Deterministic tools to predict gas assisted gravity drainage recovery factor

Naturally fractured rocks contain most of the world's petroleum reserves.This significant amount of oil can be recovered efficiently by gas assisted gravity drainage(GAGD).Although,GAGD is known as one of the most effective recovery methods in reservoir engineering,the lack of available simulation and mathematical models is considerable in these kinds of reservoirs.The main goal of this study is to provide efficient and accurate methods for predicting the GAGD recovery factor using data driven techniques.The proposed models are developed to relate GAGD recovery factor to the various parameters including model height,matrix porosity and permeability,fracture porosity and permeability,dip angle,viscosity and density of wet and non-wet phases,injection rate,and production time.In this investigation,by considering the effective parameters on GAGD recovery factor,three different efficient,smart,and fast models including artificial neural network(ANN),least square support vector machine(LSSVM),and multi-gene genetic programming(MGGP)are developed and compared in both fractured and homogenous porous media.Buckinghamπtheorem is also used to generate dimensionless numbers to reduce the number of input and output parameters.The efficiency of the proposed models is examined through statistical analysis of R-squared,RMSE,MSE,ARE,and AARE.Moreover,the performance of the generated MGGP correlation is compared to the traditional models.Results demonstrate that the ANN model predicts the GAGD recovery factor more accurately than the LSSVM and MGGP models.The maximum R^(2)of 0.9677 and minimum RMSE of 0.0520 values are obtained by the ANN model.Although the MGGP model has the lowest performance among the other used models(the R2 of 0.896 and the RMSE of 0.0846),the proposed MGGP correlation can predict the GAGD recovery factor in fractured and homogenous reservoirs with high accuracy and reliability compared to the traditional models.Results reveal that the employed models can easily predict GAGD recovery factor without requiring complicate governing equations or running complex and time-consuming simulation models.The approach of this research work improves our understanding about the most significant parameters on GAGD recovery and helps to optimize the stages of the process,and make appropriate economic decisions.

Hot bend assisted gas forming of AA5083 sheet for making V-shaped trough containing deep uneven concavities

Employing low pressurized gas for shaping superplastic metal sheets into complex contours has long been adopted in the aero/auto industries and it is commonly recognized as superplastic forming （SPF）. The most undesired feature of SPF would be an uneven thickness distribution in the final formed part. However, there are techniques that lessen this disadvantage. Low pressurized gas was used to make a V-shaped trough containing deep uneven concavities using superplastic AA5083. The auxiliary yet influential procedure of mechanically hot bending the flat sheet into a V-shape precedes the gas-forming process. In this first quick hot-bending operation, buckling will occur if the depth of bending exceeds a certain level. The degree of buckling and associated contours will affect the thickness distribution as well as the wrinkling location in the gas-formed product. A better thickness distribution is obtainable at the cost of wrinkle formation. Wrinkling can be purposely arranged to achieve better uniform thickness distribution, but it needs to be located outside the trim line of the gas-formed semi-product. Therefore, it is critical to manipulate the hot bending procedure to yield a suitable pre-form allowing a successful sequential gas-forming process.

Simulation and experiment investigations on fabrication of Fe-based amorphous powders by a novel atomization process equipped with assisted gas nozzles

Based on computational fluid dynamics method,the effect of atomization gas pressure on the atomization efficiency of Laval nozzle was studied,and then a discrete phase model was established and combined with industrial trials to study the effect of a new type of assisted gas nozzles(AGNs)on powder size distribution and amorphous powder yield.The results show that increasing the atomization pressure can effectively improve the gas velocity for the Laval nozzle;however,it will decrease the aspiration pressure,and the optimal atomization pressure is 2.0 MPa.Compared with this,after the application of AGNs with the inlet velocity of 200 m s^(-1),assisted gas jet can increase the velocity of overall droplets in the break-up and solidification area by 40 m s^(-1) and the maximum cooling rate is increased from 1.9×10^(4) to 2.3×10^(4) K s^(-1).The predicted particle behavior is demonstrated by the industrial trails,that is,after the application of AGNs,the median diameter of powders d50 is decreased from 28.42 to 25.56 lm,the sphericity is increased from 0.874 to 0.927,the fraction of amorphous powders is increased from 90.4% to 99.4%,and only the coercivity is increased slightly due to the accumulation of internal stress.It is illustrated that the AGNs can improve the yield of fine amorphous powders,which is beneficial to providing high-performance raw powders for additive manufacturing technology.