CN111259600B - Optimization efficiency method for improving automatic well position optimization - Google Patents
Optimization efficiency method for improving automatic well position optimization Download PDFInfo
- Publication number
- CN111259600B CN111259600B CN202010059372.7A CN202010059372A CN111259600B CN 111259600 B CN111259600 B CN 111259600B CN 202010059372 A CN202010059372 A CN 202010059372A CN 111259600 B CN111259600 B CN 111259600B
- Authority
- CN
- China
- Prior art keywords
- well
- production
- grid
- oil
- optimization
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000004519 manufacturing process Methods 0.000 claims abstract description 73
- 239000002245 particle Substances 0.000 claims abstract description 49
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 31
- 238000004088 simulation Methods 0.000 claims abstract description 28
- 238000009826 distribution Methods 0.000 claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims abstract description 6
- 238000012067 mathematical method Methods 0.000 claims abstract description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 230000035699 permeability Effects 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000005530 etching Methods 0.000 claims 1
- 238000012935 Averaging Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002431 foraging effect Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
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
- E21B43/00—Methods or apparatus for obtaining oil, gas, water, soluble or meltable materials or a slurry of minerals from wells
- E21B43/30—Specific pattern of wells, e.g. optimising the spacing of wells
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Geology (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Feedback Control In General (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The method for improving the optimization efficiency of automatic well position optimization utilizes a production potential map to initialize well positions to replace a particle swarm algorithm to randomly initialize well positions, invokes digital-analog software to perform complete oil reservoir numerical simulation operation, and combines a speed and position updating strategy to update speed and position parameters in the particle swarm algorithm; then, a threshold value parameter epsilon is added to evaluate the well distribution provided by each particle, numerical simulation software is called to perform simulation calculation of all production time, for simulation schemes with well distribution result evaluation threshold values lower than epsilon, the rest simulation time adopts a mathematical method to perform prediction simulation to judge whether algorithm iteration stop conditions are met, namely maximum iteration algebra; and if the operation is not satisfied, finally obtaining the optimal well position and the optimal result. The invention combines a particle swarm mathematical optimization algorithm and an oil deposit engineering theory, has stronger advantages in the aspects of well distribution results and computers, and has certain applicability and reliability for well position optimization of actual oil deposit.
Description
Technical Field
The invention relates to a method for improving the optimization efficiency of automatic well position optimization, in particular to a method for improving the optimization efficiency of automatic well position optimization.
Background
The automatic well position optimization is generally to obtain the optimal net present value or accumulated oil yield by means of the oil reservoir model and mathematical optimization algorithm and through automatic iterative optimization of the parameters such as the input well position and the like by a computer. Numerical simulation models are fundamental tools of automatic well position optimization, and are generally used for evaluating objective functions in well position optimization. However, each evaluation of the objective function needs to call the numerical simulator to simulate and calculate, so that almost 99% of CPU consumption is spent on evaluation of the objective function based on the numerical simulator, and the efficiency of well position optimization is greatly affected.
Currently, a particle swarm optimization (Particle Swarm Optimization, PSO) algorithm is a global random search algorithm based on swarm intelligence, which is proposed by simulating migration and swarming behaviors in the process of swarm foraging under the heuristic of artificial life research results of Kennedy and Eberhart. Compared with genetic algorithm, the particle swarm algorithm does not need complex operations such as coding, crossing, mutation and the like. Particle swarm optimization is applied in well position optimization, mainly by starting a random initial set of particles, each particle representing a possible optimal well layout scheme, and all particles having an fitness value. In the optimization process, each particle memorizes and follows the current optimal particle in the space of the solution. The particle swarm optimization algorithm is a random algorithm, and a method of calculating and averaging for many times is needed when automatic well position optimization is carried out, so that the particle swarm optimization algorithm is an iterative solution algorithm used in the method.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention aims to provide a method for improving the optimization efficiency of automatic well position optimization, which reduces the optimization time as much as possible and improves the optimization efficiency while maintaining the optimization effect of the automatic well position. By using the production potential map and the Gompertz prediction model as auxiliary technical means, the automatic well position optimization can be completed rapidly under the condition that the oil reservoir numerical model is called as little as possible.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
