Metamodels’ Development for High Pressure Die Casting of Aluminum Alloy
Abstract
:1. Introduction
- White-box models: These are rigorous models based on mass and energy balances with the process rate or kinetics equations. They give an almost exact image of the physical laws and the behavior of the given real system. Complete knowledge of the way the system works is needed to develop the model;
- Black-box models: These are developed by measuring the inputs and outputs of the system and fitting a linear or nonlinear mathematical function to approximate the operation of the system. In this case, since data from experiments on the real system are used to build the model, we are not given any insight into or understanding of how the system works;
- Grey-box models: These are semi-empirical-based or experimentally adjusted models. Grey-box models are developed using white-box models whose parameters are estimated using the measured system inputs and outputs. Some examples are neuro-fuzzy systems or semi-empirical models.
2. High-Pressure Die Casting Modeling
3. Methodology
3.1. Variables Selection
3.2. Design of Experiments
3.3. Numerical Simulations: Obtaining the Data
3.4. Metamodel Development: Regression Model
4. Design of the Tests and Implementation
4.1. Case Study and Variables’ Selection
4.2. Design of Experiments
4.3. Numerical Simulation
4.4. Metamodel Development
- Number of estimators: This is the number of boosting stages to perform. Gradient boosting is robust to overfitting, so a large number usually results in better performance. However, although the GBR is robust at a higher number of trees, it can still overfit at a point. Hence, this should be tuned;
- Learning rate: This parameter determines the impact of each tree on the outcome. The GBR works by starting with an initial estimate, which is updated using the output of each tree. The learning parameter controls the magnitude of this change in the estimates. Lower values are generally preferred as they make the model robust to the specific characteristics of the tree and thus allow generalizing well. Lower values would require a higher number of trees to model all the relations and would be computationally expensive;
- Subsample: The fraction of observations to be selected for each tree considering that the selection is performed by random sampling. Values slightly less than 1 make the model robust by reducing the variance, and typical values around 0.8 generally perform well but can be tuned further;
- Max depth: This is the maximum depth of a tree, used to control overfitting as a higher depth will allow the model to learn relations very specific for a sample.
5. Results
6. Discussion of the Results
7. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Gao, Y.; Liu, X.; Huang, H.; Xiang, J. A hybrid of FEM simulations and generative adversarial networks to classify faults in rotor-bearing systems. ISA Trans. 2021, 108, 356–366. [Google Scholar] [CrossRef]
- Piltyay, S.; Bulashenko, A.; Herhil, Y.; Bulashenko, O. FDTD and FEM simulation of microwave waveguide polarizers. In Proceedings of the 2020 IEEE 2nd International Conference on Advanced Trends in Information Theory (ATIT), Kyiv, Ukraine, 25–27 November 2020; pp. 357–363. [Google Scholar]
- Carlini, M.; McCormack, S.J.; Castellucci, S.; Ortega, A.; Rotondo, M.; Mennuni, A. Modeling and numerical simulation for an innovative compound solar concentrator: Thermal analysis by FEM approach. Energies 2020, 13, 548. [Google Scholar] [CrossRef] [Green Version]
- Gong, X.; Bustillo, J.; Blanc, L.; Gautier, G. FEM simulation on elastic parameters of porous silicon with different pore shapes. Int. J. Solids Struct. 2020, 190, 238–243. [Google Scholar] [CrossRef]
