CN108509694B - Proppant paving form prediction method based on BP neural network - Google Patents
Proppant paving form prediction method based on BP neural network Download PDFInfo
- Publication number
- CN108509694B CN108509694B CN201810205015.XA CN201810205015A CN108509694B CN 108509694 B CN108509694 B CN 108509694B CN 201810205015 A CN201810205015 A CN 201810205015A CN 108509694 B CN108509694 B CN 108509694B
- Authority
- CN
- China
- Prior art keywords
- proppant
- neural network
- laying form
- parameters
- sand
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 21
- 239000004576 sand Substances 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000010276 construction Methods 0.000 claims abstract description 15
- 239000002245 particle Substances 0.000 claims abstract description 15
- 239000003795 chemical substances by application Substances 0.000 claims abstract description 9
- 238000013507 mapping Methods 0.000 claims abstract description 9
- 238000004088 simulation Methods 0.000 claims abstract description 9
- 238000007689 inspection Methods 0.000 claims abstract description 5
- 238000012360 testing method Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- 210000002569 neuron Anatomy 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 2
- 238000013508 migration Methods 0.000 description 4
- 230000005012 migration Effects 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 239000012530 fluid Substances 0.000 description 3
- 239000007788 liquid Substances 0.000 description 3
- 238000003756 stirring Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B43/00—Methods or apparatus for obtaining oil, gas, water, soluble or meltable materials or a slurry of minerals from wells
- E21B43/25—Methods for stimulating production
- E21B43/26—Methods for stimulating production by forming crevices or fractures
- E21B43/267—Methods for stimulating production by forming crevices or fractures reinforcing fractures by propping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Geology (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Environmental & Geological Engineering (AREA)
- Computer Hardware Design (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Fluid Mechanics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A proppant laying form prediction method based on a BP neural network comprises the following steps: selecting sand ratio, proppant particle size, proppant density and construction discharge capacity as main factors influencing the laying form of the proppant, and selecting balance height, balance time and sand bank front edge distance as main parameters for describing the laying form of the proppant; simulating the laying form of the propping agent in the crack under different parameters by using a crack simulation experiment device; collecting and collating experimental data and dividing the experimental data into training samples and inspection samples; setting parameters of a BP neural network, and establishing a nonlinear mapping relation from sand ratio, proppant particle size, proppant density, construction discharge capacity to balance height, balance time and sand bank leading edge distance; training and checking the neural network; predicting the new sample proppant placement morphology; the method realizes the prediction of the laying form of the propping agent by utilizing the strong learning capability of the BP neural network, has simple and convenient operation and is convenient for the field application of the oil field.
Description
Technical Field
The invention relates to the field of petroleum engineering, in particular to a proppant laying form prediction method based on a BP neural network, which is used for predicting the laying form of a proppant in a fracture in a fracturing process and provides a basis for selection of a proppant and construction parameters in an oil field.
Technical Field
Due to the fact that the conventional oil and gas resources cannot meet the social requirements in recent years, development of unconventional reservoirs is increasingly deepened. The hydraulic fracturing technology has become a very effective means for developing unconventional reservoir oil and gas resources, however, in order to form sand-filled fractures with high conductivity in a reservoir, a proppant must be effectively filled in the fractures, so that the research on the migration rule and the laying form of the proppant in the fractures is particularly important. The research on the laying form of the proppant in the fracture mainly focuses on simulating the settling and migration process of the proppant by utilizing a fracture simulation experiment device; however, the proppant is not only influenced by the type of the proppant but also influenced by construction parameters and other factors in the migration process, so that a mathematical expression conforming to the actual settling and migration rule of the proppant on site is difficult to establish, and the prediction of the laying form of the proppant in the fracture is greatly limited.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a proppant paving form prediction method based on a BP neural network, which can predict the proppant paving form and perform weight analysis by using a trained neural network so as to obtain the weight of main factors influencing the proppant paving form, provide scientific and practical weight basis for further establishing a proppant evaluation model, and avoid experimental investment and complex mathematical operation.
