Wyniki wyszukiwania - BazTech

1

Comparison of selected methods of multi-parameter data visualization used for classification of coals

Jamroz D., Niedoba T.

Physicochemical Problems of Mineral Processing

|

2015

|

Vol. 51, iss. 2

769--784

EN

Methods of multi-parameter data visualization through the transformation of multidimensional space into two-dimensional one allow to present multidimensional data on computer screen, thus making it possible to conduct a qualitative analysis of this data in the most natural way for human – by a sense of sight. In the paper a comparison was made to show the efficiency of selected seven methods of multidimensional visualization and further, to analyze data describing various coal type samples. Each of the methods was verified by checking how precisely a coal type can be classified when a given method is applied. For this purpose, a special criterion was designed to allow an evaluation of the results obtained by means of each of these methods. Detailed information included presentation of methods, elaborated algorithms, accepted parameters for best results as well the results. The framework for the comparison of the analyzed multi-parameter visualization methods includes: observational tunnels method multidimensional scaling MDS, principal component analysis PCA, relevance maps, autoassociative neural networks, Kohonen maps and parallel coordinates method.

2

Application of the observational tunnels method to select a set of features sufficient to identify a type of coal

Jamroz D., Niedoba T.

Physicochemical Problems of Mineral Processing

|

2014

|

Vol. 50, iss. 1

185−202

EN

Coal is a material which has many features deciding about its quality. Among them, the decisive ones are mainly ash contents, sulfur contents and combustion heat. The paper presents the investigation of coal characteristics of three selected coal types in the context of their energetic value. For this purpose samples were collected from three different Polish mines: coal types 31, 34.2 and 35 (Polish classification of coals). Each of these materials was separated into particle size fractions (9 fractions) and then into 8 density fractions by separation in heavy liquids. For each size-density fractions obtained in this way, chemical analyses were performed which allowed for determination of such features as combustion heat, sulfur contents, ash contents, volatile parts contents and analytical moisture. Altogether, seven dimensions of grained material characteristics were obtained. The data prepared in this way was subsequently analyzed for correlation with the purpose of determining significant relations between investigated features. It was stated that the most correlated coal features are density, combustion heat, ash contents and volatile parts contents. For multidimensional analysis and identification of coal type, the modern image visualization technique, the Observational Tunnels Method, was applied. After performing seven-dimensional analysis aimed at the proper recognition of coal type, it was decided to determine the minimum amount of random variables, which describe a particular material in order to identify its type. It was stated that the crucial coal identification parameter is “analytical moisture”. Due to existing correlation between individual features, three of them were selected for testing: analytical moisture, sulfur contents and volatile parts contents. On the basis of the obtained images, it was stated that it was possible to obtain a view with the data concerning each type of coal being located in other part of the space. Subsequently, it was checked if a similar result is possible when the parameter “volatile parts contents” is replaced with highly correlated parameters “combustion heat” and “ash contents”. In both cases the exchange of these variables did not produce good enough results. This can be explained by a different scale of empirical data making it impossible to obtain a clear multidimensional image for which all three types of coal would be located in other parts of space. However, it was proved that the modern graphical and computer methods can be successfully applied to identify the types of particulate materials.

3

Application of multi-parameter data visualization by means of autoassociative neural networks to evaluate classification possibilities of various coal types

Jamroz D.

Physicochemical Problems of Mineral Processing

|

2014

|

Vol. 50, iss. 2

719--734

EN

The significance of data visualization in modern research is growing steadily. In mineral processing scientists have to face many problems with understanding data and finding essential variables from a large amount of data registered for material or process. Hence it is necessary to apply visualization of such data, especially when a set of data is multi-parameter and very complex. This paper puts forward a proposal to introduce the autoassociative neural networks for visualization of data concerning three various types of hard coal. Apart from theoretical discussion of the method, the empirical applications of the method are presented. The results revealed that it is a useful tool for a researcher facing a complicated set of data which allows for its proper classification. The optimal neural network parameters to successfully separate the analyzed three types of coal were found out for the analyzed example.

4

Physicochemical properties of phosphates applied in animal feeding

Gajda-Janiak A., Jamroz D., Wzorek Z.

Polish Journal of Chemical Technology

|

2005

|

Vol. 7, nr 1

20-23

EN

Phosphorus, in view of a wide spectrum of influences on the living beings, may be treated as a universal element. Cellular nucleus as well as enzymes, hormones and proteins contain phosphorus. 75 wt. % of total phosphorus in the organism is located in bones, the rest of it, among other things, appears in teeth, blood and phospholipids. In order to compensate the deficiency of phosphorus in animals feeding, various calcium-phosphorus compounds, different in the form and the degree of hydration produced from the phosphate rock, are applied. The influence of the physicochemical properties of the selected fodder phosphates on their solubility, therefore, on their bioavailability, has been presented in this paper. The results obtained should enable an optimization of the phosphorus content in the fodders and a subsequent less wasteful use of phosphate additives in animal feeding.