CN116070545A - Processing method and device for stratum fluid sampling parameters and computing equipment - Google Patents
Processing method and device for stratum fluid sampling parameters and computing equipment Download PDFInfo
- Publication number
- CN116070545A CN116070545A CN202310101625.6A CN202310101625A CN116070545A CN 116070545 A CN116070545 A CN 116070545A CN 202310101625 A CN202310101625 A CN 202310101625A CN 116070545 A CN116070545 A CN 116070545A
- Authority
- CN
- China
- Prior art keywords
- pumping
- target
- parameters
- sampling
- fluid
- 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.)
- Pending
Links
- 239000012530 fluid Substances 0.000 title claims abstract description 208
- 238000005070 sampling Methods 0.000 title claims abstract description 137
- 238000003672 processing method Methods 0.000 title abstract description 10
- 238000005086 pumping Methods 0.000 claims abstract description 286
- 238000000034 method Methods 0.000 claims abstract description 144
- 239000000523 sample Substances 0.000 claims abstract description 139
- 239000000706 filtrate Substances 0.000 claims abstract description 93
- 238000005553 drilling Methods 0.000 claims abstract description 92
- 238000004088 simulation Methods 0.000 claims abstract description 89
- 230000008569 process Effects 0.000 claims abstract description 87
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 82
- 238000004140 cleaning Methods 0.000 claims abstract description 79
- 238000012545 processing Methods 0.000 claims abstract description 52
- 230000008859 change Effects 0.000 claims abstract description 35
- 238000011109 contamination Methods 0.000 claims description 20
- 238000010586 diagram Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 5
- 230000000875 corresponding effect Effects 0.000 description 52
- 239000003921 oil Substances 0.000 description 45
- 230000006870 function Effects 0.000 description 18
- 238000004422 calculation algorithm Methods 0.000 description 17
- 238000013528 artificial neural network Methods 0.000 description 13
- 239000010410 layer Substances 0.000 description 11
- 210000002569 neuron Anatomy 0.000 description 11
- 230000035699 permeability Effects 0.000 description 7
- 238000012546 transfer Methods 0.000 description 7
- 230000009545 invasion Effects 0.000 description 6
- 238000009530 blood pressure measurement Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000007906 compression Methods 0.000 description 3
- 230000006835 compression Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000009977 dual effect Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 239000011435 rock Substances 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 239000010779 crude oil Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000012065 filter cake Substances 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 230000033001 locomotion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 239000000341 volatile oil Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- 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
- E21B49/00—Testing the nature of borehole walls; Formation testing; Methods or apparatus for obtaining samples of soil or well fluids, specially adapted to earth drilling or wells
- E21B49/08—Obtaining fluid samples or testing fluids, in boreholes or wells
-
- 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
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mining & Mineral Resources (AREA)
- Entrepreneurship & Innovation (AREA)
- Geology (AREA)
- Economics (AREA)
- Fluid Mechanics (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Algebra (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Educational Administration (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Environmental & Geological Engineering (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Sampling And Sample Adjustment (AREA)
Abstract
The application discloses a processing method, a processing device and a computing device for stratum fluid sampling parameters, wherein the processing method comprises the following steps: acquiring logging data and adjacent well data of a target measuring point; according to logging data and adjacent well data, obtaining stratum fluid parameters of a target measuring point; inputting each stratum fluid parameter into a pre-trained prediction model corresponding to each probe for processing to obtain a simulation result of each pumping cleaning process; the simulation result of the pumping cleaning process comprises change information of the pollution rate of the filtrate of the drilling fluid; and comparing simulation results of all the pumping cleaning processes, and determining target sampling parameters according to the comparison results. By the method, the operation parameters during formation fluid sampling can be rapidly acquired, so that an optimal working system during formation fluid sampling can be formulated, the operation risk can be reduced, and the operation time and cost can be saved.
Description
Technical Field
The application relates to the technical field of oilfield exploration, in particular to a processing method, a processing device and computing equipment for stratum fluid sampling parameters.
Background
In oil field exploration and production, formation fluid composition is the most interesting problem for oil field workers, and the most intuitive method is to use a cable formation pressure measurement sampling instrument or a formation pressure measurement sampling instrument while drilling, lower the instrument to a specified depth underground and obtain a sample. However, during drilling, water-based or oil-based drilling fluids continually percolate into the formation due to the permeability of the formation and the over-balanced pressure during drilling, and if the drilling fluid invades the formation too much, the drilling fluid filtrate and undisturbed formation fluids dissolve into each other, causing serious contamination of the formation. Thus, predicting the sampling timing of undisturbed formation fluid while drilling presents a significant challenge.
The acquisition of undisturbed formation fluid samples is largely dependent on the determination of the degree of contamination during the well logging process. When the undisturbed formation fluid is extracted, the drilling fluid filtrate is firstly extracted, then the mixture of the drilling fluid filtrate and the undisturbed formation fluid is mixed, and the percentage of the undisturbed formation fluid content in the formation fluid sample can be extracted to a satisfactory degree only after the extraction time is long enough. However, pumping is time consuming and it is not always possible to pump, otherwise there is a significant loss in time and economy, and it is therefore particularly important to predict the timing of sampling of undisturbed formation fluid.
In the prior art, the sampling time, the probe type, the pumping parameters and the like when the formation fluid is sampled are judged according to the experience of an operation engineer and an interpretation engineer, and the judgment method is simple and rough, has low accuracy and cannot essentially solve the field problem.
Disclosure of Invention
In view of the foregoing, the present application has been developed to provide a method, apparatus, and computing device for processing formation fluid sampling parameters that overcome, or at least partially solve, the foregoing problems.
According to one aspect of the present application, there is provided a method of processing formation fluid sampling parameters, the method comprising:
acquiring logging data and adjacent well data of a target measuring point;
according to logging data and adjacent well data, obtaining stratum fluid parameters of a target measuring point;
inputting each stratum fluid parameter into a pre-trained prediction model corresponding to each probe for processing to obtain a simulation result of each pumping cleaning process;
the simulation result of the pumping cleaning process comprises change information of the pollution rate of the filtrate of the drilling fluid;
and comparing simulation results of all the pumping cleaning processes, and determining target sampling parameters according to the comparison results.
Optionally, the change information of the drilling fluid filtrate pollution rate includes: and the change information of the pollution rate of drilling fluid filtrate along with the pumping time, the pumping volume, the pumping pressure drop and the pumping speed.
