Development of a 3D Virtual Welding Simulator Using Weld Bead Created by Voxelization Technique

Year 2024, Volume: 12 Issue: 4, 1977 - 1992, 23.10.2024

Kayhan Ayar , Soydan Serttaş , Gülüzar Çit , Cemil Öz , Fehim Fındık

https://doi.org/10.29130/dubited.1323945

Cited By: 1

https://izlik.org/JA64UC48CM

Abstract

In this study, we developed and implemented a cost-reducing, real-time virtual welding simulator to train welder candidates. In order to make a real-time welding simulation, a three-dimensional weld bead form was designed. We used a parabola as the basic bead slice shape, considering the similarity between the parabola and the bead slice. During the welding process, the parameters of the weld bead shape are calculated at each time step using an artificial neural network. This network determines the shape of the weld bead and the depth of penetration, based on inputs received from the sensor device that tracks the motions of the torch. After the parabola’s parameters have been determined, the voxel map and corresponding hash-based octree data structure are generated in real-time. By using the voxelized data, a weld bead isosurface consisting of triangles is reconstructed with a marching cubes algorithm allowing us to generate more realistic weld seam shapes. We used multi-threaded programming for voxelization and isosurface extraction to reduce the computation cost on high-resolution virtual scenes. The isosurface extraction times for different thread counts and also a feature comparison with other simulators in the literature are shown in this paper.

Keywords

welding simulator , virtual reality , weld bead , weld seam , voxel

Vokselleştirme Tekniği ile Oluşturulan Kaynak Dolgusunu Kullanan 3B Bir Sanal Kaynak Simülatörü Geliştirilmesi

https://izlik.org/JA64UC48CM

Abstract

Bu çalışmada, kaynakçı adaylarının eğitiminde kullanılmak üzere gerçek zamanlı ve maliyeti düşük bir sanal kaynak simülatörü tasarlanıp geliştirilmiştir. Gerçek zamanlı bir kaynak simülasyonu yapmak için öncelikle üç boyutlu bir kaynak dikiş formu tasarlanmıştır. Parabol ve kaynak dikişi arasındaki benzerlik göz önünde bulundurularak temel kaynak dikişi formu olarak parabol kullanılmıştır. Kaynak işlemi sırasında, yapay sinir ağı kullanılarak her zaman adımında kaynak dikişi şeklinin parametreleri hesaplanır. Bu ağ, torcun hareketini izleyen sensör cihazından alınan girdilere dayalı olarak kaynak dikişinin şeklini ve derinliğini belirler. Parabolün parametreleri belirlendikten sonra, gerçek zamanlı olarak voksel haritası ve karşılık gelen sekizli-ağaç veri yapısı oluşturulur. Vokselleştirilmiş veriler kullanılarak üçgenlerden oluşan kaynak dikişi eş-yüzeyi, daha gerçekçi kaynak dikişi şekilleri oluşturmamızı sağlayan yürüyen küp algoritması ile yeniden yapılandırılmıştır. Yüksek çözünürlüklü sanal sahnelerde hesaplama ve işlem maliyetini düşürmek amacıyla vokselizasyon ve eş-yüzey çıkarma işlemleri için çok iş parçacıklı programlama tekniği kullanılmıştır. Bu çalışmada, farklı iş parçacıkları için eş-yüzey çıkarma süreleri gösterilmiş olup geliştirilen simülatörün literatürdeki diğer simülatörlerle karşılaştırması da sunulmuştur.

Keywords

kaynak simülatörü , sanal gerçeklik , kaynak dolgusu , kaynak dikişi , voksel.

