Simulation of the Pressure-Sensitive Seepage Fracture Network in Oil Reservoirs with Multi-Group Fractures

Stress sensitivity is a very important index to understand the seepage characteristics of a reservoir.In this study,dedicated experiments and theoretical arguments based on the visualization of porous media are used to assess the effects of the fracture angle,spacing,and relevant elastic parameters on the principal value of the permeability tensor.The fracture apertures at different angles show different change rates,which influence the relative permeability for different sets of fractures.Furthermore,under the same pressure condition,the fractures with different angles show different degrees of deformation so that the principal value direction of permeability rotates.This phenomenon leads to a variation in the water seepage direction in typical water-injection applications,thereby hindering the expected exploitation effect of the original well network.Overall,the research findings in this paper can be used as guidance to improve the effectiveness of water injection exploitation in the oil field industry.

Numerical Simulation of Liquid-Solid Coupling in Multi-Angle Fractures in Pressure-Sensitive Reservoirs

This study clarifies the seepage characteristics of complex fractured pressure-sensitive reservoirs,and addresses a common technological problem,that is the alteration of the permeability degree of the reservoir bed(known to be responsible for changes in the direction and velocity of fluid flows between wells).On the basis of a new pressuresensitive equation that considers the fracture directional pressure-sensitive effect,an oil-gas-water three-phase seepage mathematical model is introduced,which can be applied to pressure-sensitive,full-tensor permeability,ultralow-permeability reservoirs with fracture-induced anisotropy.Accordingly,numerical simulations are conducted to explore the seepage laws for ultralow-permeability reservoirs.The results show that element patterns have the highest recovery percentage under a fracture angle of 45°.Accounting for the pressure-sensitive effect produces a decrease in the recovery percentage.Several patterns are considered:inverted five-seven-and nine-spot patterns and a cross-row well pattern.Finally,two strategies are introduced to counteract the rotation of the direction of the principal permeability due to the fracture directional pressure-sensitive effect.

Deep-Learning-Based Production Decline Curve Analysis in the Gas Reservoir through Sequence Learning Models

Production performance prediction of tight gas reservoirs is crucial to the estimation of ultimate recovery,which has an important impact on gas field development planning and economic evaluation.Owing to the model’s simplicity,the decline curve analysis method has been widely used to predict production performance.The advancement of deep-learning methods provides an intelligent way of analyzing production performance in tight gas reservoirs.In this paper,a sequence learning method to improve the accuracy and efficiency of tight gas production forecasting is proposed.The sequence learning methods used in production performance analysis herein include the recurrent neural network(RNN),long short-term memory(LSTM)neural network,and gated recurrent unit(GRU)neural network,and their performance in the tight gas reservoir production prediction is investigated and compared.To further improve the performance of the sequence learning method,the hyperparameters in the sequence learning methods are optimized through a particle swarm optimization algorithm,which can greatly simplify the optimization process of the neural network model in an automated manner.Results show that the optimized GRU and RNN models have more compact neural network structures than the LSTM model and that the GRU is more efficiently trained.The predictive performance of LSTM and GRU is similar,and both are better than the RNN and the decline curve analysis model and thus can be used to predict tight gas production.