Optionally, comparing the simulation results of each pump cleaning process, and determining the target sampling parameter according to the comparison result further includes:
for any pumping cleaning process simulation result, acquiring pumping time and/or pumping volume required by achieving a target drilling fluid filtrate pollution rate under specified pumping parameters;
comparing pumping time and/or pumping volume required by reaching the target drilling fluid filtrate pollution rate under the designated pumping parameters corresponding to the simulation results of each pumping cleaning process, and determining target sampling parameters according to the comparison results; wherein the target sampling parameters include: target pump time, target probe type, and target pump parameters.
Optionally, comparing the pumping time required for reaching the target drilling fluid filtrate pollution rate under the designated pumping parameters corresponding to the simulation results of each pumping cleaning process, and determining the target sampling parameters according to the comparison results further comprises:
the shortest pumping time is determined as the target pumping time, the pumping parameter corresponding to the shortest pumping time is determined as the target pumping parameter, and the type of probe corresponding to the shortest pumping time is determined as the target probe type.
Optionally, the method further comprises:
For each probe, constructing a plurality of black oil model pumping sampling cases according to the sampling value range of each stratum fluid parameter;
performing numerical simulation processing according to the pumping sampling cases of the black oil models to obtain simulation results of the pumping cleaning processes of the samples;
and constructing sample data according to the pumping sampling cases of the black oil models and the simulation results of the pumping cleaning processes of the samples, and training to obtain a prediction model corresponding to the probe.
Optionally, performing numerical simulation processing according to the plurality of black oil model pumping sampling cases to obtain a plurality of sample pumping cleaning process simulation results further includes:
establishing a grid diagram corresponding to the stratum and the probe;
distributing stratum fluid parameters contained in any black oil model pumping sampling case to each grid in the grid chart;
solving a mass conservation equation under a multiphase multicomponent system aiming at each grid, and analyzing a solving result to obtain a sample pump cleaning process simulation result.
Optionally, inputting each formation fluid parameter into a pre-trained predictive model corresponding to each probe for processing further comprises:
determining a target model type according to the predicted demand information of the user;
And respectively inputting each stratum fluid parameter into a prediction model of the target model type corresponding to each probe for processing.
According to another aspect of the present application, there is provided a treatment apparatus for formation fluid sampling parameters, the apparatus comprising:
the first acquisition module is suitable for acquiring logging data and adjacent well data of the target measuring point;
the second acquisition module is suitable for acquiring stratum fluid parameters of the target measuring point according to the logging information and the adjacent well information;
the processing module is suitable for inputting the stratum fluid parameters into the pre-trained prediction models corresponding to the probes respectively for processing to obtain the simulation results of the pumping cleaning process;
the simulation result of the pumping cleaning process comprises change information of the pollution rate of the filtrate of the drilling fluid;
and the decision module is suitable for comparing simulation results of all the pumping cleaning processes and determining target sampling parameters according to the comparison results.
Optionally, the change information of the drilling fluid filtrate pollution rate includes: and the change information of the pollution rate of drilling fluid filtrate along with the pumping time, the pumping volume, the pumping pressure drop and the pumping speed.
Optionally, the decision module is further adapted to:
for any pumping cleaning process simulation result, acquiring pumping time and/or pumping volume required by achieving a target drilling fluid filtrate pollution rate under specified pumping parameters;
Comparing pumping time and/or pumping volume required by reaching the target drilling fluid filtrate pollution rate under the designated pumping parameters corresponding to the simulation results of each pumping cleaning process, and determining target sampling parameters according to the comparison results; wherein the target sampling parameters include: target pump time, target probe type, and target pump parameters.
Optionally, the decision module is further adapted to:
the shortest pumping time is determined as the target pumping time, the pumping parameter corresponding to the shortest pumping time is determined as the target pumping parameter, and the type of probe corresponding to the shortest pumping time is determined as the target probe type.
Optionally, the apparatus further comprises:
the numerical simulation module is suitable for constructing a plurality of pumping sampling cases of the black oil model according to the sampling value range of each stratum fluid parameter aiming at each probe; performing numerical simulation processing according to the pumping sampling cases of the black oil models to obtain simulation results of the pumping cleaning processes of the samples;
and the model training module is suitable for constructing sample data according to the pumping sampling cases of the black oil models and the simulation results of the pumping cleaning processes of the samples and performing training treatment to obtain a prediction model corresponding to the probe.
Optionally, the numerical simulation module is further adapted to: establishing a grid diagram corresponding to the stratum and the probe; distributing stratum fluid parameters contained in any black oil model pumping sampling case to each grid in the grid chart; solving a mass conservation equation under a multiphase multicomponent system aiming at each grid, and analyzing a solving result to obtain a sample pump cleaning process simulation result.
Optionally, the processing module is further adapted to: determining a target model type according to the predicted demand information of the user; and respectively inputting each stratum fluid parameter into a prediction model of the target model type corresponding to each probe for processing.
According to yet another aspect of the present application, there is provided a computing device comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the processing method of the stratum fluid sampling parameter.
According to yet another aspect of the present application, there is provided a computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the method of processing formation fluid sampling parameters as described above.
According to the processing method, the processing device and the computing equipment of the stratum fluid sampling parameters, logging data and adjacent well data of a target measuring point are obtained; according to logging data and adjacent well data, obtaining stratum fluid parameters of a target measuring point; inputting each stratum fluid parameter into a pre-trained prediction model corresponding to each probe for processing to obtain a simulation result of each pumping cleaning process; the simulation result of the pumping cleaning process comprises change information of the pollution rate of the filtrate of the drilling fluid; and comparing simulation results of all the pumping cleaning processes, and determining target sampling parameters according to the comparison results. By the method, the operation parameters during formation fluid sampling can be rapidly obtained, the optimal operation system during formation fluid sampling is formulated, the operation risk can be reduced, and the operation time and cost can be saved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 illustrates a flow chart of a method of processing formation fluid sampling parameters provided by embodiments of the present application;
FIG. 2 illustrates a flow chart of a method of processing formation fluid sampling parameters provided in accordance with another embodiment of the present application;
fig. 3 shows a schematic view of a pump cleaning process;
FIG. 4 shows a schematic diagram of random parameters in an embodiment of the present application;
FIG. 5 is a schematic diagram showing simulation results of a plurality of black oil models in an embodiment of the present application;
FIG. 6 shows a schematic diagram of various probes in an embodiment of the present application;
FIG. 7 shows a schematic diagram of an artificial neuron in an embodiment of the present application;
FIG. 8 shows a schematic diagram of a neural network in an embodiment of the present application;
FIG. 9a shows a schematic diagram of the operation of a cable formation manometry sampling apparatus;
FIG. 9b shows a schematic of the operation of the sampling while drilling instrument;
FIG. 10 illustrates a flow chart of a method of processing formation fluid sampling parameters in an embodiment of the present application;
FIG. 11 is a schematic diagram of a treatment apparatus for formation fluid sampling parameters according to an embodiment of the present application;
fig. 12 shows a schematic structural diagram of a computing device according to an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
FIG. 1 shows a flow chart of a method of processing formation fluid sampling parameters provided by an embodiment of the present application, the method being applied to any device having computing power. As shown in fig. 1, the method comprises the steps of:
step S101, logging data and adjacent well data of a target measuring point are obtained.
