Optimization of Process Parameters in Laser Powder Bed Fusion of SS 316L Parts Using Artificial Neural Networks
Abstract
:1. Introduction
2. Materials and Methods
2.1. Experimental Setup
2.2. Artificial Neural Network
2.3. Hyperparameter Optimization and K-Fold Cross-Validation
2.4. Process Parameter Optimization Algorithm
3. Results and Discussion
3.1. Hyperparameter Optimization and K-Fold Cross-Validation
3.2. Performance of the ANN
3.3. Optimization of Process Parameters and Performance
4. Conclusions
- Hyperparameter optimization and cross-validation are crucial steps in developing a robust prediction model. The combination can reduce the model loss and enhance the performance on unseen data.
- Neural networks are highly sensitive to the training data. To have comparable performance for every property, training data must contain inclusive data points within the range. Having less data in the given range would affect the performance of the predictions.
- Finding the optimal parameters for the laser powder bed fusion process requires an understanding of the combined effect of the process parameters on the part properties. ANN is a powerful tool in modeling the combined relationship and obtaining the optimal process parameters in the given range of data.
Author Contributions
Funding
Conflicts of Interest
References
- Gong, H.; Snelling, D.; Kardel, K.; Carrano, A. Comparison of Stainless Steel 316L Parts Made by FDM- and SLM-Based Additive Manufacturing Processes. JOM 2019, 71, 880–885. [Google Scholar] [CrossRef]
- Shayfull, Z.; Sharif, S.; Zain, A.M.; Ghazali, M.F.; Saad, R.M. Potential of Conformal Cooling Channels in Rapid Heat Cycle Molding: A Review. Adv. Polym. Technol. 2014, 33, 21381. [Google Scholar] [CrossRef]
- Dowling, L.; Kennedy, J.; O’Shaughnessy, S.; Trimble, D. A Review of Critical Repeatability and Reproducibility Issues in Powder Bed Fusion. Mater. Des. 2020, 186, 108346. [Google Scholar] [CrossRef]
- Malekipour, E.; El-Mounayri, H. Common Defects and Contributing Parameters in Powder Bed Fusion AM Process and Their Classification for Online Monitoring and Control: A Review. Int. J. Adv. Manuf. Technol. 2018, 95, 527–550. [Google Scholar] [CrossRef]
- Markl, M.; Körner, C. Multiscale Modeling of Powder Bed–Based Additive Manufacturing. Annu. Rev. Mater. Res. 2016, 46, 93–123. [Google Scholar] [CrossRef]
- Shipley, H.; McDonnell, D.; Culleton, M.; Coull, R.; Lupoi, R.; O’Donnell, G.; Trimble, D. Optimisation of Process Parameters to Address Fundamental Challenges during Selective Laser Melting of Ti-6Al-4V: A Review. Int. J. Mach. Tools Manuf. 2018, 128, 1–20. [Google Scholar] [CrossRef]
- Tian, Y.; Tomus, D.; Rometsch, P.; Wu, X. Influences of Processing Parameters on Surface Roughness of Hastelloy X Produced by Selective Laser Melting. Addit. Manuf. 2017, 13, 103–112. [Google Scholar] [CrossRef]
- Moussaoui, K.; Rubio, W.; Mousseigne, M.; Sultan, T.; Rezai, F. Effects of Selective Laser Melting Additive Manufacturing Parameters of Inconel 718 on Porosity, Microstructure and Mechanical Properties. Mater. Sci. Eng. A 2018, 735, 182–190. [Google Scholar] [CrossRef]
