Abstract
The filling stage is a critical phenomenon in sand casting for making reliable castings. Latest research has demonstrated that for most liquid engineering alloys, the critical meniscus velocity of the melt at the ingate is in the range of 0.4–0.6 m s−1. The work described in this research paper is to use neural network (NN) technology to propose digital twin approach for gating system design that allow to understand and model its performances faster and more reliable than traditional methods. This approach was applied in the case of sand casting of liquid aluminum alloy (EN AC-44200). The approach is based first on a digital representation of filling process to perform the melt flow simulations using a combination of the gating system design parameters, selected as a training cases from Taguchi orthogonal array (OA). The second step of the approach is the data capture of functional gating design system to train up the feed-forward back-propagation NN model. The validation of the well-trained NN model is assessed by interrogating predicted ingate velocity to it and making reliable predictions with high accuracy. The claim is that such digital twin approach is an effective solution to recognize the functional design parameters from the entire filling systems used during casting process.
Similar content being viewed by others
References
Bakhtiarani, F. N., & Raiszadeh, R. (2011). Healing of double-oxide film defects in commercial purity aluminium melt. Metallurgical and Materials Transaction, 42(2), 331–340.
Bangyikhan, K. (2005). Effects of oxide film, Fe-rich phase, porosity and their interactions on tensile properties of cast Al–Si–Mg alloys. Ph.D. Thesis, University of Birmingham, School of Metallurgy and Materials.
Baoguang, S., Xiuhong, K., & Dianzhong, L. (2010). A novel technique for reducing macrosegregation in heavy steel ingots. Journal of Materials Processing Technology, 210, 703–711.
Basuny, F. H., Ghazy, M., Kandeil, A. Y., & El-Sayed, M. A. (2016). Effect of casting conditions on the fracture strength of Al-5Mg alloy castings. Advances in Materials Science and Engineering. https://doi.org/10.1155/2016/6496348.
Bozchaloei, G. E., Varahram, N., Davami, P., & Kim, S. K. (2012). Effect of oxide bifilms on the mechanical properties of cast Al–7Si–0.3 Mg alloy and the roll of runner height after filter on their formation. Materials Science and Engineering A, 548, 99–105.
Brownlee, J. (2019). Better deep learning: Train faster, reduce overfitting, and make better, predictions machine. Vermont: Learning Mastery.
Campbell, J. (1993). Invisible macrodefects in castings. Journal de Physique IV, C7, 861–872. https://doi.org/10.1051/jp4:19937135.
Campbell, J. (2015). Complete casting handbook: Metal casting processes, metallurgy, techniques and design (2nd ed.). Oxford: Butterworth-Heinemann. ISBN 978-0-444-63509-9.
Campbell, J. (2016). The consolidation of metals: The origin of bifilms. Journal of Materials Science, 51(1), 96–106.
Cao, X., & Campbell, J. (2003). The nucleation of Fe-rich phases on oxide films in Al-11.5Si-0.4Mg cast alloys. Metallurgical Materials Transaction A, 34(7), 1409–1420.
Cao, X., & Campbell, J. (2005). Oxide inclusion defects in Al–Si–Mg cast alloys. Canadian Metallurgical Quarterly, 44(4), 435–448.
Chen, W. J., Lin, C. X., Chen, Y. T., & Lin, J. R. (2016). Optimization design of a gating system for sand casting aluminium A356 using a Taguchi method and multi-objective culture-based QPSO algorithm. Advances in Mechanical Engineering, 8(4), 1–14.
Dai, X., Yang, X., Campbell, J., & Wood, J. (2004). Influence of oxide film defects generated in filling on mechanical strength of aluminium alloy castings. Materials Science Technology, 20(4), 505–513.
Daniel, G., Kumar, G., & Rizvi, A. U. H. (2019). Optimization of material removal rate in wire-EDM using Genetic Algorithm. International Journal of Applied Engineering Research, 14(1), 313–315.
Divandari, M., Campbell, J. (2001). Mechanisms of bubble damage in castings. Ph.D. Dissertation, University of Birmingham, the School of Metallurgy and Materials.
Dorofki, M., Elshafie, A., Jaafar, O., Karim, O., & Mastura, S. (2012). Comparison of artificial neural network transfer functions abilities to simulate extreme runoff data. In International conference on environment, energy and biotechnology IPCBEE, vol. 33. Singapore: IACSIT Press.
Fortmann-Roe, S. (2012). Understanding the bias-variance tradeoff. Retrieved Oct 2020, from http://scott.fortmann-roe.com/docs/BiasVariance.html.
Ghosh, I., Das, K. D., & Chakraborty, N. (2014). An artificial neural network model to characterize porosity defects during solidification of A356 aluminum alloy. Neural Computing and Applications, 25(3–4), 653–662.
Gopalan, R., & Prabhu, N. K. (2011). Oxide bifilms in aluminium alloy castings: A review. Materials Science Technology, 27(12), 1757–1769.
Green, N. R., & Campbell, J. (1994). Influence of oxide film filling defects on the strength of Al–7Si–Mg alloy castings (94–114). Transaction of the American Foundrymens Society, 102, 341–348.
