Pore pressure is essential data in drilling design,and its accurate prediction is necessary to ensure drilling safety and improve drilling efficiency.Traditional methods for predicting pore pressure are limited when f...Pore pressure is essential data in drilling design,and its accurate prediction is necessary to ensure drilling safety and improve drilling efficiency.Traditional methods for predicting pore pressure are limited when forming particular structures and lithology.In this paper,a machine learning algorithm and effective stress theorem are used to establish the transformation model between rock physical parameters and pore pressure.This study collects data from three wells.Well 1 had 881 data sets for model training,and Wells 2 and 3 had 538 and 464 data sets for model testing.In this paper,support vector machine(SVM),random forest(RF),extreme gradient boosting(XGB),and multilayer perceptron(MLP)are selected as the machine learning algorithms for pore pressure modeling.In addition,this paper uses the grey wolf optimization(GWO)algorithm,particle swarm optimization(PSO)algorithm,sparrow search algorithm(SSA),and bat algorithm(BA)to establish a hybrid machine learning optimization algorithm,and proposes an improved grey wolf optimization(IGWO)algorithm.The IGWO-MLP model obtained the minimum root mean square error(RMSE)by using the 5-fold cross-validation method for the training data.For the pore pressure data in Well 2 and Well 3,the coefficients of determination(R2)of SVM,RF,XGB,and MLP are 0.9930 and 0.9446,0.9943 and 0.9472,0.9945 and 0.9488,0.9949 and 0.9574.MLP achieves optimal performance on both training and test data,and the MLP model shows a high degree of generalization.It indicates that the IGWO-MLP is an excellent predictor of pore pressure and can be used to predict pore pressure.展开更多
Determining reasonable fracturing stage spacing is the key to horizontal well fracturing.Different from traditional stage spacing optimization methods based on the principle of maximum stimulated reservoir volume,in t...Determining reasonable fracturing stage spacing is the key to horizontal well fracturing.Different from traditional stage spacing optimization methods based on the principle of maximum stimulated reservoir volume,in this paper,by considering the integrity of the wellbore interface,a fracture propagation model was established based on displacement discontinuity method and the competition mechanism of multifracture joint expansion,leading to the proposal of an unequal stage spacing optimization model.The results show that in the first stage,the interfacial fractures spread symmetrically along the axis of the central point during that stage,while in the second and subsequent stages,the interfacial fractures of each cluster extend asymmetrically along the left and right sides.There are two kinds of interface connectivity behaviour:in one,the existing fractures first extend and connect within the stage,and in the other,the fractures first extend in the direction close to the previous stage,with the specific behaviour depending on the combined effect of stress shadow and flow competition during hydraulic fracture expansion.The stage spacing is positively correlated with the number of fractures and Young’s modulus of the cement and formation and is negatively correlated with the cluster spacing and horizontal principal stress difference.The sensitivity is the strongest when the Young’s modulus of the cement sheath is 10-20 GPa,and the sensitivity of the horizontal principal stress difference is the weakest.展开更多
A novel metal-enamel interlocking coating was designed and prepared in situ by co-deposition of Ni-enamel composite layer and subsequent air spray of enamel with 10 wt% nanoscale Ni. During the firing process, the ext...A novel metal-enamel interlocking coating was designed and prepared in situ by co-deposition of Ni-enamel composite layer and subsequent air spray of enamel with 10 wt% nanoscale Ni. During the firing process, the external enamel layer was melted and jointed with the enamel particles at the upper part of the Ni-plating layer to form the enamel pegs. Thermal shock tests of pure enamel, enamel with 10 wt% Ni composite and metal-enamel interlocking coatings were conducted at 600 °C in water and static air. The results indicated that the metal-enamel interlocking showed superior thermal shock resistance to both pure enamel and enamel with 10 wt% Ni composite coatings. The enhanced performance was mainly attributed to the advantageous effects of mechanical interlocking of the enamel pegs formed at the enamel/Ni-plating interface. Meanwhile, during thermal shock test, big clusters formed by nanoscale Ni agglomerations were oxidised to be a Ni/NiO core–shell structure while small single nanoscale Ni grains were oxidised completely, which both improved the thermal shock resistance of enamel coating significantly.展开更多
Photo-induced water oxidation based on first row transition metal complexes has drawn much attention recently as a part of the efforts to design systems for solar fuel production.Here,the classic tetradentate ligand T...Photo-induced water oxidation based on first row transition metal complexes has drawn much attention recently as a part of the efforts to design systems for solar fuel production.Here,the classic tetradentate ligand TPA(tris(2-pyridylmethyl)amine)is used together with cobalt(II)in CH_(3)CN to form a mononuclear cobalt complex[Co(TPA)Cl]Cl.Single crystal X-ray diffraction shows that[Co(TPA)Cl]Cl is composed of discrete cationic units with a penta-coordinate cobalt center,along with chloride counter ions.In borate buffer,the Co complex acts as a water oxidation catalyst,as shown by the presence of a catalytic wave in electrochemistry.Under visible light irra-diation,in the presence of photosensitizer and electron acceptor,the Co complex catalyzes O2 evolution with a turnover frequency(TOF)of 1.0 mol(O_(2))·mol(Co)^(-1)·s^(-1)and a turnover number(TON)of 55 mol(O_(2))·mol(Co)^(-1)in pH 8 borate buffer.展开更多
文摘Pore pressure is essential data in drilling design,and its accurate prediction is necessary to ensure drilling safety and improve drilling efficiency.Traditional methods for predicting pore pressure are limited when forming particular structures and lithology.In this paper,a machine learning algorithm and effective stress theorem are used to establish the transformation model between rock physical parameters and pore pressure.This study collects data from three wells.Well 1 had 881 data sets for model training,and Wells 2 and 3 had 538 and 464 data sets for model testing.In this paper,support vector machine(SVM),random forest(RF),extreme gradient boosting(XGB),and multilayer perceptron(MLP)are selected as the machine learning algorithms for pore pressure modeling.In addition,this paper uses the grey wolf optimization(GWO)algorithm,particle swarm optimization(PSO)algorithm,sparrow search algorithm(SSA),and bat algorithm(BA)to establish a hybrid machine learning optimization algorithm,and proposes an improved grey wolf optimization(IGWO)algorithm.The IGWO-MLP model obtained the minimum root mean square error(RMSE)by using the 5-fold cross-validation method for the training data.For the pore pressure data in Well 2 and Well 3,the coefficients of determination(R2)of SVM,RF,XGB,and MLP are 0.9930 and 0.9446,0.9943 and 0.9472,0.9945 and 0.9488,0.9949 and 0.9574.MLP achieves optimal performance on both training and test data,and the MLP model shows a high degree of generalization.It indicates that the IGWO-MLP is an excellent predictor of pore pressure and can be used to predict pore pressure.
