Combining soft computing techniques and the finite element method to design and optimize complex welded products

One of the main objectives when designing welded products is to reduce strains and deformations. Strains can cause excessive angular distortion. This results in a welded product that does not meet acceptable tolerances. The geometry of the weld bead height and width depends on the input parameters speed, voltage and current, and provides the welded joint with strength and quality. As welded products become increasingly complex, deformations become more difficult to predict as they depend greatly on the welding sequence. This paper shows how a combination of the Finite Element Method, Genetic Algorithms and Regression Trees may be used to design and optimize complex welded products. Initially, Artificial Neural Networks and Regression Trees that are based on heuristic methods and evolutionary algorithms were used in predicting the weld bead geometry according to the input parameters. Then, thermo-mechanical Finite Element models were created to obtain the temperature field and the angular distortion using the weld bead geometry that the best predictive models generated. Finally, optimization techniques that are based on Genetic Algorithms were used to validate these Finite Element models against experimental results, and to subsequently find the optimal welding sequence to use in the manufacture of complex welded products.

[1]  Tso-Liang Teng,et al.  Effect of welding sequences on residual stresses , 2003 .

[2]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[3]  Malcolm Bibby,et al.  Modelling Gas Metal Arc Weld Geometry Using Artificial Neural Network Technology , 1999 .

[4]  Vincenzo Gattulli,et al.  Output‐Only Identification and Model Updating by Dynamic Testing in Unfavorable Conditions of a Seismically Damaged Building , 2014, Comput. Aided Civ. Infrastructure Eng..

[5]  Prasad K. Yarlagadda,et al.  A study on the quality improvement of robotic GMA welding process , 2003 .

[6]  Young-Soo Yang,et al.  Sensitivity analysis for process parameters in GMA welding processes using a factorial design method , 2003 .

[7]  J. Goldak,et al.  A new finite element model for welding heat sources , 1984 .

[8]  A. De,et al.  Development of a Three-Dimensional Heat-Transfer Model for the Gas Tungsten Arc Welding Process Using the Finite Element Method Coupled with a Genetic Algorithm–Based Identification of Uncertain Input Parameters , 2008 .

[9]  Anna Timofiejczuk,et al.  Analysis of images recorded during welding processes , 2008 .

[10]  B. L. Josefson,et al.  A parametric study of residual stresses in multi-pass butt-welded stainless steel pipes , 1998 .

[11]  Ian H. Witten,et al.  Induction of model trees for predicting continuous classes , 1996 .

[12]  Michel Bellet,et al.  Experimental validation of finite element codes for welding deformations , 2010 .

[13]  Yang Wang,et al.  Prediction of transverse and angular distortions of gas tungsten arc bead-on-plate welding using artificial neural network , 2014 .

[14]  Tom Verstraete,et al.  Integrated multifidelity, multidisciplinary evolutionary design optimization of counterrotating compressors , 2014, Integr. Comput. Aided Eng..

[15]  William N. Venables,et al.  Modern Applied Statistics with S , 2010 .

[16]  Lin Wu,et al.  Bead geometry prediction for robotic GMAW-based rapid manufacturing through a neural network and a second-order regression analysis , 2012, Journal of Intelligent Manufacturing.

[17]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[18]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[19]  Andy J. Keane,et al.  Weld sequence optimization: The use of surrogate models for solving sequential combinatorial problems , 2005 .

[20]  G. Karsai,et al.  Artificial neural networks applied to arc welding process modeling and control , 1989, Conference Record of the IEEE Industry Applications Society Annual Meeting,.

[21]  Noorul Islam,et al.  Modeling and prediction of HAZ using finite element and neural network modeling , 2013 .

[22]  Hojjat Adeli,et al.  Cost Optimization of Structures: Fuzzy Logic, Genetic Algorithms, and Parallel Computing , 2006 .

[23]  A. Bachorski,et al.  Finite-element prediction of distortion during gas metal arc welding using the shrinkage volume approach , 1999 .

[24]  Lin Wu,et al.  Fundamental studies on in-process controlling angular distortion in asymmetrical double-sided double arc welding , 2008 .

[25]  Emilio Corchado,et al.  A soft computing method for detecting lifetime building thermal insulation failures , 2010, Integr. Comput. Aided Eng..

[26]  Johan Martinsson.  Fatigue assessment of complex welded steel structures , 2005 .

