Machine Learning Methods for diagnosing the causes of die-casting defects

Machine Learning Methods for diagnosing the causes of die-casting defects

Alicja Okuniewska, Marcin Perzyk, Jacek Kozłowski

Warsaw University of Technology, Faculty of Mechanical and Industrial Engineering, Institute of Manufacturing Technologies, Narbutta 85, 02-524 Warsaw, Poland.

DOI:

https://doi.org/10.7494/cmms.2023.2.0809

Abstract:

The research was focused on analyzing the causes of high-pressure die-casting defects, more specifically on casting leakage, which is considered perhaps the most important and common defect. The real data used for modelling was obtained from a high-pressure die-casting foundry that manufactures aluminum cylinder blocks for the world’s leading automotive brands. This paper compares and summarizes the results of applying advanced modelling using artificial neural networks, regression trees, and support vector machines methods to select artificial neural networks as the most effective method to perform a multidimensional optimization of process parameters to diagnose the causes of die-casting defects and to indicate the future research scope in this area. The developed system enables the prediction of the level of defects in castings with satisfactory accuracy and is therefore a highly relevant reference for process engineers of high-pressure foundries. This article indicates exactly which process parameters significantly influence the formation of a defect in a casting.

Cite as:

Okuniewska, A., Perzyk, M., Kozłowski, J. (2023). Machine Learning Methods for diagnosing the causes of die-casting defects. Computer Methods in Materials Science, 23(2), 45-56 . https://doi.org/10.7494/cmms.2023.2.0809

Article (PDF):

Keywords:

Fault diagnosis, Machine learning tools, Neural network, Classification trees, Support vector machine

References:

Agarwal, V. (2015). Research on data preprocessing and categorization technique for smartphone review analysis. International Journal of Computer Applications, 131(4), 30–36. https://doi.org/10.5120/ijca2015907309.

Bártová, B., Bína, V., & Váchová, L. (2022). A PRISMA-driven systematic review of data mining methods used for defects detection and classification in the manufacturing industry. Production, 32, e20210097. https://doi.org/10.1590/0103-6513.20210097.

Bharambe Ch., Jaybhaye, M.D., Dalmiya, A., Daund, C., & Shinde, D. (2023). Analyzing casting defects in high-pressure die casting industrial case study. Materials Today: Proceedings, 72(3), 1079–1083. https://doi.org/10.1016/j.matpr.2022.09.166.

Bowers, K., & Pickerel, T.V. (2019). Vox Populi 4.0: big data tools zoom in on the voice of the customer. Quality Progress, 52(3), 32–39.

Chen R.-S., Wu R.-C., & Chang C.-C. (2005). Using data mining technology to design an intelligent CIM system for IC manufacturing. In Sixth International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing and First ACIS International Workshop on Self-Assembling Wireless Networks. IEEE. https://doi.org/10.1109/SNPD-SAWN.2005.78.

Chen, S., & Kaufmann, T. (2022). Development of Data-Driven Machine Learning models for prediction of casting surface defects. Metals, 12(1), 1. https://doi.org/10.3390/met12010001.

De-Jian, X., & Young-Peng, Y. (2021). A Neural Network Based Defect Prediction Approach for Virtual High Pressure Die Casting. Journal of Physics: Conference Series, 1948, 012019. https://doi.org/10.1088/1742-6596/1948/1/012019.

Del Vecchio, C., Fenu, G., Pellegrino, F.A., Di Foggia, M., Quatrale, M., Benincasa, L., Iannuzzi, S., Acernese, A., Correra, P., & Glielmo, L. (2019). Support Vector Representation Machine for superalloy investment casting optimization. Applied Mathematical Modelling, 72, 324–336. https://doi.org/10.1016/j.apm.2019.02.033.

Esmaeilian, S., Behdad, B., & Wang (2016). The evolution and future of manufacturing: A review. Journal of Manufacturing Systems, 39, 79–100. https://doi.org/10.1016/j.jmsy.2016.03.001.

Falęcki, Z. (1997). Analiza wad odlewów. Wydawnictwa AGH.

Garson, D. (1991). Implementing neural network connection weights. AI Expert, 6(4), 45–51.

Govindarao, R., Eshwara, K., & Srinivasa Rao, P. (2022). “Defect analysis and remedies in the High-Pressure Diecasting Process with ADC-12 Alloy” – A Technical review. American Journal of Multidisciplinary Research & Development (AJMRD), 04(07), 1–8. https://www.ajmrd.com/wp-content/uploads/2022/07/A470108.pdf.

