New Approach for Optimising the Impregnations of Individual Batches of Aramid Fabrics Nov

Innovate textile materials for special clothing are intended for providing trauma protection for the wearer. Fabrics made from high performance aramid fi bres are widely used nowadays for manufacturing athletic sportswear for extreme sports due to their high specifi c tensile modulus and strength. The aim of our study was to illustrate a new approach when searching for optimal settings for impregnating individual batches of textile materials on the basis of para aramid fi bres. We demonstrate a feed-forward bottleneck (FFBN) neural network mapping technique that makes it possible to see all optima (optimal settings for best quality) in the studied process. The selections of optimal settings are based on making decisions allowing us to choose optimal settings for processes in relation to the best quality and smallest (minimal) expense. This new approach can be applied for searching optimal settings regarding different chemical treatments. If a standard statistical regression model (in the cases of non-linear relationships) experiences lack of fi t, it can be successfully substituted with the FFBN neural network mapping technique. This method can also be recommended as a double check of a studied process when we use


Introduction
Aramid bres have been produced in Russia since 1970.e history of the rst Russian para aramidbres under the name SVM (super high-modulusbre) is given on the web-page of the Alchemie Group [1]. is group was founded in 1999 to commercialise Russian materials' technologies focusing on unique materials' processes and materials that enable the Alchemie Group to supply ultra-e cient, ultra-light, ultra-high strength materials, composites, components, solutions, systems and products for the 21 st century.Aramid bres are currently in production as AuTx-WE bre based on Rusar (Russian Aramid) technology with a tenacity of over 250 cN/tex.e process of bre forming is principally di erent from that used while forming Kevlar and Twaron aramid bres.
e SVM bre has high strength (190-220 cN/tex), high modulus (75-100 GPa), and elongation at break (3,0-4,0%).is bre is used for the manufacturing high strength lightweight composites and as a fabric was applied in the creation of the rst exible Russian bullet proof vests.
e current generation of bres that have become the base for AuTx materials appeared in 1997 under the tradename RUSAR (an abreviation for Russian Aramid). is bre has very high strength (230-270 cN/tex for AuTx WE and >300 cN/tex for AuTx DWE), high modulus (100-140 GPa), elongation at break at (2,6-3,0%) and is extremly environmentally resilient.e technology of AuTx has a large potential for development [1].Nowadays the high interest for goods produced from aramide bres and fabrics has been proved by numerous research [2][3][4][5][6][7][8].In this paper we examined the impregnation processes of high performance fabrics made from aramid bres designed for the manufacturing of athletic sportswear for extreme sports using the neural network mapping technique when searching for optimal conditions regarding the studied process.Traditional statistical methods based on the designing of experiments (for example, surface response method or others) are o en used for improving the properties of textile materials [9][10][11].In some cases the arti cial neural network methods have been employed for predicting the properties of fabrics [12][13].
e application of the feed-forward bottleneck neural network (FFBN NN) mapping technique for optimisation is a relatively new method that is easy to use and non-time consuming [14][15][16][17][18][19]. e projection of multidimensional data into a 2D map enables obtaining of the input and output parameters within the same coordinates.us, a contour plot of output parameters (responses) overlapping with locations corresponding to the combinations of input parameters (setting points) enables visualisation of the optimal setting parameters of the technological processes in the 2D map.Implementation of the FFBN NN mapping technique enables the nding of several optimal solutions during the development of the new products, as well as to improve the qualities of industrial products.Application of the FFBN neural network mapping technique for pigment dyeing of aramid and arimid bres was published in a paper [20].It was of interest for considering optimisation of the impregnation process of aramid fabrics using the FFBN NN method.e FFBN NN approach in combination with the criteria functions for plotting coded diagrams is innovative within the eld of enhancing textile properties via the adjusting of impregnation parameters.

Materials
Aramid fabrics (Russian name SVM) with mass per unit areas of 131 g/m 2 (fabric 1) and 216 g/m 2 (fabric 2) produced from polyamide benzimidazole (PABI) laments were used during the impregnation treatment.
e PABI bres have extremely high modulus and strength, and are heat-resistant.ey are widely used for the production of protective clothing (i.e.bulletproof vests) [21] as well as for the recreational industry in a variety of applications ranging from boating to skiing.In this paper we studied those aramid fabrics used for the manufacturing of athletic sport wear for extreme sports, particularly sport jackets and trousers (see Figure 1).e quality of lighter fabric 1 (131 g/m 2 ) was evaluated using output parameters (responses) Y1-Y4, where Y1 represents weight gain I (%), Y2 sti ness (mm), Y3 tensile strength (daN) and Y4 elongation (%).

Plan of experimental design for the impregnation process
e diagram of the impregnation process of aramid fabrics considered in this study is represented in Figure 2. e fabric passes through a bath (2) and subsequently through squeeze rollers 3, then is directed towards drying in the air and thermo-xation at 150°C.

