Fundamentals of a recommendation system for the aluminum extrusion process based on data-driven modeling

Marcin Perzyk, Andrzej Kochański, Jacek Kozłowski

Warsaw University of Technology, Institute of Materials Processing, Warsaw, Poland.

DOI:

https://doi.org/10.7494/cmms.2022.4.0782

Abstract:

The aluminum profile extrusion process is briefly characterized in the paper, together with the presentation of historical, automatically recorded data. The initial selection of the important, widely understood, process parameters was made using statistical methods such as correlation analysis for continuous and categorical (discrete) variables and ‘inverse’ ANOVA and Kruskal–Wallis methods. These selected process variables were used as inputs for MLP-type neural models with two main product defects as the numerical outputs with values 0 and 1. A multi-variant development program was applied for the neural networks and the best neural models were utilized for finding the characteristic influence of the process parameters on the product quality. The final result of the research is the basis of a recommendation system for the significant process parameters that uses a combination of information from previous cases and neural models.

Cite as:

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

Article (PDF):

Keywords:

Aluminum extrusion, Advisory system, Product defects, Data mining, Neural networks

References:

Aluminum Extruders Council (2018). Aluminum Extrusion Manual (4th ed.).

ASM International (2005). ASM Handbook (Vol. 14A: Metalworking: Bulk Forming).

Bauser, M., Sauer, G., & Siegert, K. (2006). Extrusion (2nd ed.). ASM International.

Fourmann, J. (2017). Extrusion defects fundamentals & solutions for optimum finish [PowerPoint slides]. https://aluminium-guide.com/wp-content/uploads/2019/07/3_AEC_Extrusion_Defect_-_201.pdf.

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

Kapadia, R., Stanley, G., & Walker, M.G. (2007). Real world model-based fault management. https://gregstanleyandassociates.com/dx07-final-submission.pdf.

Köksal, G., Batmaz, İ., & Testik, M.C. (2011). A review of data mining applications for quality improvement in manufacturing industry. Expert Systems with Applications, 38(10), 13448–13467. https://doi.org/10.1016/j.eswa.2011.04.063.

Laue, K., & Stenger, H. (1981). Extrusion: Processes, Machinery, Tooling. American Society for Metals.
Lesniak, D., & Libura, W. (2007). Extrusion of sections with varying thickness through pocket dies. Journal of Materials Processing Technology, 194, 38–45. https://doi.org/10.1016/j.jmatprotec.2007.03.123.

Perzyk, M., & Kochański, A. (2003). Detection of causes of casting defects assisted by artificial neural networks. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 217(9), 1279–1284. https://doi.org/10.1243/095440503322420205.

Perzyk, M., Biernacki, R., & Kochański, A. (2005). Modeling of manufacturing processes by learning systems: The naïve Bayesian classifier versus artificial neural networks. Journal of Materials Processing Technology, 164–165, 1430–1435. https://doi.org/10.1016/j.jmatprotec.2005.02.043.

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., Kochanski, A., Kozlowski, J., Soroczynski, A., & Biernacki, R. (2014). Comparison of data mining tools for significance analysis of process parameters in applications to process fault diagnosis. Information Sciences, 259, 380–392. https://doi.org/10.1016/j.ins.2013.10.019.

Pilar Noriega M. del, & Rauwendaal, Ch. (2010). Troubleshooting the Extrusion Process. A Systematic Approach to Solving Plastic Extrusion Problems. Hanser.

Prakash, S.B., Sujith Subramanyam, H.S., Yogesh, H.K., Veerabhadrappa, Aravindrao, M.Y., & Emmini, M.G. (2021). Study of defects in aluminium extrusion process and evaluation by using quality tools. International Journal of Scientific & Engineering Research, 12(7), 355–366.

Qin, S.J. (2012). Survey on data-driven industrial process monitoring and diagnosis. Annual Reviews in Control, 36(2), 220–234. https://doi.org/10.1016/j.arcontrol.2012.09.004.

Raimundo, G.M., & Canuto, G. (2019). A proposal of symbols to standardize aluminum extrusion defects representation. Journal of Production and Automation, 2(1), 61–70.

Sheppard, T. (1999). Extrusion of Aluminium Alloys. Springer New York, NY. https://doi.org/10.1007/978-1-4757-3001-2.

Silva Peres, R., Jia, X., Lee, J., Sun, K., Colombo, A.W., & Barata, J. (2020). Industrial artificial intelligence in industry 4.0 – systematic review, challenges and outlook. IEEE Access, 8, 220121–220139. https://doi.org/10.1109/ACCESS.2020.3042874.

Stanley, G. (n.d.). Model based reasoning for fault detection and fault diagnosis. Performity LLC. https://gregstanleyandassociates.com/whitepapers/FaultDiagnosis/Model-Based-Reasoning/model-based-reasoning.htm

Zasadziński, J., Libura, W., & Richert, J. (2004). Fundamentals of advanced aluminum extrusion processes. In ET’04 Exploring innovations in aluminum extrusion technology. Proceedings of the eighth international aluminum extrusion technology seminar. May 18–21 2004 (vol. 2, pp. 391–398). ET Foundation.

Zhu, H., Couper, M.J., & Dahle, A.K. (2012). Effect of process variables on the formation of streak defects on anodized aluminum extrusions: An overview. High Temperature Materials and Processes, 31(2), 105–111. https://doi.org/10.1515/htmp-2012-0024.