Prediction of Bead Geometry with Changing Welding Speed Using Artificial Neural Network
Abstract
:1. Introduction
2. Experimental Details
2.1. Experimental System
2.2. Materials and Welding Parameters
2.3. Bead Geometry Acquisition
3. Model Development
3.1. Transient Response Tests
3.2. Model Development
3.3. Datasets Acquisition
3.4. Training Process
3.5. Results and Discussion
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Xu, Y.L.; Yu, H.W.; Zhong, J.Y.; Lin, T.; Chen, S.B. Tracking control technology during welding robot GTAW process based on passive vision sensor. J. Mater. Process. Technol. 2012, 212, 1654–1662. [Google Scholar] [CrossRef]
- Le, J.; Zhang, H.; Chen, X. Realization of rectangular fillet weld tracking based on rotating arc sensors and analysis of experimental results in gas metal arc welding. Robot. Comput.-Integr. Manuf. 2017, 49, 263–276. [Google Scholar] [CrossRef]
- Zong, Y.; Mao, J. Tolerance optimization design based on the manufacturing-costs of assembly quality. Procedia CIRP 2015, 27, 324–329. [Google Scholar] [CrossRef] [Green Version]
- Siddaiah, A.; Singh, B.K.; Mastanaiah, P. Prediction and optimization of weld bead geometry for electron beam welding of AISI 304 stainless steel. Int. J. Adv. Manuf. Technol. 2016, 89, 27–43. [Google Scholar] [CrossRef]
- Wu, S.J.; Gao, H.M.; Zhang, W.; Zhang, Y.M. Analytic weld pool model calibrated by measurements part 1: Principles. Weld. J. 2017, 96, 193–202. [Google Scholar]
- Choudhary, A.; Kumar, M.; Unune, D.R. Experimental investigation and optimization of weld bead characteristics during submerged arc welding of AISI 1023 steel. Def. Technol. 2019, 15, 72–82. [Google Scholar] [CrossRef]
- Ye, J.X.; Ye, H.; Li, Z.G.; Peng, X.L.; Zhou, J.L.; Guo, B. Improving Stability of Welding Model with ME-ELM. Trans. Intell. Weld. Manuf. 2017, 1, 61–77. [Google Scholar]
- Salleh, M.N.M.; Ishak, M.; Quazi, M.M.; Aiman, M.H. Microstructure, mechanical, and failure characteristics of laser-microwelded AZ31B Mg alloy optimized by response surface methodology. Int. J. Adv. Manuf. Technol. 2018, 99, 985–1001. [Google Scholar] [CrossRef]
- Madrid, J.; Lorin, S.; Söderberg, R.; Hammersberg, P.; Wärmefjord, K.; Lööf, J. A Virtual Design of Experiments Method to Evaluate the Effect of Design and Welding Parameters on Weld Quality in Aerospace Applications. Aerospace 2019, 6, 74. [Google Scholar] [CrossRef] [Green Version]
- Arjunan, A.; Singh, M.; Baroutaji, A.; Wang, C. Additively manufactured AlSi10Mg inherently stable thin and thick-walled lattice with negative Poisson’s ratio. Compos. Struct. 2020, 247, 112469. [Google Scholar] [CrossRef]
- Fernandes, F.; Oliveira, D.; Pereira, A. Optimal parameters for laser welding of advanced high-strength steels used in the automotive industry. Procedia Manuf. 2017, 13, 219–226. [Google Scholar] [CrossRef]
- Balázs, C.C. Approximation with Artificial Neural Networks; Faculty of Sciences, Eötvös Loránd University: Budapest, Hungary, 2001. [Google Scholar]
- Nagesh, D.; Datta, G. Prediction of weld bead geometry and penetration in shielded metal-arc welding using artificial neural networks. J. Mater. Process. Technol. 2002, 123, 303–312. [Google Scholar] [CrossRef]
- Shim, J.-Y.; Zhang, J.-W.; Yoon, H.-Y.; Kang, B.-Y.; Kim, I.-S. Prediction model for bead reinforcement area in automatic gas metal arc welding. Adv. Mech. Eng. 2018, 10, 8. [Google Scholar] [CrossRef] [Green Version]