And selecting the target measuring point position, and acquiring logging data and adjacent well data of the target measuring point position.
Step S102, each stratum fluid parameter of the target measuring point is obtained according to the logging data and the adjacent well data.
Analyzing logging data and adjacent well data to obtain relevant stratum fluid parameters of a target measuring point, wherein the method specifically comprises the following steps: reservoir thickness, porosity, permeability (horizontal and vertical), anisotropy, well diameter, drilling fluid filtrate invasion depth, formation pressure, temperature, relative position of the probe in the reservoir, compressibility of the reservoir rock, compressibility of the formation fluid, compressibility of the filtrate, viscosity of the formation fluid, viscosity of the filtrate, density of the formation fluid, density of the filtrate, and the like.
And step S103, inputting the stratum fluid parameters into a pre-trained prediction model corresponding to each probe for processing, and obtaining the simulation result of each pumping cleaning process.
In the embodiment of the application, the prediction models corresponding to the various probes are obtained in advance through sample data training, the stratum fluid parameters are respectively input into the prediction models corresponding to the probes for processing, and the prediction models output the corresponding simulation results of the pumping cleaning process.
Wherein the pumping cleaning process simulation results include: and the change information of the pollution rate of the drilling fluid filtrate, such as the change relation of the pollution rate of the drilling fluid filtrate with the factors of pumping time, pumping volume, pumping speed, pumping pressure drop and the like.
And step S104, comparing simulation results of all the pumping cleaning processes, and determining target sampling parameters according to the comparison results.
Wherein the target sampling parameter is used to characterize the working regime of the fluid sampling. The pumping speed of the sampling instrument can be changed within a certain range, for example, the pumping speed of the cable stratum pressure measuring sampling instrument (EFDT) ranges from 0 cc/s to 15cc/s, the probes arranged on the sampling instrument are also selected differently, and the pumping cleaning process effect is different when different probes and pumping speeds are adopted, so that the pumping speed and the probes with the best pumping cleaning effect can be selected as target sampling parameters according to the comparison result.
And comparing output results of the prediction models corresponding to the probes, and selecting an optimal working system according to the comparison results. Because the pressure of the shaft is greater than the pressure of the oil reservoir during drilling, the filtrate of the drilling fluid can continuously invade the oil reservoir during the formation of a filter cake, so that the fluid of the oil reservoir is polluted, and the filtrate is required to be pumped and cleaned for pollution during fluid sampling or the filtrate pollution rate reaches a certain specified value for sampling. Therefore, the minimum sampling time to reach the target drilling fluid filtrate contamination rate and its corresponding probe and pumping parameters can be determined as the target sampling parameters.
According to the processing method of the stratum fluid sampling parameters, logging data and adjacent well data of a target measuring point are obtained; according to logging data and adjacent well data, obtaining stratum fluid parameters of a target measuring point; inputting each stratum fluid parameter into a pre-trained prediction model corresponding to each probe for processing to obtain a simulation result of each pumping cleaning process; the simulation result of the pumping cleaning process comprises change information of the pollution rate of the filtrate of the drilling fluid; and comparing simulation results of all the pumping cleaning processes, and determining target sampling parameters according to the comparison results. By the method, the operation parameters during formation fluid sampling can be rapidly obtained, the optimal operation system during formation fluid sampling is formulated, the operation risk can be reduced, and the operation time and cost can be saved.
FIG. 2 is a flow chart illustrating a method of processing formation fluid sampling parameters according to another embodiment of the present application, the method being applied to any device having computing power. As shown in fig. 2, the method comprises the steps of:
step S201, for each probe, constructing a plurality of pumping sampling cases of the black oil model according to the sampling value range of each stratum fluid parameter.
The invasion process and pumping cleaning process of the drilling fluid filtrate can be simulated by using a black oil model, which is also called a low-volatile oil two-component model, and refers to a mathematical model for describing the motion rule of two systems of the crude oil solution gas containing non-volatile components and the black oil in an oil reservoir.
Fig. 3 shows a schematic view of a pump cleaning process, in which the invaded zone 31 is the area into which the drilling fluid filtrate invades, and the non-invaded zone 32 is the area into which the drilling fluid filtrate does not invade or the undisturbed formation fluid occupies a relatively high area, and the formation tester 33 pumps the drilling fluid filtrate, then the mixture of the drilling fluid filtrate and the undisturbed formation fluid, and finally the undisturbed formation fluid.
In order to use a black oil model for simulation of filtrate invasion and pump-down cleaning processes in formation testing, many factors need to be considered and various parameters and their ranges of variation should be entered to cover most cases. In the embodiments of the present application, multiple cases of black oil model pumping sampling are randomly generated using a stochastic method based on the geometry and dimensions of the selected probe, where the geometry and dimensions of the probe are related to pumping flow rate, over the entire parameter range. The more cases, the more accurate the prediction model is formed, but if the cases are too many, the time is very long, and the number of cases is selected based on the accuracy of the solution (numerical solution or analytical solution) of the cases being within a preset range.
The main parameters and the variation ranges thereof are shown in the table one, and besides the parameters shown in the table one, part of the parameters can be obtained through the parameter association formula.
List one
Fig. 4 shows a schematic diagram of random parameters in the embodiment of the present application, and for each parameter, multiple values of the parameter are generated by adopting a random method in the parameter range, and are combined into multiple black oil model pumping sampling cases.