- Forrester, A.I.; Keane, A.J. Recent advances in surrogate-based optimization. Prog. Aerosp. Sci. 2009, 45, 50–79. [Google Scholar] [CrossRef]
- Han, Z.H.; Zhang, K.S. Surrogate-based optimization. In Real-World Applications of Genetic Algorithms; InTech Open: Rijeka, Croatia, 2012; pp. 343–362. [Google Scholar]
- Forrester, A.; Sobester, A.; Keane, A. Engineering Design via Surrogate Modeling: A Practical Guide; John Wiley and Sons: Hoboken, NJ, USA, 2008. [Google Scholar]
- Fiorese, E.; Richiedei, D.; Bonollo, F. Analytical computation and experimental assessment of the effect of the plunger speed on tensile properties in high-pressure die casting. Int. J. Adv. Manuf. Technol. 2017, 91, 463–476. [Google Scholar] [CrossRef]
- Fiorese, E.; Richiedei, D.; Bonollo, F. Improved metamodels for the optimization of high-pressure die casting process. Metall. Ital. 2016, 108, 21–24. [Google Scholar]
- Krimpenis, A.; Benardos, P.; Vosniakos, G.C.; Koukouvitaki, A. Simulation-based selection of optimum pressure die-casting process parameters using neural nets and genetic algorithms. Int. J. Adv. Manuf. Technol. 2006, 27, 509–517. [Google Scholar] [CrossRef]
- Weixiong, Y.; Yi, Y.; Bin, Z. Novel methodology for casting process optimization using Gaussian process regression and genetic algorithm. Res. Dev. 2009, 3, 12. [Google Scholar]
- Bonte, M.; van den Boogaard, A.H.; Huétink, J. A Metamodel Based Optimisation Algorithm for Metal Forming Processes; Springer: Berlin/Heidelberg, Germany, 2007; pp. 55–72. [Google Scholar] [CrossRef] [Green Version]
- Seit, J. Trends and Challenges: The Die-Casting Industry on the Road to the Future. 2018. Available online: https://www.spotlightmetal.com/trends-and-challenges-the-die-casting-industry-on-the-road-to-the-future-a-676717/ (accessed on 10 September 2021).
- Udvardy, S.P. State of the Die Casting Industry. Available online: https://www.diecasting.org/wcm/Die_Casting/State_of_the_Industry/wcm/Die_Casting/State_of_the_Industry.aspx?hkey=b50b590c-a1a6-4c65-8f04-3a6d38c821dc (accessed on 10 September 2021).
- NADCA. Introduction to Die Casting; NADCA: Mt. Laurel, NJ, USA, 2016. [Google Scholar]
- NADCA. Die Casting Handbook; NADCA: Mt. Laurel, NJ, USA, 2015. [Google Scholar]
- Bazhenov, V.; Petrova, A.; Koltygin, A. Simulation of Fluidity and Misrun Prediction for the Casting of 356.0 Aluminium Alloy into Sand Molds. Int. J. Met. 2018, 12, 514–522. [Google Scholar] [CrossRef]
- Gunasegaram, D.; Farnsworth, D.; Nguyen, T. Identification of critical factors affecting shrinkage porosity in permanent mold casting using numerical simulations based on design of experiments. Int. J. Met. 2009, 209, 1209–1219. [Google Scholar] [CrossRef]
- Nastac, L. Numerical modeling of solidification morphologies and segregation patterns in cast dendritic alloys. Acta Mater. 1999, 47, 4253–4262. [Google Scholar] [CrossRef]
- Rappaz, M. Modeling of microstructure formation in solidification processes. Int. Mater. Rev. 1989, 34, 93–124. [Google Scholar] [CrossRef]
- Raffaeli, R.; Favi, C.; Mandorli, F. Virtual prototyping in the design process of optimized mold gating system for high pressure die casting. Eng. Comput. 2015, 32, 102–128. [Google Scholar] [CrossRef]
- Chen, W. A Development Of Virtual Prototyping Manufacturing System For High Pressure Die Casting Processes. WIT Trans. Built Environ. 2015, 67, 10. [Google Scholar]
- Ignaszak, Z. Validation Problems of Virtual Prototyping Systems Used in Foundry for Technology Optimization of Ductile Iron Castings. In Advances in Integrated Design and Manufacturing in Mechanical Engineering II; Springer: Berlin, Germany, 2007. [Google Scholar] [CrossRef]
