Semester
Fall
Date of Graduation
2009
Document Type
Thesis
Degree Type
MS
College
Statler College of Engineering and Mineral Resources
Department
Petroleum and Natural Gas Engineering
Committee Chair
Shahab D Mohaghegh
Abstract
A new framework is presented that uses production data history in order to build a field-wide performance prediction model. In this work artificial intelligence techniques and data driven modeling are utilized to perform a future production prediction for both synthetic and real field cases.;Production history is paired with geological information from the field to build large dataset containing the spatio-temporal dependencies amongst different wells. These spatio-temporal dependencies are addressed by information from Closest Offset Wells (COWs). This information includes geological characteristics (Spatial) and dynamic production data (Temporal) of all COWs.;Upon creation of the dataset, this framework calls for development of a series of single layer neural network, trained by back propagation algorithm. These networks are then fused together to form the "Intelligent Time-Successive Production Modeling" (ITSPM). Using only well log information along with production history of existing wells, this technique can provide performance predictions for new wells and initial hydrocarbon in place (IHIP) using a "volumetric-geostatical" method.;A synthetic oil reservoir is built and simulated using a commercial reservoir numerical simulation package. Production and well log data are extracted and converted to an all-inclusive dataset. Following the dataset generation several neural networks are trained and verified to predict different stages of production. ITSPM method is utilized to estimate the production profile for nine new wells in the reservoir. ITSPM is also applied to data from a real field. The field that is giant oil field in the Middle East includes more than 200 wells with forty years of production history. ITSPM's production predictions of the four newest wells in this reservoir are compared to real production data.
Recommended Citation
Khazaeni, Yasaman, "Intelligent time-successive production modeling" (2009). Graduate Theses, Dissertations, and Problem Reports. 4485.
https://researchrepository.wvu.edu/etd/4485