CN117574755B - Hierarchical multistage optimization method for fracturing parameters of horizontal well of shale reservoir well factory - Google Patents
Hierarchical multistage optimization method for fracturing parameters of horizontal well of shale reservoir well factory Download PDFInfo
- Publication number
- CN117574755B CN117574755B CN202311407780.7A CN202311407780A CN117574755B CN 117574755 B CN117574755 B CN 117574755B CN 202311407780 A CN202311407780 A CN 202311407780A CN 117574755 B CN117574755 B CN 117574755B
- Authority
- CN
- China
- Prior art keywords
- model
- well
- fracturing
- parameters
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 105
- 238000005457 optimization Methods 0.000 title claims abstract description 84
- 238000010276 construction Methods 0.000 claims abstract description 42
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 39
- 238000012614 Monte-Carlo sampling Methods 0.000 claims abstract description 19
- 239000011435 rock Substances 0.000 claims abstract description 17
- 238000010206 sensitivity analysis Methods 0.000 claims abstract description 8
- 238000000556 factor analysis Methods 0.000 claims abstract description 5
- 230000008878 coupling Effects 0.000 claims abstract description 4
- 238000010168 coupling process Methods 0.000 claims abstract description 4
- 238000005859 coupling reaction Methods 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 44
- 238000004088 simulation Methods 0.000 claims description 30
- 239000003921 oil Substances 0.000 claims description 29
- 238000005070 sampling Methods 0.000 claims description 26
- 238000013461 design Methods 0.000 claims description 21
- 238000004519 manufacturing process Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 16
- 239000003795 chemical substances by application Substances 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000035699 permeability Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 238000011160 research Methods 0.000 claims description 12
- 238000007637 random forest analysis Methods 0.000 claims description 11
- 230000000694 effects Effects 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 9
- 238000010801 machine learning Methods 0.000 claims description 7
- 230000008901 benefit Effects 0.000 claims description 6
- 239000010779 crude oil Substances 0.000 claims description 6
- 230000009286 beneficial effect Effects 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 230000000704 physical effect Effects 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000035945 sensitivity Effects 0.000 claims description 4
- 230000001360 synchronised effect Effects 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 230000000295 complement effect Effects 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 239000012530 fluid Substances 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 239000003129 oil well Substances 0.000 claims description 3
- 230000002787 reinforcement Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000003313 weakening effect Effects 0.000 claims description 3
- 241000257303 Hymenoptera Species 0.000 claims description 2
- 238000012938 design process Methods 0.000 claims description 2
- 238000003908 quality control method Methods 0.000 claims description 2
- 238000000342 Monte Carlo simulation Methods 0.000 description 5
- 230000006978 adaptation Effects 0.000 description 5
- 230000035772 mutation Effects 0.000 description 5
- 239000013598 vector Substances 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005465 channeling Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- 241001415846 Procellariidae Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000004083 survival effect Effects 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
- E21B43/25—Methods for stimulating production
- E21B43/26—Methods for stimulating production by forming crevices or fractures
-
- 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
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- 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)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Mining & Mineral Resources (AREA)
- Data Mining & Analysis (AREA)
- Geology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Fluid Mechanics (AREA)
- Environmental & Geological Engineering (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Computer Graphics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a hierarchical multilevel optimization method for fracturing parameters of a horizontal well of a shale reservoir well factory, which comprises the following steps: acquiring data required by construction and geological attribute modeling; interpretation of results by complementing the corrected seismic and logging; using the single-well core and logging mechanical parameters to establish a reservoir rock mechanical physical field model in a coupling way; establishing a three-dimensional crack extension model under a multi-well fracturing mode of a well platform by utilizing numerical simulation software; carrying out main control factor analysis on the parameters by using a sensitivity analysis method; expanding a sample set by improving a Monte Carlo sampling method; an optimization algorithm is used for the proxy model using a differential evolution optimization algorithm. The multi-stage optimization method provided by the invention divides the full-zone fracturing optimization problem into sub-problems, brings the inner-layer optimization result into the outer-layer optimization as constraint, establishes the optimization method of the multi-element fracturing construction parameters of the shale reservoir well factory, and provides a scientific, economical and effective solution for improving the multi-well fracturing operation efficiency of the shale reservoir horizontal well.
Description
Technical Field
The invention relates to the technical field of oil and gas field development, in particular to a hierarchical multilevel optimization method for fracturing parameters of a horizontal well of a shale reservoir well factory.
Background
Volumetric fracturing is the primary way of developing unconventional oil and gas resources such as shale reservoirs at present, and well factory fracturing modes. The development of unconventional oil and gas resources by adopting a horizontal well technology still faces a common problem, namely how to optimize parameters such as the length of a horizontal well, the number of artificial cracks, the crack spacing, the construction section length, the number of clusters in the section, the number of holes of each cluster and the like, so as to achieve the purposes of slowing down yield decrease and improving recovery ratio. And the result of main control factor analysis shows that the fracturing construction parameters have a certain influence on the post-fracturing productivity. However, whether the current fracturing construction parameters are suitable for the research area or not, and whether part of parameters have space for further optimization or not need further research.