a method for improving the optimization efficiency of automatic well site optimization, comprising the steps of:
1) Reservoir production potential initialization well site: initializing well locations by using a production potential map instead of randomly initializing well locations by a particle swarm algorithm, wherein the oil reservoir production potential map Quality map is used for representing the oil reservoir plane production potential, and the production potential map can be obtained by the following formula (1):
J i,j,k (t)＝[S o,i,j,k (t)-S or ].[P o,i,j,k (t)-P min ].LnK i,j,k .Lnr i,j,k .h woc,i,j,k .Φ i,j, k. h goc,i,j,k (1)
wherein J is i,j,k (t) is the production potential of grid (i, j, k) at time t; s is S o,i,j,k (t) is the original oil saturation of grid (i, j, k) at time t; s is S or Saturation for residual oil; p (P) o,i,j,k (t) is the oil phase pressure of grid (i, j, k) at time t; p (P) min Is the minimum bottom hole pressure; k (K) i,j,k Permeability for grid (i, j, k); r is (r) i,j,k Distance from nearest boundary for grid (i, j, k); phi i,j,k. Porosity for grid (i, j, k); h is a goc,i,j,k Distance from grid (i, j, k) to air-water interface; h is a woc,i,j,k Distance from the grid (i, j, k) to the oil-water interface;
the potential value of each grid needs to be normalized before being used, and the processing method is as shown in formula (2);
in the method, in the process of the invention,normalized production potential of grid (i, J, k) at time t, J max (t) is the maximum of all grid potential values;
2) According to the initialized well position obtained in the step 1), invoking digital-analog software to perform complete oil reservoir numerical simulation operation, and calculating a fitness value according to an operation result;
3) According to the calculated fitness value, the speed and position parameters in the particle swarm algorithm are updated by combining a speed and position updating strategy;
4) Reservoir production potential threshold constraints: adding a threshold parameter epsilon to the conclusion to evaluate the well arrangement provided by each particle, if the parameter is larger than a certain threshold value, considering the well arrangement as a good choice, then calling numerical simulation software to perform simulation calculation of all production time, otherwise, calling digital simulation software to perform simulation calculation of only the first half of the production time, and finishing the accumulated output of the second half of the production time by adopting a Gompertz output prediction model; the threshold parameter ε is as in equation (3):
wherein epsilon is a potential threshold; q (Q) now The production potential index of the well distribution scheme provided for the particles under the current iteration times; q (Q) former The production potential index of the well distribution scheme provided for the particle under the last iteration number; q is the production potential index of the well layout scheme provided by the particles; n is n z Is the number of longitudinal grids; n is n w For an optimized number of wells;
5) For simulation schemes with well distribution result evaluation thresholds lower than epsilon, the rest simulation time adopts a mathematical method to carry out predictive simulation, and the development process of the water-driven oil field is carried out, so that the process of changing the oil yield of the oil field can be described by adopting the rule of Gompertz model from 0 to recoverable reserves;
y＝e mn'+c (5)
wherein y represents oil production, m, n and c can be obtained by regression according to the related data of the oil production;
for the well layout scheme with better predicted accumulated output through the formula (5), the fact that the incomplete production year is continuously simulated accurately by using the digital-analog restarting file can be considered, the parameter eta is defined to evaluate whether the incomplete production year is required to be continuously simulated by using the restarting file, if the parameter is larger than a certain threshold value, the well layout scheme can be considered to be a better choice at the moment, and the digital-analog can be called for verification; as shown in formula (6):
wherein η is a threshold parameter; n (N) pnow Accumulated oil yield of a well-distribution scheme provided for particles under the current iteration times; n (N) pformer Accumulated oil yield of the well-distribution scheme provided for the particles under the previous iteration number;
6) Judging whether an algorithm iteration stop condition is met, namely a maximum iteration algebra; and if the steering step 3) is not satisfied, stopping, and finally obtaining the optimal well position and the optimal result.
The beneficial effects of the invention are as follows:
the method provided by the invention has strong advantages in the aspects of well distribution results and computers, and has certain applicability and reliability for automatic well position optimization of actual oil reservoirs.
