Wyniki wyszukiwania - BazTech

1

Evaluation of Sewed Thread Consumption of Jean Trousers Using Neural Network and Regression Methods

Jaouachi B., Khedher F.

Fibres & Textiles in Eastern Europe

|

2015

|

Vol. 23, no. 3 (111)

91--96

EN

This paper deals with the prediction of the sewing thread consumption of jean trousers using the neural network technique. The neural network results and analysis are discussed and investigated. Indeed the findings show that neural network consumption values give better fitting of experimental results than the ones obtained using regression technique. However, compared to the experimental consumption results, theoretical ones of the sewn jean pants seem widely predictable in the desired field of interest. Among the all parameters studied, statistical analysis results also indicate that five inputs can be considered as influential ones. When classifying these five influential inputs, only three parameters are considered most significant. In fact the thread consumed to sew jean trouser samples remains influenced especially by the thread properties and needle fineness as well. Compared with the regression model, the neural network model gives a more accurate prediction and to a great extent provides the amount of sewing thread.

PL

Praca dotyczy przewidywania zużycia nici szewnych przy szyciu spodni dżinsowych stosując technikę sztucznych sieci neuronowych. Badania wykazują , że wyniki zapotrzebowania nici uzyskane za pomocą sztucznych sieci neuronowych są bardziej zgodne z eksperymentami niż te uzyskane techniką regresji. Przeprowadzając kolejne analizy, określono najbardziej racjonalną strukturę sztucznych sieci neuronowych z pięcioma wejściami i trzema parametrami mającymi najbardziej istotny wpływ na zużycie. Stwierdzono, że zależy ono głównie od właściwości nitki i rodzaju igły. Porównując wyniki otrzymane z zastosowania sztucznych sieci neuronowych z wynikami otrzymanymi za pomocą metody regresji stwierdzono, że pierwsza metoda daje lepsze wyniki.

2

Evaluation of the Residual Bagging Height using the Regression Technique and Fuzzy Theory

Jaouachi B.

Fibres & Textiles in Eastern Europe

|

2013

|

Vol. 21, no. 4 (100)

92--98

EN

This paper deals with the evaluation of the residual bagging height using the fuzzy theory method. An experimental design was used to objectively evaluate the effect of input parameters on the residual bagging height of knitted fabrics using two different yarn structures without and within elastane filament. Our findings show that among the overall input parameters tested, two are influential. In our experimental design the fuzzy theory method was applied using five different membership functions: triangular-shaped, trapezoidal function, Gaussian, generalized-bell and Đ-shaped . To prove our results, the experimental regression technique and fuzzy theory were compared. In addition, among the other membership functions tested, the triangular membership function gives a more effective evaluation and widely fits to residual bagging height behaviour.

PL

Praca opisuje ocenę wysokości odkształcenia przy wypychaniu dzianin przy zastosowaniu teorii zbiorów rozmytych. Eksperymentalny system został opracowany do oceny wpływu parametrów wyjściowych. Do badań przyjęto dzianiny wykonane z dwóch rodzajów przędzy, z oraz bez elastomerowego składnika. Nasze wyniki pokazują, że spośród wszystkich badanych parametrów wejściowych 2 posiadają istotne znaczenie. Do badań korzystano z metody zbiorów rozmytych stosując 5 różnych funkcji przynależności: trójkątną, trapezoidalną, Gaussowską, dzwonową oraz typu Pi. Dla oceny uzyskanych wyników przeprowadzono porównanie danych uzyskanych z teorii zbiorów rozmytych oraz techniki regresji danych doświadczalnych. Stwierdzono, że najlepsze rezultaty uzyskano stosując metodę trójkątnej funkcji przynależności, przy której korelacja z danymi eksperymentalnymi wysokości odkształcenia przy wypychaniu była największa.

3

Consumption of the sewing thread of jean pant using Taguchi design analysis

Jaouachi B., Khedher F., Mili F.

Autex Research Journal

|

2012

|

Vol. 12, no. 4

81--86

EN

This work deals with the evaluation of sewing thread consumption in jeans and classic pants clothing. Six different input parameters are chosen and used for investigation. To objectively evaluate their contributions, a Taguchi design analysis was applied. Based on the comparison between each input parameter effect, this experimental analysis helped us to classify the overall tested factors. Indeed, our findings show that the sewing yarn affects widely the thread consumption during stitching of the pant. In spite of their non negligible impact, the number of stitches per cm and the needle type can be considered as influential input factors on thread consumption. In our experimental design the other tested factors were kept constant.