- Larimian, T.; Kannan, M.; Grzesiak, D.; AlMangour, B.; Borkar, T. Effect of Energy Density and Scanning Strategy on Densification, Microstructure and Mechanical Properties of 316L Stainless Steel Processed via Selective Laser Melting. Mater. Sci. Eng. A 2020, 770, 138455. [Google Scholar] [CrossRef]
- Khaimovich, A.; Balyakin, A.; Oleynik, M.; Meshkov, A.; Smelov, V. Optimization of Process Parameters for Powder Bed Fusion Additive Manufacturing Using a Linear Programming Method: A Conceptual Framework. Metals 2022, 12, 1976. [Google Scholar] [CrossRef]
- Greco, S.; Gutzeit, K.; Hotz, H.; Kirsch, B.; Aurich, J.C. Selective Laser Melting (SLM) of AISI 316L—Impact of Laser Power, Layer Thickness, and Hatch Spacing on Roughness, Density, and Microhardness at Constant Input Energy Density. Int. J. Adv. Manuf. Technol. 2020, 108, 1551–1562. [Google Scholar] [CrossRef]
- Liu, Q.C.; Elambasseril, J.; Sun, S.J.; Leary, M.; Brandt, M.; Sharp, P.K. The Effect of Manufacturing Defects on the Fatigue Behaviour of Ti-6Al-4V Specimens Fabricated Using Selective Laser Melting. Adv. Mater. Res. 2014, 891–892, 1519–1524. [Google Scholar] [CrossRef]
- Laakso, P.; Riipinen, T.; Laukkanen, A.; Andersson, T.; Jokinen, A.; Revuelta, A.; Ruusuvuori, K. Optimization and Simulation of SLM Process for High Density H13 Tool Steel Parts. Phys. Procedia 2016, 83, 26–35. [Google Scholar] [CrossRef]
- Ravichander, B.B.; Amerinatanzi, A.; Shayesteh Moghaddam, N. Study on the Effect of Powder-Bed Fusion Process Parameters on the Quality of as-Built IN718 Parts Using Response Surface Methodology. Metals 2020, 10, 1180. [Google Scholar] [CrossRef]
- Liu, Y.; Wu, Z.; Wang, Q.; Zhao, L.; Zhang, X.; Gao, W.; Xu, J.; Song, Y.; Song, X.; Zhang, X. Optimization of Parameters in Laser Powder Bed Fusion TA15 Titanium Alloy Using Taguchi Method. Crystals 2022, 12, 1385. [Google Scholar] [CrossRef]
- Strano, G.; Hao, L.; Everson, R.M.; Evans, K.E. Surface Roughness Analysis, Modelling and Prediction in Selective Laser Melting. J. Mater. Process. Technol. 2013, 213, 589–597. [Google Scholar] [CrossRef]
- Cao, L.; Li, J.; Hu, J.; Liu, H.; Wu, Y.; Zhou, Q. Optimization of Surface Roughness and Dimensional Accuracy in LPBF Additive Manufacturing. Opt. Laser Technol. 2021, 142, 107246. [Google Scholar] [CrossRef]
- Yao, X.; Moon, S.K.; Bi, G. A hybrid machine learning approach for additive manufacturing design feature recommendation. Rapid Prototyp. J. 2017, 23, 983–997. [Google Scholar] [CrossRef]
- Sosnovik, I.; Oseledets, I. Neural networks for topology optimization. Russ. J. Numer. Anal. Math. Model. 2019, 34, 215–223. [Google Scholar] [CrossRef]
- Ye, D.; Fuh, J.Y.H.; Zhang, Y.; Hong, G.S.; Zhu, K. In situ monitoring of selective laser melting using plume and spatter signatures by deep belief networks. ISA Trans. 2018, 81, 96–104. [Google Scholar] [CrossRef]
- Scime, L.; Beuth, J. Using machine learning to identify in-situ melt pool signatures indicative of flaw formation in a laser powder bed fusion additive manufacturing process. Addit. Manuf. 2019, 25, 151–165. [Google Scholar] [CrossRef]