Grand View Research (2019). Metal Casting Market Size, Share & Trends Analysis Report by Material (Aluminum, Iron, Steel), by Application (Automotive & Transportation, Building & Construction, Industrial), by Region, and Segment Forecasts, 2020–2025. https://www.grandviewresearch.com/industry-analysis/metal-casting-market.

Grzegorzewski, P., & Kochański, A. (2019a). From data to reasoning. In P. Grzegorzewski, A. Kochanski, J. Kacprzyk (Eds.), Soft Modeling in Industrial Manufacturing (pp. 15–25). Springer Cham. https://doi.org/10.1007/978-3-030-03201-2_2.

Grzegorzewski, P., & Kochański, A. (2019b). Data preprocessing in industrial manufacturing. In P. Grzegorzewski, A. Kochanski, J. Kacprzyk (Eds.), Soft Modeling in Industrial Manufacturing (pp. 27–41). Springer Cham. https://doi.org/10.1007/978-3-030-03201-2_3.

Hur, J., Lee, H., & Baek, J.-G. (2006). An intelligent manufacturing process diagnosis system using hybrid data mining. In P. Perner (Ed.), Advances in Data Mining. Applications in Medicine, Web Mining, Marketing, Image and Signal Mining, 6th Industrial Conference on Data Mining, ICDM 2006, Leipzig, Germany, July 14–15, 2006, Proceedings (pp. 561–575). Springer Berlin, Heidelberg. https://doi.org/10.1007/11790853_44.

Jacob, D. (2017). Quality 4.0 impact and strategy handbook. Getting digitally connected quality management. Retrieved May 24, 2021, from http://generisgp.com/2018/02/15/the-quality-4-0-impact-and-strategy-handbook/.

Karimi, F., Sultana, S., Shirzadi Babakan, A., & Suthaharan, S. (2019). An enhanced support vector machine model for urban expansion prediction. Computers, Environment and Urban Systems, 75, 61–75. https://doi.org/10.1016/j.compenvurbsys.2019.01.001.

Khan, W., Kumar, T., Cheng, Z., Raj, K., Roy, A.M., & Luo, B. (2022). SQL and NoSQL databases software architectures performance analysis and assessments – A systematic literature review. Big Data and Cognitive Computing, 7(2), 97. https://doi.org/10.3390/bdcc7020097.

Köksal, İ., Batmaz, M.C., & Testik, M. (2011). A review of data mining applications for quality improvement in the manufacturing industry. Expert Systems with Applications, 38(10), 13448–13467.

Kozłowski, J., Jakimiuk, M., Rogalewicz, M., Sika, R., & Hajkowski, J. (2019). Analysis and control of high-pressure die-casting process parameters with use of data mining tools. In Advances in Manufacturing II (Vol. 2: Production Engineering and Management, pp. 253–267). Springer Cham. https://doi.org/10.1007/978-3-030-18789-7_22.

Mijwel, M.M. (2018). Artificial Neural Networks advantages and disadvantages. Research Gate. https://www.researchgate.net/profile/Maad-Mijwil/publication/323665827_Artificial_Neural_Networks_Advantages_and_Disadvantages/links/5aa2c-01faca272d448b5a23d/Artificial-Neural-Networks-Advantages-and-Disadvantages.pdf.

Miłek, D. (2017). Development of the foundry industry in Poland. In Metal 2017. 26th International Conference on Metallurgy and Materials May 24th–26th 2017 / Hotel Voronez I, Brno, Czech Republic, EU (pp. 2250–2256). https://www.confer.cz/metal/2017/read/1718-the-development-of-the-foundry-industry-in-poland.pdf.

Okuniewska, A. (2020). Methods review of advanced data analysis tools, in process control and diagnostics. In K. Piech (Red.), Zagadnienia aktualnie poruszane przez młodych naukowców. 17. Creativetime.

Okuniewska, A., Perzyk, M.A., & Kozłowski, J. (2021). Methodology for diagnosing the cause of die-casting defects, based on advanced big data modelling. Archives of Foundry Engineering, 4, 103–109. https://doi.org/10.24425/afe.2021.138687.

Parlak, I.E., & Emel, E. (2023). Deep learning-based detection of aluminum casting defects and their types. Engineering Applications of Artificial Intelligence, 118, 105636. https://doi.org/10.1016/j.engappai.2022.105636.

Patil, G.G., & Inamdar, K.H. (2014). Prediction of casting defects through artificial neural network. International Journal of Science, Engineering and Technology, 02(06), 298–314.

Perzyk, M., & Soroczynski, A. (2019). Assessment of selected tools used for knowledge extraction in industrial manufacturing. In P. Grzegorzewski, A. Kochanski, J. Kacprzyk (Eds.), Soft Modeling in Industrial Manufacturing (pp. 75–88). Springer Cham. https://doi.org/10.1007/978-3-030-03201-2_5.