Gu, C., Lu, Y., Cinkilic, E., Miao, J., Klarner, A., Yan, X., et al. (2019). Predicting grain structure in high pressure die casting of aluminum alloys: A coupled cellular automaton and process model. Computational Materials Science, 15, 64–75.
Huang, C., & Ying, K. (2019). Intelligent parametric design for a multiple-quality-characteristic glue-dispensing process. Journal of Intelligent Manufacturing, 30, 2291–2305.
Jiaqi, W., Paixian, F., Hongwei, L., Dianzhong, L., & Yiyi, L. (2012). Shrinkage porosity criteria and optimized design of a 100-ton 30Cr2Ni4MoV forging ingot. Materials and Design, 35, 446–456.
Juretzko, F. R., & Stefanescu, D. M. (2005). Comparison of mold filling simulation with high speed video recording of real-time mold filling. AFS Transactions, 113, 1–11.
Krimpenis, A., Benardos, P. G., Vosniakos, G. C., & Koukouvitaki, A. (2006). Simulation-based selection of optimum pressure die-casting process parameters using neural nets and genetic algorithms. International Journal of Advanced Manufacturing and Technology, 27, 509–517.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444.
Lin, J., Ma, L., & Yao, Y. (2019). Segmentation of casting defect regions for the extraction of microstructural properties. Engineering Applications of Artificial Intelligence, 85, 150–163.
Majidi, S. H., Griffin, J., & Beckermann, C. (2018). Simulation of air entrainment during mold filling: Comparison with water modeling experiments. Metallurgical and Materials Transaction B, 49(5), 2599–2610.
Martin, T., Demuth, H. B., Beale, M. H., & De Jess, O. H. (2014). Neural network design (2nd edn). Texas, United States, ISBN 13:9780971732117.
Mi, J., Harding, R. A., & Campbell, J. (2004). Effects of the entrained surface film on the reliability of castings. Metallurgical and Materials Transaction A, 35(9), 2893–2902.
Modaresi, A., Safikhani, A., Noohi, A. M. S., Hamidnezhad, N., & Maki, S. M. (2017). Gating system design and simulation of gray iron casting to eliminate oxide layers caused by turbulence. International Journal of Metalcast, 11(2), 328–339.
Mrzyglod, B., Gumienny, G., Wilk-Kołodziejczyk, D., & Regulski, K. (2019). Application of selected artificial intelligence methods in a system predicting the microstructure of compacted Graphite Iron. Journal of Materials Engineering and Performance, 28, 3894–3904.
Mukherjee, T., & DebRoy, T. (2019). A digital twin for rapid qualification of 3D printed metallic components. Applied Materials Today, 14, 59–65.
Nastac, L. (1999). Numerical modeling of solidification morphologies and segregation patterns in cast dendritic alloys. Acta Materialia, 47, 4253–4262.
Nimbulkar, S. L., & Dalu, R. S. (2016). Design optimization of gating and feeding system through simulation technique for sand casting of wear plate. Perspectives in Science, 8, 39–42.
Nyahumwa, C., Green, N. R., & Campbell, J. (1998). Effect of mold-filling turbulence on fatigue properties of cast aluminium alloys (98-58). Transaction American Foundrymens Society, 106, 215–224.
ProCast User Manual Version 2009. (2009). 1. ESI group. The virtual try-out space company.
Qi, Q., & Tao, F. (2018). Digital twin and big data towards smart manufacturing and industry 4.0: 360 degree comparison. IEEE Access, 6, 3585–3593.
Raiszadeh, R., & Griffiths, W. D. (2006). A method to study the history of a double oxide film defect in liquid aluminium alloys. Metallurgical Materials Transaction B, 37(6), 865–871.
Raiszadeh, R., & Griffiths, W. D. (2008). A semi-empirical mathematical model to estimate the duration of the atmosphere within a double oxide film defect in pure aluminium alloy. Metallurgical Materials Transaction B, 39(2), 298–303.
Redelinghuys, A. J. H., Basson, A. H., & Kruger, K. (2020). A six-layer architecture for the digital twin: A manufacturing case study implementation. Journal of Intelligent Manufacturing, 31, 1383–1402.
Renukananda, K. H., & Ravi, B. (2016). Multi-gate systems in casting process: Comparative study of liquid metal and water flow. Materials and Manufacturing Processes, 31(8), 1091–1101.
Ross, P. J. (1996). Taguchi techniques for quality engineering: Loss function, orthogonal experiments, parameter and tolerance design (2nd ed.). New York: McGraw-Hill. ISBN 0070539588.
Roy, R. K. (2010). A primer on the Taguchi method (2nd ed.). Dearborn: Society of Manufacturing Engineers. ISBN 10: 0872638642.
Ruddle, R. W. (1956). The running and gating of Sand casting: A review of the literature, Monograph No. 19. London: Institute of Metal.
Runyoro, J., Boutorabi, S. M. A., & Campbell, J. (1992). Critical gate velocity for film-forming casting alloys. A basis for process specification. Transaction of the American Foundrymens Society, 100, 225–234.
