Approximation of Ausferrite Content in the Compacted Graphite Iron with the Use of Combined Techniques of Data Mining

Open access

Abstract

This article presents the methodology for exploratory analysis of data from microstructural studies of compacted graphite iron to gain knowledge about the factors favouring the formation of ausferrite. The studies led to the development of rules to evaluate the content of ausferrite based on the chemical composition. Data mining methods have been used to generate regression models such as boosted trees, random forest, and piecewise regression models. The development of a stepwise regression modelling process on the iteratively limited sets enabled, on the one hand, the improvement of forecasting precision and, on the other, acquisition of deeper knowledge about the ausferrite formation. Repeated examination of the significance of the effect of various factors in different regression models has allowed identification of the most important variables influencing the ausferrite content in different ranges of the parameters variability.

[1] Skvarenina, S. & Shin, Y.C. (2006). Laser-assisted machining of compacted graphite iron. International Journal of Machine Tools and Manufacture. 46(1), 7-17.

[2] Pietrowski, S. (2000). Compendium of knowledge about compacted cast iron. Solidification of Metals and Alloys. 2(44), 279-292. (in Polish).

[3] Guzik, E. & Kleingartner, T. (2009). A study on the structure and mechanical properties of compacted cast iron with pearlitic-ferritic matrix. Archives of Foundry Engineering. 9(3), 55-60.

[4] Mierzwa, P. & Soiński, M.S. (2011). The effect of thermal treatment on the mechanical properties of compacted cast iron. Archives of Foundry Engineering. 10(spec.1), 133-138.

[5] Pytel, A. & Gazda, A. (2014). Evaluation of selected properties in austempered compacted cast iron (AVCI). Transactions of Foundry Research Institute. LIV(4), 23-31. DOI: 10.7356/iod.2014.18.

[6] Soiński, M.S. & Jakubus, A. (2014). Initial Assessment of Abrasive Wear Resistance of Austempered Cast Iron with Compacted Graphite. Archives of Metallurgy and Materials. 59(3), 1073-1076. DOI: 10.2478/amm-2014-0183.

[7] Regulski, K., Wilk-Kołodziejczyk, D. & Gumienny, G. (2016). Comparative analysis of the properties of the Nodular Cast Iron with Carbides and the Austempered Ductile Iron with use of the machine learning and the Support Vector Machine. The International Journal of Advanced Manufacturing Technology. 87(1), 1077-1093. DOI: 10.1007/s00170-016-8510-y.

[8] Friedman, J.H. (1991). Multivariate adaptive regression splines. The Annals of Statistics. 19(1), 1-67.

[9] Abraham, A., Steinberg, D. & Philip, N.S. (2001). Rainfall forecasting using soft computing models and multivariate adaptive regression splines. IEEE SMC Transactions, Special issue on Fusion of Soft Computing and Hard Computing in Industrial Applications. 1, 1-6.

[10] Malash, G.F. & El-Khaiary, M.I. (2010). Piecewise Linear Regression: A Statistical Method for the Analysis of Experimental Adsorption Data by the Intraparticle-Diffusion Models. Chemical Engineering Journal. 163, 256-263. http://dx.doi.org/10.1016/j.cej.2010.07.059.

[11] Butte, N.F., Wong, W.W., Adolph, A.L., Puyau, M.R., Vohra, F.A. & Zakeri, I.F. (2010). Validation of cross-sectional time series and multivariate adaptive regression splines models for the prediction of energy expenditure in children and adolescents using doubly labeled water. The Journal of Nutrition. 140(8), 1516-1523.

[12] De Andrés, J., Lorca, P., de Cos Juez, F. & Sánchez-Lasheras, F. (2011). Bankruptcy forecasting: a hybrid approach using fuzzy c-means clustering and multivariate adaptive regression splines (MARS). Expert Systems with Applications. 38(3), 1866-1875.

[13] Plonsky, L. & Oswald, F.L. (2016). Multiple Regression as a flexible alternative to ANOVA in L2 Research. Studies in Second Language Acquisition. 1-14. DOI: 10.1017/S0272263116000231.

[14] Behera, A.K., Verbert, J., Lauwers, B. & Duflou, J.R. (2013). Tool path compensation strategies for single point incremental sheet forming using multivariate adaptive regression splines. Computer-Aided Design. 45, 3.

[15] Mukhopadhyay, A. & Iqbal, A., (2009). Prediction of mechanical property of steel strips using multivariate adaptive regression splines. J App Stat. 36, 1.

[16] Jakubski, J., Malinowski, P., Dobosz, St. M. & Major-Gabryś, K. (2013). ANN Modelling for the analysis of the Green Moulding Sands properties. Archives of Metallurgy and Materials. 58(3), 961-964.