According to the fact that the number of the fracturing construction parameters in a common site is large, sensitive parameters are selected to optimize according to the result of sensitive analysis, and therefore the calculation cost of optimization is reduced. In addition, a proxy model needs to be constructed, namely an efficient mathematical approximation model, and the calculation efficiency can be remarkably improved, so that the model is gradually developed into a new calculation method, is widely applied to the aspects of oil reservoir numerical simulation calculation, optimization design, inverse analysis and the like, and greatly improves the analysis efficiency of oil reservoir numerical simulation problems. The existing agent model commonly used mainly comprises the following steps: polynomial response surface proxy model, radial basis proxy model, kriging proxy model, artificial neural network proxy model, support vector regression proxy model, mobile least squares proxy model, etc. The existing fracturing parameters are multiple in sources, abnormal value deletion exists among different parameters, meanwhile, more influencing factors are not preprocessed, errors exist in subsequent simulation results easily, and therefore the calculation space samples are required to be expanded through a sampling method. The prior Monte Carlo method is an important method for sample sampling treatment, but has the problems of more sampling times and large variance coefficient, so that the subsequent oil reservoir numerical simulation result has deviation, and the improvement of the Monte Carlo simulation method is necessary to realize the improvement of the sampling efficiency.
The variable types of the multi-fracturing parameter optimization design problem of the shale reservoir horizontal well pattern are complex (integer and non-integer variables), the variable dimensions are high, the variables are interrelated, the number of constraint conditions is large, the constraint condition types are large, and the like. Although intelligent optimization algorithms solve many optimization problems in recent years, when dealing with large-scale optimization problems, local optimization may still be involved, because the performance of the optimization algorithm is rapidly degraded with the increase of decision variables. Therefore, a great amount of optimization design work is required to be carried out on the basis of the existing single well fracturing parameter optimization design scheme of the horizontal well, a multi-stage optimization method is required to be established, the problem is divided into two sub-problems of an inner layer and an outer layer, the single well fracturing parameters of the inner layer are optimized firstly, and then the inner layer results are taken as constraint bands to enter the outer layer to optimize well pattern parameters. Intelligent algorithm optimization is selected for each sub-problem. Compared with single well optimization and single factor optimization results, the research scheme for optimizing the whole-area engineering parameters from the whole angle is more reasonable and effective.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, provides a layered multistage optimization method for fracturing parameters of a horizontal well of a shale reservoir well factory, provides a multistage optimization method, divides the problem of full-zone fracturing optimization into sub-problems, introduces an inner layer optimization result into an outer layer optimization as constraint, considers that inter-well interference does not occur in the outer layer optimization as constraint, establishes an optimization method for multi-element fracturing construction parameters of the shale reservoir well factory, and provides a scientific, economical and effective solution for improving the multi-well fracturing operation efficiency of the shale reservoir horizontal well.
The invention relates to a method for hierarchical multilevel optimization of fracturing parameters of a horizontal well of a shale reservoir well factory, which adopts the technical scheme that the method comprises the following steps:
Step 1: acquiring data required by construction and geological attribute modeling; because the earthquake and outcrop data are limited, a logging interpretation model is established by using core logging data to obtain a geological model and numerical simulation data, when the data volume is insufficient, reservoir parameter prediction is carried out by a machine learning method to complement missing parameters, attribute modeling is realized by adopting a kriging interpolation or parameter prediction method based on small sample learning, and the later geological attribute modeling precision is improved by using geological statistics information;
Step 2: the corrected earthquake and logging interpretation result is complemented, and a three-dimensional shale reservoir geological structure model is constructed based on parameters of permeability, porosity and oil saturation; based on interpretation results of seismic ants and imaging logging, combining on-site core observation, realizing multi-scale natural fracture modeling by taking a weak surface of a bedding surface and a lithology change interface as constraints and adopting a discrete fracture network DFN modeling key technology, carrying out reinforcement correction on the density and attribute parameters of well point observation fractures, and establishing a multi-scale shale reservoir discrete natural fracture model of a research area;
Step 3: the weakening effect of natural cracks on Young modulus and Poisson ratio of surrounding rock is comprehensively considered by utilizing single well core and logging mechanical parameters, and a reservoir rock mechanical physical field model is established through coupling; establishing an oil reservoir numerical simulation model by using the fractured production well, and obtaining an oil reservoir pressure field model by fitting production data; combining the regional stress background, the rock mechanical physical field and the reservoir pressure field, and establishing a three-dimensional ground stress field model by adopting a finite element method;
Step 4: based on the constructed shale reservoir model, a three-dimensional crack expansion model under a multi-well fracturing mode of a well platform is established by utilizing numerical simulation software, and aiming at the problem of horizontal well fracturing, the conventional sequential or zip-type fracturing is not easy to control an inter-well induced stress field, so that sequential or zip-type fracturing is adopted; based on a commercial software simulation sequence or a crack extension process of the zipper type fracturing, analyzing influence factors of a crack extension rule to obtain the relation between different parameter combinations and a crack control reserve, and providing guidance for the optimal design of the multi-well sequence or the zipper type fracturing;
step 5: carrying out crack extension main control factor analysis on the parameters by using a sensitivity analysis method, processing and retaining the characteristics with obvious influence on the results by the high-dimensional data, reducing similar characteristics, and analyzing the object to be analyzed to contain geological parameters, crack parameters and construction parameters; finally, core factors influencing the yield of multi-well fracturing of the horizontal well are obtained, the data dimension is reduced, the operation is simplified, and the purposes of improving the data processing speed and reducing the cost are achieved;
Step 6: expanding a sample set by improving a Monte Carlo sampling method by using core factors and numerical simulation results which influence the transformation effect, and constructing a platform well pattern fracturing proxy model based on the sample set, wherein the proxy model is established by adopting a radial basis function; the agent model is beneficial to simplifying the calculated amount without calling a numerical simulation platform when an optimization algorithm is used, optimizing the searching range to be larger and obtaining a fracturing construction scheme which is closer to an optimal solution;
Step 7: using a differential evolution optimization algorithm to use an optimization algorithm for the agent model, and taking the maximum net present value as an objective function; in the problem of optimizing the well pattern parameters of the horizontal well, more variables are needed to be optimized, including the crack parameters and the well pattern parameters of a single well; and (3) adopting a hierarchical optimization method for the inner layer and the outer layer, optimizing the single well crack parameters of the inner layer, and taking the inner layer result as a restraint belt to the outer layer to optimize the well pattern parameters.
