipelines of oil and gas, Proc.ICME, Ribeirao Preto, SP, Brazil, pp. 8103–8117.
Pepin TJ (2009); Effects of submerged arc weld (SAW) parameters on bead geometry and notch-toughness for X70 and X80 linepipe steels, Master thesis, Edmonton, Alberta.
Choudhury S, Sharma A, Mohanty UK, Kasai R, Komura M and Tanaka M (2017); Mathematical model of complex weld penetration profile: A case of square AC wave form arc welding, J. Manuf. Process., pp. 483–491.
Yang L, Bibby M and Chandel R (1993); Linear regression equations for modeling the submerged-arc welding process, J. Mater. Process. Technol., 39(1), pp. 33–42.
Sen M, Mukherjee M and Pal TK (2014); Prediction of weld bead geometry for double pulse gas metal arc welding process by regression analysis, In Fifth International and 26th All India Manufacturing Technology, Design and Research Conference, IIT Guwahati, Assam, India., pp. 814-816.
Singh RP, Garg RK and Shukla DK (2015); Mathematical modeling of effect of polarity on weld bead geometry in submerged arc welding, J. Manuf. Processes, 21, pp.14-22.
Datta S, Bandyapadhyay A and Pal PK (2006); Quadratic response surface modeling for prediction of bead geometry in submerged arc welding, Indian Weld J., 39(1), pp.33-43.
Saha S and Das S (2018); Investigation on the effect of activating flux on tungsten inert gas welding of austenitic stainless steel using AC polarity, Indian Welding J., 51(2), pp. 84-92.
Mahapatra MM, Ali MS, Dutta GL, Pradhan B (2005); Modelling and predicting the effects of process parameters on weldment characteristics in shielded metal arc welding, Indian Weld J., 38 (2), pp. 22-29.
Roy J, Majumder A, Rai RN, Sana SC (2015); Study the influence of heat input on the shape factors and HAZ width during submerged arc welding, Indian Weld J., 48(1), pp. 51-55.
Sharma A, Arora N and Mishra B (2015); Mathematical model of bead profile in high deposition welds, J. Mater. Process. Technol., 220, pp.65-75.
Petkovic D (2017); Prediction of laser welding quality by computational intelligence approaches, Optik, 140, pp.597-600.
Campbell S, Galloway A and McPherson N (2012); Artificial neural network prediction of weld geometry performed using GMAW with alternating shielding gases, Welding J., 91(6), pp.174–181.
Dhas JER and Kumanan S (2010); Neuro hybrid model to predict weld bead width in submerged arc welding process, J. Scientific Ind. Res., 69, pp.350–355.
Sarkar A, Dey P, Rai RN and Saha SC (2016); A comparative study of multiple regression analysis and back propagation neural network approaches on plain carbon steel in submerged-arc welding, SÄdhanÄ., 41(5), pp.549-559.
Xiong J, Zhang G, Hu J and Wu L (2014); Bead geometry prediction for robotic GMAW-based rapid manufacturing through a neural network and a second-order regression analysis, J. Intell. Manuf., 25(1), pp.157–163.
Kumar R, Dilthey U, Dwivedi DK and Ghosh PK (2009); Thin sheet welding of Al 6082 alloy by AC pulseGMA and AC wave pulse-GMA welding, Mater. Des., 30, pp. 306-313.
Tong H, Ueyama T, Harada S and Ushio M (2001); Quality and productivity improvement in aluminium alloy thin sheet welding using alternating current pulsed metal inert gas welding system, Sci. Technol. Weld .Join., 6 (4), pp.203-208.
Murugan N and Gunaraj V (2005); Prediction and control of weld bead geometry and shape relationships in submerged arc welding of pipes, J. Mater. Process. Technol., 168, pp.478-487.
