Article
Open Access
Quality prediction of semi-solid die casting of aluminum alloy in terms of machine learning
Zhiyuan Wang1Xiaogang Hu2,∗Gan Li1Zhen Xu1Hongxing Lu1Qiang Zhu1,∗
1 Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen 518055, China
2 School of Advanced Manufacturing, Sun Yat-Sen University, Shenzhen 518107, China
  • Volume
    Volume 1 Issue 3, 2024
  • Citation
    Wang Z, Hu X, Li G, Xu Z, Lu H, et al. Quality prediction of semi-solid die casting of aluminum alloy in terms of machine learning. Adv. Manuf. 2024(3):0015, https://doi.org/10.55092/am20240015. 
  • DOI
    10.55092/am20240015
  • Copyright
    Copyright2024 by the authors. Published by ELSP.
Abstract

Semi-solid die casting of aluminum alloy has been successfully employed to manufacture high-performance components with precise net shapes. However, the quality of these components is highly susceptible to variations in both environmental conditions and process parameters, leading to a narrow process window that restricts its widespread application in engineering. In this study, a machine learning (ML) model has been developed to identify defective products through the detection of injection pressure, thereby providing a foundation for monitoring and further optimizing the manufacturing process. Among various ML algorithms, the Multilayer Perceptron (MLP) is the most effective for overall quality prediction. Additionally, the mechanism for identifying defect types based on pressure curves has been revealed: the filling pressure at the gate entrance has been found to exhibit a strong correlation with the internal quality of the casting, while the V-P transition point has been identified as a reliable indicator of the external quality.

Keywords

semi-solid processing; die casting; machine learning; quality classification; injection pressure