Preferably, the method for establishing the shale gas logging interpretation model based on the core data and the field data by using a machine learning method comprises the following steps: formation pressure, porosity, oil saturation, permeability; because of the limitation of the data of the problem, the small sample learning method can establish an accurate model by using limited data, and a random forest method is selected for parameter prediction, so that the random forest algorithm has the advantages of overfitting resistance, high noise tolerance and less adjustment parameters.
Preferably, the construction of the construction site model should include a geologic model, a three-dimensional fracture model, an attribute model, a rock mechanics model and a ground stress model, wherein in the above model construction, the established geologic model needs to be constrained by a trend body fitted by a wave impedance inversion body, and the rock mechanics and ground stress models should be quality controlled by data interpreted by a single well hard spot.
Preferably, for the multi-well fracturing problem, the synchronous fracturing method has long operation period, high construction cost and larger risk of cross flow among wells, so sequential or zip-type fracturing is adopted, the fracturing construction period is shortened by alternately carrying out fracturing and perforation operations on two wells, the fracturing cost is saved, the horizontal platform well sequential or zip-type fracturing crack expansion research is carried out by utilizing commercial software, the production dynamic data and the fluid data are obtained by high-pressure physical property data, mine test data and core displacement data in a laboratory, the modeling process needs to complete the coarsening of a fine geological model, the processing of capillary pressure data, the processing of a relative permeability curve, the initialization of a numerical model and the processing of the production dynamic data, and finally, a full-area numerical simulation model is established, and model parameters are adjusted based on historical data fitting.
Preferably, the geological parameters include: reservoir pressure, permeability, porosity, crude oil viscosity, stress sensitivity coefficient; the fracture parameters include: the number of cracks, the included angle of the cracks, the half length of the cracks and the interval of the cracks; the construction parameters include: well spacing, row spacing, number of fracturing stages, proppant dose.
Preferably, the parameters are subjected to sensitivity analysis and screening to influence core factors of the transformation effect, a platform well pattern fracturing proxy model is sampled and constructed through a Monte Carlo sampling method, the proxy model is selected to be built by adopting a radial basis function, and the purpose of constructing the proxy model is to simplify calculation.
Preferably, the method for improving Monte Carlo sampling is adopted to expand the collected sample value space, and when the Monte Carlo sampling is actually improved, the cross entropy important sampling method and the scattered sampling method are combined to construct an approximate function, so that the sampling times and variance coefficients of the algorithm are reduced, and the calculation efficiency of the final improved Monte Carlo sampling algorithm is improved.
Preferably, the method for constructing the fracturing agent model mainly comprises a response surface, a Kriging model, a radial basis function and a support vector machine method, and the radial basis function has the advantages of isotropy and simple form, is widely applied, is a model constructed by taking the radial function as a basis function through linear superposition, and can be expressed as follows:
,
wherein: n is the number of sample points; for the point to be measured x and the ith sample point/> A Euclidean distance between them; /(I)The weight coefficient of the sample point; /(I)As a basis function, the commonly used basis function form is mainly polynomial/>Gauss/>Thin sample strip/>And cube/>Wherein c is a smoothing parameter, and r is the Euclidean distance between the point x to be measured and any sample point.
Preferably, the maximum net present value is used as an objective function to optimize the fracturing construction parameters of the well pattern of the horizontal well, a hierarchical optimization method aiming at the well pattern of the horizontal well is designed, and the objective function is established firstly:
,
,
,
Wherein NPV represents Shan Jingjing present values; b is the discount rate,%; t is the production age of the oil well; p 0 is the price of crude oil, yuan/m 3;Qoil is the oil yield of one year, and m 3/year; f is the fracturing cost, yuan; c op is the operation maintenance cost of one year; c tax is the sum of the tax types, yuan/m 3.
Preferably, the hierarchical optimization method is to decompose a complex engineering system design problem into a system-level optimization and a plurality of parallel sub-problem optimization, in the process of optimizing design, the system transmits expected values of system design variables to all the sub-problems, all the sub-problems make the difference between the sub-problem results and the expected values of the design variables transmitted by the system-level minimum on the premise of meeting the constraint conditions of the subject, all the sub-problem optimization results are returned to the system level, the system coordinates the inconsistency of the design variables among all the sub-problems through consistency constraint, all the zone fracturing parameters in the body are combined into a system-level problem, all the sub-problems are combined into single well parameters, and the sub-problems are optimized by adopting a differential evolution algorithm, and the fracturing parameter combination with the maximum zone clean value is obtained by taking the non-channeling crack as constraint.
Compared with the prior art, the invention has the following beneficial effects:
1. the method solves the problem of insufficient modeling data, establishes a shale gas logging interpretation model by utilizing a random forest method based on core data and field data, and comprises the following steps: the introduction of the small sample learning method can establish an accurate model by using limited labeling data.
2. The method adopts a sequential or zip-type fracturing method aiming at the problem of multi-well optimization of the horizontal well, and has strong inter-well stress interference due to asymmetric crack extension phenomenon in the multi-well fracturing process, so that the transverse extension of internal cracks is restrained, and compared with a synchronous fracturing scheme, the zip-type fracturing scheme has better performance in the aspects of improving the complexity of the cracks and increasing the surface area of the cracks, and is beneficial to improving the oil gas yield.
