Abstract
The complex sand-casting process combined with the interactions between process parameters makes it difficult to control the casting quality, resulting in a high scrap rate. A strategy based on a data-driven model was proposed to reduce casting defects and improve production efficiency, which includes the random forest (RF) classification model, the feature importance analysis, and the process parameters optimization with Monte Carlo simulation. The collected data includes four types of defects and corresponding process parameters were used to construct the RF model. Classification results show a recall rate above 90% for all categories. The Gini Index was used to assess the importance of the process parameters in the formation of various defects in the RF model. Finally, the classification model was applied to different production conditions for quality prediction. In the case of process parameters optimization for gas porosity defects, this model serves as an experimental process in the Monte Carlo method to estimate a better temperature distribution. The prediction model, when applied to the factory, greatly improved the efficiency of defect detection. Results show that the scrap rate decreased from 10.16% to 6.68%.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Sertucha J, Lacaze J. Casting defects in sand-mold cast irons–An illustrated review with emphasis on spheroidal graphite cast irons. Metals, 2022, 12(3): 504–584.
Giannetti C, Ransing R S, Ransing M R, et al. Knowledge management and knowledge discovery for process improvement and sustainable manufacturing: A foundry case study. Proceedings of the Sustainable Design and Manufacturing, 2014: 537–548.
Tao F, Qi Q, Liu A, et al. Data-driven smart manufacturing. Journal of Manufacturing Systems, 2018, 48: 157–169.
Antony J, Mcdermott O, Sony M. Revisiting Ishikawa’s original seven basic tools of quality control: A global study and some new insights. IEEE Transactions on Engineering Management, 2021, 99: 1–16.
Sai T V, Vinod T, Sowmya G. A critical review on casting types and defects. Engineering and Technology, 2017, 3(2): 463–468.
Natarajan N K. Review analysis of casting defects with respect to Indian standards in cast iron foundry. Journal of Chemical and Pharmaceutical Sciences, 2016, 2: 63–68.
Suthar J, Persis J, Gupta R. Predictive modeling of quality characteristics - A case study with the casting industry. Computers in Industry, 2023, 146: 1–16.
Chen S, Kaufmann T. Development of data-driven machine learning models for the prediction of casting surface defects. Metals, 2021, 12(1): 1–15.
Zhang Y, Zhang R, Wang Y, et al. Big data driven decision-making for batch-based production systems. Procedia CIRP, 2019, 83: 814–818.
Lundgren M, Hedlind M, Kjellberg T. Model-driven process planning and quality assurance. Procedia CIRP, 2015, 33: 209–214
Yin S, Ding S X, Xie X, et al. A review on basic data-driven approaches for industrial process monitoring. IEEE Transactions on Industrial Electronics, 2014, 61(11): 6418–6428.
Ktari A, El Mansori M. Intelligent approach based on FEM simulations and soft computing techniques for filling system design optimisation in sand casting processes. The International Journal of Advanced Manufacturing Technology, 2021, 114(3–4): 981–995.
Ge Z. Review on data-driven modeling and monitoring for plant-wide industrial processes. Chemometrics and Intelligent Laboratory Systems, 2017, 171: 16–25.
Tao F, Cheng J, Qi Q, et al. Digital twin-driven product design, manufacturing and service with big data. The International Journal of Advanced Manufacturing Technology, 2017, 94(9–12): 3563–3576.
Babu S R, Musi R, Thiele K, et al. Classification of nonmetallic inclusions in steel by data-driven machine learning methods. Steel Research International, 2022, 94(1): 2200617.
Boto F, Murua M, Gutierrez T, et al. Data driven performance prediction in steel making. Metals, 2022, 12(2): 172–191.
Zhao Y, Qian F, Gao Y. Data driven die casting smart factory solution. Recent Advances in Intelligent Manufacturing: First International Conference on Intelligent Manufacturing and Internet of Things and 5th International Conference on Computing for Sustainable Energy and Environment, IMIOT and ICSEE 2018, Chongqing, China, 2018, 923: 13–21.
Liu D, Du Y, Chai W, et al. Digital twin and data-driven quality prediction of complex die-casting manufacturing. IEEE Transactions on Industrial Informatics, 2022, 18(11): 8119–8128.
Bak C, Roy A G, Son H. Quality prediction for aluminum diecasting process based on shallow neural network and data feature selection technique. CIRP Journal of Manufacturing Science and Technology, 2021, 33: 327–338.
Chakrabarti A, Sukumar R P, Jarke M, et al. Efficient modeling of digital shadows for production processes: A case study for quality prediction in high pressure die casting processes. In: Proc. 2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA), Porto, Portugal, 2021: 1–9.
Fang Y, Ma L, Yao Z, et al. Process optimization of biomass gasification with a Monte Carlo approach and random forest algorithm. Energy Conversion and Management, 2022, 264: 115734.
Kozlovsky V N, Lysov V E, Antipov D V, et al. Calculation and statistical experiment on the Monte Carlo method when assessing the stability of the technical characteristics of the automobile generator set in mass production. In: Proceedings of the 2019 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), Saint Petersburg and Moscow, Russia, 2019: 565–568.
Zhou J, Ji X, Liao D, et al. Research and application of enterprise resource planning system for foundry enterprises. China Foundry, 2013, 10(1): 7–17.
Lee D K. Data transformation: A focus on the interpretation. KJA, 2020, 73(6): 503–8.
Singh D. Investigating the impact of data normalization on classification performance. Applied Soft Computing, 2020, 97(Pta2): 105524.
Yuan Y, Wu L, Zhang X. Gini-impurity index analysis. IEEE Transactions on Information Forensics and Security, 2021, 16: 3154–3169.
Takaya S, Marc R, Guy B. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE, 2015, 10(3): 1–21.
Shen Z Q, Zheng H L, Li T T, et al. The Influence of the residual Mg content in the ductile cast iron on the formation law of spherodial graphite. Advanced Materials Research, 2011, 415–417: 907–914.
Acknowledgments
This work was financially supported by the National Key Research and Development Program of China (2022YFB3706800, 2020YFB1710100), and the National Natural Science Foundation of China (51821001, 52090042, 52074183).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors declare that they have no conflict of interest.
Additional information
Dong-hong Wang Male. His research interests mainly focus on material genetic engineering and intelligent thermal manufacturing. E-mail: wangdh2009@sjtu.edu.cn
Da Shu E-mail: dshu@sjtu.edu.cn
Rights and permissions
About this article
Cite this article
Guan, B., Wang, Dh., Shu, D. et al. Data-driven casting defect prediction model for sand casting based on random forest classification algorithm. China Foundry 21, 137–146 (2024). https://doi.org/10.1007/s41230-024-3090-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41230-024-3090-1