TitleThe Influence of Changes in Active Binder Content on the Control System of the Moulding Sand Quality
Journal titleArchives of Foundry Engineering
KeywordsQuality Management ; Green moulding sand ; artificial neural networks
Divisions of PASNauki Techniczne
Archives of Foundry Engineering continues the publishing activity started by Foundry Commission of the Polish Academy of Sciences (PAN) in Katowice in 1978. The initiator of it was the first Chairman Professor Dr Eng. Wacław Sakwa – Corresponding Member of PAN, Honorary Doctor of Czestochowa University of Technology and Silesian University of Technology. This periodical first name was „Solidification of Metals and Alloys” , and made possible to publish the results of works achieved in the field of the Basic Problems Research Cooperation. The subject of publications was related to the title of the periodical and concerned widely understand problems of metals and alloys crystallization in a casting mold. In 1978-2000 the 44 issues have been published. Since 2001 the Foundry Commission has had patronage of the annually published “Archives of Foundry” and since 2007 quarterly published “Archives of Foundry Engineering”. Thematic scope includes scientific issues of foundry industry:
- Theoretical Aspects of Casting Processes,
- Innovative Foundry Technologies and Materials,
- Foundry Processes Computer Aiding,
- Mechanization, Automation and Robotics in Foundry,
- Transport Systems in Foundry,
- Castings Quality Management,
- Environmental Protection.
AbstractArtificial 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. The presented investigations were aimed at the selection of the neural network able to predict the active bentonite content in the moulding sand on the basis of this sand properties such as: permeability, compactibility and the compressive strength. Then, the data of selected parameters of new moulding sand were set to selected artificial neural network models. This was made to test the universality of the model in relation to other moulding sands. An application of the Statistica program allowed to select automatically the type of network proper for the representation of dependencies occurring in between the proposed moulding sand parameters. The most advantageous conditions were obtained for the uni-directional multi-layer perception (MLP) network. Knowledge of the neural network sensitivity to individual moulding sand parameters, allowed to eliminate not essential ones.
PublisherThe Katowice Branch of the Polish Academy of Sciences
TypeArtykuły / Articles