[27]  Dean Deng,et al.  Influence of deposition sequence on welding residual stress and deformation in an austenitic stainless steel J-groove welded joint , 2013 .

[28]  K. Moore,et al.  Modeling, Sensing and Control of Gas Metal Arc Welding , 2003 .

[29]  Srećko Švaić,et al.  Numerical and Experimental Modeling of a T-joint Fillet Welding Process , 2012 .

[30]  M. H. Kadivar,et al.  Optimizing welding sequence with genetic algorithm , 2000 .

[31]  Giuseppe Casalino,et al.  Deformation prediction and quality evaluation of the gas metal arc welding butt weld , 2003 .

[32]  Rade Kutil,et al.  A generalization of quad-trees applied to shape coding , 2011, 2011 18th International Conference on Systems, Signals and Image Processing.

[33]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[34]  Achim Zeileis,et al.  evtree: Evolutionary Learning of Globally Optimal Classification and Regression Trees in R , 2014 .

[35]  Ghalib Tham,et al.  Predicting the GMAW 3F T-fillet geometry and its welding parameter , 2012 .

[36]  Sofiane Guessasma,et al.  New Computational Model Based on Finite Element Method to Quantify Damage Evolution Due to External Sulfate Attack on Self-Compacting Concretes , 2013, Comput. Aided Civ. Infrastructure Eng..

[37]  Yi Liu,et al.  Effect of welding sequence on residual stress and distortion in flat-bar stiffened plates , 2010 .

[38]  Emilio Corchado,et al.  Optimising operational costs using Soft Computing techniques , 2011, Integr. Comput. Aided Eng..

[39]  F. J. Martinez-de-Pison,et al.  Using Genetic Algorithms to Optimize the Material Behaviour Model in Finite Element Models of Processes with Cyclic Loads , 2010 .

[40]  Timothy J. Ross,et al.  Logical models for the propagation of disparate information and uncertainty across effectivity trees , 2011, Integr. Comput. Aided Eng..

[41]  Sheng Zhu,et al.  Overlapping model of beads and curve fitting of bead section for rapid manufacturing by robotic MAG welding process , 2011 .

[42]  Hsuan-Liang Lin.  The use of the Taguchi method with grey relational analysis and a neural network to optimize a novel GMA welding process , 2012, J. Intell. Manuf..

[43]  Yuping Wang,et al.  Multiobjective bilevel optimization for production-distribution planning problems using hybrid genetic algorithm , 2014, Integr. Comput. Aided Eng..

[44]  D. C. Weckman,et al.  Prediction of weld pool and reinforcement dimensions of GMA welds using a finite-element model , 1989 .

[45]  Hidekazu Murakawa,et al.  Numerical simulation of temperature field and residual stress in multi-pass welds in stainless steel pipe and comparison with experimental measurements , 2006 .

[46]  Norman McPherson,et al.  Artificial neural network prediction of weld geometry performed using GMAW with alternating shielding gases , 2012 .

[47]  Ill-Soo Kim,et al.  An investigation into an intelligent system for predicting bead geometry in GMA welding process , 2005 .

[48]  Iradj Sattari-Far,et al.  Study on welding temperature distribution in thin welded plates through experimental measurements and finite element simulation , 2011 .

[49]  Hisham Al-Mubaid,et al.  A model for mining material properties for radiation shielding , 2012, Integr. Comput. Aided Eng..

[50]  Roberto Fernandez Martinez,et al.  Comparative analysis of learning and meta-learning algorithms for creating models for predicting the probable alcohol level during the ripening of grape berries , 2012 .

[51]  Prasad K. Yarlagadda,et al.  Prediction of welding parameters for pipeline welding using an intelligent system , 2002 .

[52]  Guangzhe Fan,et al.  Regression Tree Analysis Using TARGET , 2005 .

[53]  G. Liang,et al.  Study on the temperature measurement of AZ31B magnesium alloy in gas tungsten arc welding , 2008 .

[54]  Yashar Javadi,et al.  Influence of welding sequence on welding distortions in pipes , 2008 .

[55]  Jeong-ick Lee,et al.  A comparison in a back-bead prediction of gas metal arc welding using multiple regression analysis and artificial neural network , 2000 .

[56]  Prasad K. Yarlagadda,et al.  A study on prediction of bead height in robotic arc welding using a neural network , 2002 .

[57]  Jianming Gong,et al.  Optimization of welding joint between tower and bottom flange based on residual stress considerations in a wind turbine , 2010 .