The particle size characteristic (d50, the particle size value corresponding to 50% of the cumulative mass fraction of the sieve analysis curve, μm) of formation sand is a key parameter in sand control design. In order to obtain the vertical distribution profile of particle size, the response relationship between reservoir particle size and logging curve based on a machine learning method is studied. Classical machine learning often lacks a feature extraction process inside the model. Moreover, when a single sampling point is used as the input, the adjacent data association relationship is missing to reflect the horizon information. Considering the geological continuity of reservoirs, using the trend and background information of logging curves, taking the depth adjacent data points as machine learning eigenvalues, a grain size profile prediction method based on multiple sampling points is proposed. A prediction model based on random forest, support vector machine, Xtreme gradient boosting tree and artificial neural networks is constructed and trained. The results show that, compared with the single point mapping model, the prediction accuracy of each model considering the vertical geological continuity of reservoir is higher than that of single point prediction. The five point mapping ANN model (ANN -5) has the best prediction effect, with the highest correlation coefficient 0.819 and the least error measures 9.59 of the testing set. It is proved that multiple sampling points are used as input to implicitly utilize part of the stratum information and effectively improve the prediction accuracy. The influence of feature point density on the accuracy of the model is also studied. The Gaussian kernel density distribution of the feature points of the samples in the two-dimensional input space of the training set and the feature point density of the training set at the sample points of the test set are calculated. It is concluded that the RMSE of the sample points of the test set in the high-density area is generally low. The prediction accuracy of the model will be further improved as the number of training samples increases. AHP is used to determine the weight of each factor affecting the model selection, and fuzzy comprehensive evaluation is used to optimize the machine learning model. According to the optimized model, the grain size profile of the reservoir in adjacent blocks is predicted. The predictions capture well the trend of grain size change and simulate its peak value.

In order to obtain the actual change characteristics of the gas-water relative permeability in coalbed methane (CBM) reservoirs and to further deepen the understanding of the gas-water production process of CBM reservoirs, a relative permeability dynamic calculation method of CBM reservoirs combined with the real-time production situation of the reservoir was constructed. Firstly, the production history match of the target single coal seam or multiple coal seams is carried out using the multiple coal seam whole process coupling flow model, which is to obtain the basic physical parameters of the reservoir and fluid. Then, based on the obtained basic physical parameters, the full production cycle productivity prediction of the CBM well is carried out. At the same time, the reservoir parameters are averaged according to the real-time expansion behavior of the reservoir pressure drop, and the gas-water permeability curve of the CBM reservoir is calculated based on the averaged reservoir parameters and the actual fluid migration. The results show that the relative permeability dynamic calculation method of CBM reservoirs proposed in this paper can dynamically calculate the actual gas-water relative permeability of the CBM reservoir on the basis of real-time quantitative analysis of the internal production situation of the CBM reservoir. There is a reversal point on the gas relative permeability curve calculated by the method proposed in this paper. The reversal point characterizes the stable and continuous supply of desorption gas in CBM reservoirs. If the actual expansion of the CBM reservoir pressure drop is not considered and the reservoir parameters are averaged in the whole area, the calculated gas-water relative permeability of the CBM reservoir will be low. For multiple coal seam reservoirs, the interlayer mass exchange of fluids and the decrease in the reservoir pressure caused by the crossflow cannot be ignored. The ratio of the crossflow of gas to gas production can reach 0.57, and the ratio of the crossflow of water to water production can reach 0.69 after 3 years of production. The calculated gas-water relative permeability of the CBM reservoir under the condition of ignoring the crossflow is low, which is only 42.9% and 24.4% respectively of the calculated gas-water relative permeability under the condition of considering the crossflow. In the actual production process of CBM wells, the water saturation remains at a high value, more than 40%. Restricted by the high water saturation, the gas relative permeability of CBM reservoirs is low, less than 0.2.