Drawings
FIG. 1 is a flow chart of a method for improving the optimization efficiency of automatic well position optimization;
FIG. 2 is a three-dimensional permeability profile of a reservoir in accordance with an embodiment of the present invention;
FIG. 3 is a schematic representation of reservoir production potential in accordance with an embodiment of the present invention;
FIG. 4 is a graph of well position optimization results in an embodiment of the present invention;
FIG. 5 is a graph showing the comparison of algorithm effects in an embodiment of the present invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and examples, but the present invention is not limited to the following examples.
As shown in fig. 1, a method for improving the optimization efficiency of automatic well position optimization is characterized by comprising the following steps:
1) Reservoir production potential initialization well site: initializing well locations by using a production potential map instead of randomly initializing well locations by a particle swarm algorithm, wherein the oil reservoir production potential map Quality map is used for representing the oil reservoir plane production potential, and the production potential map can be obtained by the following formula (1):
J i,j,k (t)＝[S o,i,j,k (t)-S or ].[P o,i,j,k (t)-P min ].LnK i,j,k .Lnr i,j,k .h woc,i,j,k .Φ i,j, k. h goc,i,j,k (1)
wherein J is i,j,k (t) is the production potential of grid (i, j, k) at time t; s is S o,i,j,k (t) is the original oil saturation of grid (i, j, k) at time t; s is S or Saturation for residual oil; p (P) o,i,j,k (t) is the oil phase pressure of grid (i, j, k) at time t; p (P) min Is the minimum bottom hole pressure; k (K) i,j,k Permeability for grid (i, j, k); r is (r) i,j,k Distance from nearest boundary for grid (i, j, k); phi i,j,k. Porosity for grid (i, j, k); h is a goc,i,j,k Distance from grid (i, j, k) to air-water interface; h is a woc,i,j,k Distance from the grid (i, j, k) to the oil-water interface;
the potential value of each grid needs to be normalized before being used, and the processing method is as shown in formula (2);
in the method, in the process of the invention,normalized production potential of grid (i, J, k) at time t, J max (t) is the maximum of all grid potential values;
2) According to the initialized well position obtained in the step 1), invoking digital-analog software to perform complete oil reservoir numerical simulation operation, and calculating a fitness value according to an operation result;
3) According to the calculated fitness value, the speed and position parameters in the particle swarm algorithm are updated by combining a speed and position updating strategy;
4) Reservoir production potential threshold constraints: adding a threshold parameter epsilon to the conclusion to evaluate the well arrangement provided by each particle, if the parameter is larger than a certain threshold value, considering the well arrangement as a good choice, then calling numerical simulation software to perform simulation calculation of all production time, otherwise, calling digital simulation software to perform simulation calculation of only the first half of the production time, and finishing the accumulated output of the second half of the production time by adopting a Gompertz output prediction model; the threshold parameter ε is as in equation (3):
wherein epsilon is a potential threshold; q (Q) now The production potential index of the well distribution scheme provided for the particles under the current iteration times; q (Q) former The production potential index of the well distribution scheme provided for the particle under the last iteration number; q is the production potential index of the well layout scheme provided by the particles; n is n z Is the number of longitudinal grids; n is n w For an optimized number of wells;
5) For simulation schemes with well distribution result evaluation thresholds lower than epsilon, the rest simulation time adopts a mathematical method to carry out predictive simulation, and the development process of the water-driven oil field is carried out, so that the process of changing the oil yield of the oil field can be described by adopting the rule of Gompertz model from 0 to recoverable reserves;
y＝e mn'+c (5)
wherein y represents oil production, m, n and c can be obtained by regression according to the related data of the oil production;
for the well layout scheme with better predicted accumulated output through the formula (5), the fact that the incomplete production year is continuously simulated accurately by using the digital-analog restarting file can be considered, the parameter eta is defined to evaluate whether the incomplete production year is required to be continuously simulated by using the restarting file, if the parameter is larger than a certain threshold value, the well layout scheme can be considered to be a better choice at the moment, and the digital-analog can be called for verification; as shown in formula (6):
wherein η is a threshold parameter; n (N) pnow Accumulated oil yield of a well-distribution scheme provided for particles under the current iteration times; n (N) pformer Accumulated oil yield of the well-distribution scheme provided for the particles under the previous iteration number;
6) Judging whether an algorithm iteration stop condition is met, namely a maximum iteration algebra; and if the steering step 3) is not satisfied, stopping, and finally obtaining the optimal well position and the optimal result.