基金This work was supported by the Natural Science Foundation of Heilongjiang Province of China(YQ2021E005)the National Natural Science Foundation of China(No.51774094)+2 种基金the Youth Fund Project of National Natural Science Foundation of China(52004065)the Heilongjiang Natural Science Foundation Project(excellent youth project)(YQ2021E006)"Reveal the top"Science and Technology Project of Heilongjiang Province(2021ZZ10-04).
文摘Determining reasonable fracturing stage spacing is the key to horizontal well fracturing.Different from traditional stage spacing optimization methods based on the principle of maximum stimulated reservoir volume,in this paper,by considering the integrity of the wellbore interface,a fracture propagation model was established based on displacement discontinuity method and the competition mechanism of multifracture joint expansion,leading to the proposal of an unequal stage spacing optimization model.The results show that in the first stage,the interfacial fractures spread symmetrically along the axis of the central point during that stage,while in the second and subsequent stages,the interfacial fractures of each cluster extend asymmetrically along the left and right sides.There are two kinds of interface connectivity behaviour:in one,the existing fractures first extend and connect within the stage,and in the other,the fractures first extend in the direction close to the previous stage,with the specific behaviour depending on the combined effect of stress shadow and flow competition during hydraulic fracture expansion.The stage spacing is positively correlated with the number of fractures and Young’s modulus of the cement and formation and is negatively correlated with the cluster spacing and horizontal principal stress difference.The sensitivity is the strongest when the Young’s modulus of the cement sheath is 10-20 GPa,and the sensitivity of the horizontal principal stress difference is the weakest.
基金financially supported by the Excellent Youth Foundation of Liaoning Province(No.2019-YQ-03)the CNPC Science and Technology Development Project(Nos.2019B4013 and 2019A-3911)+2 种基金the National Key R&D Program of China(Nos.2019YFF0217500 and 2016ZX05022-055)the Science Fund for Distinguished Young Scholars of Shaanxi Provincethe Ministry of Industry and Information Technology Project(No.MJ-2017-J-99)。
文摘A novel metal-enamel interlocking coating was designed and prepared in situ by co-deposition of Ni-enamel composite layer and subsequent air spray of enamel with 10 wt% nanoscale Ni. During the firing process, the external enamel layer was melted and jointed with the enamel particles at the upper part of the Ni-plating layer to form the enamel pegs. Thermal shock tests of pure enamel, enamel with 10 wt% Ni composite and metal-enamel interlocking coatings were conducted at 600 °C in water and static air. The results indicated that the metal-enamel interlocking showed superior thermal shock resistance to both pure enamel and enamel with 10 wt% Ni composite coatings. The enhanced performance was mainly attributed to the advantageous effects of mechanical interlocking of the enamel pegs formed at the enamel/Ni-plating interface. Meanwhile, during thermal shock test, big clusters formed by nanoscale Ni agglomerations were oxidised to be a Ni/NiO core–shell structure while small single nanoscale Ni grains were oxidised completely, which both improved the thermal shock resistance of enamel coating significantly.
基金This work was supported by grants from the Swed-ish Energy Agency and the Knut and Alice Wallenberg Foundation.Mohammad Mirmohades is acknowledged for the excited state lifetime measurement.
文摘Photo-induced water oxidation based on first row transition metal complexes has drawn much attention recently as a part of the efforts to design systems for solar fuel production.Here,the classic tetradentate ligand TPA(tris(2-pyridylmethyl)amine)is used together with cobalt(II)in CH_(3)CN to form a mononuclear cobalt complex[Co(TPA)Cl]Cl.Single crystal X-ray diffraction shows that[Co(TPA)Cl]Cl is composed of discrete cationic units with a penta-coordinate cobalt center,along with chloride counter ions.In borate buffer,the Co complex acts as a water oxidation catalyst,as shown by the presence of a catalytic wave in electrochemistry.Under visible light irra-diation,in the presence of photosensitizer and electron acceptor,the Co complex catalyzes O2 evolution with a turnover frequency(TOF)of 1.0 mol(O_(2))·mol(Co)^(-1)·s^(-1)and a turnover number(TON)of 55 mol(O_(2))·mol(Co)^(-1)in pH 8 borate buffer.