3. The invention provides a fracturing agent model which is established by adopting an agent model technology and adopting a radial basis function algorithm, the agent model has the function of achieving the purpose of simplifying calculation while representing the relation between parameters and fracturing transformation effect, the traditional optimization problem needs to call a numerical simulation platform, the calculated amount is large, and the iteration number is limited. According to the method, the training set parameters are obtained by using the improved Monte Carlo sampling method, the traditional Monte Carlo method is improved by selecting a mode of combining the cross entropy important sampling method and the scattered sampling method, the variance can be reduced, the sampling operation efficiency is improved, and the agent model is optimized.
4. In order to efficiently solve the large-scale optimization problem, the invention provides a multi-stage optimization method, the large-scale optimization problem is decomposed into two sub-problems, decision variables are divided into two layers, a differential evolution algorithm is selected to optimize a single well problem, as an inner layer result, the result of the inner optimization problem is a constraint condition of an outer full-area optimization problem, and the optimal fracturing construction parameters and the number and positions of well platforms, which take no interference as constraint and the maximum result of NPV in the whole area, are obtained through multiple iterations of the outer layer optimization algorithm.
Drawings
FIG. 1 is a flow chart of a method for providing a hierarchical multi-level optimization design of volumetric fracturing parameters of a shale reservoir well factory;
FIG. 2 is a flow chart of a method of multi-stage optimization of a platform well fracturing hierarchy;
FIG. 3 is a schematic diagram of a shale reservoir platform research well group fracturing natural fracture modeling result;
FIG. 4 is a schematic diagram of a shale reservoir platform well factory fracturing dual horizontal well bore configuration;
FIG. 5 is a graph of fracture propagation reform volume results for a shale reservoir platform well factory;
fig. 6 is a graph of comparison of fracture reform volumes before and after a multi-stage optimization method for fracturing and layering in shale reservoir platform wells.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Embodiment 1, the method for hierarchical multistage optimization of fracturing parameters of horizontal wells of shale reservoir well factories, disclosed by the invention, comprises the following steps of:
Step 1: acquiring data required by construction and geological attribute modeling; because the earthquake and outcrop data are limited, the plane distribution and the section distribution of the whole research area are difficult to be explained by acquiring data required by modeling, therefore, partial parameters can be obtained according to the correlation between the research parameters and the logging parameters, a logging interpretation model is required to be established by using core logging data to acquire a geological model and numerical simulation data, when the data volume is insufficient, reservoir parameter prediction is carried out by a machine learning method to complement missing parameters, attribute modeling is realized by adopting a kriging interpolation or a parameter prediction method based on small sample learning, and the modeling precision of later geological attributes is improved by using geological statistics information;
step 2: the method comprises the steps of establishing a fault skeleton model based on the obtained permeability, porosity and oil saturation parameters by supplementing corrected earthquake and logging interpretation results, determining intersection relations of all faults based on three-dimensional earthquake interpretation results to obtain a reasonable fault model, and establishing a three-dimensional shale reservoir geological structure model based on the earthquake interpretation level as constraint; in addition, multi-source data described by combining with natural cracks are used for explaining faults and large-scale cracks through seismic ant body data, medium-small-scale cracks are interpreted based on logging data and core crack identification results, seismic ant body interpretation results and imaging logging are used as the basis, on-site core observation is combined, multi-scale natural crack modeling is realized through taking a layer-surface weak plane and lithology change interface as constraints and adopting a discrete crack network DFN modeling key technology, an established regional crack development intensity field is used as constraints, well point observation crack density and attribute parameters are subjected to reinforcement correction, and a multi-scale shale reservoir discrete natural crack model of a research area is established;
Step 3: the weakening effect of natural cracks on Young modulus and Poisson ratio of surrounding rock is comprehensively considered by utilizing single well core and logging mechanical parameters, and a reservoir rock mechanical physical field model is established through coupling; establishing an oil reservoir numerical simulation model by using the fractured production well, and obtaining an oil reservoir pressure field model by fitting production data; according to the geological features of the oil reservoir, a lithology model, a reservoir physical hole saturation model, an oil layer model and the like are established by utilizing logging interpretation result data and combining a three-dimensional seismic inversion data body. Based on the core data of the horizontal well and the logging interpretation result, establishing a quantitative relation between reservoir parameters and seismic elastic parameters by using a petrophysical analysis method, obtaining elastic parameters such as transverse wave impedance, longitudinal wave impedance and the like, converting the seismic elastic parameters into shale reservoir parameters, and finally establishing an attribute model by adopting sequential Gaussian simulation; combining the regional stress background, the rock mechanical physical field and the reservoir pressure field, and establishing a three-dimensional ground stress field model in a simulation mode by adopting a finite element method based on a shale reservoir rock mechanical model containing layer cracks and natural crack characteristics;
Step 4: based on the constructed shale reservoir model, a three-dimensional crack expansion model under a multi-well fracturing mode of a well platform is established by utilizing numerical simulation software, and aiming at the problem of horizontal well fracturing, the conventional sequential or zip-type fracturing is not easy to control an inter-well induced stress field, so that sequential or zip-type fracturing is adopted; based on a commercial software simulation sequence or a crack extension process of the zipper type fracturing, analyzing influence factors of a crack extension rule to obtain the relation between different parameter combinations and a crack control reserve, and providing guidance for the optimal design of the multi-well sequence or the zipper type fracturing;
Step 5: carrying out crack extension main control factor analysis on the parameters by using a sensitivity analysis method, processing and retaining the characteristics with obvious influence on the results by the high-dimensional data, reducing similar characteristics, and analyzing the object to be analyzed to contain geological parameters, crack parameters and construction parameters; finally, core factors influencing the yield of multi-well fracturing of the horizontal well are obtained, data dimension reduction and simplified operation are realized, as shale reservoir gas has obvious multi-scale characteristics, main parameters influencing the flow conductivity of the fracture are screened by multi-factor shadows in the fracture expansion process, the purpose of improving the data processing speed is realized, the time and the cost are saved, and the purpose of improving the data processing speed and reducing the cost is realized;
Step 6: expanding a sample set by improving a Monte Carlo sampling method by using core factors and numerical simulation results which influence the transformation effect, and constructing a platform well pattern fracturing proxy model based on the sample set, wherein the proxy model is established by adopting a radial basis function; the agent model is beneficial to simplifying the calculated amount without calling a numerical simulation platform when an optimization algorithm is used, optimizing the searching range to be larger and obtaining a fracturing construction scheme which is closer to an optimal solution;
Step 7: using a differential evolution optimization algorithm to use an optimization algorithm for the agent model, and taking the maximum net present value as an objective function; in the optimization problem of the well pattern parameters of the horizontal well, the variables to be optimized are more, including the fracture parameters (diversion capacity, interval, half-fracture length and the like) and the well pattern parameters (well spacing, rejection, well pattern form and the like) of the single well; and (3) adopting a hierarchical optimization method for the inner layer and the outer layer, optimizing the single well crack parameters of the inner layer, and taking the inner layer result as a restraint belt to the outer layer to optimize the well pattern parameters.