FIG. 5 shows a schematic of simulation results for a number of black oil models in an example of the present application, assuming a maximum pumping pressure drop of 300psi, a reservoir thickness of 50 feet, a probe relative position of 0.5, a filtrate intrusion thickness of 8 inches, a porosity of 0.2, a well diameter of 8.5 inches, an anisotropy of 0.1, etc., and a maximum pumping rate of 25cc/s. Because of the small flow area of standard, small, elliptical probes, pumping rates of only 6.8cc/s, 3.6cc/s and 7.8cc/s can be achieved at a pumping pressure drop of 300 psi. Wherein the abscissa indicates the pumping time in hours and the ordinate indicates the contamination rate (in particular percentage) of the drilling fluid filtrate. Curve 51 shows the change in drilling fluid filtrate contamination rate with pumping time for a 3D probe, pumping rate of 25cc/s, curve 52 shows the change in drilling fluid filtrate contamination rate with pumping time for a standard probe, pumping rate of 6.9cc/s, curve 53 shows the change in drilling fluid filtrate contamination rate with pumping time for an elliptical probe, pumping rate of 7.8cc/s, and curve 54 shows the change in drilling fluid filtrate contamination rate with pumping time for a small probe, pumping rate of 3.6 cc/s. It can be seen that the rate of contamination of the drilling fluid filtrate with pumping time is not consistent with different probes and pumping rates.
Step S202, performing numerical simulation processing according to a plurality of black oil model pumping sampling cases to obtain simulation results of a plurality of sample pumping cleaning processes.
Specifically, a grid diagram corresponding to the stratum and the probe is established; distributing stratum fluid parameters contained in any black oil model pumping sampling case to each grid in the grid chart; solving a mass conservation equation under a multiphase multicomponent system aiming at each grid, and analyzing a solving result to obtain a sample pump cleaning process simulation result.
In a multiphase multicomponent system, the mass conservation (continuity) equation for each component i in the alpha phase is:
wherein α=1, … n p ；i＝i,…n c ；
Is of porosity, S α Saturation of alpha phase, t is time, C iα Is the mass fraction of component i in the alpha phase ρ α Density of alpha phase, q α Source confluence ratio of alpha phase, u α The speed of the alpha phase is specifically expressed as follows:
wherein p is α Is the pressure of alpha phase, K is the permeability, K rα Relative permeability of alpha phase, mu α The fluid viscosity of the alpha phase, g is gravity acceleration, and Z is the height in the vertical direction.
According to the process of carrying out numerical simulation processing on a plurality of black oil model pumping sampling cases, namely, the numerical solution process of the mass conservation equation, the numerical solution can be carried out by combining the characteristics of oil reservoirs and fluids, the boundary and the initial condition, and the specific solution process is as follows: (1) discretizing the differential equation and the boundary conditions; (2) Dividing an oil reservoir and a probe into different grids, wherein the dividing precision of grids near the probe is higher; (3) Assigning an initial formation and fluid parameters to each grid; (4) Specifying filtrate intrusion and pump cleaning procedures such as specifying pump rate, maximum pump pressure drop, etc.; (5) Starting at 0, solving the mass conservation equation for each grid, namely, pumping the formation fluid parameters contained in the sampling case for each black oil model, bringing the formation fluid parameters into the corresponding formation fluid parameters for each grid and solving the mass conservation equation; (6) Adding a time step, and solving a mass conservation equation for each grid; (7) The steps are circulated until a specified condition is met, such as a drilling fluid filtrate contamination rate of less than 1%. It should be noted that, the pressure and the saturation can be obtained by performing numerical simulation on the sampling case pumped by the black oil model, the pressure and the saturation can represent the invasion and the cleaning process of the drilling fluid, and the change trend of the pollution rate of the filtrate of the drilling fluid along with various parameters in the invasion and the cleaning process of the drilling fluid can be obtained by circularly solving.
Numerical simulation is performed on the pumping sampling cases of each black oil model, and simulation results comprise a change relation of a drilling fluid filtrate pollution rate along with pumping time, a change relation of a drilling fluid filtrate pollution rate along with pumping volume, a change relation of a drilling fluid filtrate pollution rate along with pumping pressure drop, a change relation of a drilling fluid filtrate pollution rate along with pumping speed (namely pumping flow), and a fluid breakthrough time and volume, wherein the pumping time and pumping volume are when the drilling fluid filtrate pollution rate is a preset value, and for example, the pumping time and pumping volume are respectively 50%, 40%, 30%, 20%, 10% and 5%.
And step S203, constructing sample data according to the multiple black oil model pumping sampling cases and the multiple sample pumping cleaning process simulation results, and performing training treatment to obtain a prediction model corresponding to the probe.
In practical applications, small suction probes, focused probes, standard probes, elliptical probes, pad probes, dual packer probes, 3D pad probes, etc., may be used, with different probes having different geometries and dimensions, and if new probes are present, may be processed in the same manner.
FIG. 6 shows a schematic diagram of various probes in an embodiment of the present application, including a 3D probe 61, a small suction probe 62, a focused probe 63, a standard probe 64, an elliptical large suction probe 65, an ultra-large suction probe 66, and a pad probe 67, and a dual packer probe 68. The suction area of the small suction probe 62 is: 132.67mm 2 、0.21in 2 The suction port area of the focusing probe 63 is: 446.53mm 2 、0.69in 2 The suction area of the standard probe 64 is: 506.45mm 2 、0.79in 2 The suction port area of the elliptical large suction port probe 65 is: 1496.41mm 2 、2.32in 2 The suction port area of the oversized suction port probe 66 is: 3878.5mm 2 、6.01in 2 The suction port area of the plate probe 67 is: 19498.26mm 2 、30.22in 2 The suction area of the dual packer probe 68 is: 540745.68mm 2 、38.15in 2 . Of course, other types of probes may be used in practice. For each probe described above, a predictive model is trained using sample data, respectively.
Since the numerical simulation of black oil model cases can be very long, it can take hours or even days for a case to take place in particularly difficult cases. This is unacceptable for engineering applications. For example, if used as a design tool for a pumping regime, it may take a long time to calculate different probes, different formation conditions, different fluid properties. Thus, in embodiments of the present application, a predictive model is constructed based on the big data for determining the fluid sampling regime.
Based on big data formed by the numerical simulation results, a prediction model with high operation speed and high prediction precision is established by using a mathematical method, so that the numerical simulation of a case can be rapidly completed, and the prediction precision is similar to that of a black oil model result.
In an alternative way, the sample data is divided into a training data set, a test data set and a check data set, for example, 70% of the sample data is divided into the training data set for training the model, 15% of the sample data is divided into the test data set for testing the prediction model obtained by training, and 15% of the sample data is divided into the check data set for checking the accuracy of the prediction model.
In an alternative way, the predictive model is trained using any one of the following algorithms: k-neighbor algorithm, artificial neural network algorithm, kerling interpolation algorithm, interpolation algorithm.
