Accesso libero

Prediction of Mechanical Properties of Woven Fabrics by ANN

Sherien N. Elkateb
Sherien N. Elkateb
   | 11 dic 2022
Fibres & Textiles in Eastern Europe's Cover Image
INFORMAZIONI SU QUESTO ARTICOLO
Articolo precedente
Articolo Successivo
Cita
Article Category: Research Article
Pubblicato online: 11 dic 2022
Pagine: 54 - 59
DOI: https://doi.org/10.2478/ftee-2022-0036
Parole chiave
© 2022 Sherien N. Elkateb, published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Fig. 1

Neural Network architecture for all mechanical properties
Neural Network architecture for all mechanical properties

Fig. 2

Overall Training Performance of ANN model
Overall Training Performance of ANN model

Comparison between actual and predicted values of properties tested in the weft direction

Run Tensile strength (N) “Stiffness”Bending length * 10−2 (m) Elongation %
Actual Predicted Actual Predicted Actual Predicted
1 258.00 258.00 2.10 2.15 17.70 17.60
2 234.00 234.00 2.00 1.95 13.70 13.50
3 321.00 321.00 2.40 2.37 21.80 21.20
4 307.00 307.00 2.20 2.20 21.20 21.20
5 251.00 251.00 2.10 2.11 13.50 13.30
6 290.00 290.00 2.10 2.09 20.50 20.50
7 241.00 241.00 2.00 2.01 15.10 14.60
8 312.00 312.00 2.30 2.31 20.70 21.10
9 290.00 290.00 2.10 2.09 20.50 20.50
10 228.00 228.00 2.00 1.99 13.10 13.50
11 284.00 284.00 2.00 2.00 19.20 19.20
12 207.00 207.00 1.90 1.92 13.20 13.40
13 290.00 290.00 2.20 2.22 21.70 21.60
14 284.00 284.00 2.00 2.00 19.20 19.20
15 290.00 290.00 2.20 2.22 21.70 21.60

Factors and levels of weft yarns

Levels
Factors 1 2 3
X1 Weft density (picks/m) 0.23 0.25 0.27
X2 Weft yarn count (Nm) 40/1 50/1 ------
X3 Fiber blend ratio of weft yarn Polyester (PE %) 0% 50% 65%
X4 Fiber blend ratio of weft yarn Cotton (C%) 100% 50% 35%

Experimental model

Run X1 X2 X3 X4
Picks/m Weft yarn PE % C %
count (Nm)
1 1 1 1 1
2 1 1 2 2
3 1 1 3 3
4 1 2 1 1
5 1 2 2 2
6 1 2 3 3
7 2 1 1 1
8 2 1 2 2
9 2 1 3 3
10 2 2 1 1
11 2 2 2 2
12 2 2 3 3
13 3 1 1 1
14 3 1 2 2
15 3 1 3 3
16 3 2 1 1
17 3 2 2 2
18 3 2 3 3

Comparison between the prediction performance of all properties by ANNs

Tested properties Tensile strength (N) “Stiffness” Bending length * 10−2 (m) Elongation %
Statistical factors warp weft warp weft warp weft
R-squared :coefficient of determination 1.00 1.00 0.97 0.98 0.99 0.99
MSE :mean squared error 0.00 0.00 0.00 0.00 0.04 0.07
RMSE :root mean squared error 0.04 0.03 0.05 0.02 0.20 0.27
MAE :mean absolute error 0.03 0.02 0.04 0.02 0.15 0.19
MAPE: mean absolute percentage error 0.01% 0.01% 1.62% 0.88% 0.69% 1.14%

Comparison between actual and predicted values of properties tested in the warp direction

Run Tensile strength (N) “Stiffness” Bending length * 10−2 (m) Elongation %
Actual Predicted Actual Predicted Actual Predicted
1 357.00 357.00 2.30 2.39 20.50 20.90
2 334.00 334.00 2.20 2.15 19.40 19.30
3 377.00 377.00 2.70 2.67 22.40 22.50
4 368.00 368.00 2.50 2.50 22.30 22.00
5 358.00 358.00 2.40 2.42 22.00 22.00
6 360.00 360.00 2.40 2.35 22.60 22.60
7 368.00 368.00 2.00 1.95 20.70 20.70
8 369.00 369.00 2.50 2.53 23.10 23.40
9 360.00 360.00 2.40 2.35 22.60 22.60
10 351.00 351.00 2.20 2.19 21.60 21.70
11 350.00 350.00 2.30 2.32 21.30 21.40
12 331.00 331.00 2.00 2.09 15.70 15.70
13 353.00 353.00 2.40 2.42 23.30 23.00
14 350.00 350.00 2.30 2.32 21.30 21.40
15 353.00 353.00 2.40 2.42 23.30 23.00

ANN Training Algorithm

-Train network using Levenberg-Maquardt back-propagation
- Activation function: (trainlm). -Hidden layer size =10
-Performance: Mean squared error (mse) -Gradient: 1.00e-05
eISSN:
2300-7354
Lingua:
Inglese
Frequenza di pubblicazione:
6 volte all'anno
Argomenti della rivista:
Business and Economics, Business Management, Business Informatics, Process Management, Industrial Chemistry, Cellulose, Paper and Textiles, Polymer Science and Technology, Materials Sciences, Biomaterials and Natural Materials
Feed RSS della rivista