Shale Gas Reservoir Development Strategies Using Complex Specified Bottom-hole Pressure Well Architectures

摘要

The principal objective of this article is to develop artificial expert systems capable of instantaneously and accurately predicting the performance of complex wells, proposing complex well designs and predicting average reservoir properties for shale gas wells operating under specified bottom-hole pressure (BHP). Artificial neural networks (ANNs) provide the backbone of an expert system. Other methods, such as traditional well testing, numerical reservoir simulation and decline curve analysis, have inherent limitations or require significant time and effort to get results. The ANN methodology has the ability to recognize patterns among various parameters in the presence of large databases. It is a powerful tool, especially when the existing relationships between the dependent and independent parameters are vague or are not well understood, as it is capable of instantly solving problems that do not have known analytical or numerical solutions. Complex wells are scarce in shale gas reservoirs, so utilizing real data in ANN training is not possible most of the time. Accordingly, numerical reservoir simulation is used to generate the database necessary for training the expert systems.