پديد آورنده :
سوراني، منصور
عنوان :
آناليز رياضي داده ها، مدل سازي و ارزيابي تاثير متغيرهاي عملياتي واحد تبديل كاتاليستي پالايشگاه اصفهان بر عملكرد و محصولات آن
مقطع تحصيلي :
كارشناسي ارشد
گرايش تحصيلي :
مهندسي شيمي
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده مهندسي شيمي
صفحه شمار :
دوازده،89ص.: مصور،جدول،نمودار
يادداشت :
ص.ع.به فارسي و انگليسي
استاد راهنما :
ارجمند مهرباني
توصيفگر ها :
شبكه عصبي , بهينه سازي , الگوريتم ژنتيك
تاريخ نمايه سازي :
1/9/93
استاد داور :
محسن نصراصفهاني،محسن دوازده امامي
چكيده انگليسي :
Mathematical Analysis of Data Modeling and Evaluation of Operational Condition of Catalytic Reforming of Isfahan Refinery on Its Operation and Products Mansour Sourani mansour sourani@ce iut ac ir Date of Submission 2014 9 15 Department of Chemical Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language FarsiSupervisor Arjomand Mehrabani arjomand@cc iut ac irAbstract In this thesis a mathematical model based on artificial neural network for catalyticreformer unit I of Isfahan oil refinery was made This model is able to projection the unitoutlet factors included production rate and associated octane number and also LPGproductivity and gas feed ratio based on 15 inlet factors included feed rate and other feed scharacteristics catalyst life time weight average bed temperature and etc Number of 819industrial data were used for education validation and examination of different neuralnetworks and ultimately based on maximum correlation coefficient and minimum residualerror a cascade four layer network consisting 15 neurons in first layer 10 neurons in 2ndlayer 7 neurons in 3rd layer and 4 neurons in last layer was selected The neurons transferfunctions in all layers were tan sigmoid and Levenberg Marquardt algorithm was used forartificial neural network education Overall correlation coefficient for real data andselected neural network outputs is equal to 0 96942 and maximum residual error forprediction of process performance in one working period is equal to 1 2912 unit Thereforean objective function for maximizing the difference between economical values added ofunit normal condition and optimum condition was defined Using the model and geneticcondition and optimum condition was 6 7972 104 $ which means using the results thealgorithm the amount of chlorine and water in recycle gas WABT and feed rate wereoptimized The average difference between economical value added of unit normalperformance of unit can be improved Keywords Catalytic reforming unit Modeling neural network Optimizing Genetic algorithm
استاد راهنما :
ارجمند مهرباني
استاد داور :
محسن نصراصفهاني،محسن دوازده امامي