- Gaikwad, A.; Williams, R.J.; de Winton, H.; Bevans, B.D.; Smoqi, Z.; Rao, P.; Hooper, P.A. Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing. Mater. Des. 2022, 221, 110919. [Google Scholar] [CrossRef]
- Kouraytem, N.; Li, X.; Tan, W.; Kappes, B.; Spear, A.D. Modeling Process–Structure–Property Relationships in Metal Additive Manufacturing: A Review on Physics-Driven versus Data-Driven Approaches. J. Phys. Mater. 2021, 4, 032002. [Google Scholar] [CrossRef]
- Shen, X.; Yao, J.; Wang, Y.; Yang, J. Density Prediction of Selective Laser Sintering Parts Based on Artificial Neural Network. In Advances in Neural Networks—ISNN 2004; Lecture Notes in Computer, Science; Yin, F.L., Wang, J., Guo, C., Eds.; Springer: Berlin/Heidelberg, Germany, 2004; Volume 3174, ISNN 2004. [Google Scholar] [CrossRef]
- Wang, R.J.; Li, J.; Wang, F.; Li, X.; Wu, Q. ANN Model for the Prediction of Density in Selective Laser Sintering. Int. J. Manuf. Res. 2009, 4, 362. [Google Scholar] [CrossRef]
- Rong-Ji, W.; Xin-hua, L.; Qing-ding, W.; Lingling, W. Optimizing process parameters for selective laser sintering based on neural network and genetic algorithm. Int. J. Adv. Manuf. Technol. 2009, 42, 1035. [Google Scholar] [CrossRef]
- Nguyen, D.S.; Park, H.S.; Lee, C.M. Optimization of Selective Laser Melting Process Parameters for Ti-6Al-4V Alloy Manufacturing Using Deep Learning. J. Manuf. Process. 2020, 55, 230–235. [Google Scholar] [CrossRef]
- Lo, Y.L.; Liu, B.Y.; Tran, H.C. Optimized hatch space selection in double-scanning track selective laser melting process. Int. J. Adv. Manuf. Technol. 2019, 105, 2989. [Google Scholar] [CrossRef]
- Srinivasan, S.; Swick, B.; Groeber, M.A. Laser Powder Bed Fusion Parameter Selection via Machine-Learning-Augmented Process Modeling. JOM 2020, 72, 4393–4403. [Google Scholar] [CrossRef]
- Ravichander, B.B.; Rahimzadeh, A.; Farhang, B.; Shayesteh Moghaddam, N.; Amerinatanzi, A.; Mehrpouya, M. A Prediction Model for Additive Manufacturing of Inconel 718 Superalloy. Appl. Sci. 2021, 11, 8010. [Google Scholar] [CrossRef]
- Chaudhry, S.; Soulaïmani, A. A Comparative Study of Machine Learning Methods for Computational Modeling of the Selective Laser Melting Additive Manufacturing Process. Appl. Sci. 2022, 12, 2324. [Google Scholar] [CrossRef]
- Caiazzo, F.; Caggiano, A. Laser Direct Metal Deposition of 2024 Al Alloy: Trace Geometry Prediction via Machine Learning. Materials 2018, 11, 444. [Google Scholar] [CrossRef] [PubMed]
- Eshkabilov, S.; Ara, I.; Azarmi, F. A Comprehensive Investigation on Application of Machine Learning for Optimization of Process Parameters of Laser Powder Bed Fusion-Processed 316L Stainless Steel. Int. J. Adv. Manuf. Technol. 2022, 123, 2733–2756. [Google Scholar] [CrossRef]
- Gor, M.; Dobriyal, A.; Wankhede, V.; Sahlot, P.; Grzelak, K.; Kluczyński, J.; Łuszczek, J. Density Prediction in Powder Bed Fusion Additive Manufacturing: Machine Learning-Based Techniques. Appl. Sci. 2022, 12, 7271. [Google Scholar] [CrossRef]
- 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. Int. J. Adv. Manuf. Technol. 2021, 113, 419–433. [Google Scholar] [CrossRef]
