The Prediction of Moulding Sand Moisture Content Based on the Knowledge Acquired by Data Mining Techniques

Archives of Metallurgy and Materials

A. Opaliński¹  M. Brzeziński¹  J. Jakubski¹  M. Głowacki¹  K. Regulski¹ 

[1] AGH University of Science and Technology, Al. A. Mickiewicza 30, 30-059 Kraków, Poland

关键词: Keywords: Application of Information Technology to the Foundry Industry;    Moulding sands;    Decision trees;    ANOVA;    Data mining;   

DOI  :  10.1515/amm-2016-0277

学科分类：金属与冶金

来源: Akademia Gorniczo-Hutnicza im. Stanislawa Staszica / University of Mining and Metallurgy

【 摘 要 】

The subject of the study is the improvement of the quality of moulding sand preparation. An exploration research performed on the data concerning moulding sand quality parameters was described. The aim of the research was to find relationships between various factors determining the properties of moulding sands and, based on the results obtained, build models predicting the sand moisture content with the induction of classification and regression trees. A two-match prediction approach was demonstrated and its effectiveness in evaluating the moulding sand moisture content was discussed. The knowledge in the form of rules acquired in this way can be used in the creation of knowledge bases for systems supporting decisions in the diagnostics of the moulding sand rebonding process. Formalized knowledge also facilitates further processing of the measurement data.

【 授权许可】

Unknown