Application of neural network to the determination of well-test interpretation model for horizontal wells

Well-test model identification and, subsequently, model parameters determination is more complex in horizontal wells as compared to vertical wells. This is due to the increase in number of flow regimes occurring during a flow period and due to the fact that strong correlation exists between model parameters.; This study presents a new approach for automatic model identification and computer-aided well-test interpretation in horizontal wells. The new approach is based on using neural network to (1) identify the well-test interpretation model; (2) identify flow regimes, and (3) mark the position of identified flow regions on the derivative plot of well test data.; This work consists of first generating common model signatures using Ozkan and Ragavan analytical solutions for horizontal well in various reservoir and inner boundary conditions assuming laterally boundless reservoir. Next, these signatures are used to train neural networks for three identification stages, namely, model identification, flow regime identification, and position of flow regime identification. Separate networks were trained, then tested and validated using synthetic as well as field data. Once the three identification stages are completed, specialized plots for data points falling into each flow regime are used to determine initial model parameters. Finally, non-linear regression software was used to determine final model parameters.; A comparative study was carried out using different network architectures and data preparation schemes. Modular approach with direct data utilization is found to be most suitable for field implementation of our approach.