- Chiang, K.; Liu, N.; Tsai, T. Modeling and analysis of the effects of processing parameters on the performance characteristics in the high pressure die casting process of Al-Si alloys. Int. J. Adv. Manuf. Technol. 2009, 41, 1076–1084. [Google Scholar] [CrossRef]
- Kwon, H.; Kwon, H. Computer aided engineering (CAE) simulation for the design optimization of gate system on high pressure die casting (HPDC) process. Robot. -Comput.-Integr. Manuf. 2019, 55, 147–153. [Google Scholar] [CrossRef]
- Cleary, P.; Ha, J.; Prakash, M.; Nguyen, T. Short shots and industrial case studies: Understanding fluid flow and solidification in high pressure die casting. Appl. Math. Model. 2012, 34, 2018–2033. [Google Scholar] [CrossRef] [Green Version]
- Anglada, E.; Meléndez, A.; Vicario, I.; Arratibel, E.; Cangas, G. Simplified models for high pressure die casting simulation. Procedia Eng. 2015, 132, 974–981. [Google Scholar] [CrossRef] [Green Version]
- Hong, C.; Umeda, T.; Kimura, Y. Numerical models for casting solidification:Part II. Application of the boundary element method to solidification problems. Metall. Trans. B 1984, 15, 101–107. [Google Scholar] [CrossRef]
- Hetu, J.; Gao, D.; Kabanemi, K.; Bergeron, S.; Nguyen, K.; Loong, C. Numerical modeling of casting processes. Adv. Perform. Mater. 1998, 5, 65–82. [Google Scholar] [CrossRef]
- Snyder, D.; Waite, D.; Amin, A. Application of efficient parallel processing to finite element modeling of filling, solidification, and defect prediction for ultra-large shape castings. In Light Metals: Proceedings of Sessions, TMS Annual Meeting; TMS: Pittsburgh, PA, USA, 1997; pp. 919–925. [Google Scholar]
- Jauregui, R.; Silva, F. Numerical Validation Methods. In Numerical Analysis Theory and Application; Awrejcewicz, J., Ed.; IntechOpen: Rijeka, Croatia, 2011; Chapter 8; pp. 155–174. [Google Scholar]
- NADCA. Die Casting Process Control; NADCA: Mt. Laurel, NJ, USA, 2015. [Google Scholar]
- Adamane, A.R.; Arnberg, L.; Fiorese, E.; Timelli, G.; Bonollo, F. Influence of injection parameters on the porosity and tensile properties of high-pressure die cast Al-Si alloys: A review. Int. J. Met. 2015, 9, 43–53. [Google Scholar] [CrossRef]
- dos Santos, S.L.; Antunes, R.A.; Santos, S.F. Influence of injection temperature and pressure on the microstructure, mechanical and corrosion properties of a AlSiCu alloy processed by HPDC. Mater. Des. 2015, 88, 1071–1081. [Google Scholar] [CrossRef]
- Anglada, E.; Meléndez, A.; Vicario, I.; Arratibel, E.; Aguillo, I. Adjustment of a high pressure die casting simulation model against experimental data. Procedia Eng. 2015, 132, 966–973. [Google Scholar] [CrossRef] [Green Version]
- Anglada, E.; Meléndez, A.; Vicario, I.; Idoiaga, J.K.; Mugarza, A.; Arratibel, E. Prediction and validation of shape distortions in the simulation of high pressure die casting. J. Manuf. Process. 2018, 33, 228–237. [Google Scholar] [CrossRef]
- Wynants, L.; Bouwmeester, W.; Moons, K.; Moerbeek, M.; Timmerman, D.; Van Huffel, S.; Van Calster, B.; Vergouwe, Y. A simulation study of sample size demonstrated the importance of the number of events per variable to develop prediction models in clustered data. J. Clin. Epidemiol. 2015, 68, 1406–1414. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Lawson, J. Design and Analysis of Experiments with R; Chapman and Hall/CRC: Boca Raton, FL, USA, 2014. [Google Scholar]
- Dantzig, J.A.; Rappaz, M. Solidification: -Revised & Expanded; EPFL Press: Lausanne, Switzerland, 2016. [Google Scholar]
- Lewis, R.; Ravindran, K. Finite element simulation of metal casting. Int. J. Numer. Methods Eng. 2000, 47, 29–59. [Google Scholar] [CrossRef]