Establishing a shale gas logging interpretation model based on core data and field data by using a machine learning method, wherein the shale gas logging interpretation model comprises the following steps: formation pressure, porosity, oil saturation, permeability; most machine learning prediction methods require supervised learning on a large number of data sets, but due to the limitation of the data of the problem, small sample learning methods can build an accurate model with limited data, such as Support Vector Machines (SVMs), random Forests (RF), convolutional feedforward neural networks (CNNs); by selecting a random forest method for parameter prediction in comparison with the problem, the random forest algorithm is essentially an algorithm formed by combining a group of decision trees based on the traditional decision tree theory, and has the advantages of overfitting resistance, high noise tolerance and less adjustment parameters.
Random forest algorithms implement autonomous sampling of a data set by constructing a set of decision trees. The regression prediction model results are as follows:
,
in the formula: random forests are formed from a set of decision trees Combined, random vector/>Obeying an independent distribution, X represents the input vector, i.e. the number of decision subtrees.
The construction of the construction area model should include a geological model, a three-dimensional fracture model, an attribute model, a rock mechanics model and a ground stress model, wherein in the model construction, a trend body fitted by a wave impedance inversion body is needed to restrain the established geological model, and the rock mechanics and ground stress model should be subjected to quality control by data interpreted by a single well hard point.
For the multi-well fracturing problem, the synchronous fracturing method has long operation period, high construction cost and larger risk of cross flow among wells, so that sequential or zip-type fracturing is adopted, the fracturing construction period is shortened by alternately carrying out fracturing and perforation on two wells, and the fracturing cost is saved. Based on the established geological model, a crack model and a ground stress model. And carrying out horizontal platform well sequence or zip-type fracture propagation research by utilizing petrel commercial software, obtaining production dynamic data and fluid data through high-pressure physical property data, mine test data and core displacement data in a laboratory, wherein the modeling process is required to complete the processes of coarsening a fine geological model, processing capillary pressure data, processing a relative permeability curve, initializing a numerical model and processing the production dynamic data, finally establishing a full-area numerical simulation model, fitting and adjusting model parameters based on historical data, then carrying out full-area reserve fitting and historical fitting, then carrying out dynamic prediction, verifying the accuracy of the model by utilizing the production historical data (daily oil yield and bottom hole pressure) of a hydrocarbon reservoir, and accordingly adjusting the model parameters, so that the numerical simulation result of the adjusted model can reflect the real situation.
The geological parameters include: reservoir pressure, permeability, porosity, crude oil viscosity, stress sensitivity coefficient; the fracture parameters include: the number of cracks, the included angle of the cracks, the half length of the cracks and the interval of the cracks; the construction parameters include: well spacing, row spacing, number of fracturing stages, proppant dose. The above parameters are the main influencing factors affecting the horizontal well sequence or the zip-type fracturing productivity, wherein the fracture parameters and the construction parameters are the main parameters affecting the maximum retrofit volume.
And (3) carrying out sensitivity analysis and screening on parameters to influence core factors of the transformation effect, sampling and constructing a platform well pattern fracturing proxy model by a Monte Carlo sampling method, wherein the proxy model is constructed by adopting a radial basis function, and the purpose of constructing the proxy model is to simplify calculation.
The collected sample value space is expanded by adopting an improved Monte Carlo sampling method, when the Monte Carlo sampling is actually improved, the cross entropy important sampling method is combined with a scattered sampling method to construct an approximate function, so that the sampling times and variance coefficients of an algorithm are reduced, and the calculation efficiency of the final improved Monte Carlo sampling algorithm is improved.
The improved Monte Carlo method is used for sampling the core sensitivity factors. The method comprises the steps of following the following steps in the process of carrying out numerical simulation sampling on oil reservoirs by improving a Monte Carlo method, inputting basic data influencing the yield of a last fractured well, obtaining random numbers influencing the yield of the fractured well through sampling treatment, further carrying out final simulation on the yield of the fractured well of a well factory by a scattered sampling method, calculating a relevant variance coefficient, carrying out accuracy judgment, outputting a relevant result if sampling is reasonable, and re-selecting intermediate parameter values to carry out multiple iterations if sampling accuracy is not reasonable.