K-proximity algorithm: is one of the simplest algorithms and is also one of the most commonly used algorithms. Is known collectively as K Nearest Neighbors, i.e., K nearest neighbors. Of course, the value of K is critical. The principle is that when a new value x is predicted, the output value is predicted based on the specific gravity of the K points from which it is closest.
Artificial neural network algorithm: when the neural network model is an ANN (Artifificial Neural Network, artificial neural network) model, the big data formed by the output results of numerical simulation is used as training data of the neural network model, namely, pumping sampling cases of each black oil model are used as input, and the change of the pollution rate of drilling fluid filtrate along with the pumping time, the change of the pollution rate of the drilling fluid filtrate along with the volume of pumping fluid and the change of the pollution rate of the drilling fluid filtrate along with the pumping pressure drop are used as output of the neural network model.
Artificial neurons are the most basic elements that make up neural networks, similar to biological neurons. Fig. 7 shows a schematic diagram of an artificial neuron in an embodiment of the present application, the artificial neuron being composed of five parts: (1) input:x 1 ，x 2 ，…，x m is the m input variables of the artificial neuron. (2) weight and threshold parameters: w (w) 1 ，w 2 ，…，w m The m network weights of the artificial neurons reflect the connection strength of the input variable and the neural network, b is the threshold value of the artificial neurons, and b can enable the transfer function to move left and right, thereby being beneficial to the capability of the neural network. (3) linear combination: linearly combining the input values with weights and thresholds, z= Σx i w i ++, of the material; (4) transfer function f 71: the transfer function is also called as a function, a transfer function, an excitation function and the like, and the function of the transfer function is to perform function operation on z to obtain the output of the artificial neuron. The usual transfer functions are: threshold functions, linear functions, logarithmic Sigmoid functions, tangential Sigmoid functions, etc. (5) output: the output o=f (Σx) i w i +)。
After the artificial neurons are arranged, the artificial neural network can be connected, and fig. 8 shows a schematic diagram of the neural network in the embodiment of the application, wherein the artificial neural network is composed of three layers: an input layer 81, an hidden layer 82 and an output layer 83. Data is input by the input layer 81, pre-processed (e.g., denoised, smoothed, normalized, etc.), and input to the hidden layer 82 along with weights and thresholds. The hidden layer 82 may be a single layer or multiple layers, with one or more artificial neurons in each layer. The output of the hidden layer 82 is passed to the output layer 83 after operation of the transfer function 84. The output layer gives an estimate 85 of the artificial neural network, i.e., y, and is correlated with the measured value 86 (i.e., the true value)
By comparing, a loss function or an objective function is calculated, and the objective function can be minimized by a gradient descent method, an M-L optimization method or a quasi-newton method, and the values of the parameters w and b in the model are obtained, so that y=f (X, w, b) is obtained.
The objective function specifically comprises the following steps:
the kriging interpolation method not only considers the correlation of the point to be estimated and the known position, but also considers the spatial correlation of the variables. The kriging interpolation method is further divided into a simple kriging interpolation method, a common kriging interpolation method, a generalized kriging interpolation method, a coordinated kriging interpolation method, a bayesian kriging interpolation method, an indicated kriging interpolation method, and the like.
In an alternative way, after the predictive model is obtained by training with multiple algorithms, the accuracy of the predictive model trained by the various algorithms is verified, and the predictive model with the highest accuracy is reserved for designing a sampling working system, while other predictive models are abandoned.
Step S204, logging data and adjacent well data of the target measuring point are obtained.
Step S205, each stratum fluid parameter of the target measuring point is obtained according to the logging data and the adjacent well data.
The parameters of each formation fluid are used as the input of a prediction model and are consistent with the parameters contained in the pumping sampling cases of the black oil model.
Step S206, inputting the stratum fluid parameters into the pre-trained prediction models corresponding to the probes for processing, and obtaining the simulation results of the pumping cleaning process.
And (3) inputting each stratum fluid parameter into a prediction model corresponding to each probe for processing, and outputting a corresponding pumping cleaning process simulation result by the prediction model corresponding to each probe. Wherein the pumping cleaning process simulation results include: the method comprises the following steps of changing relation information of a drilling fluid filtrate pollution rate along with pumping time, changing relation information of the drilling fluid filtrate pollution rate along with pumping volume, changing relation information of the drilling fluid filtrate pollution rate along with pumping speed and changing relation information of filtrate pollution rate along with pumping pressure drop.
In an optional manner, the pre-trained prediction model corresponding to any probe comprises a numerical type prediction model and an analytic type prediction model, wherein the numerical type prediction model is a prediction model obtained by training according to a numerical class algorithm, the analytic type prediction model is a prediction model obtained by training according to an analytic class algorithm, and different types of models have differences in calculation speed and calculation precision.
The numerical type algorithm includes: the finite difference method, the iteration method, the IMPES method, the semi-implicit method or the fully implicit method, and the analysis type algorithm is an artificial neural network algorithm. Determining a target model type according to the predicted demand information of the user; and respectively inputting each stratum fluid parameter into a prediction model of the target model type corresponding to the probe for processing. For example, if the user looks at the prediction speed more, a prediction model of the resolution type is selected, and if the user looks at the prediction accuracy more, a prediction model of the numerical type is selected.
Step S207, for any pumping cleaning process simulation result, acquiring pumping time and/or pumping volume required for reaching the target drilling fluid filtrate pollution rate under the specified pumping parameters; and comparing the pumping time and/or pumping volume required by reaching the target drilling fluid filtrate pollution rate under the designated pumping parameters corresponding to the simulation results of each pumping cleaning process, and determining target sampling parameters according to the comparison results.
Wherein the target sampling parameters include: target pump time, target probe type, and target pump parameters. The specified pumping parameters, i.e. the specified pumping parameters, may specify a pumping rate and a maximum pumping pressure drop, i.e. a pumping time and/or a pumping volume required to reach the target contamination rate at the specified pumping rate and with the maximum pumping pressure drop is obtained.
In one embodiment, the target sampling parameter is determined by comparing the pump times. Specifically, the shortest pumping time is determined from the respective pumping times, the shortest pumping time is determined as a target pumping time, pumping parameters (pumping rate and pumping pressure drop) corresponding to the shortest pumping time are determined as target pumping parameters, and the type of probe corresponding to a predictive model which outputs a simulation result including a pumping cleaning process to which the shortest pumping time belongs is the target probe type.
