The productivity of coalbed methane (CBM) depends heavily on the heat environment, and directly reflects the quality of the well. Following the theories of phase space reconstruction and Bayesian evidence framework, this paper puts forward a Bayes-least squares-support vector machine (Bayes-LS-SVM) model for the prediction of energy-efficient productivity of CBM under Bayesian evidence network based on chaotic time series. The energy-efficient productivity stands for the gas and water production of CBM wells at a low energy consumption, despite the disturbance from the heat environment. The proposed model avoids the local optimum trap of backpropagation neural network (BPNN), and overcomes the main defects of the SVM: high time consumption of parameter determination, and proneness to overfitting. In our model, the model parameters are optimized through three-layer Bayesian evidence inference, and the input vector for prediction is selected adaptively. In this way, the model construction is not too empirical, and the constructed model is highly adaptive. Then, the theory on phase space reconstruction was applied to investigate the chaotic property of the time series on CBM production, and the Bayes-LS-SVM was adopted to predict the time series after phase space reconstruction, in comparison with neural network prediction methods like SVM and BPNN. Experimental results show that the proposed model boast quick computing, accurate fitting, flexible structure, and strong generalization ability.

No abstract

The finite volume method (FVM) can adapt to complex boundaries, achieve conservation of integrals, and generate flexible integral grids. Compared with the finite difference method (FDM), the FVM is immune to numerical oscillations and numerical dispersions. This paper aims to simulate the coalbed methane (CBM)-water two-phase flow in complex coal rock, and predict the CBM and water outputs in an accurate manner. Therefore, the FVM was introduced to create a simulation model of coalbed methane (CBM) productivity in 3D dual-porosity coal reservoir under non-equilibrium adsorption and pseudo-steady state conditions. The established model was applied to an actual project in Qinshui Basin, Shanxi Province, China. The historical gas and water outputs of a single CBM well were fitted with our model, and the simulated curves agree with the overall trend of the historical drainage and production curves. Next, the change trends of gas and water outputs in the CBM well were predicted, and the sensitivities of gas well productivity to three main reservoir parameters were analyzed. The results correctly reflect the productivity trend of the CBM well, indicating the correctness and feasibility of our model. Our research effectively simulates the migration of the CBM in coal rock with complex boundaries, providing a valuable reference for the development of the CBM.