The method for constructing the fracturing agent model mainly comprises a response surface, a Kriging model, a radial basis function and a support vector machine method, wherein the radial basis function has the advantages of isotropy and simple form, is widely applied, is a model constructed by taking the radial function as a basis function through linear superposition, and can be expressed as follows:
,
wherein: n is the number of sample points; for the point to be measured x and the ith sample point/> A Euclidean distance between them; /(I)The weight coefficient of the sample point; /(I)As a basis function, the commonly used basis function form is mainly polynomial/>Gauss/>Thin sample strip/>And cube/>Wherein c is a smoothing parameter, and r is the Euclidean distance between the point x to be measured and any sample point.
The constructed horizontal well fracturing agent model comprises a single well fracturing model and a full-zone fracturing model, and is convenient for optimizing problem grading calling model solving. Firstly, a single well model is built, input parameters are fracturing construction parameters to be optimized, output parameters are parameters representing transformation effects such as fracture half length, fracture conductivity and the like, single-row and full-area models can be obtained from the single well model, a sample set is expanded through a Monte Carlo sampling method by core factors and numerical simulation results influencing the transformation effects, a horizontal well pattern fracturing proxy model of a platform is built by utilizing radial basis functions based on the sample set, a proxy model result is fitted with the numerical simulation results, the sampling method is utilized to continuously supplement a training set to optimize the proxy model until fitting accuracy reaches more than 0.8, and the proxy model result is considered to represent the numerical simulation result.
Optimizing the fracturing construction parameters of the well pattern of the horizontal well by taking the maximum net present value as an objective function, designing a hierarchical optimizing method aiming at the well pattern of the horizontal well, and firstly establishing the objective function:
,
,
,
Wherein NPV represents Shan Jingjing present values; b is the discount rate,%; t is the production age of the oil well; p 0 is the price of crude oil, yuan/m 3;Qoil is the oil yield of one year, and m 3/year; f is the fracturing cost, yuan; c op is the operation maintenance cost of one year; c tax is the sum of the tax types, yuan/m 3.
According to Shan Jingjing present value functions, a full-area net present value function can be obtained, and hierarchical optimization is carried out by taking the maximum full-area net present value as an objective function.
The hierarchical optimization method is to decompose a complex engineering system design problem into a system-level optimization and a plurality of parallel sub-problem optimization, in the optimization design process, the system transmits expected values of system design variables to all the sub-problems, all the sub-problems minimize the gap between the sub-problem results and the expected values of the design variables transmitted by the system level on the premise of meeting the constraint conditions of the subject, all the sub-problem optimization results are returned to the system level, the system coordinates the inconsistency of the design variables among all the sub-problems through consistency constraint, all the zone fracturing parameters in the system are combined into system-level problems, all the single well parameters are combined, and the sub-problems are optimized by adopting a differential evolution algorithm, and the fracturing parameter combination with the maximum total zone clean value is obtained by taking the non-pressure channeling crack as constraint.
The optimization selection intelligent optimization algorithm of the sub-problems, such as genetic algorithm, particle swarm algorithm, differential evolution algorithm and the like. Differential evolution algorithms use real number coding, differential-based simple mutation operations, and a "one-to-one" competitive survival strategy, reducing the complexity of the evolutionary computation operations compared to genetic algorithms. The differential evolution algorithm mainly comprises four parts of population initialization, mutation, crossover and selection.
(1) Population initialization
,
Wherein: i individual serial numbers in the population; j individual attribute sequence numbers; n p population sizes; d, individual dimension; the upper bound of the j-th variable; /(I) Lower bound of the j-th variable.
(2) Variation of
Mutation is the operation of generating a new individual from the original individual, and a new mutation vector is generated by the following formula:
,
wherein: r1, r2, r3 are random individual serial numbers; f is mutation operator [0,2]; g is the algebra of evolution.
(3) Crossover
The crossover is the operation of generating a new individual by a variant individual and a current individual according to a certain rule, mainly for increasing the diversity of interference parameter vectors, and the operation process is as follows:
,
Wherein: rand (j) is the j-th estimate of the random number generator between [0,1 ]; rnbr (i) is a randomly selected sequence; c R is a crossover operator, and takes on real numbers between [0,1 ].
(4) Selection of
The selection is to screen new individuals generated by the crossover operation, and the passing individuals enter the next generation. The value of the optimization function is called an adaptation value, and the adaptation value of the new individual is compared with the adaptation value of the current individual, and the individual mode of selecting smaller adaptation values is selected for screening, so that the adaptation value of the individual can be ensured to be gradually reduced through continuous iteration.
Firstly, establishing a reservoir physical property and mechanical parameter evaluation model constrained by geological information and logging information to obtain relevant parameters required by modeling, complementing and correcting the parameters, further constructing a ground stress model, carrying out horizontal well multi-well sequence or zip fracturing and yield numerical simulation by combining specific site construction parameters, and simultaneously carrying out history fitting and correction on the model by combining site data to determine boundary limits of the parameters; and further carrying out core fracture main control factor identification by a sensitivity analysis method, constructing a horizontal well yield proxy model of a well factory by adopting an improved Monte Carlo sampling method, taking core main control parameters which influence the fracturing modification effect by simulation initialization as input parameters into the proxy model, taking the maximum net present value as an objective function, taking a regression boundary limit as a constraint, and carrying out model parameter layering multistage optimization by using a differential evolution algorithm. When optimizing, the whole-zone fracturing optimization problem is divided into sub-problems, an inner layer optimization result is brought into an outer layer to be optimized as constraint, inter-well interference is not considered in the outer layer optimization as constraint, and an optimization method of multi-element fracturing construction parameters of a shale reservoir well factory is established, so that a scientific, economical and effective solution is provided for improving the multi-well fracturing operation efficiency of the shale reservoir horizontal well.
