GMAW welding procedure expert system based on machine learning

Abstract

In order to simplify the robot preparation before welding and improve the automation of the whole welding process, an intelligent expert system for Gas Metal Arc Welding is designed in this paper. In the system, the user inputs the initial welding information and the output interface displays suitable welding procedure parameter schemes. The user can choose the schemes according to the actual requirements or directly generate the welding procedure specification required by the enterprise format for direct use. In addition, the system also combines the database technology and XGBoost algorithm in the field of machine learning, migrates the model trained on the data set to predict the welding raw data, accumulates more data for daily use to optimize the model, which makes the whole system more systematic and intelligent, and achieves the goal of more accurate use.

Keywords

Welding / expert system / machine learning / database

References

[1] Wang B,Freiheit T.Towards intelligent welding systems from a HCPS perspective: a technology framework and implementation roadmap.J Manuf Syst2022;65:244-59

[2] Madavi K,Lohar G.Metal inert gas (MIG) welding process: a study of effect of welding parameters.Mater Today Process2022;51:690-8

[3] Huysmans S,De Bruycker E.Weldability study of additive manufactured 316L austenitic stainless steel components-welding of AM with conventional 316L components.Weld World2021;65:1415-27

[4] Dong Z,Tassenberg K,Dong H.Transformation from human-readable documents and archives in arc welding domain to machine-interpretable data.Comput Ind2021;128:103439

[5] Trotta G,Semeraro Q.Optimizing process parameters in micro injection moulding considering the part weight and probability of flash formation.J Manuf Process2022;79:250-8

[6] Weng H,Feng M,Chen C.Multi-objective optimizations of the Q355C steel gas metal arc welding process based on the grey correlation analysis.Int J Adv Manuf Technol2022;121:3567-82

[7] Nguyen DS,Lee CM.Optimization of selective laser melting process parameters for Ti-6Al-4V alloy manufacturing using deep learning.J Manuf Process2020;55:230-5

[8] Sparham M,Mardi N,Dahari M.ANFIS modeling to predict the friction forces in CNC guideways and servomotor currents in the feed drive system to be employed in lubrication control system.J Manuf Process2017;28:168-85

[9] Ding D,Pan Z.Towards an automated robotic arc-welding-based additive manufacturing system from CAD to finished part.CAD Comput Aided Des2016;73:66-75

[10] Bologna F,Romano D.Automatic welding imperfections detection in a smart factory via 2-D laser scanner.J Manuf Process2022;73:948-60

[11] Kenda M,Bračun D.Condition based maintenance of the two-beam laser welding in high volume manufacturing of piezoelectric pressure sensor.J Manuf Syst2021;59:117-26

[12] Liu L,Chen S.Quality analysis of CMT lap welding based on welding electronic parameters and welding sound.J Manuf Process2022;74:1-13

[13] Miler D,Žeželj D.Optimisation of welded beams: how cost functions affect the results.Proc Des Soc: Des Conf2020;1:2531-40

[14] Kuklik J,Wippo V.Laser welding of additively manufactured thermoplastic components assisted by a neural network-based expert system. In: High-Power Laser Materials Processing: Applications, Diagnostics, and Systems XI, Proceedings of SPIE - The International Society for Optical Engineering. SPIE; 2022 Feb 20-24:The Society of Photo-Optical Instrumentation Engineers (SPIE).

[15] Shahriari D,Jahazi M.Development of an expert system to characterize weld defects identified by ultrasonic testing. In: ASME 2013 Pressure Vessels and Piping Conference, PVP 2013 Jul 14-18, 2013. Vol 5. American Society of Mechanical Engineers, Pressure Vessels and Piping Division (Publication) PVP. American Society of Mechanical Engineers (ASME); 2013: Nondestructive Evaluation Engineering Division; Pressure Vessels and Piping Division.

[16] Cheng Y,Zhou Q,Yuan W.Real-time sensing of gas metal arc welding process - a literature review and analysis.J Manuf Process2021;70:452-69

[17] Cullen M,Ji J.Classification of transfer modes in gas metal arc welding using acoustic signal analysis.Int J Adv Manuf Technol2021;115:3089-104

[18] Lughofer E,Pollak R.Autonomous supervision and optimization of product quality in a multi-stage manufacturing process based on self-adaptive prediction models.J Process Control2019;76:27-45

[19] Rønsch GØ,Kulahci M.Real-time adjustment of injection molding process settings by utilizing Design of Experiment, time series profiles and PLS-DA.Qual Eng2022;34:215-29

[20] Jagdeesh Patil S. Expert system: a fault diagnosis expert system for high-power industrial production platform. In: Shetty NR, Patnaik LM, Nagaraj HC, Hamsavath PN, Nalini N, editors. Emerging research in computing, information, communication and applications. Singapore: Springer; 2022. p. 317-23.

[21] Silva CW. Intelligent robotics - misconceptions, current trends, and opportunities.Intell Robot2021;1:3-17

[22] Su C,Wang J,Cui L.A review of causality-based fairness machine learning.Intell Robot2022;2:244-74

[23] Zhang Y,Pu J.Development and application of knowledge-based software for railcar frame welding process.Int J Adv Manuf Technol2021;112:273-84

[24] Liu G,Huang M,Chen Z.Integrated modelling of automobile maintenance expert system based on knowledge graph.J Phys: Conf Ser2021;1983:012118

[25] Xiao H,Wang W.Multi-channel domain adaptation deep transfer learning for bridge structure damage diagnosis.IEEJ Transactions Elec Engng2022;17:1637-47

[26] Ahmed F.Recursive approach to combine expert knowledge and data-driven RSW weldability certification decision making process.Robot Comput-Integr Manuf2023;79:102428

[27] Zhang Y,Liu Y.American Welding SocietyAdaptive intelligent welding manufacturing.Weld J2021;100:63-83

[28] Guan K,Du L,Yang X.Method for fusion of neighborhood rough set and XGBoost in welding process decision-making.J Intell Manuf2023;34:1229-40

[29] Jiang J,Zhang Z.Machine learning integrated design for additive manufacturing.J Intell Manuf2022;33:1073-86

[30] Jafarian M.A fuzzy multi-attribute approach to select the welding process at high pressure vessel manufacturing.J Manuf Process2012;14:250-6

[31] Koyee RD,Eisseler R.Modeling and optimization of turning duplex stainless steels.J Manuf Process2014;16:451-67

[32] Martínez R,Martins Almeida Silva A.Analysis of GMAW process with deep learning and machine learning techniques.J Manuf Process2021;62:695-703

[33] Horváth CM,Thomessen T.Bead geometry modeling on uneven base metal surface by fuzzy systems for multi-pass welding.Expert Syst Appl2021;186:115356

[34] Farahani S,Basu S.A data-driven predictive maintenance framework for injection molding process.J Manuf Process2022;80:887-97

[35] Wang B.A study on spot welding quality judgment based on hidden Markov model.Proc Inst Mech Eng Part E J Process Mech Eng2021;235:208-18

[36] Jiang JC,Xu X,Liu JK.Achieving better connections between deposited lines in additive manufacturing via machine learning.Math Biosci Eng2020;17:3382-94

[37] Chen T.XGBoost: a scalable tree boosting system. In: 22nd Acm SIGKDD International Conference on Knowledge Discovery and Data Mining. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery; 2016 Aug 16-17; New York; 2016.p.785-94.