- Gandin, C.A.; Desbiolles, J.L.; Rappaz, M.; Thevoz, P. A three-dimensional cellular automation-finite element model for the prediction of solidification grain structures. Metall. Mater. Trans. A 1999, 30, 3153–3165. [Google Scholar] [CrossRef]
- Smith, M. Neural Networks for Statistical Modeling; Thomson Learning: Boston, MA, USA, 1993. [Google Scholar]
- Williams, C.K.; Rasmussen, C.E. Gaussian Processes for Machine Learning; MIT Press: Cambridge, MA, USA, 2006; Volume 2. [Google Scholar]
- Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef] [Green Version]
- Friedman, J.H. Greedy function approximation: A gradient boosting machine. Ann. Stat. 2001, 29, 1189–1232. [Google Scholar] [CrossRef]
- Orzechowski, P.; La Cava, W.; Moore, J.H. Where are we now?: A large benchmark study of recent symbolic regression methods. In Proceedings of the Genetic and Evolutionary Computation Conference, Kyoto, Japan, 15–19 July 2018; pp. 1183–1190. [Google Scholar]
Explanatory Variable | Details |
---|---|
Mold temperature | Average temperature of both cavity units (fixed and mobile) at the beginning of each injection |
Alloy temperature | Temperature of the alloy at the start of each injection |
Phase 1 velocity | Average piston velocity during the first phase of the alloy injection |
Phase 2 velocity | Maximum piston velocity reached during the second phase of the alloy injection |
Explanatory Variable | Min | Max |
---|---|---|
Mold temperature (C) | 149 | 318 |
Alloy temperature (C) | 620 | 710 |
Phase 1 velocity (m/s) | 0.1 | 0.75 |
Phase 2 velocity (m/s) | 1 | 6 |
Response Variable | Details |
---|---|
Misrun risk | Qualitative variable that represents the risk of the part to remain unfilled in some areas; it is a continuous variable whose value goes from 0 to 3 (0 = no risk; 3 = very high risk) |
Shrinkage | Continuous variable that predicts shrinkage defects, that is porosity caused by the alloy contraction during solidification; it is a continuous variable measured in % |
Microporosity | Continuous variable that predicts microporosity defects, that is porosity lower than 0.1% caused mainly by air entrapment during filling and solidification; it is a continuous variable measured in % |
Macroporosity | Continuous variable that predicts macroporosity defects, that is porosity greater than 0.1% caused by the combination of air entrapment and shrinkage; it is a continuous variable measured in % |
Grain density | Continuous variable that predicts the grain density measured in number of grains per cm |
Eutectic | Continuous variable that predicts the amount of eutectic phase measured in %; the rest of the microstructure will be the fcc phase |
SDAS | Continuous variable that predicts the secondary dendrite arm spacing (SDAS) of the microstructure measured in m |
Response Variable | NMAE (%) | |
---|---|---|
Misrun risk | 0.76 | 7 |
Shrinkage | 0.86 | 7 |
Microporosity | 0.48 | 9 |
Macroporosity | 0.37 | 14 |
Grain density | 0.13 | 16 |
Eutectic | 0.51 | 16 |
SDAS | 0.94 | 4 |
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 (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Anglada, E.; Boto, F.; García de Cortazar, M.; Garmendia, I. Metamodels’ Development for High Pressure Die Casting of Aluminum Alloy. Metals 2021, 11, 1747. https://doi.org/10.3390/met11111747
Anglada E, Boto F, García de Cortazar M, Garmendia I. Metamodels’ Development for High Pressure Die Casting of Aluminum Alloy. Metals. 2021; 11(11):1747. https://doi.org/10.3390/met11111747
Chicago/Turabian StyleAnglada, Eva, Fernando Boto, Maider García de Cortazar, and Iñaki Garmendia. 2021. "Metamodels’ Development for High Pressure Die Casting of Aluminum Alloy" Metals 11, no. 11: 1747. https://doi.org/10.3390/met11111747