Indian Welding Journal

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Estimation of Bead on Plate Geometry of Super Duplex Stainless Steel on Low Carbon Steel using Artificial Neural Networks


Affiliations
1 Mechanical Engineering Department Kalyani Government Engineering College Kalyani - 741235, West Bengal, India
     

   Subscribe/Renew Journal


Bead on plate geometry gives a priori knowledge about weld characteristics. In the current work, bead on plate experimental data are taken from one previously published work and different training algorithms are applied to get trained with the experimental data. Experiments were done using four-factor, five-level central composite rotatable design with full replication technique using response surface methodology. The working range of each parameter was decided upon by inspecting the weld bead for smooth appearance and the absence of visible defects. Bead of Super Duplex Stainless Steel was deposited on low carbon steel substrate using flux cored arc welding. An attempt is made in this work to predict the bead geometry parameters using Artificial Neural Networks (ANN). Effectiveness of three different ANN training functions are compared to choose the best model of these three. TRAINLM (LevenbergMarquardt) algorithm is found to be the most appropriate training function for prediction of bead geometry in this work.

Keywords

Welding, FCAW, Bead on Plate welding, Super Duplex Stainless Steel, Neural Networks, ANN, Prediction.
User
Subscription Login to verify subscription
Notifications
Font Size

  • Saha MK and Das S (2016); A review on different cladding techniques employed to resist corrosion, Journal of the Association of Engineers, India, 86(1&2), pp.51-63.

  • Saha MK and Das S (2018); Gas metal arc weld cladding and its anti-corrosion performance- a brief review, Athens Journal of Technology and Engineering, 5(2), pp.155-174.

  • Kurtulmus M, Yukler AI, Bilici MK and Catalgol Z (2015); Effects of welding current and arc voltage on FCAW weld bead geometry, International Journal of Research in Engineering and Technology, 4(9), pp.23-28.

  • Cary HB and Helzer SC (2005); Modern Welding Technology, Prentice Hall, New York.

  • Palani PK and Murugan N (2006); Development of Mathematical Models for Prediction of Weld Bead Geometry in Cladding by Flux Cored Arc Welding, International Journal of Advanced Manufacturing Technology, 30, pp.669-676.

  • Nowacki J, Maciej UM and lajac P (2009); FCAW welding of duplex steel in construction of chemical cargo carriers, Welding International, 23(1), pp.34-42.

  • Mandai A, Saha MK, Hazra Rand Das S (2016); Influence of heat input on weld bead geometry using duplex stainless steel wire electrode on low alloy steel specimens, Cogent Engineering, 3(1), pp.1143598/1-14

  • Saha MK, Dhara LN and Das S (2017); The variation of profile of y-stainless steel weld bead with a change of heat input, Reason-A Technical Journal, 16, pp.46-56.

  • Saha MK and Das S (2020); Weld bead profile of duplex stainless steel bead on E350 low alloy steel plate done by FCAW using 100% C02 as shielding gas, Journal of the Association of Engineers, India, 90(1-2), pp.28-38.

  • Bose s and Das S (2022); Evaluating suitable weld condition to obtain enlarged bead widttl of 316 stainless steel towards weld cladding, Indian Science Cruiser,.36(1), pp.19-27.

  • Saha MK, Hazra R, Mondal A and Das S (2019); Effect of heat input on geometry of austenitic stainless steel weldbead on low carbon steel, J. Inst. Eng. (Indian) Ser. C, 100(4), pp.607-615.

  • Haykin S (2005); Neural Networks- A Comprehensive Foundation, 2nd ed., Pearson Prentice Hall.

  • Zhao C and Gao F {1999); Melt temperature profile prediction for thermoplastic injection molding, Polymer Engineering &Science, 39(9), p.1787.

  • Petrova T and Kazmer D (1999); Hybrid neural models for pressure control in injection molding, Advances in Polymer Technology, 18(1), pp.19-31.

  • Cheng PJ and Lin SC (2000); Using neural networks to predict bending angle of sheet metal formed by laser, International Journal of Machine Tools & Manufacture, 40 pp.1185-1197.

  • Jacobs R A (1988); Increased rates of convergence through learning rate adaptation, Neural Networks, 1(4), pp.295-307.

  • Dass, Roy Rand Chattopadhyay AB (1996); Evaluation of wear of turning carbide inserts using neural networks, International Journal of Machine Tools and Manufacture, 36(7), pp.789-797.

  • Das S, Chattopadhyay AB and Murthy ASR (1996); Force parameters for on-line tool wear estimation: a neural network approach, Neural Networks, 9(9), pp.1639-1645.

  • DasS, BandyopadhyayPPandChattopadhyayAB(1997); Neural-networks-based tool wear monitoring in turning medium carbon steel using a coated carbide tool, Journal of Materials Processing Technology, 63(1-3), pp.187-192.

  • Ghanta KC and Das S (2013); Neural networks based modeling of viscosity for facilitating transportation of magnetite ore-water slurry, Journal of the Association of Engineers, India, 83(2), pp.43-54.

  • Li R, Dong M and Gao H (2021); Prediction of Bead Geometry with Changing Welding Speed Using Artificial Neural Network, Materials,14(6), pp.1494/1-9.

