5809

5424

كارشناسي ارشد

تكنولوژي نساجي

اصفهان: دانشگاه صنعتي اصفهان، دانشكده نساجي

1389

نه،97ص.: مصور،جدول،نمودار

ص.ع.به فارسي و انگليسي

داريوش سمناني، محمدشيخ زاده

3/2/90

محمد قانع، عبدالكريم حسيني

مهندسي نساجي

ID5424

به فارسي و انگليسي: قابل رويت در نسخه ديجيتالي

98 Optimization of hybrid yarns properties Ayntrmyngl Made Artificial Intelligence Mehdi soleymani dorcheh dorcheh@gmail com Data of Submission 17 07 2010 Department of Textile Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language FarsiSuperviser Dariush Semnani d semnani@cc iut ac irMohammad Sheikhzadeh m sh110@cc iut ac irAbstractEach yarn in the textile industry have common characteristics related to gender andthe conditions they are produced and combined them with special characteristics and can be optimized tocreate In this project several samples of different yarn polyester viscose and cotton material with different countsby Intermingling jet are mixed together and then some physical characteristics and quality of yarn producedis measured Properties measured in this study include cv Thin Thick Nep hair and physical propertiesincluding strength and elongation are Then with the sample dataAnd using Perceptron neural network algorithm backward error yarns of different properties have beenpredicted First of all the software Excel data obtained were classified according to the seven parameters andthe physical quality and the above mentioned has been drawn in separate graphs and the detailed results arediscussed In case of genetic algorithm for different mutation crossover selection and other cases there were other some interesting results and some results away from mental introduced in this project that causes theaccuracy or inaccuracy of any of them and the best modes were introduced More to obtain the best yarn produced from above characteristics has been helping of the genetic algorithm This property has a genetic algorithm that can integrate the various data given to the prediction that someyarn so far have not been produced This work and the different modes in the genetic algorithm there aredifferent types of state proposed by the genetic algorithm to investigate the reasons and predictive accuracyor inaccuracy is expressed It seems that the best prediction of cotton yarn filament by the hybrid system with count of 7 and thenpolyester viscose yarn hybrid count is 17 Key Words Hybrid yarns genetic algorithm Artificial Intelligence

داريوش سمناني، محمدشيخ زاده

محمد قانع، عبدالكريم حسيني