Influence of the training set value on the quality of the neural network to identify selected moulding sand properties

• Autorzy: Jakubski J. , Dobosz S. M. , Major-Gabryś K.
• Języki publikacji: EN

Abstrakty

EN

Artificial neural networks are one of the modern methods of the production optimisation. An attempt to apply neural networks for controlling the quality of bentonite moulding sands is presented in this paper. This is the assessment method of sands suitability by means of detecting correlations between their individual parameters. This paper presents the next part of the study on usefulness of artificial neural networks to support rebonding of green moulding sand, using chosen properties of moulding sands, which can be determined fast. The effect of changes in the training set quantity on the quality of the network is presented in this article. It has been shown that a small change in the data set would change the quality of the network, and may also make it necessary to change the type of network in order to obtain good results.

Słowa kluczowe

EN

information technology; foundry industry; quality management; green moulding sands; neural network

PL

technologia informacyjna; przemysł odlewniczy; zarządzanie jakością; masa formierska; sieć neuronowa

• Wydawca: Komisja Odlewnictwa Polskiej Akademii Nauk Oddział w Katowicach
• Czasopismo: Archives of Foundry Engineering
• Rocznik: 2013
• Tom: Vol. 13, iss. 2
• Strony: 49--52
• Opis fizyczny: Bibliogr. 13 poz., tab., wykr.

Twórcy

autor

Jakubski J.

• AGH University of Science and Technology, Faculty of Foundry Engineering, Cracow, Poland

autor

Dobosz S. M.

• AGH University of Science and Technology, Faculty of Foundry Engineering, Cracow, Poland

autor

Major-Gabryś K.

• AGH University of Science and Technology, Faculty of Foundry Engineering, Cracow, Poland

Bibliografia

• [1] Perzyk, M., Maciejak, S. & Kozłowski, J. (2011). Application of time-series analysis for prediction of molding sand properties in production cycle. Archives of Foundry Engineering. 1(2), 95-100.
• [2] Sika, R. & Ignaszak, Z. (2011). Data acquisition in modeling using neural networks and decision trees. Archives of Foundry Engineering. 11(2), 113–122.
• [3] Ignaszak, Z. & Sika, R. (2008). The system to explore the chosen production data and its testing in the foundry. Archives of Mechanical Technology and Automation. 28, 61-72.
• [4] Hülya, K. D., Erdoğan Ö. & Cevdet M. Ç. (2007). The use of neural networks for the prediction of wear loss and surface roughness of AA 6351 aluminum alloy. Materials & Design. 27, 156-159. DOI: 10.1016/j.matdes.2004.09.011.
• [5] Mahesh, B., Parappagoudar, D., Pratihar, K. & Datta, G.L. (2008). Forward and reverse mappings in green sand mould system using neural networks. Applied Soft Computing. 8, 239-260. DOI: 10.1016/j.asoc.2007.01.005.
• [6] Perzyk, M., Biernacki, R. & Kochański, A. (2005). Modeling of manufacturing processes by learning systems: The naïve Bayesian classifier versus artificial neural networks. Journal of Material Processing Technology. 164, 164-165, DOI: 10.1016/j.jmatprotec.2005.02.043.
• [7] Rudy, Cz. (2012). Preparing and rebonding of moulding sand. Retrieved June 11, 2012, from http://www.technical.com.pl/ files/exposition/Konferencje_IX_Konferencja_Odlewnicza_Technical_xxaec.pdf.
• [8] Ignaszak, Z. & Mikołajczak, P. (2008). Issues of data bases in advanced coupled modeling of porosities in castings on example of system calcosoft. ATMiA. 28(3), 81-94.
• [9] Malinowski, P., Suchy, J.S. & Pater, M. (2012). Simulation DB – technological knowledgebase – new trend of data management. Journal of Achievements in Materials and Manufacturing Engineering. 55(1), 129-134.
• [10] Jakubski J., Malinowski P. & Hajduk M. (2011). MouldingSandDB – a modern database storing moulding sands properties research results. Archives of Foundry Engineering. 11(1), 21-24.
• [11] Jakubski, J. & Dobosz, S. M. (2010). Selected parameters of moulding sands for designing quality control systems. Archives of Foundry Engineering. 10(3), 11-16.
• [12] Jakubski, J. & Dobosz, S. M. (2010). The usage of data mining tools for green moulding sands quality control. Archives of Metallurgy and Materials. 55(3), 843-849.
• [13] Jakubski, J., Dobosz, S. M. & Major-Gabryś, K. (2011). Active binder content as a factor of the control system of the moulding sand quality. Archives of Foundry Engineering. 11(1), 49-52.