Top

International Journal on Interactive Design and Manufacturing (IJIDeM)

Published in:

14-05-2023 | Original Paper

A comparative study of machine learning algorithms in the prediction of bead geometry in wire-arc additive manufacturing

Authors: Mukesh Chandra, K. E. K. Vimal, Sonu Rajak

Published in: International Journal on Interactive Design and Manufacturing (IJIDeM) | Issue 9/2024

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

The article presents a comparative study of machine learning algorithms for predicting bead geometry in wire-arc additive manufacturing. It highlights the importance of machine learning in optimizing manufacturing processes, particularly in predicting the bead width and height in WAAM. The study employs five different ML algorithms—Linear Regression, Decision Tree Regression, Random Forest Regression, XGBoost, and Artificial Neural Networks—to predict the bead geometry based on various input parameters. The research methodology includes data collection, pre-processing, and visualization, followed by hyper-parameter tuning and evaluation of the ML models. The results demonstrate the effectiveness of these algorithms in predicting bead geometry, with some models showing superior performance in terms of accuracy and efficiency. The study concludes by identifying the best-performing algorithms for predicting bead height and width, providing valuable insights for industrial applications in additive manufacturing.

AI Generated

This summary of the content was generated with the help of AI.

Abstract

In the past few years, machine learning (ML) has become a widely used computational tool in manufacturing. The present study conducted a comparative analysis of five machine learning (ML) algorithms to predict the bead geometry in wire-arc additive manufacturing (WAAM). A robotic-controlled gas metal arc welding (GMAW) based WAAM setup was employed to deposit the beads. For the purpose of training and testing the ML models, a dataset consisting of four independent variables (travel speed, torch angle, wire feed rate, and contact tube to workpiece distance) and two dependent variables (bead height and width) was collected. The study employed five ML models including decision tree, random forest, XGBoost algorithm, linear regression, and artificial neural networks (ANN). The performance of ML models was evaluated using statistical metrics such as index of merit (IM), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R² value). A comparison of ML algorithms revealed that ANN (R² value = 0.6505) performed better than the XGBoost (R² value = 0.5916) in predicting the bead height. The lowest value of MSE and MAE equal to 0.0611 and 0.1893 respectively was achieved for ANN in predicting the bead height. For the prediction of bead width, linear regression (R² value = 0.8486) performed better than ANN (R² value = 0.8316). The lowest value of MSE and MAE equal to 0.1730 and 0.3157 respectively was achieved for linear regression in predicting the bead width. Linear regression is most suitable for datasets having strong collinearity, however, ANN, Random Forest and XGBoost performed very well in prediction when the dataset shows high non-linear relations. The comparison of ML algorithms revealed that computational work using machine learning gives high-performance results with minimal use for resources and time. Hence, machine learning can be the most effective computational tool in modern manufacturing industries.

previous article Numerical investigation of forces and acceleration for air-sea unmanned aerial vehicle in transition

next article Optimization and numerical analysis of friction stir welding parameters of AA7075-T651 and AA 1200-H19 using tapered tool

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Kotsiopoulos, T., Sarigiannidis, P., Ioannidis, D., Tzovaras, D.: Machine learning and deep learning in smart manufacturing: the smart grid paradigm. Comput. Sci. Rev. 40, 100341 (2021). https://doi.org/10.1016/j.cosrev.2020.100341MathSciNetCrossRef

Oladipupo, T.: Types of machine learning algorithms. New Adv. Mach. Learn. (2010). https://doi.org/10.5772/9385CrossRef

Johnson, N.S., et al.: Invited review: machine learning for materials developments in metals additive manufacturing. Addit. Manuf. (2020). https://doi.org/10.1016/j.addma.2020.101641CrossRef

Guo, S., et al.: Machine learning for metal additive manufacturing: towards a physics-informed data-driven paradigm. J. Manuf. Syst. 62, 145–163 (2022). https://doi.org/10.1016/j.jmsy.2021.11.003CrossRef