- Kshirsagar, R.; Jones, S.; Lawrence, J.; Tabor, J. Prediction of Bead Geometry Using a Two-Stage SVM-ANN Algorithm for Automated Tungsten Inert Gas (TIG) Welds. J. Manuf. Mater. Process. 2019, 3, 39. [Google Scholar] [CrossRef] [Green Version]
- Ding, D.H.; Shen, C.; Pan, Z.X.; Cuiuri, D.; Li, H.J.; Larkin, N.; van Duin, S. Towards an automated robotic arc-welding–based additive manufacturing system from CAD to finished part. Comput.-Aided Des. 2016, 73, 66–75. [Google Scholar] [CrossRef] [Green Version]
- Ahmed, A.N.; Noor, C.W.M.; Allawi, M.F.; El-Shafie, A. RBF-NN-based model for prediction of weld bead geometry in Shielded Metal Arc Welding (SMAW). Neural Comput. Appl. 2018, 29, 889–899. [Google Scholar] [CrossRef]
- Las-Casas, M.S.; De Ávila, T.L.D.; Bracarense, A.Q.; Lima, E.J. Weld parameter prediction using artificial neural network: FN and geometric parameter prediction of austenitic stainless steel welds. J. Braz. Soc. Mech. Sci. Eng. 2018, 40, 26. [Google Scholar] [CrossRef]
- Kumar, N.P.; Devarajan, P.K.; Vendan, S.A.; Shanmugam, N. Prediction of bead geometry in cold metal transfer welding using back propagation neural network. Int. J. Adv. Manuf. Technol. 2016, 93, 385–392. [Google Scholar] [CrossRef]
- Muhammad, J.; Altun, H.; Abo-Serie, E. Welding seam profiling techniques based on active vision sensing for intelligent robotic welding. Int. J. Adv. Manuf. Technol. 2017, 88, 127–145. [Google Scholar] [CrossRef]
- Ye, G.; Guo, J.; Sun, Z.; Li, C.; Zhong, S. Weld bead recognition using laser vision with model-based classification. Robot. Comput. Manuf. 2018, 52, 9–16. [Google Scholar] [CrossRef]
- Manorathna, R.P.; Phairatt, P.; Ogun, P.; Widjanarko, T.; Chamberlain, M.; Justham, L.; Marimuthu, S.; Jackson, M.R. Feature extraction and tracking of a weld joint for adaptive robotic welding. In Proceedings of the 2014 13th International Conference on Control Automation Robotics & Vision, Singapore, 10–12 December 2014; pp. 1368–1372. [Google Scholar]
- Chiu, C.Y.; Verma, B. Effect of varying hidden neurons and data size on clusters, layers, diversity and accuracy in neural ensemble classifier. In Proceedings of the IEEE International Conference on Computational Science and Engineering, Sydney, NSW, Australia, 3–5 December 2013; pp. 455–459. [Google Scholar]
Material | C | Mn | Si | S | P | Cr | Ni | Cu | Fe |
---|---|---|---|---|---|---|---|---|---|
Q235 | 0.17 max | 0.35–0.80 | 0.30 max | 0.035 max | 0.035 max | 0.03 max | 0.03 max | 0.3 max | Bal. |
ER70s-6 | 0.06–0.15 | 1.40–1.85 | 0.80–1.15 | 0.04 max | 0.03 max | 0.15 max | 0.15 max | 0.5 max | Bal. |
Structure | Training MSE | Test MSE |
---|---|---|
33-2-2 | 6.7624 × 10−3 | 7.8341 × 10−3 |
33-4-2 | 2.5074 × 10−3 | 7.3037 × 10−3 |
33-6-2 | 1.9432 × 10−3 | 6.372 × 10−3 |
33-8-2 | 2.1679 × 10−3 | 8.3761 × 10−3 |
33-10-2 | 1.3076 × 10−3 | 7.8045 × 10−3 |
33-12-2 | 3.0185 × 10−3 | 8.2483 × 10−3 |
33-14-2 | 3.5779 × 10−3 | 6.888 × 10−3 |
33-16-2 | 2.3568 × 10−3 | 6.5465 × 10−3 |
33-18-2 | 4.5394 × 10−3 | 7.3875 × 10−3 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Li, R.; Dong, M.; Gao, H. Prediction of Bead Geometry with Changing Welding Speed Using Artificial Neural Network. Materials 2021, 14, 1494. https://doi.org/10.3390/ma14061494
Li R, Dong M, Gao H. Prediction of Bead Geometry with Changing Welding Speed Using Artificial Neural Network. Materials. 2021; 14(6):1494. https://doi.org/10.3390/ma14061494
Chicago/Turabian StyleLi, Ran, Manshu Dong, and Hongming Gao. 2021. "Prediction of Bead Geometry with Changing Welding Speed Using Artificial Neural Network" Materials 14, no. 6: 1494. https://doi.org/10.3390/ma14061494