In another embodiment, the target sampling parameters are determined by comparing the pumping volumes, for example, a minimum pumping volume is determined from the pumping volumes, the pumping parameters (pumping rate and pumping pressure drop) corresponding to the minimum pumping volume are the target pumping parameters, and the type of probe corresponding to the output prediction model including the simulation result of the pumping cleaning process to which the minimum pumping volume belongs is the target probe type.
In another embodiment, the pump time and pump volume are comprehensively compared to determine the target sampling parameter, preferably the corresponding pump time, pump parameter and probe type with the shortest pump time and the smallest pump volume are determined as the target sampling parameter. And if the result of meeting the minimum pumping time and the minimum pumping volume simultaneously does not exist, comprehensively evaluating the pumping time and the pumping volume, and determining the target sampling parameter according to the evaluation result. For example, a composite score is calculated from the pumping time and pumping volume, and the pumping time, pumping parameter and probe type corresponding to the pumping time and pumping volume with the highest score are determined as the target sampling parameter.
In addition, after the simulation result of the pumping cleaning process is obtained through prediction of the prediction model, real data can be detected to be used for detecting the prediction accuracy of the prediction model, specifically, pumping parameters and actual drilling fluid filtrate pollution rates at a plurality of moments are collected and compared with the prediction result of the prediction model, and therefore the prediction accuracy of the prediction model is estimated. The drilling fluid filtrate contamination rate may be converted from intermediate data (including actual fluid density values, conductivity values, or other fluid property data, etc.), which may be collected by a wireline formation manometry sampling instrument (EFDT) or an while drilling sampling Instrument (IFSA).
FIG. 9a shows a schematic diagram of the operation of the cable formation pressure measurement sampling apparatus, as shown in FIG. 9a, before logging, the cable formation pressure measurement sampling apparatus 910 is placed to a target depth downhole, then the probe 911 is set on the well wall, after the setting is successful, the pumping module 912 is started, formation fluid enters the pipeline through the suction port, and the parameter signal values including the fluid density value, the conductivity value, the fluid property and the like measured in real time are generated through the parameter measuring device 913, and the data are transmitted to the surface logging system through the remote transmission of the cable in real time.
FIG. 9b shows a schematic of the operation of the while-drilling sampling apparatus, as shown in FIG. 9b, with the while-drilling sampling apparatus 920 being placed to a target depth downhole prior to logging, and the surface system being in communication with a downhole mud delivery device that issues surface commands to the while-drilling sampling apparatus 920. The while-drilling sampling apparatus 920 then seats the probe 921 on the well wall, after the seat is successful, starts the pumping module 922, and the formation fluid enters the pipeline through the suction port, and passes through the parameter measurement device 923 to generate a parameter signal value, namely, a fluid density value, a conductivity value, a fluid property and the like, which are measured in real time, and the data is uploaded to the surface logging system in real time through the mud transmission device.
According to the processing method for the stratum fluid sampling parameters, a plurality of black oil model pumping sampling cases are constructed and digital solving is carried out, so that a filtrate pumping cleaning process is simulated, relevant change information of the drilling fluid filtrate pollution rate in the pumping cleaning process is obtained, the information is used as a big data training prediction model, the prediction model is used for replacing the black oil model to determine sampling relevant parameters, and efficiency can be improved; formation and fluid parameters are obtained according to conventional logging data and adjacent well data, and given a maximum pumping pressure drop, a specified pumping rate and a specified filtrate contamination rate, a target pumping time and/or a target pumping volume and a corresponding pumping rate and an optimal probe type are determined, so that an optimal working system for sampling formation fluid is obtained, and relevant working parameters for sampling formation fluid can be determined efficiently, so that working risks can be reduced, and working time and cost can be saved.
FIG. 10 is a flow chart of a method of processing formation fluid sampling parameters according to an embodiment of the present application, as shown in FIG. 10, and specifically includes the following steps:
in step S1001, a probe is selected.
Step S1002, inputting conventional logging information and adjacent well information, and obtaining formation fluid parameters according to the conventional logging information and the adjacent well information. And obtaining storage thickness, porosity, horizontal permeability, anisotropy (vertical permeability/horizontal permeability), well diameter, drilling fluid filtrate invasion depth, formation pressure, temperature, relative position of a probe in storage, compression coefficient of stored rock, compression coefficient of formation fluid, compression coefficient of filtrate, viscosity of formation fluid, viscosity of filtrate, density of formation fluid, density of filtrate and the like at the measuring points according to conventional well logging data and adjacent well data.
Step S1003, prescribing a pumping rate, a maximum pressure drop, and a target drilling fluid filtrate contamination rate.
Step S1004, selecting a prediction model according to the requirements of the calculation speed and the precision.
Step S1005, calculating a pumping time, a pumping volume, a pumping rate, a pumping pressure drop, etc. for achieving the target drilling fluid filtrate contamination rate according to the selected model.
If a numerical type prediction model is selected, simulating a pumping cleaning sampling process by using the numerical type prediction model, and predicting the change relation of the pollution rate of drilling fluid filtrate along with pumping time, the pollution rate of drilling fluid filtrate along with pumping volume, the pollution rate of drilling fluid filtrate along with pumping speed and the pollution rate of drilling fluid filtrate along with pumping pressure drop; and predicting the pumping time and pumping volume required to reach the target drilling fluid filtrate contamination rate at the specified pumping rate, maximum pressure drop.
If the analysis type prediction model is selected, calculating a pumping clean sampling process by using the analysis type prediction model, predicting the change relation of the drilling fluid filtrate pollution rate along with the pumping time, the drilling fluid filtrate pollution rate along with the pumping volume, the drilling fluid filtrate pollution rate along with the pumping speed and the drilling fluid filtrate pollution rate along with the pumping pressure drop, and predicting the pumping time and the pumping volume required for reaching the target drilling fluid filtrate pollution rate under the specified pumping speed and the maximum pressure drop.
Step S1006, judging whether all probes and cases are completed. If yes, go to step S1009; if not, step S1007 is performed.
The formation fluid parameters obtained through conventional logging data and adjacent well data are partial approximate values, so that each formation fluid parameter can be adaptively adjusted according to actual needs, a plurality of cases are built according to different parameter values and are input into a prediction model for processing, and finally, prediction results corresponding to the plurality of cases are comprehensively compared.
Step S1007, determines whether a change in formation fluid parameters is required. If yes, go to step S1008; if not, step S1001 is performed, and if no change in formation fluid parameters is required, indicating that the simulation of the selected probe is complete, step S1001 is performed to select a new probe for simulation.