Examples:
the test reservoir is surrounded by an active body of water, and a gas cap is constructed at the top position. The original reservoir pressure is 23.8MPa, the depth of the top of the reservoir is about 2340m, and the average permeability is 0.1 mu m 2 The average porosity is 0.2, the number of effective grids is 1761, the effective grids are divided into 5 small layers longitudinally, and the number of planar effective grids is about 352. The original well layout scheme of the example considers that the side bottom water is sufficient, so that only 10 production wells are provided, and no water injection well is provided. The three-dimensional distribution of the permeability of a specific reservoir is shown in figure 2.
The method comprises the following steps:
in order to verify the practicability and accuracy of the established well position optimization model, four different strategies are adopted for well distribution for the oil reservoir: original well-layout scheme (Original), optimizing well location (PSO) only by using standard particle swarm algorithm, combining particle swarm algorithm with production potential map auxiliary technical means (PSO+QM), and combining particle swarm algorithm with production potential map and Gompertz prediction model auxiliary technical means (PSO+QM+GM). In the particle swarm optimization algorithm, 50 particles are selected, and the iteration number is set to be 100. Some particles provide well placement schemes that are in an ineffective grid without running digital-to-analog software. Thus the running model is at most 3×50×100=15000 times, which saves time considerably compared to the exhaustive algorithm. Considering that the particle swarm is a random optimization algorithm, each scheme adopts a method of averaging by running 3 times.
1) Reservoir production potential initialization well site: generating a test reservoir production potential map (fig. 3) using the production potential map calculation formulas (1) and (2), and initializing the well location using the production potential map;
2) According to the initialized well position, calling digital-analog software to perform complete oil reservoir numerical simulation operation, and calculating the fitness value accumulated oil yield according to an operation result;
3) According to the calculated fitness value, the speed and position parameters in the particle swarm algorithm are updated by combining a speed and position updating strategy;
4) Evaluating the production potential of a well arrangement scheme provided by each particle, if the parameter is greater than a potential threshold epsilon (the threshold is set to be 0.9 in the example), considering that the well arrangement is a good choice, then calling numerical simulation software to perform simulation calculation of all production time, otherwise calling numerical simulation software to perform simulation calculation of only the first half of the production time, and finishing the accumulated yield of the second half of the production time by adopting a Gompertz yield prediction model;
5) According to whether the accumulated oil yield obtained by the yield prediction model is larger than a potential threshold value eta (the threshold value is set to be 0.8 in the example), when the accumulated oil yield is larger than 0.8, continuously performing accurate simulation on incomplete production years by taking into account a digital-analog restarting file, and re-evaluating the fitness value;
6) Judging whether an algorithm iteration stop condition is met, wherein the maximum iteration number in the example is 100; and if the steering step 3) is not satisfied, stopping, and finally obtaining the optimal well position and the optimal result. FIG. 4 is a final well position optimization result graph. FIG. 5 is a graph showing the cumulative oil production versus iteration number for four schemes. As can be seen from fig. 5, the final optimization results of the four schemes are pso+qm > pso+qm+gm > PSO > Original, respectively, which proves that the well location deployment result using the optimization algorithm is better than the Original scheme. The first few generations of PSO schemes do not perform well, and as the iteration progresses, a better well-distribution scheme can be gradually found, but overall, no particle swarm-combined auxiliary techniques (PSO+QM+GM and PSO+QM) perform well. It can be seen that the selection of a good initial scheme using the production potential map has a large impact on the subsequent iterations of PSO.
From the optimization result, the schemes PSO+QM+GM and PSO+QM, the difference between the final accumulated oil yield obtained by optimization is 0.08X10% 6 m 3 Pso+qm+gm is 1.63% less than pso+qm. However, the average time of the PSO+QM is about 11.25 hours, and the average time of the PSO+QM+GM is only 7.62 hours, which is 47.64% less than the average time of the PSO+QM. Thus, for large reservoir models, the advantages of the scheme PSO+QM+GM in terms of time savings would be very significant. Therefore, the PSO+QM+GM optimization model has stronger advantages than other models in the aspect of comprehensively considering the accumulated oil production and the machine time. Therefore, in the well site optimization of an actual oil reservoir, the PSO+QM+GM optimization model is recommended.