Nasiri, S., Khosravani, M.R.: Machine learning in predicting mechanical behavior of additively manufactured parts. J. Mater. Res. Technol. 14, 1137–1153 (2021). https://doi.org/10.1016/j.jmrt.2021.07.004CrossRef

Qi, X., Chen, G., Li, Y., Cheng, X., Li, C.: Applying neural-network-based machine learning to additive manufacturing: current applications, challenges, and future perspectives. Engineering 5(4), 721–729 (2019). https://doi.org/10.1016/j.eng.2019.04.012CrossRef

Wang, Q., Jiao, W., Wang, P., Zhang, Y.M.: A tutorial on deep learning-based data analytics in manufacturing through a welding case study. J. Manuf. Process. 63, 2–13 (2021). https://doi.org/10.1016/j.jmapro.2020.04.044CrossRef

DebRoy, T., Mukherjee, T., Wei, H.L., Elmer, J.W., Milewski, J.O.: Metallurgy, mechanistic models and machine learning in metal printing. Nat. Rev. Mater. 6(1), 48–68 (2021). https://doi.org/10.1038/s41578-020-00236-1CrossRef

Lee, C., Seo, G., Kim, D., Kim, M., Shin, J.H.: Development of defect detection ai model for wire + arc additive manufacturing using high dynamic range images. Appl. Sci. (2021). https://doi.org/10.3390/app11167541CrossRef

10.

Chen, X., et al.: A review on wire-arc additive manufacturing: typical defects, detection approaches, and multisensor data fusion-based model. Int. J. Adv. Manuf. Technol. 117(3–4), 707–727 (2021). https://doi.org/10.1007/s00170-021-07807-8CrossRef

11.

Yaseer, A., Chen, H.: Machine learning based layer roughness modeling in robotic additive manufacturing. J. Manuf. Process. 70(September), 543–552 (2021). https://doi.org/10.1016/j.jmapro.2021.08.056CrossRef

12.

Farias, F.W.C., da Cruz Payão Filho, J., e Oliveira, V.H.P.M.: Prediction of the interpass temperature of a wire arc additive manufactured wall: FEM simulations and artificial neural network. Addit. Manuf. 48, 102387 (2021)

13.

Nalajam, P.K., Varadarajan, R.: A hybrid deep learning model for layer-wise melt pool temperature forecasting in wire-arc additive manufacturing process. IEEE Access 9, 100652–100664 (2021). https://doi.org/10.1109/ACCESS.2021.3097177CrossRef

14.

Xia, C., Pan, Z., Zhang, S., Li, H., Xu, Y., Chen, S.: Model-free adaptive iterative learning control of melt pool width in wire arc additive manufacturing. Int. J. Adv. Manuf. Technol. 110(7–8), 2131–2142 (2020). https://doi.org/10.1007/s00170-020-05998-0CrossRef

15.

Wu, D., Chen, H., Huang, Y., Chen, S.: Online monitoring and model-free adaptive control of weld penetration in VPPAW based on extreme learning machine. IEEE Trans. Ind. Informatics 15(5), 2732–2740 (2019). https://doi.org/10.1109/TII.2018.2870933CrossRef

16.

Wang, Y., et al.: Active disturbance rejection control of layer width in wire arc additive manufacturing based on deep learning. J. Manuf. Process. 67(March), 364–375 (2021). https://doi.org/10.1016/j.jmapro.2021.05.005CrossRef

17.

Ding, D., He, F., Yuan, L., Pan, Z., Wang, L., Ros, M.: The first step towards intelligent wire arc additive manufacturing: an automatic bead modelling system using machine learning through industrial information integration. J. Ind. Inf. Integr. 23, 100218 (2021). https://doi.org/10.1016/j.jii.2021.100218CrossRef

18.

Gokhale, N.P., Kala, P., Sharma, V.: Thin-walled metal deposition with GTAW welding-based additive manufacturing process. J. Brazilian Soc. Mech. Sci. Eng. (2019). https://doi.org/10.1007/s40430-019-2078-zCrossRef

19.

