شماره راهنما :
1151 دكتري
پديد آورنده :
شريف زاده لاري، منصوره
عنوان :
بهبود تخمين پارامترهاي پتروفيزيكي مخازن نفتي با استفاده از تركيب الگوهاي زمين آماري چند نقطه اي و روشهاي هوشمند تشخيص الگو
گرايش تحصيلي :
مخابرات سيستم
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر
صفحه شمار :
شانزده، [133]ص.: مصور، جدول، نمودار
استاد راهنما :
رسول اميرفتاحي، نادر فتحيان پور
توصيفگر ها :
زمين آمار , آمار چند نقطه اي , تطبيق الگو , داده سخت , Filtersim , شبيه سازي
استاد داور :
محمدرضا احمدزاده، مرتضي طبايي
تاريخ ورود اطلاعات :
1396/12/19
رشته تحصيلي :
برق و كامپيوتر
دانشكده :
مهندسي برق و كامپيوتر
كد ايرانداك :
ID1151 دكتري
چكيده انگليسي :
Improving the estimation of reservoir petrophysical parameters using combined application of multiple point geostatistic and intelligent pattern recognition techniques Mansoureh Sharifzadehlari m sharifzadeh@ec iut ac ir Date of Submission 2017 08 30 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree PHD Language FarsiSupervisor Dr Rassoul Amirfattahi and Dr Nader FathianpourAbstractDue to the depletion of natural petroleum resources in one hand and the increasing trend of demandfrom industrial sectors in recent years on the other hand the need for developing new efficient pro cedures for exploration and production of petroleum resources has attracted more research works inrecent years One way to overcome such difficulties is to improve the currently available multiplepoint geostatistical techniques known as MPG or MPS in literature which are capable of simulatingheterogeneous and complicated petroleum reservoirs with non linear structures So far a number ofalgorithms have been developed to implement different types of multiple point methods In currentresearch the advantages and disadvantages of commonly employed MPS algorithms are evaluatedin order to develop new and more efficient MPS algorithms with less pitfalls In this regard we havetried to not only maintain the merits of previous methods but to add more advanced and efficient ca pabilities such as application of pattern recognition and image processing techniques in recoveringpatterns hidden in the training images Such techniques could improve the validity and accuracy ofrealizations produced in the course of simulation procedure Because of the commercially availableand popularity of Zhang s original Filtersim algorithm and its later developments we have focusedour research work on improving Filtersim algorithm throughout current research In the first part ofcurrent thesis we have introduced new adaptive filters derived from inferred training images basedon principal components analysis Such approach has not only reduced the dimension of patternspace to the number of filters in filter score space but could recover more realistic patterns analo gous to the patterns existing in the training images The results showed more consistent simulationsthan those obtained by conventional Filtersim algorithm which uses fixed and predefined gradientfilters Next a newly developed algorithm based on our improved Filtersim called Random Par titioning Algorithm RPA was introduced to reduce both the computing time and improving thecontinuity of the recovered patterns In RPA advantageous aspects of both raster path and ran dom partitioning methods of searching in the simulation procedure simultaneously In the third part
استاد راهنما :
رسول اميرفتاحي، نادر فتحيان پور
استاد داور :
محمدرضا احمدزاده، مرتضي طبايي