References

• [1] G. Karsai, K. Andersen, G.E. Cook, and R.J. Barnett, "Neural network methods for the modeling and control of welding processes," Journal of Intelligent Manufacturing, vol. 3, pp. 229-235, 1992.
• [2] S. Teeravarunyou, and B. Poopatb, "Computer based welding training system," International Journal of Industrial Engineering: Theory Applications and Practice, vol. 6, no. 2, pp. 116-125, 2009.
• [3] K.M. Kanti, and P.S. Rao, "Prediction of bead geometry in pulsed gma welding using back propagation neural network,". Journal of Materials Processing Technology, vol. 200(1-3), pp. 300-305, 2008.
• [4] Q. Xue, S. Ma, Y. Liang, J. Wang, Y. Wang, F. He, and M. Liu, "Weld bead geometry prediction of additive manufacturing based on neural network," 11th International Symposium on Computational Intelligence and Design, China, 2018, pp. 47-51.
• [5] P.K. Jayashree, S. Sharma, and N. Shetty, "TIG welding parameters optimization of Al–Si–Mg ternary alloy–SiC powder reinforced composites using Taguchi and RSM techniques," Cogent Engineering, vol. 9, no. 1, 2022.
• [6] S.K. Katheria, D. Kumar, T.A. Khan, and M.K. Singh, "Reality based skills development approach in welding technology: An overview," Materials Today: Proceedings, vol. 47, no. 19, pp. 7184-7188, 2021.
• [7] C. Papakostas, C. Troussas, A. Krouska, and C. Sgouropoulou, "User acceptance of augmented reality welding simulator in engineering training," Education and Information Technologies, vol. 27, no. 1, pp. 791-817, 2022.
• [8] C. Wu, C. Wen, and L. Wu, "A microcomputer-controlled welder training system," Computers & Education, vol. 20, no. 3, pp. 271-274, 1993.
• [9] Y. Top, "Using Simulator in Training of Arc Welder," Sakarya University Journal of Science, vol. 2, no. 1, pp. 93-98, 1998.
• [10] C. Oz, F. Findik, O. Iyibilgin, U. Soy, Y. Kiyan, S. Serttas et al., K. Ayar, S. Uslu, and Y. Yasar, "Welding simulators: from past to present day," Metal Dunyasi, vol. 201, pp. 108-111, 2010.
• [11] D. Mavrikios, V. Karabatsou, D. Fragos, and G. Chryssolouris, "A prototype virtual reality-based demonstrator for immersive and interactive simulation of welding process," International Journal of Computer Integrated Manufacturing, vol. 9, pp. 294-300, 2006. [12] K. Fast, T. Gifford, and R. Yancey, "Virtual training for welding," Proceedings of the Third IEEE and ACM International Symposium on Mixed and Augmented Reality, 2004, pp. 298-299.
• [13] S.A. White, M. Prachyabrued, T.L. Chambers, C.W. Borst, and D. Reiners, "Low-cost simulated mig welding for advancement in technical training," Virtual Reality, vol. 15, no. 1, pp. 69-81, 2011.
• [14] https://www.lincolnelectric.com/en-gb/equipment/training-equipment /vrtex360/ pages/ vrtex-360.aspx Accessed 21 May 2018
• [15] Soldamatic’s HyperReal-Sim™: What is it all about?, December 2022. [Online]. Available: https://seaberyat.com/en/hyperreal-sim-of-soldamatic-what-is-it-about/
• [16] V.G. Bharat and P. Rajashekar, "Virtual reality for metal arc welding: a review and design concept," International Journal of Mechanical Engineering and Technology, vol. 8, no. 1, pp. 132-138, 2017.
• [17] P.K. Palani, and N. Murugan, "Modeling and simulation of wire feed rate for steady current and pulsed current gas metal arc welding using 317L flux cored wire," The International Journal of Advanced Manufactoring Technology, vol. 34, pp. 1111-1119, 2007.
• [18] Ö.K. Kalkan, Ş, Karabulut, and G. Höke, "Effect of virtual reality‑based training on complex industrial assembly task performance," Arabian Journal for Science and Engineering, vol. 46, no. 12, pp. 12697-12708, 2021.
• [19] C. Oz, and M.C. Leu, "Human-computer interaction system with artificial neural network using motion tracker and data glove," International Conference on Pattern Recognition and Machine Intelligence, vol. 3776, pp. 280-286, 2005.