The above description is only specific for the method and is not intended to limit the scope of the present invention. Any equivalent changes and modifications can be made by those skilled in the art without departing from the spirit and principles of this invention, and are intended to be within the scope of this invention.
Claims (1)
1. A method for improving the optimization efficiency of automatic well site optimization, comprising the following steps:
1) Reservoir production potential initialization well site: initializing well locations by using a production potential map instead of randomly initializing well locations by a particle swarm algorithm, wherein the oil reservoir production potential map Quality map is used for representing the oil reservoir plane production potential, and the production potential map can be obtained by the following formula (1):
J i,j,k (t)＝[S o,i,j,k (t)-S or ].[P o,i,j,k (t)-P min ].LnK i,j,k .Lnr i,j,k .h woc,i,j,k .Φ i,j, k. h goc,i,j,k (1)
wherein J is i,j,k (t) is the production potential of grid (i, j, k) at time t; s is S o,i,j,k (t) is the original oil saturation of grid (i, j, k) at time t; s is S or Saturation for residual oil; p (P) o,i,j,k (t) is the grid (i, j, k) at tOil phase pressure of etching; p (P) min Is the minimum bottom hole pressure; k (K) i,j,k Permeability for grid (i, j, k); r is (r) i,j,k Distance from nearest boundary for grid (i, j, k); phi i,j,k. Porosity for grid (i, j, k); h is a goc,i,j,k Distance from grid (i, j, k) to air-water interface; h is a woc,i,j,k Distance from the grid (i, j, k) to the oil-water interface;
the potential value of each grid needs to be normalized before being used, and the processing method is as shown in formula (2);
in the method, in the process of the invention,normalized production potential of grid (i, J, k) at time t, J max (t) is the maximum of all grid potential values;
2) According to the initialized well position obtained in the step 1), invoking digital-analog software to perform complete oil reservoir numerical simulation operation, and calculating a fitness value according to an operation result;
3) According to the calculated fitness value, the speed and position parameters in the particle swarm algorithm are updated by combining a speed and position updating strategy;
4) Reservoir production potential threshold constraints: adding a threshold parameter epsilon to the conclusion to evaluate the well arrangement provided by each particle, if the parameter is larger than a certain threshold value, considering the well arrangement as a good choice, then calling numerical simulation software to perform simulation calculation of all production time, otherwise, calling digital simulation software to perform simulation calculation of only the first half of the production time, and finishing the accumulated output of the second half of the production time by adopting a Gompertz output prediction model; the threshold parameter ε is as in equation (3):
wherein epsilon is a potential threshold; q (Q) now The production potential index of the well distribution scheme provided for the particles under the current iteration times; q (Q) former The production potential index of the well distribution scheme provided for the particle under the last iteration number; q is the production potential index of the well layout scheme provided by the particles; n is n z Is the number of longitudinal grids; n is n w For an optimized number of wells;
5) For simulation schemes with well distribution result evaluation thresholds lower than epsilon, the rest simulation time adopts a mathematical method to carry out predictive simulation, and the development process of the water-driven oil field is carried out, so that the process of changing the oil yield of the oil field can be described by adopting the rule of Gompertz model from 0 to recoverable reserves;
y＝e mn'+c (5)
wherein y represents oil production, m, n and c can be obtained by regression according to the related data of the oil production;
for the well layout scheme with better predicted accumulated output through the formula (5), the fact that the incomplete production year is continuously simulated accurately by using the digital-analog restarting file can be considered, the parameter eta is defined to evaluate whether the incomplete production year is required to be continuously simulated by using the restarting file, if the parameter is larger than a certain threshold value, the well layout scheme can be considered to be a better choice at the moment, and the digital-analog can be called for verification; as shown in formula (6):
wherein η is a threshold parameter; n (N) pnow Accumulated oil yield of a well-distribution scheme provided for particles under the current iteration times; n (N) pformer Accumulated oil yield of the well-distribution scheme provided for the particles under the previous iteration number;