Figure 2: A diagram of the impregnation process
Statistical designs of experiments (DOEs) is commonly used in many industries (chemical, polymer, car manufacturing, biotech, food and dairy, pulp and paper, steel and mining, plastic and paints, electronic, telecom, etc.).DOEs can be used for the developments of new products and processes, enhancements of existing products and processes, optimising the qualities and performances of products, screening important factors, minimization of products' costs and pollution, robustness testing of products and processes, and so on.e goal of our study was improvement of the impregnation process.
e following ve independent variables (which affect the qualities of impregnated fabrics) were chosen for the study: the concentration of latex (AH7) (x 1 , g/l), concentration of gelatin (x 2 , g/l), concentration of binder (Carbamol) (x 3 , g/l), concentration of catalyst, MgCl 2 х 6 Н 2 О (x 4 , g/l), and heat xation time, (x 5 , s).Each of the 5 independent variables were explored on 5 levels: -2, -1, 0, +1 and +2.e contents and concentrations of components in the impregnation bath used during this study as coded and non-coded values are represented in Table 1.e parameters were varied according to the speci cation requirements of the technological impregnation process.A design matrix including the 32 runs (number of experiments) was composed and is represented in Table 2, where Y1-Y4 are response variables related to fabric 1 while Y5-Y7 relate to fabric 2. e input parameters X1-X5 are represented in the coded units (as code levels).
e relationships were examined between the output properties of fabrics (Y1-Y7) depending on the concentrations of the ingredients in the impregnating bath and conditions (times) of the heat settings of lm-forming compositions.e goal of optimisation was to discover the maximal or minimal values of the  objective functions in order to reach the best qualities for the products.In this case the generalised response should be determined.Normalisation of the data was performed in order to obtain a generalised response.
In order to obtain the normalized values of the response variables (y n ), each y value was divided by its maximal value (y n1 = y 1 /y 1max , y n2 = y 2 /y 2max , ..., y nk = y k /y kmax ).As a result values no greater than one were obtained for each of the response and could be compared.e goal of our optimisation was the maximisations of Y3, Y4, Y6 and Y7 and the minimisations of Y1, Y2 and Y5.erefore, the generalised values of the response variables was obtained using Equations 1 and 2 for fabric 1 and fabric 2, correspondingly.(Y n_gen1 ) = y n3 *y n4 / y n1 *y n2 (1) (Y n_gen2 ) = y n6 *y n7 / y n5 (2) It should be noted that the normalised values of "Y" were used in the neural network method described below.

Feed-forward bottleneck (FFBN) neural network
e general concept of arti cial neural networks (ANN) is based on simpli ed imitation of the human nervous system.A simple network has a feed-forward structure: signals ow from inputs forward through any hidden units, eventually reaching the output units.Input data are organised as vectors (based on linear algebra).In other words the input layer serves for introducing the values of the input variables.(In Figure 3 one can see fragments of vectors from the design matrix).Neural networks are typically organised in layers.e hidden and output layer neurons are connected to all the units in the preceding layer.In the study we applied the FFBN NN-containing input layer, hidden layer and de-mapping of input (output layer) (see Figure 4).Layers are made up of a number of interconnected "nodes" which contain an "activation function".
e FFBN neural network applied in the study refers to an auto associative neural network.e feed-forward nets here are trained to produce an approximation of the identity mapping between network inputs and outputs using back propagation or similar learning procedures [14][15][16][17][18][19]. is neural network can deal with linear and nonlinear correlation amongst variables.Multidimensional data sets are di cult to interpret and visualise.
e FFBN neural network was used for compression and visualisation of the data in  3. e principle of bottleneck layer mapping: the two neurons within the hidden layer produce, for each input object x i , a corresponding pair of coordinates (h i = {h i,1 , h i,2 }). e run number »i« marked as a vector xi = {x i1 x i2 x i3 ...x im }.In the FFBN each i-th object is projected onto a two dimensional map with coordinate h i1 /h i2 (see blue arrow).In our experiment we have got 32 projection points (k = 32) corresponding to 32 experimental settings.Input data are represented as vectors X1-X5 corresponding to 5 columns in the design matrix with 32 rows related to the 32 setting points (see Table 2).A special architecture of error back-propagation neural network was used (5,2,5), in which the data are fed into the 5-nodes input layer and then transferred through the 2-nodes hidden layer (compared to a bottleneck) to the 5-nodes output layer.The number of nodes in the input and output layers correspond to the number of independent variables which is equal to 5 (number of factors in DOE).During the training process we are able to get within the output nodes, the values more similar to the input variables of the samples, after passing the bottleneck of the twonode hidden layer.The signals in the two hidden nodes are then taken as two coordinates for each input object acting as a 2D projection of samples into a map.For each of the 32 experimental settings the corresponding value of Y (Y1-Y7) was determined in the course of the experiment.e projection of 32 combinations of experimental conditions and values of response within the same coordinates H1/H2 enables determination of optima in the impregnation process.Figure 5 illustrates the experimental data for fabric 1 with surface density 131 g/m 2 .It represents the 34 setting points overlapped with the contour plots of responses: Y1-weight gain, Y2-sti ness, Y3-tensile strength, Y4-elongation and generalised values Ygen1 = Y3*Y4/ Y1*Y2.
e dark green (in colour picture)/grey (in the grey scale picture) area corresponds to maximal values.For fabric 1 it corresponds to combination 15. us, for fabric 1 optimal condition settings correspond to levels of X1-X5 (+,-,-,-,-) with parameter X1 at level +1 and parameters Х2-Х5 at the level -1.us, the optimal settings for fabric 1 enable obtaining of the following quality characteristics: Y1 = 5.0%, Y2 = 51mm, Y3 = 233daN; Y4 = 6.4%. Figure 6 represents the experimental data for fabric 2 with surface density 216 g/m 2 .e thirty two (32) experimental setting points are overlapped with the contour plots of responses: Y5-weight gain, Y6wear resistance, Y7-tear force; and generalised values Ygen2 = Y6*Y7/ Y5.For fabric 2 optima for generalised response correspond to combination 14, 18 and central values (zero level (27-32)) (marked with red circles in Figure 6).Non-coded values of Y5-Y7 in that points are seen in Table 2.We can also select the optimal settings by taking into account individual responses Y6, Y7 and Y5 (not generalised).If the weight gain (Y5) is insignificant (or the values for Y5 at point 24 satisfy our requrements) and we would like to get the highest wear resistance (Y6) and tear force (Y7) we obviously would select point 24 (see Figure 6). is point 24 corresponds to the highest values of Y7 (Y7 = 62daN) and Y6 (Y6 = 367cycles) keeping the Y5 at the middle level (Y5 = 8.8%).us, three (multimum) optima were recommended for fabric 2. e rst optimum corresponds to the setting point 14 (-,+,-,-,-); the second optimum belongs to point 18 (2,0,0,0,0); and the third optimum is located at the centre point 27-32 (0,0,0,0,0).To obtain the highest wear resistance and tear force keeping the weight gain at the middle level we recommend setting point number 24 (0,0,0,+2,0).Visualisation of the process in the 2D map provides signi cant information for making decisions and selecting a suitable condition for the experiment.An optimal solution was chosen on the basis of a compromise decision.