- Zou, M.; Jiang, W.G.; Qin, Q.H.; Liu, Y.C.; Li, M.L. Optimized XGBoost Model with Small Dataset for Predicting Relative Density of Ti-6Al-4V Parts Manufactured by Selective Laser Melting. Materials 2022, 15, 5298. [Google Scholar] [CrossRef]
- Khanzadeh, M.; Chowdhury, S.; Marufuzzaman, M.; Tschopp, M.A.; Bian, L. Porosity prediction: Supervised-learning of thermal history for direct laser deposition. J. Manuf. Syst. 2018, 47, 69. [Google Scholar] [CrossRef]
- So, M.S.; Seo, G.J.; Kim, D.B.; Shin, J.-H. Prediction of Metal Additively Manufactured Surface Roughness Using Deep Neural Network. Sensors 2022, 22, 7955. [Google Scholar] [CrossRef]
- Theeda, S.; Ravichander, B.B.; Jagdale, S.H.; Kumar, G. Optimization of Laser Process Parameters Using Machine Learning Algorithms and Performance Comparison. In Proceedings of the 2022 International Solid Freeform Fabrication Symposium, Austin, TX, USA, 25–27 July 2022. [Google Scholar] [CrossRef]
- Chia, H.Y.; Wu, J.; Wang, X.; Yan, W. Process Parameter Optimization of Metal Additive Manufacturing: A Review and Outlook. J. Mater. Inform. 2022, 2, 16. [Google Scholar] [CrossRef]
- La Fé-Perdomo, I.; Ramos-Grez, J.A.; Jeria, I.; Guerra, C.; Barrionuevo, G.O. Comparative Analysis and Experimental Validation of Statistical and Machine Learning-Based Regressors for Modeling the Surface Roughness and Mechanical Properties of 316L Stainless Steel Specimens Produced by Selective Laser Melting. J. Manuf. Process. 2022, 80, 666–682. [Google Scholar] [CrossRef]
- Jagdale, S.H.; Theeda, S.; Ravichander, B.B.; Kumar, G. Surface morphology and Hardness of powder Bed Fused SS316L as a Function of Process Parameters. In Proceedings of the 2022 International Solid Freeform Fabrication Symposium, Austin, TX, USA, 25–27 July 2022. [Google Scholar] [CrossRef]
- Gatões, D.; Alves, R.; Alves, B.; Vieira, M.T. Selective Laser Melting and Mechanical Properties of Stainless Steels. Materials 2022, 15, 7575. [Google Scholar] [CrossRef]
- Guzmán, J.; Nobre, R.d.M.; Nunes, E.R.; Bayerlein, D.L.; Falcão, R.B.; Sallica-Leva, E.; Neto, J.B.F.; Oliveira, H.R.; Chastinet, V.L.; Landgraf, F.J.G. Laser Powder Bed Fusion Parameters to Produce High-Density Ti–53%Nb Alloy Using Irregularly Shaped Powder from Hydride-Dehydride (HDH) Process. J. Mater. Res. Technol. 2021, 10, 1372–1381. [Google Scholar] [CrossRef]
- Gorsse, S.; Huchinson, C.; Goune, M.; Banerjee, R. Additive manufacturing of metals: A brief review of the characteristic microstructures and properties of steels, Ti-6Al-4V and high-entropy alloys. Sci. Technol. Adv. Mater. 2017, 18, 584. [Google Scholar] [CrossRef] [PubMed]
- Parikh, Y.; Kuttolamadom, M. Property-Graded Stainless Steel 316L by Selective Laser Melting: Characterization & Design. J. Manuf. Sci. Eng. 2023, 144, 61008. [Google Scholar] [CrossRef]
- Abadi, M.; Barham, P.; Chen, J.; Chen, Z.; Davis, A.; Dean, J.; Devin, M.; Ghemawat, S.; Irving, G.; Isard, M.; et al. TensorFlow: A System for Large-Scale Machine Learning. arXiv 2016, arXiv:1605.08695. [Google Scholar] [CrossRef]