Ismail, M.I.S., Okamoto, Y., Okada, A.: Neural network modeling for prediction of weld bead geometry in laser microwelding. Adv. Opt. Technol. (2013). https://doi.org/10.1155/2013/415837CrossRef

20.

Mbodj, N.G., Abuabiah, M., Plapper, P., El Kandaoui, M., Yaacoubi, S.: Bead geometry prediction in laser-wire additive manufacturing process using machine learning: case of study. Appl. Sci. (2021). https://doi.org/10.3390/app112411949CrossRef

21.

Nikam, S.H., Jain, N.K., Sawant, M.S.: Optimization of parameters of micro-plasma transferred arc additive manufacturing process using real coded genetic algorithm. Int. J. Adv. Manuf. Technol. 106(3–4), 1239–1252 (2020). https://doi.org/10.1007/s00170-019-04658-2CrossRef

22.

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. 10(8), 1–9 (2018). https://doi.org/10.1177/1687814018781492CrossRef

23.

Xiong, J., Zhang, G., Hu, J., Wu, L.: Bead geometry prediction for robotic GMAW-based rapid manufacturing through a neural network and a second-order regression analysis. 2012, https://doi.org/10.1007/s10845-012-0682-1

24.

Venkata Rao, K., Parimi, S., Suvarna Raju, L., Suresh, G.: Modelling and optimization of weld bead geometry in robotic gas metal arc-based additive manufacturing using machine learning, finite-element modelling and graph theory and matrix approach. Soft Comput. 26, 1–15 (2022)CrossRef

25.

Li, R., Dong, M., Gao, H.: Prediction of bead geometry with changing welding speed using artificial neural network. Materials (Basel) 14(6), 1–9 (2021). https://doi.org/10.3390/ma14061494CrossRef

26.

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). https://doi.org/10.3390/jmmp3020039CrossRef

27.

Deng, J., Xu, Y., Zuo, Z., Hou, Z., Chen, S.: Bead geometry prediction for multi-layer and multi-bead wire and arc additive manufacturing based on XGBoost. In: Transactions on Intelligent Welding Manufacturing, pp. 125–135. Springer, Berlin (2019)CrossRef

28.

Panda, B., Akhil, K.S., Savalani, G.M.M.: Evaluation of genetic programming-based models for simulating bead dimensions in wire and arc additive manufacturing. J. Intell. Manuf. (2016). https://doi.org/10.1007/s10845-016-1282-2CrossRef

29.

Xing, Y., Lv, C., Zhao, Y., Liu, Y., Cao, D., Kawahara, S.: Prediction of deposition bead geometry in wire arc additive manufacturing using machine learning. J. Mater. Res. Technol. (2020). https://doi.org/10.1016/j.jmrt.2022.08.154CrossRef

30.

Langelandsvik, G., Akselsen, O.M., Furu, T., Roven, H.J.: Review of aluminum alloy development for wire arc additive manufacturing. Materials (Basel) 14(18), 1–26 (2021). https://doi.org/10.3390/ma14185370CrossRef

31.

Wang, Z., et al.: Data-driven modeling of process, structure and property in additive manufacturing: a review and future directions. J. Manuf. Process. 77(March), 13–31 (2022). https://doi.org/10.1016/j.jmapro.2022.02.053CrossRef

32.

Mustafa, U., Chandra, M., Paulraj, S.: Influence of filler wire diameter on mechanical and corrosion properties of AA5083-H111 Al–Mg alloy sheets welded using an AC square wave GTAW process. Trans. Indian Inst. Met. 71(8), 1975–1983 (2018). https://doi.org/10.1007/s12666-018-1331-yCrossRef

33.

Buitinck, L. et al.: API design for machine learning software: experiences from the scikit-learn project. pp. 1–15, 2013, [Online]. Available: http://arxiv.org/abs/1309.0238

34.