Perzyk, M., Kochański, A., & Kozlowski, J. (2003). Istotność względna sygnałów wejściowych sieci neuronowej. Informatyka w Technologii Materiałów, 3(3–4), 125–132.

Perzyk, M., Biernacki, R., & Kozlowski, J. (2008). Data mining in manufacturing: Significance analysis of process parameters. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 222(11), 1503–1516. https://doi.org/10.1243/09544054JEM1182.

Perzyk, M., Dybowski, B., & Kozłowski, J. (2019). Introducing advanced data analytics in perspective of Industry 4.0. in die casting foundry. Archives of Foundry Engineering, 19(1), 53–57. https://doi.org/10.24425/afe.2018.125191.

Perzyk, M., Kochański, A., & Kozłowski, J. (2022). Fundamentals of a recommendation system for the aluminum extrusion process based on data-driven modeling. Computer Methods in Materials Science, 22(4), 173–188. https://doi.org/10.7494/cmms.2022.4.0782.

Raluca, D. (2021). Knowledge management systems in Quality 4.0. MATEC Web of Conferences, 342, 09003. https://doi.org/10.1051/matecconf/202134209003.

Rokach, L., & Maimon, O. (2006). Data mining for improving the quality of manufacturing: a feature set decomposition approach. Journal of Intelligent Manufacturing, 17(3), 285–299. https://doi.org/10.1007/s10845-005-0005-x.

Ruiz A. (2017). Breaking the 80/20 rule: How data catalogs transform data scientists’ productivity. IBM Cloud. https://medium.com/@armand_ruiz/breaking-the-80-20-rule-how-data-catalogs-transform-data-scientists-productivity-7759a23a8893

Sabau A.S. (2006). Alloy shrinkage factors for the investment casting process. Metallurgical and Materials Transactions,37B(1), 131–140.

Sata, A., & Ravi, B. (2017). Bayesian inference-based investment-casting defect analysis system for industrial application. The ,International Journal of Advanced Manufacturing Technology, 90(9–12), 3301–3315. https://doi.org/10.1007/s00170-016-9614-0.

Seit J. (2018). Trends and challenges: the die-casting industry on the road to the future, future prospects, spotlight metal the ,network for metal casting. Retrieved 10 September, 2021, from https://www.spotlightmetal.com/trends-and-challengesthe-die-casting-industry-on-the-road-to-the-future-a-676717/.

StatSoft (2011a). Drzewa klasyfikacyjne i regresyjne (C&RT). Retrieved 10 November, 2022, from https://www.statsoft.pl/textbook/stathome_stat.html?https%3A%2F%2Fwww.statsoft.pl%2Ftextbook%2Fstcart.html.

StatSoft (2011b). Metoda wektorów nośnych. Retrieved 10 November, 2022, from https://www.statsoft.pl/textbook/stathome_stat.html?https%3A%2F%2Fwww.statsoft.pl%2Ftextbook%2Fstsvm.html.

Tariq, S., Tariq, A., Masud, M., Rehman, Z. (2021). Minimizing the casting defects in high-pressure die casting using Taguchi analysis. Scientia Iranica, International Journal of Science & Technology, 29(1), 53–69. https://doi.org/10.24200/sci.2021.56545.4779.

Thomas, P., Suhner, M.-C., Meutelet, B., & Brachotte, G. (2004). Quality monitoring of high-pressure die casting process based on Bayesian and neural networks. IFAC Proceedings Volumes, 37(15), 299–304. https://doi.org/10.1016/S1474-6670(17)31040-6.

Timofeev, R. (2004). Classification and Regression Trees (CART) Theory and Applications [Master Thesis]. CASE Center of Applied Statistics and Economics, Humboldt University, Berlin.

Tseng, T.-L., Jothishankar, M.C., Wu, T., Xing, G., & Jiang, F. (2004). Applying data mining approaches for defect diagnosis in manufacturing industry. In: IIE Annual Conference and Exhibition 2004 – Houston, TX, United States. Duration: May 15 2004 → May 19 2004 (pp. 1441–1447).

Vapnik, V. (2000). The Nature of Statistical Learning Theory. Springer New York, NY.
Wang, L., Törngren, M., & Onori, M. (2015). Current status and advancement of cyber-physical systems in manufacturing. ,Journal of Manufacturing Systems, 37(2), 517–527. https://doi.org/10.1016/j.jmsy.2015.04.008.

Xu, L.D., Xu, E.L., & Li, L. (2018). Industry 4.0: state of the art and future trends. International Journal of Production Research, 56(8), 2941–2962. https://doi.org/10.1080/00207543.2018.1444806.