• [20] C. Oz, and M.C. Leu, "American sign language word recognition with a sensory glove using artificial neural networks," Engineering Applications of Artificial Intelligence, vol. 24, no. 7, pp.1204-1213, 2011.
• [21] S. Serttas, K. Ayar, G. Cit, and C. Oz, "Multi-threaded application for marching cubes algorithm," International Symposium On Innovative Technologies In Engineering and Science, Turkiye, 2014, pp. 821-825.
• [22] C. Oz, S. Serttas, K. Ayar, and F. Findik, "Effect of virtual welding simulator on tig welding training," Journal of Materials Education, vol. 37, pp.197-218, 2015
• [23] G. Cit, K. Ayar, and C. Oz, "A real-time virtual sculpting application by using an optimized hash-based octree," Turkish Journal of Electrical Engineering and Computer Science, vol. 24, no. 4, pp. 2274-2289, 2016.
• [24] G. Cook, R. Barnett, D. Hartman, and A. Strauss, "Neural network systems techniques in weld modeling and control," Computer Aided and Integrated Manufacturing Systems Techniques and Applications, 1997.
• [25] P. Li, M.T.C. Fang, and J. Lucas, "Modelling of submerged arc weld beads using self-adaptive offset neutral networks," Journal of Materials Processing Technology, vol. 71, no. 2, pp. 288-298, 1997.
• [26] B. Chan, J. Pacey, and M. Bibby, "Modelling gas metal arc weld geometry using artificial neural network technology," Canadian Metallurgical Quarterly, vol. 38, no. 1, pp. 43-51, 1999.
• [27] M.I.S. Ismail, Y. Okamoto, and A. Okada, "Neural network modeling for prediction of weld bead geometry in laser microwelding," Advances in Optical Technologies, 2013.
• [28] N. Murugan, and V. Gunaraj, "Prediction and control of weld bead geometry and shape relationships in submerged arc welding of pipes," Journal of Materials Processing Technology, vol. 168, no. 3, pp. 478-487, 2005.
• [29] D. Jo, Y. Kim, U. Yang, G.A. Lee, and J.S. Choi, "Visualization of virtual weld beads," Proceedings of the ACM Symposium on Virtual Reality Software and Technology, 2009, pp. 269-270.
• [30] J. Xiong, G. Zhang, H. Gao, and L. Wu, "Modeling of bead section profile and overlapping beads with experimental validation for robotic gmaw-based rapid manufacturing," Robotics and Computer-Integrated Manufacturing, vol. 29, no. 2, pp. 417-423, 2013.
• [31] P.K. Palani, and N. Murugan, "Optimization of weld bead geometry for stainless steel claddings deposited by fcaw," Journal of Materials Processing Technology, vol. 190, pp. 291-299, 2007.
• [32] K.N. Gowtham, M. Vasudevan, V. Maduraimuthu, and T. Jayakumar, "Intelligent modeling combining adaptive neuro fuzzy inference system and genetic algorithm for optimizing welding process parameters," Metallurgical and Materials Transactions B, vol. 42, no. 2, pp. 385-392, 2011.
• [33] J.E. Pinto-Lopera, J.M.S.T. Motta, and S.C.A. Alfaro, "Real-time measurement of width and height of weld beads in gmaw processes," Sensors, vol. 16, no. 9, pp. 1-14, 2016.
• [34] C.M. Horvath, J. Botzheim, T. Thomessen, and P. Korondi, "Bacterial memetic algorithm trained fuzzy system-based model of single weld bead geometry," IEEE Access, vol. 8, pp. 164864-164881, 2020.
• [35] Y. He, D. Li, Z. Pan, G. Ma, L. Yu, H. Yuan, and J. Le, "Dynamic modeling of weld bead geometry features in thick plate gmaw based on machine vision and learning," Sensors, vol. 20, no. 24:7104, 2020.
• [36] S.K. Gupta, S. Mehrotra, A. R. Raja, M. Vashista, and M.Z.K. Yusufzai, "Effect of welding speed on weld bead geometry and percentage dilution in gas metal arc welding of SS409L", Materials Today: Proceedings, vol. 18, no. 7, pp. 5032-5039, 2019.
• [37] J.H. Park, M. Cheepu, and S.M. Cho, "Analysis and characterization of the weld pool and bead geometry of inconel 625 super-TIG welds," Metals - Open Access Metallurgy Journal, vol. 10, no. 3:365, 2020.
