Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 2015

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: KES

Sortuj według:

Ogranicz wyniki do:

Use of Artificial Neural Networks for Modelling the Drape Behaviour of Woollen Fabrics Treated with Dry Finishing Processes

Kursun B. S., Kalaoğlu F., Jevšnik S., Eryuruk S. H., Saricam C.

Fibres & Textiles in Eastern Europe

2015

Vol. 23, no. 2 (110)

90--99

The relationship between fabric drape, low stress mechanical properties and finishing processes is relatively complex. This paper demonstrates the possibility of using artificial neural networks to identify the fabric drape of woollen fabrics treated with different dry finishing processes (stenter, decatising, superfinish, formula, KADE strong/weak - autoclave decatizing). The mechanical and surface properties of woollen fabrics were measured by both the KES-FB and FAST systems, and then the results obtained were applied to artiicial neural network (ANN) modelling. ANN models were compared by verifying the Mean Square Error (MSE) and Correlation coefficient (R-value). The results indicated that each model is capable of making quantitatively accurate drape behaviour predictions for wool fabrics (Rmin = 0.92, MSEmin = 0).

Związek pomiędzy układalnością tkaniny, właściwościami mechanicznymi przy niskich naprężeniach a procesami wykańczalniczymi jest stosunkowo skomplikowany. Artykuł ten wskazuje na możliwość wykorzystania sztucznych sieci neuronowych do identyfikacji układalności tkanin wełnianych poddanych procesom suchego wykańczania. Właściwości mechaniczne i powierzchniowe wełnianych tkanin zmierzono za pomocą KES-FB i FAST, a następnie otrzymane wyniki wprowadzono do sztucznej sieci neuronowej (ANN). Modele ANN porównano przez weryfikację blędu średniokwadratowego i współczynnika korelacji. Wyniki wykazały, że każdy model może być wykorzystany do utworzenia ilościowo dokładnych prognoz układalności dla tkanin wełnianych.

Human-Friendly Design of Virtual System “female body-dress”

Guo M., Kuzmichev V. E., Adolphe D. C.

Autex Research Journal

2015

Vol. 15, no. 1

19--29

Recently, the development efforts focused on the computer simulation of garments, which depend on the material's physico-mechanical properties. It intends to achieve the best possible and realistic simulations of garments, which are available for pressure prediction. In this manner, 3D garment virtual technology improvements allow the visualization of pressure areas with values where the fabric might be too tight against the body. Although the purposes of simulation graphics were acceptable, the accuracy for apparel shaping is not enough to meet the needs of Virtual Prototyping and CAD utilization especially while the fabric properties system design was inadequate. Moreover, the existing pressure simulation is intended to simply predict the pressure index or how the textile deformation extend, which are deficient in real human's perception. In this research, the 3D shapes belonging to typical female bodies and dresses made of different fabrics were obtained by 3D body scanners (ScanWorX and TELMAT). Through reconstruction for the 3D torso shapes, the volumetric eases between body and dress were calculated by means of a software Rhinoceros. A new approach for the selection of textile properties based on the Kawabata Evaluation System (KES) was proposed to investigate its relations with dress shaping and pressure comfort. Finally, fabric properties tested by the KES-F system were compared with volumetric eases, objective pressure indexes and subjective comfort scores to reveal the relations how the fabric properties have impacts on dress outside shaping and inside pressure comfort of a female body. In this manner, the human-friendly CAD instead of mechanical approach existing before has been presented as a new approach to promote the construction of a realistic system for the 3D simulation optimization.