In order to overcome the defects of the prior art, the technical scheme of the invention is as follows:
a proppant laying form prediction method based on a BP neural network comprises the following steps:
the method comprises the following steps: selecting sand ratio, proppant particle size, proppant density and construction discharge capacity as main parameters influencing the laying form of the proppant, and selecting balance height, balance time and sand bank front edge distance as main parameters describing the laying form of the proppant;
step two: simulating the laying form of the propping agent in the fracture with different parameters by using a fracturing fluid loss parallel plate fracture simulation device, collecting and collating experimental data, and dividing the experimental result into two groups, wherein one group is used as a training sample and the other group is used as an inspection sample;
step three: selecting main parameters influencing the laying form of the proppant as an input layer of a BP (back propagation) neural network, setting parameters of the neural network, and inputting a training sample into the neural network for training so as to establish a nonlinear mapping relation from the input layer to the output layer, wherein the parameters describing the laying form of the proppant are the output layer of the BP neural network;
step four: after the BP neural network is trained, inputting a test sample into the trained neural network to obtain a prediction result, calling MATLAB program corrcoef to compare and judge between a numerical matrix of the prediction result and a true value matrix of the test sample, if the similarity is more than 0.9, the model is valid, and if the similarity does not meet the requirement, the neural network parameters and the number of hidden nodes are reset until the precision requirement is met;
step five: and inputting the values of the sand ratio of the new sample, the particle size of the proppant, the density of the proppant and the construction discharge capacity into a neural network model to predict the laying form of the proppant.
The concrete method of the third step is as follows:
adopting three layers of BP neural networks, wherein an input layer comprises four neuron nodes of sand ratio, proppant particle size, proppant density and construction discharge capacity; the output layer comprises three neuron nodes of balance height, balance time and sand bank leading edge distance, and the initial value of the number of hidden nodes is set to be any integer within 3 to 12, so that the nonlinear mapping relation from the input layer to the output layer is established.
The expressed neural network adopts no less than 20 groups of experimental data, a training function is selected as a self-adaptive Ir gradient descent method with a learning rate of no more than 0.05 and an error of no more than one percent, the iteration step length is 5000, and the network is trained.
The invention has the beneficial effects that: the method selects sand ratio, proppant particle size, proppant density and construction discharge capacity as main parameters influencing the laying form of the proppant, selects balance height, balance time and sand bank front edge distance as main parameters describing the laying form of the proppant, utilizes a parallel plate fracture simulation experiment device to simulate the laying form of the proppant under different parameters, arranges experimental data into training samples and detection samples, establishes a BP neural network model and sets network parameters, trains and adjusts the network so as to establish an optimal nonlinear mapping relation from the sand ratio, the proppant particle size, the proppant density, the construction discharge capacity to the balance height, the balance time and the sand bank front edge distance.
Drawings
FIG. 1 is a diagram of the BP neural network structure of the present invention.
Detailed Description
The technical solution of the present invention is further specifically described below by way of examples, but the present invention is not limited to the examples described below.
The method comprises the following steps: the sand ratio, the particle size of the proppant, the density of the proppant and the construction discharge capacity are selected as main parameters influencing the laying form of the proppant, and the balance height, the balance time and the front edge distance of the sand bank are selected as main parameters describing the laying form of the proppant.
Before the experiment begins, the slickwater fracturing fluid with the viscosity of 1 mPa.s is selected as experimental parameters, the sand ratio comprises six of 0.02, 0.03, 0.04, 0.05, 0.06 and 0.08, the particle size of the propping agent comprises six of 0.21mm, 0.32mm, 0.45mm, 0.64mm and four, and the density of the propping agent comprises 1450kg/m3、1540kg/m3、1890kg/m3、2600kg/m3、2770kg/m3、2880kg/m3、3020kg/m3Seven kinds of the construction displacement comprises 4m3/h、5m3/h、6m3/h、7m3/h、8m3Five,/h, different combinations of these parameters were used for the design experiments.
Step two: the parallel plate fracture simulation device for fracturing fluid loss is used for simulating the laying form of the propping agent in the fracture under different parameters, collecting and arranging experimental data, and dividing experimental results into two groups, wherein one group is used as a training sample, and the other group is used as an inspection sample.
