Wyniki wyszukiwania - BazTech

1

Artificial Neural Networks as a Tool for Supporting a Moulding Sand Control System Based on the Dependency between Selected Moulding Sand Properties

Mrzygłód Barbara, Jakubski Jarosław, Opaliński Andrzej, Regulski Krzysztof

Journal of Casting & Materials Engineering

|

2023

|

Vol. 7, no. 2

15--21

EN

The article presents the potential for using artificial neural networks to support decisions related to the rebonding of green moulding sand. The basic properties of the moulding sand tested in foundries are discussed, especially compactibility as it gives the most information about the quality of green moulding sand. First, the data that can predict the compactibility value without the need for testing are defined. Next, a method for constructing an artificial neural network is presented and the network model which produced the best results is analysed. Additionally, two applications were designed to allow the investigation results to be searchable by determining the range of values of the moulding sand parameters.

2

Studies of mechanical and technological parameters and evaluation of the role of lustrous carbon carriers in green moulding sands with hybrid bentonite

Kamińska Jadwiga, Stachowicz Mateusz, Puzio Sabina, Angrecki Michał

Archives of Civil and Mechanical Engineering

|

2023

|

Vol. 23, no. 1

art. no. e11, 2023

EN

Green moulding sands containing special carbonaceous additives, which are the source of lustrous carbon (LC), are discussed in this paper. Five potential lustrous carbon carriers, i.e., two types of hard coal dust (No.1 and No.2), amorphous graphite (No.3) and two hydrocarbon resins (No.4 and No.5), were selected for tests as carbonaceous additives to conventional moulding sands. To better emphasize the differences in the additives used, reference green moulding sand (GMS1) was prepared and subjected to a wide range of basic tests focussed on technological parameters, such as permeability (Pw), friability (Fw), Dietert mouldability test (PD) and compactability (Z) and mechanical parameters, such as compressive strength (Rcw), tensile strength (Rmw), strength in the transformation zone (Rkw). The proposed comprehensive spectrum of tests was repeated on sands with five carbonaceous additives. The most important for the use of additives as carbon carriers was to interrelate the content of lustrous carbon (LC), loss on ignition (LOI) and the obtained results of mechanical and technological tests carried out on conventional moulding sands with the surface quality of iron castings. For this purpose, a series of iron castings was made in the prepared moulding sands and used for the assessment of surface quality based on a number of roughness parameters (Ra, Rz, Rp, Rq, Rv, Rlr, RSm). As a result of the studies it was found that the carbonaceous additives proposed for use help to obtain high-quality surfaces in iron castings.

3

Research on Selected Types of Lustrous Carbon Carriers After the High - Temperature Pyrolysis

Kamińska Jadwiga, Stachowicz M., Kubecki M.

Archives of Foundry Engineering

|

2021

|

Vol. 21, iss. 1

56--62

EN

For research purposes and to demonstrate the differences between materials obtained from the carbonaceous additives to classic green moulding sands, five lustrous carbon carriers available on the market were selected. The following carbonaceous additives were tested: two coal dusts (CD1 and CD2), two hydrocarbon resins (HR1 and HR2) and amorphous graphite (AG1). The studies of products and material effects resulting from the high-temperature pyrolysis of lustrous carbon carriers were focused on determining the tendency to gas evolution, including harmful compounds from the BTEX group (benzene, toluene, ethylbenzene and xylene). Moreover, the content of lustrous carbon (LC), the content of volatile matter and loss on ignition (LOI) of the carbonaceous additives were tested. The solid products formed during high-temperature pyrolysis were used for the quantitative and qualitative evaluation of elemental composition after the exposure to temperatures of 875oC in a protective atmosphere and 950oC in an oxidizing atmosphere. The conducted studies have indicated the necessity to examine the additives to classic green moulding sands, which is of particular importance for the processing, rebonding and storage of waste sand. The studies have also revealed some differences in the quantitative and qualitative composition of elements introduced to classic moulding sands together with the carbonaceous additives that are lustrous carbon carriers. It was also considered necessary to conduct a research on lustrous carbon carriers for their proper and environmentally friendly use in the widely propagated technology of classic green sand system.

4

MouldingSandDB - a modern database storing moulding sands properties research results

Jakubski J., Malinowski P., Hajduk M.

Archives of Foundry Engineering

|

2011

|

Vol. 11, iss. 1s

21-24

EN

The complexity of foundry processes requires the use of modern, advanced IT tools for optimization, storage and analysis of technical data. Properties of moulding and core sands that are collected in research laboratories, manufacturers, and finally in the foundries, are not in use later on. It seems important to create a database that will allow to use the results stored, along with the possibility of searching according to set criteria, adjusted to casting practice. This paper presents part of the database named "MouldingSandDB", which allows to collect and search data for synthetic moulding sands.

5

Active binder content as a factor of the control system of the moulding sand quality

Jakubski J., Dobosz S. M., Major-Gabryś K.

Archives of Foundry Engineering

|

2011

|

Vol. 11, iss. 1

49-52

EN

One of the modern methods of the production optimisation are artificial neural networks. Neural networks are gaining broader and broader application in the foundry industry, among others for controlling melting processes in cupolas and in arc furnaces, for designing castings and supply systems, for controlling moulding sand processing, for predicting properties of cast alloys or selecting parameters of pressure castings. 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 obtained by using the Statistica 9.0 program. 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. 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.