[17] Sztangret, L., Szeliga, D., Kusiak, J. & Pietrzyk, M. (2012). Application of inverse analysis with metamodelling for identification of metal flow stress. Canadian Metallurgical Quarterly. 51, 440-446.

[18] Rauch, L., Sztangret, L. & Pietrzyk, M. (2013). Computer system for identification of material models on the basis of plastometric tests. Archives of Metallurgy and Materials. 58(3), 737-743. DOI:20.2478/amm-2013-0063.

[19] Shaikhina, T., Lowe, D., Daga, S., Briggs, D., Higgins, R. & Khovanova (2017). Decision tree and random forest models for outcome prediction in antibody incompatible kidney transplantation. Biomed. Signal Process Control. http://dx.doi.org/10.1016/j.bspc.2017.01.012.

[20] Breiman, L. (1999). Random forest. Mach. Learn. 45, 1-35, http://dx.doi.org/10.1023/A:1010933404324.

[21] Friedman, J. (2003). Recent advances in predictive (machine) learning, Proceedings of Phystat, Stanford University.

[22] Yang, H., Roe, B.P. & Zhu, J. (2007). Studies of stability and robustness for artificial neural networks and boosted decision trees. Nucl.Instrum.Meth. A574, 342-349.

[23] Kluska-Nawarecka, S., Wilk-Kołodziejczyk, D., Dajda, J., Macura, M. & Regulski, K. (2014). Computer-assisted integration of knowledge in the context of identification of the causes of defects in castings. Archives of Metallurgy and Materials. 59(2), 743-746.

[24] Mrzygłód, B., Kowalski, A., Olejarczyk-Wożeńska, I., Adrian, H., Głowacki, M. & Opaliński, A. (2015). Effect of heat treatment parameters on the formation of ADI microstructure with additions of Ni, Cu, Mo. Archives of Metallurgy and Materials. 60(3A), 1941-1948.

[25] Olejarczyk-Wozenska, I., Adrian, H. & Mrzyglod, B. (2014). Mathematical model of the process of pearlite austenitization. Archives of Metallurgy and Materials. 59(3), 981-986.

[26] Kluska-Nawarecka, S., Gorny, Z. & Wilk-Kolodziejczyk, D. (2007). The logic of plausible reasoning in the diagnosis of castings defects. Archives of Metallurgy and Materials. 52(3), 375-380.

[27] Warmuzek, M. & Regulski, K. (2011). A procedure of in situ identification of the intermetallic AlTMSi phase precipitates in the microstructure of the aluminum alloys. Practical Metallography. 48(12), 660-683.

[28] Kluska-Nawarecka, S., Wilk-Kołodziejczyk, D., Regulski, K. & Dobrowolski, G. (2011). Rough sets applied to the RoughCast system for steel castings, Intelligent Information and Database Systems. Part II, Nguyen, N.T., Kim, Ch.G., Janiak, A. (Eds.), Springer Lecture Notes in Computer Science 6592, 52-61.

[29] David, J., Švec, P., Garzinová, R., Kluska-Nawarecka, S., Wilk-Kołodziejczyk, D. & Regulski, K. (2016). Heuristic modeling of casting processes under the conditions uncertainty. Archives of Civil and Mechanical Engineering. 16(2), 179-185.

[30] David, J., Jancikova, Z., Frischer, R. & Vrozina, M. (2013). Crystallizer’s Desks Surface Diagnostics with Usage of Robotic System. Archives of Metallurgy and Materials. 58(3), 907-910.

[31] Smyksy, K., Ziółkowski, E., Wrona, R. & Brzeziński, M. (2013). Performance evaluation of rotary mixers through monitoring of power energy parameters. Archives of Metallurgy and Materials. 58(3), 911-914.

[32] Glowacz, A. & Glowacz, Z. (2017). Recognition of rotor damages in a DC motor using acoustic signals. Bulletin of the Polish Academy of Sciences Technical Sciences. 65(2), 187-194.

[33] Maciol, P. Gawad, J. & Podorska, D. (2007). Arrangement of flow modification devices in continuous casting tundish based on multicriterion optimization. Archives of Metallurgy and Materials. 52 (1), 105-112.

Archives of Foundry Engineering

The Journal of Polish Academy of Sciences

Journal Information


CiteScore 2016: 0.42

SCImago Journal Rank (SJR) 2016: 0.192
Source Normalized Impact per Paper (SNIP) 2016: 0.316

Cited By

Metrics

All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 121 121 18
PDF Downloads 46 46 9