- Liu, J.; Ye, J.; Silva Izquierdo, D.; Vinel, A.; Shamsaei, N.; Shao, S. A Review of Machine Learning Techniques for Process and Performance Optimization in Laser Beam Powder Bed Fusion Additive Manufacturing. J. Intell. Manuf. 2022. [Google Scholar] [CrossRef]
- Kingma, D.P.; Ba, J. Adam: A Method for Stochastic Optimization. arXiv 2017, arXiv:1412.6980. [Google Scholar] [CrossRef]
- Anguita, D.; Ghelardoni, L.; Ghio, A.; Oneto, L.; Ridella, S. The ‘K’ in K-Fold Cross Validation. In Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, 25–27 April 2012; pp. 441–446. [Google Scholar]
- Deng, Y.; Mao, Z.; Yang, N.; Niu, X.; Lu, X. Collaborative Optimization of Density and Surface Roughness of 316L Stainless Steel in Selective Laser Melting. Materials 2020, 13, 1601. [Google Scholar] [CrossRef]
S. No. | Laser Power (W) | Scan Speed (mm/s) | Hatch Spacing (μm) | VED Ev (J/mm3) | Relative Density (%) | Surface Roughness (μm) | Micro- Hardness (HV) | Dimensional Error (μm) |
---|---|---|---|---|---|---|---|---|
1 | 150 | 710 | 129 | 54.5 | 98.7 | 9.0 | 257.1 | 3.0 |
2 | 150 | 890 | 111 | 50.6 | 99.2 | 9.3 | 256.5 | 19.0 |
3 | 185 | 710 | 129 | 67.3 | 98.9 | 13.9 | 258.9 | 28.0 |
4 | 185 | 830 | 117 | 63.5 | 98.9 | 8.3 | 266.2 | 6.7 |
5 | 185 | 890 | 111 | 62.4 | 98.3 | 12.1 | 248.4 | 4.0 |
6 | 220 | 830 | 111 | 79.6 | 98.6 | 12.6 | 258.2 | 47.0 |
7 | 220 | 890 | 117 | 70.4 | 97.9 | 10.1 | 260.5 | 42.3 |
8 | 255 | 710 | 123 | 97.3 | 97.6 | 16.4 | 234.3 | 38.3 |
9 | 255 | 770 | 129 | 85.5 | 97.9 | 14.7 | 258.1 | 17.0 |
10 | 200 | 800 | 120 | 69.4 | 99.1 | 11.0 | 248.8 | 8.7 |
11 | 290 | 880 | 117 | 93.9 | 97.1 | 10.8 | 256.9 | 13.0 |
12 | 200 | 725 | 117 | 78.6 | 98.1 | 8.9 | 236.9 | 31.3 |
13 | 200 | 800 | 111 | 75.1 | 97.7 | 12.5 | 239.3 | 20.8 |
14 | 200 | 650 | 125 | 82.1 | 97.2 | 12.3 | 240.7 | 18.3 |
15 | 290 | 750 | 125 | 103.1 | 98.4 | 20.8 | 275.7 | 20.0 |
16 | 220 | 770 | 129 | 73.9 | 98.6 | 9.7 | 262.3 | 70.7 |
17 | 150 | 830 | 117 | 51.5 | 98.4 | 9.0 | 245.7 | 15.7 |
18 | 255 | 830 | 111 | 92.1 | 98.8 | 14.9 | 251.4 | 18.0 |
19 | 185 | 770 | 123 | 65.1 | 98.9 | 10.3 | 243.9 | 2.3 |
20 | 150 | 770 | 123 | 52.8 | 99.2 | 8.4 | 253.5 | 18.0 |
21 | 220 | 710 | 123 | 83.9 | 98.5 | 10.7 | 250.6 | 24.7 |
22 | 255 | 890 | 117 | 81.6 | 98.4 | 14.4 | 254.9 | 52.7 |
23 | 290 | 675 | 129 | 111.0 | 96.7 | 16.9 | 255.9 | 11.0 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 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 (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Theeda, S.; Jagdale, S.H.; Ravichander, B.B.; Kumar, G. Optimization of Process Parameters in Laser Powder Bed Fusion of SS 316L Parts Using Artificial Neural Networks. Metals 2023, 13, 842. https://doi.org/10.3390/met13050842
Theeda S, Jagdale SH, Ravichander BB, Kumar G. Optimization of Process Parameters in Laser Powder Bed Fusion of SS 316L Parts Using Artificial Neural Networks. Metals. 2023; 13(5):842. https://doi.org/10.3390/met13050842
Chicago/Turabian StyleTheeda, Sumanth, Shweta Hanmant Jagdale, Bharath Bhushan Ravichander, and Golden Kumar. 2023. "Optimization of Process Parameters in Laser Powder Bed Fusion of SS 316L Parts Using Artificial Neural Networks" Metals 13, no. 5: 842. https://doi.org/10.3390/met13050842