The device is connected with an experimental pipeline well and used for checking the tightness of a pipeline valve and the device under the name of 'a parallel plate fracture simulation device for fracturing fluid loss' with the patent number of 201420450355.6; adding fracturing fluid into the liquid storage tank, and starting a stirring pump to start stirring; according to the sand ratio, the particle size of the proppant and the density of the proppant determined by the design of the experimental scheme, weighing a certain amount of the proppant, slowly adding the proppant into a liquid storage tank, and continuously stirring to mix the proppant with the fracturing fluid; and (2) opening a data acquisition system, starting a screw pump, gradually increasing the discharge capacity of the pump to the designed discharge capacity, ensuring that the flow rate of the sand-carrying liquid is stable, stopping the pump after the proppant accumulation height reaches the balance height, recording three parameter values of the balance height, the balance time and the front edge distance of the sand bank to obtain the experimental data shown in the table 1, taking the first 20 groups of the experimental data as training samples, and taking the last 5 groups of the experimental data as inspection samples.
Step three: selecting main parameters influencing the laying form of the proppant as an input layer of a BP (back propagation) neural network, setting parameters of the neural network, and inputting a training sample into the neural network for training so as to establish a nonlinear mapping relation from the input layer to the output layer, wherein the parameters describing the laying form of the proppant are the output layer of the BP neural network;
establishing a BP neural network, selecting sand ratio, proppant particle size, proppant density and discharge capacity as input layer neurons of the neural network, selecting balance height, balance time and sand bank leading edge distance as output layer neurons of the neural network, setting a transfer function from an output layer to a hidden layer as an S-type tangent function, setting a training function as an adaptive lr gradient descent method, thereby establishing a nonlinear mapping relation from the input layer to the output layer, wherein the nonlinear mapping relation is detailed as shown in FIG. 1,
step four: after the BP neural network is trained, inputting a test sample into the trained neural network to obtain a prediction result, calling an MATLAB program to carry out normalization processing on input layer data and output layer data of the training sample, calling an MATLAB neural network tool kit program package to establish a network, setting the initial value of the number of hidden nodes to be any integer value within 3 to 12, setting the learning rate to be 0.05, setting the error to be 0.01 and setting the iteration step length to be 5000; and calling MATLAB program corrcoef to compare and judge the numerical matrix of the prediction result with the true value matrix of the test sample, if the similarity is more than 0.9, the model is effective, and if the similarity does not meet the requirement, the neural network parameters and the number of hidden layer nodes are reset until the precision requirement is met.
And training the established neural network by using the training sample data subjected to normalization processing until the error iteration is terminated.
In order to test and improve the precision of the neural network, an MATLAB program is utilized to carry out normalization processing on input layer data of a test sample and input the data into the neural network, the obtained result is subjected to reverse normalization processing to obtain a predicted value, the similarity between a predicted value matrix and a truth value matrix of the test sample is compared, the number of hidden nodes is adjusted, the highest similarity is found when the number of hidden nodes is 7, the neural network is optimal, and the specific numerical value comparison is shown in a table 2.
Step five: inputting the values of the sand ratio of the new sample, the particle size of the proppant, the density of the proppant and the construction discharge capacity into a neural network model to predict the laying form of the proppant; the laying form of the new sample proppant under different discharge capacities can be predicted by utilizing the established BP neural network, a simulation experiment is not needed in the process, the investment of manpower and financial resources is greatly saved, and the method is simple, effective and convenient to popularize.
Table 1 proppant placement simulation experiment result data table
TABLE 2 BP neural network truth and predicted value comparison table
The above description is only a partial description of the preferred embodiments of the present invention, and any person skilled in the art may modify the above technical solutions. Therefore, any simple modifications or equivalent substitutions made according to the technical solution of the present invention belong to the scope of the claims of the present invention.