4

Sizing Effect on Wet-Pneumatic Spliced Denim Yarn Performance

Jaouachi B, Hassen M B, Sakli F

Fibres & Textiles in Eastern Europe

|

2011

|

Vol. 19, no. 5 (88)

129--132

EN

In this study, the mechanical behaviour of parent as well as wet spliced cotton denim yarns were compared before and after sizing in order to evaluate the sizing contribution and to predict the effectiveness of sized splices during weaving. The sizes used were natural (CarboxyMethylCellulose size) and synthetic (Acrylic size).It is found that splicing improves the breaking strength of both parent and spliced yarns, while sizing improves the elongation at break of only wet pneumatic spliced yarns. The same results were obtained under cyclical tensioning.

PL

W badaniach porównano właściwości mechaniczne bawełnianych przędz dżinsowych konwencjonalnych i skręcanych na mokro. Porównano je przed i po naniesieniu preparacji dla określenia jej wpływu na efektywność tkania. Zastosowano preparacje naturalne (karboksymetylocelulozowe) i syntetyczne (akrylowe) . Stwierdzono, ze splecenie przędz powoduje zwiększenie wytrzymałości na zrywanie zarówno dla obydwu przypadków podczas gdy pokrycie preparacją powoduje zwiększenie wydłużenia przy zerwaniu tylko dla przędz pneumatycznie splecionych na mokro. Podobne wyniki uzyskano przy cyklicznym obciążaniu przędz.

5

Predicting residual bagging bend height of knitted fabric using fuzzy modelling and neural networks

Jaouachi B, Louati H., Hellali H.

Autex Research Journal

|

2010

|

Vol. 10, no. 4

110--115

EN

In this research, fuzzy modelling and neural network methods were used and compared to predict the residual bagging bend height of knitting fabric samples. Studies undertaken to minimize the bagging phenomenon vary significantly with the test conditions including the experimental field of interest, the input parameters and the applied method. Hence, we attempt to formulate a theoretical model of predicting bagging behaviour in our experimental design of interest. By analysing the bend height of overall bagging samples, this paper provides an effective neural network model to evaluate and predict the residual bagging bend height of the knitting specimens after test. It also provides the impact of each input parameter in our experimental field of interest to simulate this phenomenon after use. Moreover, the contribution of these influential input parameters was analysed and discussed. Nevertheless, our results show that residual bagging height decreases when yarn contains elastane filament, Spandex©. This finding is in agreement with Mirostawa et al. [11] that with an increase of the elastane content in fabric, permanent bagging decreases, whereas elastic bagging increases. According to the analytical results obtained, the neural network model gives a more accurate prediction than the fuzzy one.

6

Optimisation of the behaviour of sized wet spliced yarns

Jaouachi B., Ben Hassen M., Sakli F.

Autex Research Journal

|

2009

|

Vol. 9, no. 1

1--4

EN

This work presents the contribution of optimisation analysis of the performance of wet pneumatic spliced cotton yarns using two different methods: the superimposed contours method and the function of desirability. Cotton yarn linear density (Yc), length of splice (SL), duration of water joining (Dwj) and duration of air joining (Daj) were optimised in the experimental field of interest. In this study regression equations expressing multi-component splice mechanical performances were elaborated by using the response surface method. In order to validate the results, a desirability function, multi-objective technique was used to select optimal parameter zones which give high splice behaviour. The results show that there are zones of compromise where wet pneumatic splice behaves better before weaving. In this work, the spliced yarn performance was optimised.

7

Impact of the splicer parameters on the spliced open-end Denim spun-yarns physico-mechanical performances

Jaouachi B, Sahnoun M.

Autex Research Journal

|

2009

|

Vol. 9, no. 3

66--69

EN

In this work, the open end splicer parameters as the compressed air (pressure, P and durations of tearing, Dt), the fibres feeding during splicing operation (1S10 and EII), and the recalling yarn codes (RI, RII and RIII) were investigated. In order to evaluate the contribution of the splicing conditions on the open end splice physico-mechanical behavior, we used the experimental Tagauchi design method. This kind of experimental design allows us, using simplification method, to reduce the amount of the experiments. To evaluate the splice appearance, the subjective (the experts notes) method and the objective (referring to a developed Thickness index value) one are compared. In our experimental field of interest, the results show that the feeding fibres parameter level increase gives the lowest Thickness index value which means good splice appearance. However, the compressed air remains the most important parameter because it represents the influential one on both the strength and the longitudinal characteristics of the spliced open-end spun-yarns (length of splice and the expert judgments).

8

Strength of wet spliced denim yarns after sizing using a central composite design

Jaouachi B., Ben Hassen M., Sakli F.

Autex Research Journal

|

2007

|

Vol. 7, no. 3

159--165

EN

The retained strength of wet spliced yarns can be controlled to some extent by suitable choices of certain factors related to the process. In order to understand how these variables influence the breaking force of wet spliced yarns, a central composite design was formulated and three variables - yarn count, the duration of air joining and the duration of water joining - were considered. Analysis of the results indicates that yarn count and length of splice contribute significantly to this mechanical property of wet sized spliced yarns. The duration of water joining, the duration of air joining of splice and the recipe size have a considerable effects.