Abstract
Fishbone multilateral wells are applied to enhance well productivity by increasing the contact area between the bottomhole and reservoir region. Fishbone wells are characterized by reduced operational time and a competitive cost in comparison to hydraulic fracturing operations. However, limited models are reported to determine the productivity of fishbone wells. In this paper, several artificial intelligence methods were applied to estimate the performance of fishbone wells producing from a heterogeneous and anisotropic gas reservoir. The well productivity was determined using an artificial neural network, a fuzzy logic system and a radial basis network. The models were developed and validated utilizing 250 data sets, with the inputs being the permeability ratio (Kh/Kv), flowing bottomhole pressure and lateral length. The results showed that the artificial intelligence models were able to predict the fishbone well productivity with an acceptable absolute error of 7.23%. Moreover, a mathematical equation was extracted from the artificial neural network, which is able to provide a simple and direct estimation of fishbone well productivity. Actual flow tests were used to evaluate the reliability of the developed model, and a very acceptable match was obtained between the predicted and actual flow rates, wherein an absolute error of 6.92% was achieved. This paper presents effective models for determining the well performance of complex multilateral wells producing from heterogeneous reservoirs. The developed models will help to reduce the uncertainty associated with numerical methods, and the extracted equation can be inserted into commercial software, thereby significantly reducing deviation between the actual data and simulated results.
Highlights
A multilateral well is defined as a well with multiple branches in the lower bore-hole targeting the pay zone in the same layer or different layers
Ahmed et al [6] extended the model proposed by Abdulazeem and Alnuaim in order to predict the performance of fishbone wells producing from gas reservoirs
Several artificial intelligence models were investigated to obtain the model with the lowest average absoSluetveerpaelrcaerntitfaicgiaeleirnrtoerll(iAgeAnPceE)maonddemls awxiemreuminvceosrtrigelaatteidontocooebffitaciinentth(eCmC)odvealluwe.ithAtsheensloitwiveistyt aavnearlaygsies wabassopluetrefoprmerecdenfotargeeacehrrAoIr t(eAchAnPiqEu)eainndormdearxtimo oupmtimcoizreretlhaetiomnodceolepffaicriaemntet(eCrsC. )Evaluaet.inAg stehnesfiitsihvbitoynaenpaelyrfsoisrmwaanscpeeursfoinrgmtehdefoorrigeiancahl AdaIttaecshonwiqeude sinigonrifidcearntot doepvtiamtiioznesthbetmwoeednelthpearparmedeitcetresd
Summary
A multilateral well is defined as a well with multiple branches in the lower bore-hole targeting the pay zone in the same layer or different layers. Ahmed et al [6] extended the model proposed by Abdulazeem and Alnuaim in order to predict the performance of fishbone wells producing from gas reservoirs They reported that their extended model was able to determine the gas production rate for a wide range of reservoir and well parameters. Al-Mashhad et al [16] evaluated the performance of multilateral wells using an artificial neural network (ANN) Their ANN model was able to determine the oil production rate for multilateral wells based on reservoir and well parameters. They compared the developed model with several analytical models and empirical correlations. The ANN-based equation was verified using actual field data, wherein an absolute error of 6.92% was achieved
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