Preview
References
  • [1] Spencer DB, Mehrabian R, Flemings MC. Rheological behavior of Sn-15 pct Pb in the crystallization range. Metall. Trans. 1972, 3(7):1925–1932.
  • [2] Hu XG, Hu ZH, Qu WY, Li XW, Li Z, et al. A novel criterion for assessing the processability of semi-solid alloys: The enthalpy sensitivity of liquid fraction. Materialia 2019, 8:10042
  • [3] Qu W, Li D, Zhang F, Luo M, Hu X, et al. Multiphase modelling of the transient flow for Sn-15Pb and 357.0 alloys in semi-solid die casting process. J. Mater. Process. Technol. 2020, 278:116534.
  • [4] Atkinson H. Current status of semi-solid processing of metallic materials. In Advances in Material Forming, Paris, France, 2007, pp. 81–98.
  • [5] Kapranos P. Current state of semi-solid net-shape die casting. Metals 2019, 9(12):1301.
  • [6] Li G, Qu WY, Luo M, Cheng L, Guo C, et al. Semi-solid processing of aluminum and magnesium alloys: Status, opportunity, and challenge in China. Trans. Nonferrous Met. Soc. China. 2021, 31(11):3255–3280.
  • [7] Midson SP. Industrial applications for aluminum semi-solid castings. Solid State Phenom. 2015, 217–218:487–495.
  • [8] Laws KJ, Gun B, Ferry M. Effect of die-casting parameters on the production of high quality bulk metallic glass samples. Mater. Sci. Eng. A 2006, 425(1):114–120.
  • [9] Rai JK, Lajimi AM, Xirouchakis P. An intelligent system for predicting HPDC process variables in interactive environment. J. Mater. Process. Technol. 2008, 203(1):72–7
  • [10] Xu C, Zhao J, Guo A, Li H, Dai G, et al. Effects of injection velocity on microstructure, porosity and mechanical properties of a rheo-diecast Al-Zn-Mg-Cu aluminum alloy. J. Mater. Process. Technol. 2017, 249:167–171.
  • [11] Zhang H, Li DQ, Qu WY, Zhang F, Luo M, et al. Effect of primary α-Al morphology in slurry on segregation. Solid State Phenom. 2019, 285:398–402.
  • [12] Hu XG, Zhu Q, Midson SP, Atkinson HV, Dong HB, et al. Blistering in semi-solid die casting of aluminium alloys and its avoidance. Acta Mater. 2017, 124:446–455.
  • [13] Hu XG, Zhu Q, Atkinson HV, Lu HX, Zhang F, et al. A time-dependent power law viscosity model and its application in modelling semi-solid die casting of 319s alloy. Acta Mater. 2017, 124:410–420.
  • [14] Ling Y, Zhou J, Nan H, Yin Y, Shen X. A shrinkage cavity prediction model for gravity castings based on pressure distribution: A casting steel case. J. Manuf. Processes 2017, 26:433–445.
  • [15] Leonardo P, Marco S, Giovanni L. Influence of the injection molding thermal boundary conditions on the filling flow of PET. J. Manuf. Processes 2022, 81:807–816.
  • [16] Winkler M, Kallien L, Feyertag T. Correlation between process parameters and quality characteristics in aluminum high pressure die casting. In NADCA Die Casting Congress and Exposition, Chicago, USA, 5–7 October 2015.
  • [17] Soban D, Thornhill D, Salunkhe S, Long A. Visual analytics as an enabler for manufacturing process decision-making. Procedia CIRP 2016, 56:209–214.
  • [18] Kittur JK, Manjunath Patel GC, Parappagoudar MB. Modeling of pressure die casting process: an artificial intelligence approach. Int. J. Metalcast. 2016, 10(1):70–87.
  • [19] Gim J, Yang H, Turng LS. Transfer learning of machine learning models for multi-objective process optimization of a transferred mold to ensure efficient and robust injection molding of high surface quality parts. J. Manuf. Processes 2023, 87:11–24.
  • [20] Kim JS, Kim J, Lee JY. Die-casting defect prediction and diagnosis system using process condition data. Procedia Manuf. 2020, 51:359–364.
  • [21] Lin CH, Hu GH, Ho CW, Hu CY, Kuo PC. Press casting quality detection and analysis based on machine learning. In 2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), 16–19 November 2021, pp. 1–2.
  • [22] Weiderer P, Tomé AM, Lang EW. A NMF-based extraction of physically meaningful components from sensory data of metal casting processes. J. Manuf. Syst. 2020, 54:62–73.
  • [23] Bak C, Roy AG, Son H. Quality prediction for aluminum diecasting process based on shallow neural network and data feature selection technique. CIRP J. Manuf. Sci. Technol. 2021, 33:327–338.
  • [24] Deng H, Runger G, Tuv E, Vladimir M. A time series forest for classification and feature extraction. Inf. Sci. 2013, 239:142–153.
  • [25] Luo M, Li D, Qu W, Hu X, Zhu Q, et al. Mold-slug interfacial heat transfer characteristics of different coating thicknesses: effects on slug temperature and microstructure in swirled enthalpy equilibration device process. Materials 2019, 12(11):1836.
  • [26] Burges CJC. A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Discovery 1998, 2(2):121–167.
  • [27] Vapnik VN. An overview of statistical learning theory. IEEE Trans. Neural Networks 1999, 10(5):988–999.
  • [28] Rosenblatt F. Perceptron simulation experiments. Proc. IRE 1960, 48(3):301–309.
  • [29] Tin Kam H. The random subspace method for constructing decision forests. IEEE Trans. Pattern Anal. Mach. Intell. 1998, 20(8):832–844.
  • [30] Sigrist F. Gradient and Newton boosting for classification and regression. Expert Syst. Appl. 2021, 167:114080.
  • [31] 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, New York, USA, 2016, pp. 785–794.
  • [32] Quinlan JR. Simplifying decision trees. Int. J. Man Mach. Stud. 1987, 27(3):221–234.
  • [33] Boyd CR, Tolson MA, Copes WS. Evaluating trauma care: The TRISS method. J. Trauma Acute Care 1987, 27(4):370–378.
  • [34] Ke GL, Meng Q, Thomas F, Wang TF, Chen W, et al. LightGBM: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 2017, 30:3149–3157.
  • [35] Fahle S, Prinz C, Kuhlenkötter B. Systematic review on machine learning (ML) methods for manufacturing processes—Identifying artificial intelligence (AI) methods for field application. Procedia CIRP 2020, 93:413–418.
  • [36] Hanley JA, McNeil BJ. A method of comparing the areas under receiver operating characteristic curves derived from the same cases. Radiology 1983, 148(3):839–843.
  • [37] Hand DJ, Till RJ. A simple generalisation of the area under the ROC curve for multiple class classification problems. Mach. Learn. 2001, 45(2):171–186.
  • [38] Taha AA, Hanbury A. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med. Imaging 2015, 15(1):29.
Office Locations

Room 704, Cheuk Nang Centre, 9 Hillwood Road, Tsim Sha Tsui, Kowloon, Hong Kong

No.169th Liangui Road, Dongjing Street, Yuhua District, Changsha 410116, Hunan Province, China

Useful Links
About

ELSPublishing (ELSP) is an international publishing house dedicated to publishing high-quality journals, books, proceedings, and providing free conference system. ELSP is committed to promote scholarly communication and sharing, to build a globally integrated scholarly ecosystem, and to advance the cause for a wide range of scholars.

Website Copyright © 2024 ELSP