• [38] A. Siddaiah, B.K. Singh, and P. Mastanaiah, "Prediction and optimization of weld bead geometry for electron beam welding of AISI 304 stainless steel," International Journal of Advanced Manufacturing Technology, vol. 89, pp. 27-43, 2017.
• [39] A. Sattar, A. Hussain, B. Abbas, M.N. Azam, K. Mehmood, A. Wakeel, and S. Ali, "Optimization of tig welding parameters forti-6al-4v titanium alloy using the taguchi design of experiment," NUST Journal of Engineering Sciences, vol. 15, no. 2, pp. 65-77, 2022.
• [40] I.S. Kim, K.J. Son, Y.S. Yang, and P.K.D.V. Yaragada, "Sensitivity analysis for process parameters in gma welding processes using a factorial design method," International Journal of Machine Tools and Manufacture, vol. 43, no. 8, pp. 763-769, 2003.
• [41] M. Shoeb, M. Parvez, and P. Kumari, "Effect of mig welding input process parameters on weld bead geometry on hsla steel," International Journal of Engineering Science and Technology, vol. 5, no. 1, pp. 200-212, 2013.
• [42] P. Sreeraj, and T. Kannan, "Modelling and prediction of stainless steel clad bead geometry deposited by gmaw using regression and artificial neural network models," Advances in Mechanical Engineering, 2012.
• [43] E. Karadeniz, U. Ozsarac, and C. Yildiz, "The effect of process parameters on penetration in gas metal arc welding processes," Materials and Design, vol. 28, no. 2, pp. 649-656, 2007. n [44] J.S. Son, I.S. Kim, H.H. Kim, I.J. Kim, B.Y. Kang, and H.J. Kim, "A study on the prediction of bead geometry in the robotic welding system," Journal of Mechanical Science and Technology, vol. 21, no. 10, pp. 1726-1731, 2007.
• [45] S.P. Tewari, A. Gupta, and J. Prakash, "Effect of welding parameters on the weldability of material," International Journal of Engineering Science and Technology, vol. 2, no. 4, pp. 512-516, 2010. [46] H.R. Ghazvinloo, A. Honarbakhsh-Raouf, and N. Shadfar, "Effect of Arc voltage, welding current and welding speed on fatigue life, impact energy and bead penetration of aa6061 joints produced by robotic mig welding," Indian Journal of Science and Technology, vol. 3, no. 2, pp. 156-162, 2010.
• [47] B. Das, and B. Debbarma, "Influence of process parameters on depth of penetration of welded joint in mig welding process," International Journal of Research in Engineering and Technology, vol. 2, no. 10, pp. 220-224, 2013.
• [48] K. Chen, H. Chen, L. Liu, and S. Chan, "Prediction of weld bead geometry of MAG welding based on XGBoost algorithm," International Journal of Advanced Manufacturing Technology, vol. 101, pp. 2283-2295, 2019.
• [49] P.T. Trivedi, and A.P. Bhabhor, "Experimental investigation of process parameters on weld bead geometry for aluminium using gtaw," International Journal of Science and Research, vol. 3, no. 5, pp. 803-809, 2014.
• [50] K. Andersen, G.E. Cook, G. Karsai, and K. Ramaswamy, "Artificial neural networks applied to arc welding process modeling and control," IEEE Transactions on Industrial Applications, vol. 26, no. 5, pp. 824-30, 1990.
• [51] S.C. Juang, Y.S. Tarng, and H.R. Lii, "A comparison between the back-propagation and counter-propagation networks in the modeling of the tig welding process," Journal of Materials Processing Technology, vol. 75, no. 1-3, pp. 54-62, 1998.
• [52] U. Duman, "Modeling of weld penetration in high productivity GTAW," Ph.D. Thesis, Colorado School of Mines, Golden, CO, USA, 2009.
• [53] U. Esme, M. Bayramoglu, Y. Kazancoglu, and S. Ozgun, "Optimization of weld bead geometry in tig welding process using grey relation analysis and taguchi method," Materials in Tehnologies, vol. 43, no. 3, pp. 143-149, 2009.
