Assessment of Reinforcement Phase Shape in MMC Using Decision Trees

• Autorzy: Gawdzińska K. , Pelczar M.
• Języki publikacji: EN

Abstrakty

EN

This paper proposes a description of the reinforcement phase shape in MMCs by means of a decision, or classification tree analysis, recognized as a basic data mining technique. The material under examination was composed of reinforcement particles (SiC) in suspension composites with silumin matrix, made by mechanical stirring method. The use of decision tree method allowed to determine logic rules for the classification of particles to the category circle on the basis of its diameter and surface area, taking into account the division into three samples (depending on the location of the analyzed area in the casting space) and a reference sample (representative analysis area – of most desired shape in terms of composite quality - generated by simulation). To assess the accuracy of classification we used a redistribution indicator, that can be a measure used in describing the feature: homogeneity of reinforcement phase particle shape in the space of composite casting.

Słowa kluczowe

EN

shape; reinforcement phase; data mining; decision tree

PL

kształt; faza zbrojenia; data mining; drzewo decyzyjne

• Wydawca: Komisja Odlewnictwa Polskiej Akademii Nauk Oddział w Katowicach
• Czasopismo: Archives of Foundry Engineering
• Rocznik: 2013
• Tom: Vol. 13, iss. 2 spec.
• Strony: 39--42
• Opis fizyczny: Bibliogr. 12 poz., rys., tab.

Twórcy

autor

Gawdzińska K.

• Institute of Basic Technical Sciences, Maritime University of Szczecin, ul. Podgórna 51/53, 70-205 Szczecin, Poland

autor

Pelczar M.

• Faculty of Computer Science and Information Technology, West Pomeranian University of Technology, Szczecin, ul. Żołnierska 49, 71-210 Szczecin, Poland

Bibliografia

• [1] Gawdzińska, K. (2012). Material and technological conditions of quality of metal composite castings. Monograph. Archives of Foundry Engineering, 10-50.
• [2] Cholewa, M. (2007). Heat flow description during crystallization process of cast dispersive composites. Archives of Foundry Engineering. 1(7), 117-122.
• [3] Konopka, Z. (2011). Cast metal composites. Częstochowa: University of Technology Publishing House.
• [4] Śleziona, J. (1998). Basics of composite technology. Gliwice: Silesian University of Technology Publishing House.
• [5] Orłowicz, W. & Trytek, A. (2007). Shaping of microstructure and service properties of cast iron casting by surface refinement with electric arc plasma. Archives of Foundry Engineering. 7(23), 120.
• [6] Grabian, J., Gawdzińska, K., Przetakiewicz, W. & Pijanowski, M. (2011). Description of the particle distribution in the space of composite suspension casting by statistical methods. Archives of Foundry Engineering. 11(1), 31-34.
• [7] Gawdzińska, K., Berczyński, S., Chylińska, R., & Grabian, J. (2011). A description of particle shape homogeneity in the space of composite suspension casting. Archives of Foundry Engineering. 11(1), 11-14.
• [8] Gawdzińska, K. (2010). Homogeneity of particle size in the space of composite suspension casting. Archives of Foundry Engineering. 10(spec. 1), 163-168.
• [9] Gawdzińska, K. & Maliński, M. (2005). Study of Reinforcement Elements Distribution Exemplified by Composite with AlSi11 Matrix and Carbon Reinforcement. Metallurgy. 44, 45-48.
• [10] Bronsztejn, I. N., Siemiendiajew, K. A., Musiol, G., Mühlig, H. (2011). Modern compendium of mathematics. Warszawa: Wydawnictwo Naukowe PWN.
• [11] Breiman, L., Friedman, J., Stone, Ch.J., Olshen, R.A. (1984). Classification and Regression Trees. CA: Wadsworth & Brooks/Cole Advanced Books & Software.
• [12] Frątczak, E.-red. (2012). Advanced methods of statistical analysis. Warszawa: Oficyna Wydawnicza SGH w Warszawie.