  • Mukherjee A and Das 5 (2021); A simple online tool condition monitoring system using artificial neural Networks, lOP Conf. Series: Materials Science and Engineering, 1080, pp.012021/1-5.

  • Bera T and Das S (2021); Estimation of geometry and properties of weld bead using artificial neural networks, Reason-A Technical Journal, Vol. 20, pp.46-56.

  • Khan FA, Chatterjee P, Mandi s, Shaw UK, Das s and Banerjee S (2022); Estimation of roughness of machined surface using artificial neural networks, Indian Science Cruiser, 36(3), pp.27-32.

  • Mandai N, Mandai S, Mandai M C, Das S and Haldar B (2022); ANN-FPA based modelling and optimization of drilling burrs using RSM and GA, Advances in Manufacturing Processes, Intelligent Methods and Systems in Production Engineering, GCMM 2021, Lecture Notes in Networks and Systems, 335, pp.180-195.

  • Adak DK, Dutta P, Haldar B, Das S, Alsaleh NA and Dasmahapatra S (2022); Abrasive jet drilling of hard alumina flat: an experimental investigation and predictive modeling by ANN, Manufacturing Technology Today, 21(11-12), pp.ll-24.

  • Devaraj J, Ziout A, Qudeiri J A, Baalfaqih R, Baalfaqh N, Alahbabi K, Alnaqbi M and Alhosan N (2022); Using Machine Learning Models to Predict Weld Sequence gMng Minimum Distortion, Proceedings of the Advances in Science and Engineering Technology International Conferences (ASET), Dubai, United Arab Emirates, pp.1-6.

  • Das A, Bose Sand Das S (2022); ANN based estimation of geometry of bead-on-plate in pulsed gas tungsten arc welding, Journal of Mechanical Engineering- Prakash, 1(1), pp.39-46.

  • Bera T and Das S (2022); On dissimilar welding of AISI 304 and EN 8 steels through metal active gas welding: part II- estimation of weld characteristics using regression analysis and neural networks, Indian Welding Journal, 55(3), pp.71-77.

  • Penttila S, Lund H and Skriko T (2023); Possibilities of Artificial Intelligence-Enabled Feedback Control System in Robotized Gas Metal Arc Welding, Journal of Manufacturing and Materials Processing, 7(3), pp.102/1-18.

  • Matlab User Manual (2004); Version 7.0.4.365 (R14), the Math Work Inc.

  • Beale M, Hagan M and DemutH (2010); Neural Network Toolbox User's Guide, China Machine Press.

  • Anastasiadis AD, Magoulas GO and Vrahatis MN (2005); New globally convergent training scheme based on the resilient propagation algorithm, Neurocomputing, 64, pp.253-270.

  • Hager WW and Zhang H (2006); A survey of nonlinear conjugate gradient methods, Pacific of Journal

  • Optimization, 2(35), pp.35-58.

  • Meller M F (1993); A scaled conjugate gradient algorithm for fast supervised learning, Neural Networks, 6,pp. 525-533.

  • Fletcher Rand Reeves C M (1964); Function minimization by conjugate gradients, Computer Journal, 7(2), pp.149-153.

  • Pham D and Sagiroglu S (2001); Training multi layered perceptrons for pattern recognition: a comparative study of four training algorithms, International Journal of Machine Tools and Manufacture, vol.41, pp.419-430.

  • Balan AV, Kannan T and Shivasankaran N (2014); Effect of FCAW process parameters on bead geometry in super duplex stainless steel claddings, International Journal of Applied Engineering Research, 9(24), pp.27331-27346.


Abstract Views: 219

PDF Views: 1




  • Estimation of Bead on Plate Geometry of Super Duplex Stainless Steel on Low Carbon Steel using Artificial Neural Networks

Abstract Views: 219  |  PDF Views: 1

Authors

Amit Kumar Hansda
Mechanical Engineering Department Kalyani Government Engineering College Kalyani - 741235, West Bengal, India
Santanu Das
Mechanical Engineering Department Kalyani Government Engineering College Kalyani - 741235, West Bengal, India

Abstract


Bead on plate geometry gives a priori knowledge about weld characteristics. In the current work, bead on plate experimental data are taken from one previously published work and different training algorithms are applied to get trained with the experimental data. Experiments were done using four-factor, five-level central composite rotatable design with full replication technique using response surface methodology. The working range of each parameter was decided upon by inspecting the weld bead for smooth appearance and the absence of visible defects. Bead of Super Duplex Stainless Steel was deposited on low carbon steel substrate using flux cored arc welding. An attempt is made in this work to predict the bead geometry parameters using Artificial Neural Networks (ANN). Effectiveness of three different ANN training functions are compared to choose the best model of these three. TRAINLM (LevenbergMarquardt) algorithm is found to be the most appropriate training function for prediction of bead geometry in this work.

Keywords


Welding, FCAW, Bead on Plate welding, Super Duplex Stainless Steel, Neural Networks, ANN, Prediction.

References





DOI: https://doi.org/10.22486/iwj.v56i3.222952