Optimum location of surface wells for remote pressure relief coalbed methane drainage in mining areas

Based on engineering tests in the Huainan coal mining area,we studied alternative well location to improve the performance of surface wells for remote pressure relief of coalbed methane in mining areas.The key factors,affecting location and well gas production were analyzed by simulation tests for similar material.The exploitation results indicate that wells located in various positions on panels could achieve relatively better gas production in regions with thin Cenozoic layers,low mining heights and slow rate of longwall advancement,but their periods of gas production lasted less than 230 days,as opposed to wells in regions with thick Cenozoic layers,greater mining heights and fast rates of longwall advancement.Wells near panel margins achieved relatively better gas production and lasted longer than centerline wells.The rules of development of mining fractures in strata over panels control gas production of surface wells.Mining fractures located in areas determined by lines of compaction and the effect of mining are well developed and can be maintained for long periods of time.Placing the well at the end of panels and on the updip return airway side of panels,determined by lines of compaction and the effect of mining,would result in surface wells for remote pressure relief CBM obtaining their longest gas production periods and highest cumulative gas production.

Production Dynamic Prediction Method of Waterflooding Reservoir Based on Deep Convolution Generative Adversarial Network(DC-GAN)

The rapid production dynamic prediction of water-flooding reservoirs based on well location deployment has been the basis of production optimization of water-flooding reservoirs.Considering that the construction of geological models with traditional numerical simulation software is complicated,the computational efficiency of the simulation calculation is often low,and the numerical simulation tools need to be repeated iteratively in the process of model optimization,machine learning methods have been used for fast reservoir simulation.However,traditional artificial neural network(ANN)has large degrees of freedom,slow convergence speed,and complex network model.This paper aims to predict the production performance of water flooding reservoirs based on a deep convolutional generative adversarial network(DC-GAN)model,and establish a dynamic mapping relationship between well location deployment and output oil saturation.The network structure is based on an improved U-Net framework.Through a deep convolutional network and deconvolution network,the features of input well deployment images are extracted,and the stability of the adversarial model is strengthened.The training speed and accuracy of the proxy model are improved,and the oil saturation of water flooding reservoirs is dynamically predicted.The results show that the trained DC-GAN has significant advantages in predicting oil saturation by the well-location employment map.The cosine similarity between the oil saturation map given by the trained DC-GAN and the oil saturation map generated by the numerical simulator is compared.In above,DC-GAN is an effective method to conduct a proxy model to quickly predict the production performance of water flooding reservoirs.

A compositional function hybridization of PSO and GWO for solving well placement optimisation problem

Advances in technology and optimisation are helping to improve decision making in the oil and gas industry.However,most of the traditional metaheuristic algorithms applied in well placement optimisation problems suffer from extensive parameter experimentations and local optimum trapping issues.This couples with the complex and heterogeneous nature of hydrocarbon reservoirs and increased decision variables poses severe simulation process demands.This study considered a functional composition integration approach to formulate a robust hybrid metaheuristic algorithm called HGWO-PSO.The HGWO-PSO leverages on the strengths of Grey Wolf Optimiser(GWO)and Particle Swarm Optimisation(PSO)and the Clerc's parameter setting considerations.A rigorous approach which enforces regulatory agreed minimum well spacing was incorporated in the optimisation process.Reservoir models ranging from unimodal to multimodal spatial systems were used as examples to test the explorative and exploitative capabilities of the algorithms.In this paper we show the performance curve and statistical analysis of HGWO-PSO as a well placement algorithm and compares its performance with that of standalone PSO,and GWO and the traditional Genetic Algorithm(GA).Results revealed that the HGWO-PSO demonstrated comparative performances in terms of exploration and exploitation obtaining the best optimal solutions which give highest contractor's NPVs in majority of cases considered.Again,the means and standard deviations for HGWO-PSO among the various runs showed consistent and efficient performance.The Wilcoxon signed rank test conducted gave very low p-values suggesting uniqueness of HGWO-PSO from the other metaheuristic variants.Additionally,the computational speed of HGWO-PSO was relatively better as compared to the individual GWO and PSO in most the test cases.The simulation results for all test cases confirm that implementation of HGWO-PSO can cause considerable improvement in locations of wells even in heterogeneous reservoirs.