Claims (3)
1. A proppant laying form prediction method based on a BP neural network is characterized by comprising the following steps:
the method comprises the following steps: selecting sand ratio, proppant particle size, proppant density and construction discharge capacity as parameters influencing the laying form of the proppant, and selecting balance height, balance time and sand bank front edge distance as parameters describing the laying form of the proppant;
step two: simulating the laying form of the propping agent in the fracture with different parameters by using a fracturing fluid loss parallel plate fracture simulation device, collecting and collating experimental data, and dividing the experimental result into two groups, wherein one group is used as a training sample and the other group is used as an inspection sample;
step three: selecting parameters influencing the laying form of the propping agent as an input layer of a BP (back propagation) neural network, setting parameters of the neural network, describing the laying form of the propping agent as an output layer of the BP neural network, inputting a training sample into the neural network for training, and establishing a nonlinear mapping relation from the input layer to the output layer;
step four: after the BP neural network is trained, inputting a test sample into the trained neural network to obtain a prediction result, calling MATLAB program corrcoef to compare and judge between a numerical matrix of the prediction result and a true value matrix of the test sample, if the similarity is more than 0.9, the model is valid, and if the similarity does not meet the requirement, the neural network parameters and the number of hidden nodes are reset until the precision requirement is met;
step five: and inputting the values of the sand ratio of the new sample, the particle size of the proppant, the density of the proppant and the construction discharge capacity into a neural network model to predict the laying form of the proppant.
2. The method for predicting the proppant placement form based on the BP neural network as set forth in claim 1, wherein the concrete method of the third step is as follows:
adopting three layers of BP neural networks, wherein an input layer comprises four neuron nodes of sand ratio, proppant particle size, proppant density and construction discharge capacity; the output layer comprises three neuron nodes of a balance height, a balance time and a sand bank front edge distance, and the initial value of the number of hidden nodes is set to be any integer within 3 to 12, so that a nonlinear mapping relation from the input layer to the output layer is established.
3. The method for predicting the proppant placement form based on the BP neural network as set forth in claim 1 or 2, wherein the neural network is trained by selecting the training function as an adaptive Ir gradient descent method with an iteration step size of 5000 and using not less than 20 sets of experimental data and a learning rate of not more than 0.05 and an error of not more than one percent.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810205015.XA CN108509694B (en) | 2018-03-13 | 2018-03-13 | Proppant paving form prediction method based on BP neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810205015.XA CN108509694B (en) | 2018-03-13 | 2018-03-13 | Proppant paving form prediction method based on BP neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108509694A CN108509694A (en) | 2018-09-07 |
CN108509694B true CN108509694B (en) | 2022-02-18 |
Family
ID=63376548
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810205015.XA Active CN108509694B (en) | 2018-03-13 | 2018-03-13 | Proppant paving form prediction method based on BP neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108509694B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109063403B (en) * | 2018-10-22 | 2022-09-13 | 西安石油大学 | Optimal design method for slickwater fracturing |
CN110965977B (en) * | 2019-11-20 | 2021-01-08 | 中国石油大学(北京) | Fracturing construction analysis method |
CN111622730B (en) * | 2020-05-29 | 2022-04-01 | 中国石油大学(华东) | Fracturing sand adding design method based on large-scale parallel plate proppant migration and placement model experiment |
CN112761609B (en) * | 2021-02-19 | 2022-02-01 | 西南石油大学 | Optimization method for efficient laying of propping agent in hydraulic fracturing operation |
CN113095398B (en) * | 2021-04-08 | 2022-07-12 | 西南石油大学 | Fracturing data cleaning method of BP neural network based on genetic algorithm optimization |
CN115199238B (en) * | 2022-09-15 | 2022-11-25 | 四川省贝特石油技术有限公司 | Method and system for controlling feeding of superfine temporary plugging agent for gas reservoir exploitation |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008080093A2 (en) * | 2006-12-21 | 2008-07-03 | Verenium Corporation | Amylases and glucoamylases, nucleic acids encoding them and methods for making and using them |
