پديد آورنده :
ودود، مرتضي
عنوان :
پيش بيني و بهينه سازي فرآيند توليد خشك ريسي الياف اكريليك با استفاده از شبكه عصبي و الگوريتم ژنتيك
مقطع تحصيلي :
كارشناسي ارشد
گرايش تحصيلي :
تكنولوژي نساجي
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده نساجي
صفحه شمار :
دوازده، 113ص: مصور، جدول، نمودار
يادداشت :
ص.ع: به فارسي و انگليسي
استاد راهنما :
داريوش سمناني
تاريخ نمايه سازي :
21/11/88
استاد داور :
فريد شيخ الاسلام، مصطفي يوسفي
چكيده فارسي :
به فارسي و انگليسي: قابل رويت در نسخه ديجيتال
چكيده انگليسي :
Prediction and Optimization of the Acrylic Dry Spinning Production Process by Using Neural Network and Genetic Algorithm Morteza Vadood m vadood@tx iut ac ir Department of Textile engineering Isfahan University of Technology Isfahan 84156 83111 Iran Supervisors D SemnaniAbstractAcrylic fibers are major part of synthetic fibers Its special characteristics are unique so thatmany researchers have been attracted to them Process optimization and control of fibershave direct impact on the cost of energy and time Produce more with less cost and highquality is a problem that manufacturing factories face it Nature of the process is usually verycomplex and includes many parameters During the past few years some researchers haveused multi objective functions to optimize processes such as polymerization but it needssomebody with high experience and skillful because in some cases there is need to userdecision toward applied variables in functions Recently computer methods such as geneticalgorithms GA and neural networks ANN for optimizing and forecasting the behavior ofchemical processes are used and the results have been remarkable There is no comprehensive research about the optimization of acrylic fiber production in dry spinning method using computer algorithms Therefore this study has tried to use the abovementioned methods To predict the behavior of dry spinning process many parameters such as temperature ofextruder in the head and around solution viscosity water percent the amount of formic acidsolution and remaining time of solution in the reactor have been measured Regarding tocolor index of manufacturing fiber as an indicator of production quality and using statisticalmethods the affecting parameters on the process have been determined After that an ANNwas designed to predict the color index Then the parameters of ANN have been optimizedusing GA and GA itself has been optimized by tryial and error method Finally an ANN withhigh accuracy to predict dry spinning process was designed Key Words Optimization Artificial neural network Genetic algorithm Acrylic dry spinning
استاد راهنما :
داريوش سمناني
استاد داور :
فريد شيخ الاسلام، مصطفي يوسفي