Sama, S. R., Badamo, T., Lynch, P., & Manogharan, G. (2019a). Novel sprue design in metal casting via 3D sand-printing. Additive Manufacturing, 25, 563–578.
Sama, S., MacDonald, E., Voigt, E., & Manogharan, G. (2019b). Measurement of metal velocity in sand casting during mold filing. Metals, 9(10), 1079.
Sama, S. R., Wang, J., & Manogharan, G. (2018). Non-conventional mold design for metal casting using 3D sand-printing. Journal of Manufacturing Processes, 34, 65–75.
Sha, W., & Edwards, K. L. (2007). The use of artificial neural networks in materials science based research. Materials and Design, 28(6), 1747–1752.
Shabani, M. O., & Mazzahery, A. (2011). The ANN application in FEM modeling of mechanical properties of AL–Si alloy. Applied Mathematical Modelling, 35, 5707–5713.
Shaikh, M. B. N., Shazeb, A., Arfeen, K., & Mohammed, A. (2018). Optimization of multi-gate systems in casting process: Experimental and simulation studies. IOP Conference Series: Materials Science and Engineering IOP Publishing, 404(1), 012040. https://doi.org/10.1088/1757-899X/404/1/012040.
Sirrell, B., & Campbell, J. (1997). Mechanism of filtration in reduction of casting defects due to surface turbulence during mold filling. AFS Transaction, 105, 645–654.
Sirrell, B., Holliday, M., & Campbell, J. (1996). Benchmark testing the flow and solidification modeling of AI castings. JOM Journal of the Minerals Metals and Materials Society, 48(3), 20–23.
Stefanescu, D. M. (2005). Computer simulation of shrinkage related defects in metal castings: A review. International Journal of Cast Metals Research, 18(3), 129–143.
Sun, H. C., & Chao, L. S. (2009). An investigation into the effective heat transfer coefficient in the casting of aluminium in a green-sand mold. Materials Transactions, 50(6), 1396–1403.
Swaminathan, C. R., & Voller, V. R. (1994). A time-implicit filling algorithm. Applied Mathematical Modelling, 18(2), 101–108.
Swift, R. E., Jackson, J. H., & Eastwood, L. W. (1949). A study of principles of gating. AFS Transaction, 57, 76–88.
Tao, F., Cheng, J., Qi, Q., Zhang, M., Zhang, H., & Sui, F. (2018). Digital twin-driven product design, manufacturing and service with big data. International Journal of Advanced Manufacturing Technology, 94, 3563–3576.
Tong, X., Liu, Q., Pi, S., et al. (2020). Real-time machining data application and service based on IMT digital twin. Journal of Intelligent Manufacturing, 31, 1113–1132.
Tsai, K., & Luo, H. (2017). An inverse model for injection molding of optical lens using artificial neural network coupled with genetic algorithm. Journal of Intelligent Manufacturing, 28, 473–487.
Vosniakos, G. C., Galiotoua, V., Pantelisb, D., Benardosa, P., & Pavloua, P. (2009). The scope of artificial neural network metamodels for precision casting process planning. Robotics and Computer-Integrated Manufacturing, 25, 909–916.
Walker, J., Harris, E., Lynagh, C., et al. (2018). 3D printed smart molds for sand casting. Inter Metalcast, 12, 785–796.
Yang, X., Din, T., & Campbell, J. (1998). Liquid metal flow in moulds with offset sprue. International Journal of Cast Metals Research, 11(1), 1–12.
Zhang, L., & Wang, R. (2013). An intelligent system for low-pressure die-cast process parameters optimization. International Journal of Advanced Manufacturing Technology, 65, 517–524.
Zhao, X. Y., Ning, Z. L., Cao, F. Y., Liu, S. G., Huang, Y. J., Liu, J. S., et al. (2017). Effect of double oxide film defects on mechanical properties of As-cast C95800 alloy. Acta Metall Sinica Eng. Lett., 30(6), 541–549.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
The relationship between the selected gating design variables and their corresponding ingate velocity is described by the response surface methodology (RSM). A central composite design (CCD) with three level factorial design was employed in this study to construct an accurate RSM. Equation (10) shows the first-order regression model in RSM.
where Y is the response objective, xj is the independent design variables and xj xp is the interaction term. β0 is the constant term, βj is the jth linear coefficient, and βjp is the jpth interaction coefficient.
The six factors derived from the ANOVA results were used to construct the response objective. As shown in Table 6, the significant design variables three level CCD experiment, which are coded as − 1 and + 1 and the midpoint coded as 0, was employed to determine the response surface model Vingate (Chen et al. 2016).
According to the first order regression equations (Eq. 3) the relationship between selected parameters and objective was established as shown in Eq. (11) after eliminating the insignificant terms.
Rights and permissions
About this article
Cite this article
Ktari, A., El Mansori, M. Digital twin of functional gating system in 3D printed molds for sand casting using a neural network. J Intell Manuf 33, 897–909 (2022). https://doi.org/10.1007/s10845-020-01699-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10845-020-01699-3