ESTIMATION OF FOLDING AND LUMINANCE VALUES OF POLYPROPYLENE BCF YARNS USING ARTIFICIAL NEURAL NETWORK TECHNIQUE AND MODELING STUDY

摘要

Polypropylene (PP) yarn commonly used in the production of machine carpets in the world is called BCF (Bulk Continuous Filament) and the production process consists of extrusion - cooling -lubrication - gravitation - texturizing - winding - twisting. It is a fact that PP yarn has a disadvantage in terms of softness and brightness compared to acrylic, polyamide and polyester used in the production of machine-made carpets. Twisting is also an effective parameter on the sense of softness that the yarn gives. Therefore, various R&D studies are carried out to determine the effect of production parameters on softness, crimp and brightness values of PP yarn and / or to determine the production parameters required for PP yarn production with the highest values. In this study, it is aimed to develop an artificial neural network (ANN) algorithm which determines the crimp and brightness values of the heat set and freeze PP yarns by changing the BCF production parameters, the reverse engineering approach and the quantitative or categorical values of the production parameters for the yarn end with the target crimp and brightness values.