6) Judging whether an algorithm iteration stop condition is met, namely a maximum iteration algebra; and if the steering step 3) is not satisfied, stopping, and finally obtaining the optimal well position and the optimal result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010059372.7A CN111259600B (en) | 2020-01-19 | 2020-01-19 | Optimization efficiency method for improving automatic well position optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010059372.7A CN111259600B (en) | 2020-01-19 | 2020-01-19 | Optimization efficiency method for improving automatic well position optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111259600A CN111259600A (en) | 2020-06-09 |
| CN111259600B true CN111259600B (en) | 2023-07-28 |
Family
ID=70954251
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010059372.7A Active CN111259600B (en) | 2020-01-19 | 2020-01-19 | Optimization efficiency method for improving automatic well position optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111259600B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113255131B (en) * | 2021-05-25 | 2023-02-28 | 中国石油大学(华东) | New well target well position recommendation method based on cognitive calculation |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018072351A1 (en) * | 2016-10-20 | 2018-04-26 | 北京工业大学 | Method for optimizing support vector machine on basis of particle swarm optimization algorithm |
| CN109753671A (en) * | 2017-11-07 | 2019-05-14 | 中国石油大学(华东) | A kind of accurate well location optimization method of oil reservoir based on fish-swarm algorithm |
-
2020
- 2020-01-19 CN CN202010059372.7A patent/CN111259600B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018072351A1 (en) * | 2016-10-20 | 2018-04-26 | 北京工业大学 | Method for optimizing support vector machine on basis of particle swarm optimization algorithm |
| CN109753671A (en) * | 2017-11-07 | 2019-05-14 | 中国石油大学(华东) | A kind of accurate well location optimization method of oil reservoir based on fish-swarm algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 基于改进粒子群算法的不规则井网自动优化;丁帅伟;姜汉桥;周代余;赵冀;旷曦域;白鹏;;中国海上油气(01);全文 * |
| 深水油藏生产潜力评价方法对比研究;汤国平;姜汉桥;丁帅伟;胡航;余振亭;;复杂油气藏(02);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111259600A (en) | 2020-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113052371B (en) | Residual oil distribution prediction method and device based on deep convolutional neural network | |
| CN111861774B (en) | Oil reservoir production machine learning method based on parallel agent model | |
| US8005658B2 (en) | Automated field development planning of well and drainage locations | |
| CN114492213B (en) | Wavelet neural operator network model-based residual oil saturation and pressure prediction method | |
| CN109753671B (en) | Oil reservoir accurate well position optimization method based on fish swarm algorithm | |
| CN107939372B (en) | Optimal well position deployment method and device for small fault block oil reservoir | |
| US20070179917A1 (en) | Intelligent design optimization method and system | |
| CN111259600B (en) | Optimization efficiency method for improving automatic well position optimization | |
| CN116644662B (en) | Well-arrangement optimization method based on knowledge embedded neural network proxy model | |
| CN114444402A (en) | Oil reservoir injection-production optimization method based on deep reinforcement learning | |
| CN116641688A (en) | Method, system, equipment and storage medium for improving gas reservoir recovery ratio by CO2 and sealing storage thereof | |
| CN114861368B (en) | Construction method of railway longitudinal section design learning model based on near-end strategy | |
| CN114721330B (en) | Cutting process energy consumption simulation prediction method based on CBAS-ELM algorithm | |
| CN116882323B (en) | Self-adaptive agent policy optimization method considering time sequence and subdivision tasks | |
| CN107491568B (en) | Complex structure well optimization design method based on real number coding genetic algorithm | |
| Kampolis et al. | Multilevel optimization strategies based on metamodel-assisted evolutionary algorithms, for computationally expensive problems | |
| CN113032953A (en) | Intelligent optimization method for injection and production parameters of water-drive oil reservoir of multi-well system | |
| CN114925578B (en) | Automatic optimization method for round steel pipe concrete short column based on particle swarm optimization and ABAQUS | |
| CN115222140A (en) | Production optimization machine learning offline model construction method inheriting historical experience | |
| CN112182969B (en) | Method for improving robustness and optimization effect of automatic well position optimization algorithm | |
| CN111209674B (en) | River channel sand modeling method and device and readable storage medium | |
| CN114818128A (en) | Ship body local curved surface optimization neural network modeling method and ship body local curved surface optimization method | |
| CN115510752A (en) | Data-driven lateral drilling well position optimization method and device | |
| CN115221623A (en) | Ship body hydrodynamic configuration optimization design flow architecture based on artificial intelligence technology | |
| KR102101389B1 (en) | The method for numerical simulation using the well-balanced scheme and high order for the shallow water equation in the numerical analysis |
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 |