پديد آورنده :
بهشتي، اسماعيل
عنوان :
بررسي عيوب ابعادي در نورد ورق و بهينه سازي آن با استفاده از شبكه عصبي و الگوريتم هاي فرا ابتكاري
مقطع تحصيلي :
كارشناسي ارشد
گرايش تحصيلي :
طراحي كاربردي
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده مهندسي مكانيك
صفحه شمار :
چهارده، 136ص.: مصور، جدول، نمودار
استاد راهنما :
محمود سليمي
استاد مشاور :
محمود فرزين
توصيفگر ها :
نورد گرم , كنترل تختي ورق , پارامترهاي بهينه خط نورد
تاريخ نمايه سازي :
94/06/23
استاد داور :
مهدي سلماني تهراني، رضا جعفري ندوشن
تاريخ ورود اطلاعات :
1396/10/04
چكيده فارسي :
به فارسي و انگليسي
چكيده انگليسي :
146 Investigations on Dimensional Defects in Strip Rolling and Optimization of Process using Neural Network and Metaheuristic Algorithms Esmaeil Beheshti e beheshti@me iut ac ir Date of Submission 2015 07 25 Department of Mechanical Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language FarsiSupervisor Mahmoud Salimi Salimi@cc iut ac irAbstractManufacturing of high quality metal plates for various industries such as the automotive aerospace appliance and food packaging both in terms of mechanical and physicalproperties has always been a very important issue From the consumer point of view flatness is one of the most important parameter that has a great impact on final productquality Improving the quality of the plate is costly and therefore from the technical pointof view finding the optimal setting rolling parameters to minimize the number of operationand hence the manufacturing cost is an important issue In this thesis the impact of threemost effective parameters on flatness of rolled plate namely reduction work roll bendingand work roll crown were evaluated For this purpose the cost function was created usingrolling mill data slit beam method SMB and artificial neural network ANN Therequired data for SBM is obtained from the computer logs of Mobarakeh Steel Company MSC The optimum structure of ANN is determined by setting the number of neurons inthe hidden layer and learning algorithm Cost function is optimized by differentmetaheuristic algorithms such as genetic algorithm GA particle swarm optimization PSO differential evolution DE and co evolutionary particle swarm optimization CPSO Firstly reductions and weighted sum of flatness in sequential stands wereconsidered as input variables and output of cost function The required data for neuralnetwork training provided by SBM code The cost function derived from the neural networkis optimized by the mentioned metaheuristic algorithms Finally the appropriateoptimization algorithm is chosen by comparison between the results obtained from differentmetaheuristic algorithms and the cost function is optimized for different strip widths Sincethe desired flatness was not achieved for wide strip by considering the reductions as onlyinput variables of cost function work roll crown and work roll bending were alsoconsidered as input variables of cost function to achieve appropriate flatness Finally asignificant improvement in flatness is resulted by optimizing the reduction work roll crownand work roll bending in each stand Keywords Strip flatness Artificial neural network ANN Genetic algorithm GA Particleswarm optimization Differential Evolution DE Hot rolling
استاد راهنما :
محمود سليمي
استاد مشاور :
محمود فرزين
استاد داور :
مهدي سلماني تهراني، رضا جعفري ندوشن