Warsi, R., Kazmi, K.H., Chandra, M.: Mechanical properties of wire and arc additive manufactured component deposited by a CNC controlled GMAW. Mater. Today Proc. (2021). https://doi.org/10.1016/j.matpr.2021.10.114CrossRef

35.

Pekel, E.: Estimation of soil moisture using decision tree regression. Theor. Appl. Climatol. 139(3–4), 1111–1119 (2020). https://doi.org/10.1007/s00704-019-03048-8CrossRef

36.

Dong, X., Yu, Z., Cao, W., Shi, Y., Ma, Q.: A survey on ensemble learning. Front. Comput. Sci. 14(2), 241–258 (2020). https://doi.org/10.1007/s11704-019-8208-zCrossRef

37.

Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785–794

38.

Zhang, Z., Poudel, L., Sha, Z., Zhou, W., Wu, D.: Data-driven predictive modeling of tensile behavior of parts fabricated by cooperative 3D printing. J. Comput. Inf. Sci. Eng. 20(2), 1–10 (2020). https://doi.org/10.1115/1.4045290CrossRef

39.

Simon Haykin, C.: (McMaster University, Hamilton, Ontario, Neural Networks - A Comprehensive Foundation - Simon Haykin. 2005.

40.

Barrionuevo, G.O., Ramos-grez, J.A., Walczak, M., Betancourt, C.A.: Comparative evaluation of supervised machine learning algorithms in the prediction of the relative density of 316L stainless steel fabricated by selective laser melting. pp. 419–433, 2021

Title: A comparative study of machine learning algorithms in the prediction of bead geometry in wire-arc additive manufacturing
Authors: Mukesh Chandra
K. E. K. Vimal
Sonu Rajak
Publication date: 14-05-2023
Publisher: Springer Paris
Published in: International Journal on Interactive Design and Manufacturing (IJIDeM) / Issue 9/2024
Print ISSN: 1955-2513
Electronic ISSN: 1955-2505
DOI: https://doi.org/10.1007/s12008-023-01326-4

Stretch flangeability analysis of heat treated dual phase steel alloy sheet

Original Paper

Numerical comparison of advanced high strength steels forming limit curve using Banabic and Nakazima tests

Original Paper

Influence of axial thermal variation on modal behavior of axially functionally graded material beam

Original Paper

Physio-mechanical characterization of kenaf/saw dust reinforced polymer matrix composite and selection of optimal configuration using MADM-VIKOR approach

Original Paper

Simplified optimal design of NU202 cylindrical roller bearing and validation through GA

Original Paper

Hall–Petch and Hollomon modeling for microalloyed 2219Al alloys under different thermo-mechanical treatments

Original Paper

Springer Professional

A comparative study of machine learning algorithms in the prediction of bead geometry in wire-arc additive manufacturing

Abstract

Abstract

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Other articles of this Issue 9/2024

Stretch flangeability analysis of heat treated dual phase steel alloy sheet

Numerical comparison of advanced high strength steels forming limit curve using Banabic and Nakazima tests

Influence of axial thermal variation on modal behavior of axially functionally graded material beam

Physio-mechanical characterization of kenaf/saw dust reinforced polymer matrix composite and selection of optimal configuration using MADM-VIKOR approach

Simplified optimal design of NU202 cylindrical roller bearing and validation through GA

Hall–Petch and Hollomon modeling for microalloyed 2219Al alloys under different thermo-mechanical treatments

Premium Partner

Springer Professional

Abstract

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Stretch flangeability analysis of heat treated dual phase steel alloy sheet

Numerical comparison of advanced high strength steels forming limit curve using Banabic and Nakazima tests

Influence of axial thermal variation on modal behavior of axially functionally graded material beam

Physio-mechanical characterization of kenaf/saw dust reinforced polymer matrix composite and selection of optimal configuration using MADM-VIKOR approach

Simplified optimal design of NU202 cylindrical roller bearing and validation through GA

Hall–Petch and Hollomon modeling for microalloyed 2219Al alloys under different thermo-mechanical treatments