• [54] D.S. Nagesh and G.L. Datta, "Genetic algorithm for optimization of welding variables for height to width ratio and application of ann for prediction of bead geometry for tig welding process," Appled Soft Computing, vol. 10, no. 3, pp. 897-907, 2010.
• [55] A. Iqbal, S.M. Khan, and M.H. Sahir, "Ann assisted prediction of weld bead geometry in gas tungsten arc welding of hsla steels," Proceedings of the World Congress on Engineering, 2011, pp. 818-821.
• [56] M.S.M. Musthaq and M.M. Batcha, "Predicting the weld bead geometry of gta welding on aisi 202 stainless steel," International Journal of Engineering & Technology, vol. 3, no. 2, pp. 2463-2469, 2014.
• [57] A.K. Singh, V. Dey, R.N. Rai, and T. Debnath, "Weld bead geometry dimensions measurement based on pixel intensity by image analysis techniques," Journal of The Institution of Engineers (India): Series C, vol. 100, pp. 379-384, 2019.
• [58] T.L. Chambers, A. Aglawe, D. Reiners, S. White, C.W. Borst, M. Prachyabrued, and A. Bajpayee, "Real-time simulation for a virtual reality-based mig welding training system," Virtual Reality, vol. 16, no. 1, pp. 45-55, 2012.
• [59] C.S. Wu, M.X. Zhang, K.H. Li, and Y.M. Zhang, "Numerical analysis of double-electrode gas metal arc welding process," Computational Materials Science, vol. 39, no. 2, pp. 416-423, 2007.
• [60] M.A. Cavuslu, Y. Becerikli, and C. Karakuzu, "Levenberg-marquardt algoritması ile ysa eğitiminin donanımsal gerçeklenmesi," Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi, vol. 5, no. 5, pp. 1-7, 2012.
• [61] B.M. Wilamowski, Y. Chen, and A. Malinowski, "Efficient algorithm for training neural networks with one hidden layer," Proceedings of the International Joint Conference on Neural Networks, vol. 3, 1999. pp. 1725-1728.
• [62] J. Arif, N.R. Chaudhuri, S. Ray, and B. Chaudhuri, "Online levenberg-marquardt algorithm for neural network based estimation and control of power systems," Proceedings of the International Joint Conference on Neural Networks, 2009, pp. 199-206.
• [63] Y. Yang, X.M. Fu and L. Liu, "Computing surface polycube-maps by constrained voxelization," Computer Graphics Forum, vol. 30, no. 7, pp. 299-309, 2019.
• [64] L. Feng and S.H. Soon, "An effective 3d seed fill algorithm," Computers & Graphics, vol. 22, no. 5, pp. 641-644, 1998.
• [65] W. E. Lorensen and H.E. Cline, "History of the marching cubes algorithm," Computer Graphics, vol. 21, no. 4, pp. 163-169, 1987.
• [66] W.E. Lorensen, "Marching cubes: a high-resolution 3d surface construction algorithm," IEEE Computer Graphics and Applications, vol. 40, no. 2, pp. 8-15, 2020.
• [67] Y. Liao, S. Donne, and A. Geiger, "Deep marching cubes: learning explicit surface representations," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 2916-2925.
• [68] K. Ayar, G. Cit, C. Oz and S. Serttas, "Voxelization with OpenCL for virtual sculpting," International Symposium on Innovative Technologies in Engineering and Science, 2014, pp. 826-831.
• [69] A. Ozkurt, "Surface model extraction from three dimensional sampled data," Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, vol. 4, no. 3, pp. 27-36, 2002.
• [70] J. Han, "MRI and CT image based on 3d reconstruction and medical rapid prototyping," M.S. Thesis, University of Puerto Rico, Puerto Rico, 2005.
• [71] A.N. Chernikov and J. Xu, "Proof of correctness of a marching cubes algorithm carried out with coq," Proceedings of the 22nd International Meshing Roundtable, 2014, pp.505-523.
• [72] B.N. Parmar and T. Bhatt, "Volume visualization using marching cubes algorithms : survey & analysis," International Journal of Innovative Research in Technology, vol. 2, no. 11, pp. 21-25, 2016.
• [73] S. Roy and P. Augustine, "Comparative study of marching cubes algorithms for the conversion of 2d image to 3d," International Journal of Computational Intelligence Research, vol. 13, no. 3, pp. 327-337, 2017.