The above description is only a few preferred embodiments of the present invention, and any person skilled in the art may make modifications to the above described embodiments or make modifications to the same. Accordingly, the corresponding simple modifications or equivalent changes according to the technical scheme of the present invention fall within the scope of the claimed invention.
Claims (2)
1. A method for optimizing fracturing parameters of a horizontal well of a shale reservoir well in a layered and multistage manner is characterized by comprising the following steps: the method comprises the following steps:
Step 1: acquiring data required by construction and geological attribute modeling; because the earthquake and outcrop data are limited, a logging interpretation model is established by using core logging data to obtain a geological model and numerical simulation data, when the data volume is insufficient, reservoir parameter prediction is carried out by a machine learning method to complement missing parameters, attribute modeling is realized by adopting a kriging interpolation or parameter prediction method based on small sample learning, and the later geological attribute modeling precision is improved by using geological statistics information;
Step 2: the corrected earthquake and logging interpretation result is complemented, and a three-dimensional shale reservoir geological structure model is constructed based on parameters of permeability, porosity and oil saturation; based on interpretation results of seismic ants and imaging logging, combining on-site core observation, realizing multi-scale natural fracture modeling by taking a weak surface of a bedding surface and a lithology change interface as constraints and adopting a discrete fracture network DFN modeling key technology, carrying out reinforcement correction on the density and attribute parameters of well point observation fractures, and establishing a multi-scale shale reservoir discrete natural fracture model of a research area;
Step 3: the weakening effect of natural cracks on Young modulus and Poisson ratio of surrounding rock is comprehensively considered by utilizing single well core and logging mechanical parameters, and a reservoir rock mechanical physical field model is established through coupling; establishing an oil reservoir numerical simulation model by using the fractured production well, and obtaining an oil reservoir pressure field model by fitting production data; combining the regional stress background, the rock mechanical physical field and the reservoir pressure field, and establishing a three-dimensional ground stress field model by adopting a finite element method;
Step 4: based on the constructed shale reservoir model, a three-dimensional crack expansion model under a multi-well fracturing mode of a well platform is established by utilizing numerical simulation software, and sequential or zip-type fracturing is adopted for the fracturing problem of a horizontal well; based on a commercial software simulation sequence or a crack extension process of the zipper type fracturing, analyzing influence factors of a crack extension rule to obtain the relation between different parameter combinations and a crack control reserve, and providing guidance for the optimal design of the multi-well sequence or the zipper type fracturing;
step 5: carrying out crack extension main control factor analysis on the parameters by using a sensitivity analysis method, processing and retaining the characteristics with obvious influence on the results by the high-dimensional data, reducing similar characteristics, and analyzing the object to be analyzed to contain geological parameters, crack parameters and construction parameters; finally, core factors influencing the yield of multi-well fracturing of the horizontal well are obtained, the data dimension is reduced, the operation is simplified, and the purposes of improving the data processing speed and reducing the cost are achieved;
Step 6: expanding a sample set by improving a Monte Carlo sampling method by using core factors and numerical simulation results which influence the transformation effect, and constructing a platform well pattern fracturing proxy model based on the sample set, wherein the proxy model is established by adopting a radial basis function; the agent model is beneficial to simplifying the calculated amount without calling a numerical simulation platform when an optimization algorithm is used, optimizing the searching range to be larger and obtaining a fracturing construction scheme which is closer to an optimal solution;
Step 7: using a differential evolution optimization algorithm to use an optimization algorithm for the agent model, and taking the maximum net present value as an objective function; in the problem of optimizing the well pattern parameters of the horizontal well, more variables are needed to be optimized, including the crack parameters and the well pattern parameters of a single well; adopting a hierarchical optimization method, namely optimizing single well crack parameters of an inner layer by using an inner layer and an outer layer, and taking an inner layer result as a restraint belt into the outer layer to optimize well pattern parameters;
Establishing a shale gas logging interpretation model based on core data and field data by using a machine learning method, wherein the shale gas logging interpretation model comprises the following steps: formation pressure, porosity, oil saturation, permeability; because of the limitation of the data of the problem, the small sample learning method utilizes limited data to establish an accurate model, a random forest method is selected for parameter prediction, and the random forest algorithm has the advantages of overfitting resistance, high noise tolerance and less adjustment parameters;
The construction of the construction work area model comprises a geological model, a three-dimensional crack model, an attribute model, a rock mechanics model and a ground stress model, wherein in the construction of the models, the established geological model is constrained by a trend body fitted by a wave impedance inversion body, and the rock mechanics and ground stress models are subjected to quality control by data interpreted by single well hard points;
for the multi-well fracturing problem, the synchronous fracturing method has long operation period, high construction cost and larger risk of cross flow among wells, so sequential or zip-type fracturing is adopted, the fracturing construction period is shortened by alternately carrying out fracturing and perforation on two wells, the fracturing cost is saved, the horizontal platform well sequence or zip-type fracturing crack expansion research is carried out by utilizing commercial software, the production dynamic data and the fluid data are obtained by high-pressure physical property data, mine test data and core displacement data in a laboratory, the modeling process needs to complete coarsening of a fine geological model, processing of capillary pressure data, processing of a relative permeability curve, numerical model initialization and processing of the production dynamic data, and finally, a full-area numerical simulation model is established, and model parameters are adjusted based on historical data fitting;