Conclusion
Implementation of the feed-forward bottleneck neural network technique enabled the nding-out of one optimum for fabric 1 that corresponded to setting parameters in setting point 15 (+,-,-,-,-) with parameter X1 at level +1 and parameters Х2-Х5 at the level -1.For fabric 2 three (multimum) optima were recommended: corresponding to the setting points 14 (-,+,-,-,-), 18 (2, 0,0,0,0) and centre point 27-32 (0,0,0,0,0).To get the highest wear resistance and tear force keeping the weight gain at the middle level and recommended setting point number 24 (0,0,0,+2,0).e FFBN mapping technique enables the ndingout multiple optima that could be selected upon compromise decisions by taking into account the desired quality of material, as well as the technical and economic viewpoint and safety of the process.Translation of the multidimensional process input parameter's space into the 2D coordinate system and application of the criteria function as a combination of the process output parameters can be very informative and opening a whole new area of nding optimal conditions in the eld of the textile impregnation industry.

Figure 1 :
Figure 1: A pattern of a sport jacket and trousers with the pieces of aramid fabrics (darker coloured) 2D maps.e FFBN neural network is formed by means of mapping and demapping the hidden layer.e signals in the two hidden nodes are taken as two coordinates for each input object, enabling a 2D projection of experimental objects onto a 2D map.e architecture of FFBN NN is represented in Figure 3. e DOE matrics containing »m« factors (X1-Xm) with »k« numbers of runs is shown at the top of Figure

Figure 3 :
Figure 3: e architecture of feed-forward bottleneck (FFBN) neural network e 2D map with distribution of 32 experimental settings (as was determined in the plan of the experiment) is shown at the right side of Figure 4 in coordinate H1/H2.For each of the 32 experimental settings the corresponding value of response Y was determined during the course of the experiment.e projection of Y onto H1/H2 coordinates gave the contour plots of response Y. Overlapping the projections of 32 experimental objects (obtained from the FFBN neural network 2D map) with responses' contour plots in the same coordinates (H1/H2) enables visualisation and the determining of optimal settings (the dark colour in the 2D map corresponds to the highest values of response Y).

Figure 4 :
Figure 4: e architecture of FFBN neural network with input matrix (X1-X5) and projection of experimental setting (points 1-32), as well as values of generalised response Ygen1 (for fabric 1) onto 2D map with coordinate H1/H2

Table 2
Experimental layout of the design matrix employed for ve independent variables (X1-X5) and output responses (Y1-Y7) for the impregnation process of aramid fabrics