In step S1008, if the formation fluid parameters need to be changed, the formation fluid parameters are changed, a new case is generated and the process returns to step S1002, and the calculations from step S1002 to step S1007 are continued.
Step S1009, after completing all the probes and cases, compares the prediction results, and selects the optimal working system, i.e. the target sampling parameters, including the fastest sampling time, the maximum pumping rate, the optimal probe type, pumping pressure drop, etc.
In addition, after all the probes and cases are completed, the results and reports are output, so that the design and formulation of the stratum sampling working system are completed.
FIG. 11 is a schematic structural view of a treatment device for formation fluid sampling parameters according to an embodiment of the present application, as shown in FIG. 11, the device includes:
the first acquisition module 1101 is adapted to acquire logging data and adjacent well data of a target measurement point;
the second obtaining module 1102 is adapted to obtain each formation fluid parameter of the target measurement point according to the logging data and the adjacent well data;
the processing module 1103 is adapted to input each stratum fluid parameter into a pre-trained prediction model corresponding to each probe for processing, so as to obtain a simulation result of each pumping cleaning process;
the simulation result of the pumping cleaning process comprises change information of the pollution rate of the filtrate of the drilling fluid;
the decision module 1104 is adapted to compare the simulation results of each pumping cleaning process, and determine the target sampling parameters according to the comparison results.
In an alternative way, the change information of the contamination rate of the drilling fluid filtrate includes: and the change information of the pollution rate of drilling fluid filtrate along with the pumping time, the pumping volume, the pumping pressure drop and the pumping speed.
In an alternative way, the decision module 1104 is further adapted to:
for any pumping cleaning process simulation result, acquiring pumping time and/or pumping volume required by achieving a target drilling fluid filtrate pollution rate under specified pumping parameters;
comparing pumping time and/or pumping volume required by reaching the target drilling fluid filtrate pollution rate under the designated pumping parameters corresponding to the simulation results of each pumping cleaning process, and determining target sampling parameters according to the comparison results; wherein the target sampling parameters include: target pump time, target probe type, and target pump parameters.
In an alternative way, the decision module 1104 is further adapted to:
the shortest pumping time is determined as the target pumping time, the pumping parameter corresponding to the shortest pumping time is determined as the target pumping parameter, and the type of probe corresponding to the shortest pumping time is determined as the target probe type.
In an alternative, the apparatus further comprises:
the numerical simulation module is suitable for constructing a plurality of pumping sampling cases of the black oil model according to the sampling value range of each stratum fluid parameter aiming at each probe; performing numerical simulation processing according to the pumping sampling cases of the black oil models to obtain simulation results of the pumping cleaning processes of the samples;
And the model training module is suitable for constructing sample data according to the pumping sampling cases of the black oil models and the simulation results of the pumping cleaning processes of the samples and performing training treatment to obtain a prediction model corresponding to the probe.
In an alternative, the numerical simulation module is further adapted to: establishing a grid diagram corresponding to the stratum and the probe; distributing stratum fluid parameters contained in any black oil model pumping sampling case to each grid in the grid chart; solving a mass conservation equation under a multiphase multicomponent system aiming at each grid, and analyzing a solving result to obtain a sample pump cleaning process simulation result.
In an alternative, the processing module 1103 is further adapted to: determining a target model type according to the predicted demand information of the user; and respectively inputting each stratum fluid parameter into a prediction model of the target model type corresponding to each probe for processing.
According to the processing device for the stratum fluid sampling parameters, the plurality of black oil model pumping sampling cases are constructed and digital solving is carried out, so that a filtrate pumping cleaning process is simulated, relevant change information of the drilling fluid filtrate pollution rate in the pumping cleaning process is obtained, the processing device is used as a big data training prediction model, the prediction model is used for replacing the black oil model to determine sampling relevant parameters, and efficiency can be improved; formation and fluid parameters are obtained according to conventional logging data and adjacent well data, and given a maximum pumping pressure drop, a specified pumping rate and a specified filtrate contamination rate, a target pumping time and/or a target pumping volume and a corresponding pumping rate and an optimal probe type are determined, so that an optimal working system for sampling formation fluid is obtained, and relevant working parameters for sampling formation fluid can be determined efficiently, so that working risks can be reduced, and working time and cost can be saved.
Embodiments of the present application provide a non-transitory computer storage medium having stored thereon at least one executable instruction that may perform a method for processing a formation fluid sampling parameter in any of the above-described method embodiments.
FIG. 12 illustrates a schematic diagram of a computing device provided by embodiments of the present application, which are not limited to a particular implementation of the computing device.
As shown in fig. 12, the computing device may include: a processor 1202, a communication interface (Communications Interface) 1204, a memory 1206, and a communication bus 1208.
Wherein: the processor 1202, the communication interface 1204, and the memory 1206 communicate with each other via a communication bus 1208. A communication interface 1204 for communicating with network elements of other devices, such as clients or other servers, etc. The processor 1202 is configured to execute the process 1210 and may specifically perform the relevant steps of embodiments of the processing method for calculating formation fluid sampling parameters for an apparatus described above.
In particular, program 1210 may include program code including computer operating instructions.
The processor 1202 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present application. The one or more processors included by the computing device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
Memory 1206 for storing program 1210. The memory 1206 may comprise high-speed RAM memory or may further comprise non-volatile memory (non-volatile memory), such as at least one disk memory.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, embodiments of the present application are not directed to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the present application as described herein, and the above description of specific languages is provided for disclosure of preferred embodiments of the present application.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the present application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the above description of exemplary embodiments of the application, various features of embodiments of the application are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the application and aiding in the understanding of one or more of the various application's aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed application requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this application.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the present application and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
Various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components according to embodiments of the present application may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present application may also be embodied as an apparatus or device program (e.g., computer program and computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present application may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.
Claims (10)
1. A method of processing formation fluid sampling parameters, the method comprising:
acquiring logging data and adjacent well data of a target measuring point;
according to the logging information and the adjacent well information, obtaining stratum fluid parameters of the target measuring points;
inputting the stratum fluid parameters into pre-trained prediction models corresponding to the probes respectively for processing to obtain simulation results of the pumping cleaning process;
the simulation result of the pumping cleaning process comprises change information of the pollution rate of the filtrate of the drilling fluid;
and comparing simulation results of the pumping cleaning processes, and determining target sampling parameters according to the comparison results.
2. The method of claim 1, wherein the drilling fluid filtrate contamination rate variation information comprises: and the change information of the pollution rate of drilling fluid filtrate along with the pumping time, the pumping volume, the pumping pressure drop and the pumping speed.