CN106703773A (en) * | 2015-08-03 | 2017-05-24 | 中国矿业大学 | Liquid carbon dioxide bomb, propping agent blasting anti-reflection method and device |
CN107194068A (en) * | 2017-05-22 | 2017-09-22 | 中国石油大学(北京) | Shale gas fracturing process underground unusual service condition real-time estimate method for early warning and device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10012748B2 (en) * | 2013-07-31 | 2018-07-03 | Schlumberger Technology Corporation | Resource production forecasting |
-
2018
- 2018-03-13 CN CN201810205015.XA patent/CN108509694B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008080093A2 (en) * | 2006-12-21 | 2008-07-03 | Verenium Corporation | Amylases and glucoamylases, nucleic acids encoding them and methods for making and using them |
CN106703773A (en) * | 2015-08-03 | 2017-05-24 | 中国矿业大学 | Liquid carbon dioxide bomb, propping agent blasting anti-reflection method and device |
CN107194068A (en) * | 2017-05-22 | 2017-09-22 | 中国石油大学(北京) | Shale gas fracturing process underground unusual service condition real-time estimate method for early warning and device |
Non-Patent Citations (4)
Title |
---|
Research for Unsteady Seepage Flow of Asymmetrical Fractured Vertical Wells in Coalbed;Ming Li等;《2017 2nd International Conference on New Energy and Renewable Resources 》;20171231;第261-275页 * |
The applications of BP neural network based on MIV in hydraulic fracturing;Su Yujie等;《Advanced Materials Research》;20141231;第300-305页 * |
滑溜水压裂主裂缝内支撑剂输送规律实验及数值模拟;周德胜等;《石油钻采工艺》;20170720(第04期);第113-122页 * |
考虑壁面影响的矩形裂缝通道中的颗粒沉降;唐伏平等;《排灌机械工程学报》;20141228(第12期);第68-72页 * |
Also Published As
Publication number | Publication date |
---|---|
CN108509694A (en) | 2018-09-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108509694B (en) | Proppant paving form prediction method based on BP neural network | |
CN110334431B (en) | Single-well control reserve calculation and residual gas analysis method for low-permeability tight gas reservoir | |
CN104453876B (en) | Method and device for predicting oil and gas yield of compact oil and gas reservoir horizontal well | |
CN109815516A (en) | The method and device that shale gas well deliverability is predicted | |
CN114595608B (en) | Fracturing construction parameter and working system parameter optimization method and system | |
CN111062129A (en) | Shale oil complex seam network discrete fracture continuous medium mixed numerical simulation method | |
CN109711595A (en) | A kind of hydraulic fracturing operation effect evaluation method based on machine learning | |
CN109063403B (en) | Optimal design method for slickwater fracturing | |
CN112539054A (en) | Production optimization method for ground pipe network and underground oil reservoir complex system | |
CN109598482A (en) | Coal mine gas drainage design platform and its method of servicing based on network model | |
CN110489844B (en) | Prediction method suitable for uneven large deformation grade of soft rock tunnel | |
CN110924935B (en) | Method, device and equipment for determining bottom hole flowing pressure regulation and control scheme of tight oil reservoir | |
Huang et al. | A new calculation approach of heterogeneous fractal dimensions in complex hydraulic fractures and its application | |
Ren et al. | Shale gas effective fracture network volume prediction and analysis based on flow back data: A case study of southern Sichuan Basin shale | |
CN113723706B (en) | Shale gas well repeated fracturing productivity prediction method, device, terminal and storage medium | |
CN115713036A (en) | Method for predicting blowout stop time of flowing well and method for optimizing size of oil nozzle | |
CN112084637B (en) | Automatic searching method, device and equipment for fracturing high-dimensional parameters | |
RU2745684C1 (en) | Method of maintaining a safe range of fracture conductivity when putting a well with hydraulic fracturing into operation | |
CN106802986A (en) | CO being taken turns a kind of viscous crude bottom and edge water more2Handle up evaluation method | |
CN115099062A (en) | Design method for energy storage fracturing process parameters of tight oil reservoir | |
CN113887067A (en) | Compact low-permeability reservoir fracturing well pattern gas flooding effect prediction method based on LSTM | |
Liu et al. | Process of EUR prediction for shale gas wells based on production decline models—a case study on the Changning block | |
Mirzaei-Paiaman et al. | Optimization of design variables and control rules in field development under uncertainty: A case of intelligent wells and CO2 water alternating gas injection | |
CN114580136A (en) | Rationality identification method for oil reservoir development policy in extra-high water cut period | |
CN112943215A (en) | Method for selecting horizontal well from water direction by monitoring and judging oil reservoir pressure response |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |