作者: Mohammad Ali Ahmadi , Sohrab Zendehboudi , Maurice B. Dusseault , Ioannis Chatzis
DOI: 10.1016/J.PETLM.2015.07.008
关键词: Relative permeability 、 Particle swarm optimization 、 Experimental data 、 Petroleum engineering 、 Artificial neural network 、 Petroleum 、 Mathematical optimization 、 Genetic algorithm 、 Engineering 、 Simple (abstract algebra) 、 Hybrid approach
摘要: Abstract In the current research, a new approach constructed based on artificial intelligence concept is introduced to determine water/oil relative permeability at various conditions. To attain an effective tool, approaches such as neural network (ANN), hybrid of genetic algorithm and particle swarm optimization (HGAPSO) are examined. Intrinsic potential feed-forward (ANN) optimized by different algorithms composed estimate permeability. The methods algorithm, them implemented obtain optimal connection weights involved in developed smart technique. intelligent models evaluated utilizing extensive experimental data reported open literature. Results obtained from proposed tools were compared with corresponding data. average absolute deviation between model predictions relevant was found be less than 0.1% for It expected that implication HGAPSO-ANN estimation leads more reliable predictions, resulting design comprehensive simulation further plans reservoir production management.