3. The method of claim 2, wherein comparing the simulation results of each pump cleaning process, and determining the target sampling parameter based on the comparison results further comprises:
for any pumping cleaning process simulation result, acquiring pumping time and/or pumping volume required by achieving a target drilling fluid filtrate pollution rate under specified pumping parameters;
Comparing pumping time and/or pumping volume required by reaching the target drilling fluid filtrate pollution rate under the designated pumping parameters corresponding to the simulation results of each pumping cleaning process, and determining target sampling parameters according to the comparison results; wherein the target sampling parameters include: target pump time, target probe type, and target pump parameters.
4. A method according to claim 3, wherein said comparing the pumping time required to reach the target drilling fluid filtrate contamination rate at the specified pumping parameters corresponding to the simulation results of each pumping cleaning process, and determining the target sampling parameters based on the comparison results further comprises:
the shortest pumping time is determined as a target pumping time, a pumping parameter corresponding to the shortest pumping time is determined as a target pumping parameter, and a type of probe corresponding to the shortest pumping time is determined as a target probe type.
5. The method according to claim 1, wherein the method further comprises:
for each probe, constructing a plurality of black oil model pumping sampling cases according to the sampling value range of each stratum fluid parameter;
performing numerical simulation processing according to the multiple black oil model pumping sampling cases to obtain multiple sample pumping cleaning process simulation results;
And constructing sample data according to the multiple black oil model pumping sampling cases and the multiple sample pumping cleaning process simulation results, and training to obtain a prediction model corresponding to the probe.
6. The method of claim 5, wherein performing numerical simulation processing based on the plurality of black oil model pumping sampling cases to obtain a plurality of sample pumping cleaning process simulation results further comprises:
establishing a grid diagram corresponding to the stratum and the probe;
distributing stratum fluid parameters contained in any black oil model pumping sampling case to each grid in the grid chart;
solving a mass conservation equation under a multiphase multicomponent system aiming at each grid, and analyzing a solving result to obtain a sample pump cleaning process simulation result.
7. The method of claim 1, wherein the inputting the respective formation fluid parameters into respective pre-trained predictive models for each probe for processing further comprises:
determining a target model type according to the predicted demand information of the user;
and respectively inputting each stratum fluid parameter into a prediction model of the target model type corresponding to each probe for processing.
8. A treatment apparatus for formation fluid sampling parameters, the apparatus comprising:
the first acquisition module is suitable for acquiring logging data and adjacent well data of the target measuring point;
the second acquisition module is suitable for acquiring stratum fluid parameters of the target measuring point according to the logging data and the adjacent well data;
the processing module is suitable for inputting the stratum fluid parameters into a pre-trained prediction model corresponding to each probe for processing to obtain the simulation result of each pumping cleaning process;
the simulation result of the pumping cleaning process comprises change information of the pollution rate of the filtrate of the drilling fluid;
and the decision module is suitable for comparing the simulation results of the cleaning process of each pump, and determining target sampling parameters according to the comparison results.
9. A computing device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to hold at least one executable instruction that causes the processor to perform operations corresponding to the method of processing formation fluid sampling parameters as set forth in any one of claims 1-7.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the method of processing formation fluid sampling parameters according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310101625.6A CN116070545A (en) | 2023-01-18 | 2023-01-18 | Processing method and device for stratum fluid sampling parameters and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310101625.6A CN116070545A (en) | 2023-01-18 | 2023-01-18 | Processing method and device for stratum fluid sampling parameters and computing equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116070545A true CN116070545A (en) | 2023-05-05 |
Family
ID=86179915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310101625.6A Pending CN116070545A (en) | 2023-01-18 | 2023-01-18 | Processing method and device for stratum fluid sampling parameters and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116070545A (en) |
-
2023
- 2023-01-18 CN CN202310101625.6A patent/CN116070545A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2669948C2 (en) | Multistage oil field design optimisation under uncertainty | |
| US11163923B2 (en) | Automated upscaling of relative permeability and capillary pressure in multi-porosity systems | |
| EP2948895A1 (en) | Pressure transient testing with sensitivity analysis | |
| AU2007339997A1 (en) | History matching and forecasting of hydrocarbon-bearing reservoirs utilizing proxies for likelihood functions | |
| CN109100812B (en) | Rock pore fractal dimension evaluation method and device based on nuclear magnetic resonance | |
| CA2890817C (en) | System, method and computer program product for determining placement of perforation intervals using facies, fluid boundaries, geobodies and dynamic fluid properties | |
| EP1996963A2 (en) | Monte carlo simulation of well logging data | |
| US20220341835A1 (en) | Methods and Systems for Determining Reservoir and Fracture Properties | |
| WO2010104535A1 (en) | Method for predicting fluid flow | |
| US10087723B2 (en) | Methodology for building realistic numerical forward stratigraphic models in data sparse environment | |
| CN107808032B (en) | Shale gas reservoir water saturation calculation method and system | |
| US8788252B2 (en) | Multi-well time-lapse nodal analysis of transient production systems | |
| EP3737928A1 (en) | Determining fluid flow characteristics of porous mediums | |
| EP2839321A2 (en) | System and method for calibrating permeability for use in reservoir modeling | |
| RU2630852C1 (en) | Method of forecast of effective capacity of collectors on basis of received polarization parameters and conductivity for selected type of environment | |
| EP2370672A1 (en) | Method and apparatus for real time oil based mud contamination monitoring | |
| Abbasi et al. | Application of Physics-Informed Neural Networks for Estimation of Saturation Functions from Countercurrent Spontaneous Imbibition Tests | |
| Masoudi et al. | Estimation of in place hydrocarbon volume in multilayered reservoirs using deterministic and probabilistic approaches | |
| CN116070545A (en) | Processing method and device for stratum fluid sampling parameters and computing equipment | |
| CN109426657B (en) | Method and system for calculating inter-well communication coefficient of oil reservoir | |
| US20220074291A1 (en) | System and method for reservoired oil production based on calculated composition of natural tracers | |
| Dakhelpour-Ghoveifel et al. | Prediction of gas-oil capillary pressure of carbonate rock using pore network modeling | |
| Amanipoor | Providing a subsurface reservoir quality maps in oil fields by geostatistical methods | |
| Alreshedan et al. | Sensitivity analysis of the effect of pore structure and geometry on petrophysical and electrical properties of tight media: random network modeling | |
| AU2012396846A1 (en) | System, method and computer program product for evaluating and ranking geobodies using a Euler Characteristic |
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 |