Wyniki wyszukiwania - BazTech

1

Prediction of the Ultraviolet Protection of Cotton Woven Fabrics Dyed with Reactive Dystuffs

Dobnik-Dubrovski P., Brezocnik M.

Fibres & Textiles in Eastern Europe

|

2009

|

Vol. 17, no. 1 (72)

55--59

EN

Textile materials provide a simple and convenient protection against UV radiation. To assign the degree of UV radiation protection of textile materials, the Ultraviolet Protection Factor (UPF) is commonly used. This paper reports the effect of woven fabric construction (yarn fineness, type of weave, relative fabric density), the colour of bi-functional reactive dyestuffs, and Cibacron dyed fabrics on the ultraviolet protection of light summer woven fabrics. A predictive model, determined by genetic programming, was derived to describe the influence of fabric construction. Warp and weft densities, weave factor and CIELab colour components were taken into account by developing the prediction model for UPF. The results show very good agreement between the experimental and predicted values.

PL

Materiały tekstylne stanowią proste zabezpieczenie przed promieniowaniem UV. Jako miernik zabezpieczenia przed promieniowaniem UV wprowadzono powszechnie współczynnik UPF. W pracy opisano wpływ takich parametrów konstrukcyjnych tkaniny jak; gęstość liniowa przędź, typ splotu, względna gęstość tkaniny, dwufunkcyjnych reaktywnych barwników oraz barwników typu Cibacron na zabezpieczenie przed promieniowaniem UV tkanin o małej masie powierzchniowej używanych na letnie ubiory. Stworzono model pozwalający na przewidywanie wpływu struktury tkaniny na współczynnik ochrony. Wartościami wejściowymi dla modelu są: gęstość osnowowa i wątkowa, współczynnik charakterystyczny splotu i składniki sytemu kolorystycznego CIELab. Wyniki badań wskazują na bardzo dobrą zgodność pomiędzy wartościami przewidywanymi a wynikami eksperymentu.

2

Analytical study of different approaches to determine optimal cutting force model

Krizek Z., Jurkovic Z., Brezocnik M.

Archives of Materials Science

|

2007

|

Vol. 28, nr 1-4

69-74

EN

Determination of optimal machining parameters is an engineering task with aim to reduce the production cost and achieve desired product quality. Such exercise can be tackled on many different ways. The goal of this work is to present some of the possible approaches and to benchmark them among each other. These principles are analyzed: response surface methodology (RSM), evolutionary algorithms (GA & GP), support vector regression (SVR) and artificial neural networks (ANN). All methods implement completely different data handling philosophies with the same goal, to build the model which is able to predict cutting force in satisfying manner. Those aspects are chosen to be evaluated and compared: average percentage deviation of all data, ability to find generalized model and minimize the risk of over fitting and at least the runtime of each single model determination. Average percentage deviation is one of the best indicators of the quality of model. The ability to find generalized model is good indicator of the flexibility of model, and shows how model deals with unknown data. The runtime is important in a real time environment or in scenarios where conditions change frequently. Cutting force data used in this benchmark comes from experimental research of longitudinal turning process.

3

Prediction of steel machinability by genetic programming

Brezocnik M., Kovacic M., Psenicnik M.

Journal of Achievements in Materials and Manufacturing Engineering

|

2006

|

Vol. 16, nr 1-2

107--113

EN

Purpose: This paper describes intelligent system to predict steel machinability. Design/methodology/approach: The prediction of machinability of steel, depending on input parameters (percentage of calcium, percentage of oxygen, percentage of sulphur), was performed by means of genetic programming and data on the batches of steel already made. Findings: The mathematical model to predict machinability of steel obtained by genetic programming method gives only 4 wrong predictions out of 146 experimental values. The model was tested also with testing data set. The machinability of the complete test batches (27 experimental values) was successfully predicted. Research limitations/implications: Limitation of the proposed concept is the size of test data (N = 27), which means longer testing period. The 146 batches, which were used for modeling, were collected in the period of February 2004 to April 2005. Practical implications: With the proposed approach, it is possible to establish efficient planning and optimizing of production, to reduce the costs of researches and the handling changes and, finally, to increase satisfaction of the buyers due to shorter delivery times. Originality/value: The paper presents new and innovative approach to predict steel machinability by genetic programming. The prediction precision is at high level. The results show that the proposed concept can be successfully used in practice.