Interpretation and characterization of rate of penetration intelligent prediction model

Accurate prediction of the rate of penetration(ROP)is significant for drilling optimization.While the intelligent ROP prediction model based on fully connected neural networks(FNN)outperforms traditional ROP equations and machine learning algorithms,its lack of interpretability undermines its credibility.This study proposes a novel interpretation and characterization method for the FNN ROP prediction model using the Rectified Linear Unit(ReLU)activation function.By leveraging the derivative of the ReLU function,the FNN function calculation process is transformed into vector operations.The FNN model is linearly characterized through further simplification,enabling its interpretation and analysis.The proposed method is applied in ROP prediction scenarios using drilling data from three vertical wells in the Tarim Oilfield.The results demonstrate that the FNN ROP prediction model with ReLU as the activation function performs exceptionally well.The relative activation frequency curve of hidden layer neurons aids in analyzing the overfitting of the FNN ROP model and determining drilling data similarity.In the well sections with similar drilling data,averaging the weight parameters enables linear characterization of the FNN ROP prediction model,leading to the establishment of a corresponding linear representation equation.Furthermore,the quantitative analysis of each feature's influence on ROP facilitates the proposal of drilling parameter optimization schemes for the current well section.The established linear characterization equation exhibits high precision,strong stability,and adaptability through the application and validation across multiple well sections.

Settling behavior of spherical particles in eccentric annulus filled with viscous inelastic fluid

Hole cleaning is a complex process as there are many variables affecting cuttings removal(e.g.drilling fluid type,density,flow rate and rheological properties,cuttings size,drill pipe rotation speed).With the increasing number of drilling small diameter wells(e.g.coiled tubing drilling applications,ultra-deep wells drilled for exploitations of unconventional oil and gas resources),the wall resistance of the micro annulus also emerges as one of the most critical factors affecting the cuttings accumulation in wellbore.The eccentricity of drill pipes commonly observed during the drilling process of ultra-deep well and coiled tubing well makes the wall resistance effect on the cuttings transport even more prominent.Understanding the wall resistance effect on the particle settling behavior in eccentric annuli is,therefore,crucial for hydraulic design of efficient cuttings transport operations in these wells.In this study,a total of 196 sets of particle settling experiments were carried out to investigate the particle settling behavior in eccentric annuli filled with power-law fluids.The test matrix included the eccentricity ranges of 0-0.80,the dimensionless diameter ranges of 0.13-0.75 and the particle Reynolds number ranges of 0.09-32.34.A high-speed camera was used to record the particle settling process and determine the influences of the eccentricity,the dimensionless diameter,the fluid rheological properties,and the solid particle characteristics on the wall factor and the particle settling velocity.The functional relationship among the dimensionless diameter,the particle Reynolds number,and the wall factor was determined by using the method of controlling variables.An eccentric annulus wall factor model with average relative error of 5.16%was established.Moreover,by introducing Archimedes number,an explicit model of particle settling velocity in the eccentric annulus with average relative error of 10.17%was established.A sample calculation of particle settling velocity was provided to show the application of the explicit model.Results of this study can be used as a guideline by field engineers to improve hydraulic design of cuttings transport operations in concentric and eccentric annuli.

Transport feasibility of proppant by supercritical carbon dioxide fracturing in reservoir fractures

The pure supercritical carbon dioxide（SC-CO2） fracturing prevents the clay from swelling and avoids the water lock as compared with the slick-water fracturing. The CO2 molecule could replace the CH4 adsorbed in organic matter and tiny particles on the clay mineral surface in the formation. This leads to an increased cumulative gas production rate. The SC-CO2 fracturing is an alternative waterless fracturing technique for an effective future development of shale gas reservoirs. Due to its low density and viscosity as compared with the slick-water, it attracts attentions for the proppant transport. In this paper, the two phase flow of the SC-CO2 and the proppant in fractures during the SC-CO2 fracturing is analyzed with the computational fluid dynamics method. The characteristics of the proppant transport by the SC-CO2 fracturing and the slick-water fracturing are compared. Moreover, a sensitivity analysis is also performed to see the influence of various parameters on the proppant transport ability of the SC-CO2 fracturing. It is shown that the proppants in the SC-CO2 and the slick-water have similar distribution characteristics. Reducing the proppant density, the proppant diameter, and the solid volume fraction as well as increasing the injection rate can all have similar filling effects on the fractures. The feasibility of the proppant transport by the SC-CO2 fracturing in fractures is revealed and a guidance is provided for the SC-CO2 fracturing design.