The geological parameters include: reservoir pressure, permeability, porosity, crude oil viscosity, stress sensitivity coefficient; the fracture parameters include: the number of cracks, the included angle of the cracks, the half length of the cracks and the interval of the cracks; the construction parameters include: well spacing, row spacing, number of fracturing stages, proppant amount;
the method comprises the steps of performing sensitivity analysis and screening on parameters to influence core factors of transformation effects, sampling and constructing a platform well pattern fracturing proxy model by a Monte Carlo sampling method, wherein the proxy model is constructed by adopting a radial basis function, and the purpose of constructing the proxy model is to simplify calculation;
the collected sample value space is expanded by adopting an improved Monte Carlo sampling method, when the Monte Carlo sampling is actually improved, an approximate function is constructed by combining a cross entropy important sampling method and a scattered sampling method, so that the sampling times and variance coefficients of an algorithm are reduced, and the calculation efficiency of the final improved Monte Carlo sampling algorithm is improved;
The method for constructing the fracturing agent model comprises a response surface, a Kriging model, a radial basis function and a support vector machine method, wherein the radial basis function has the advantages of isotropy and simple form, is widely applied, is a model constructed by taking the radial function as a basis function through linear superposition, and is expressed as follows:
;
wherein: n is the number of sample points; for the point to be measured x and the ith sample point/> A Euclidean distance between them; /(I)The weight coefficient of the sample point; /(I)As a basis function, the basis function has a polynomial/>Gauss (Gauss)Thin sample strip/>And cube/>Wherein c is a smoothing parameter, and r is the Euclidean distance between the point x to be detected and any sample point;
the hierarchical optimization method is characterized in that a complex engineering system design problem is decomposed into a system-level optimization and a plurality of parallel sub-problem optimization, in the optimization design process, expected values of system design variables are transmitted to all the sub-problems by a system, the difference between a sub-problem result and the expected values of the design variables transmitted by the system-level is minimized on the premise that the constraint condition of the subject is met, the optimization result of all the sub-problems is returned to the system level, the system coordinates the inconsistency of the design variables among all the sub-problems through consistency constraint, the whole-area fracturing parameter combination is the system-level problem, the sub-problems are all single-well parameter combination, and the fracturing parameter combination with the maximum whole-area net-channeling value is obtained by adopting a differential evolution algorithm to optimize the sub-problems.
2. The method for hierarchical multilevel optimization of fracturing parameters of horizontal wells of shale reservoir well factories according to claim 1, which is characterized in that: optimizing the fracturing construction parameters of the well pattern of the horizontal well by taking the maximum net present value as an objective function, designing a hierarchical optimizing method aiming at the well pattern of the horizontal well, and firstly establishing the objective function:
;
;
;
Wherein NPV represents Shan Jingjing present values; b is the discount rate,%; t is the production age of the oil well; p 0 is the price of crude oil, yuan/m 3;Qoil is the oil yield of one year, and m 3/year; f is the fracturing cost, yuan; c op is the operation maintenance cost of one year; c tax is the sum of the tax types, yuan/m 3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311407780.7A CN117574755B (en) | 2023-10-27 | 2023-10-27 | Hierarchical multistage optimization method for fracturing parameters of horizontal well of shale reservoir well factory |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311407780.7A CN117574755B (en) | 2023-10-27 | 2023-10-27 | Hierarchical multistage optimization method for fracturing parameters of horizontal well of shale reservoir well factory |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117574755A CN117574755A (en) | 2024-02-20 |
CN117574755B true CN117574755B (en) | 2024-05-07 |
Family
ID=89861411
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311407780.7A Active CN117574755B (en) | 2023-10-27 | 2023-10-27 | Hierarchical multistage optimization method for fracturing parameters of horizontal well of shale reservoir well factory |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117574755B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117892559B (en) * | 2024-03-14 | 2024-06-14 | 西安现代控制技术研究所 | Ultra-remote guidance rocket overall coordination multidisciplinary hierarchical optimization method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016041189A1 (en) * | 2014-09-19 | 2016-03-24 | 杨顺伟 | Method for evaluating shale gas reservoir and seeking desert area |
CN108442911A (en) * | 2018-02-28 | 2018-08-24 | 西南石油大学 | A kind of shale gas horizontal well refracturing hydraulic fracture method for optimally designing parameters |
CN110704888A (en) * | 2019-07-04 | 2020-01-17 | 成都理工大学 | Unconventional oil and gas reservoir encrypted well volume fracturing construction parameter optimization design method |
CN111322050A (en) * | 2020-04-24 | 2020-06-23 | 西南石油大学 | Shale horizontal well section internal osculating temporary plugging fracturing construction optimization method |
CN115618759A (en) * | 2022-09-26 | 2023-01-17 | 中国石油化工股份有限公司 | Shale gas formation fracturing construction parameter optimization method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10942293B2 (en) * | 2017-07-21 | 2021-03-09 | Halliburton Energy Services, Inc. | Rock physics based method of integrated subsurface reservoir characterization for use in optimized stimulation design of horizontal wells |
-
2023
- 2023-10-27 CN CN202311407780.7A patent/CN117574755B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016041189A1 (en) * | 2014-09-19 | 2016-03-24 | 杨顺伟 | Method for evaluating shale gas reservoir and seeking desert area |
CN108442911A (en) * | 2018-02-28 | 2018-08-24 | 西南石油大学 | A kind of shale gas horizontal well refracturing hydraulic fracture method for optimally designing parameters |
CN110704888A (en) * | 2019-07-04 | 2020-01-17 | 成都理工大学 | Unconventional oil and gas reservoir encrypted well volume fracturing construction parameter optimization design method |
CN111322050A (en) * | 2020-04-24 | 2020-06-23 | 西南石油大学 | Shale horizontal well section internal osculating temporary plugging fracturing construction optimization method |
CN115618759A (en) * | 2022-09-26 | 2023-01-17 | 中国石油化工股份有限公司 | Shale gas formation fracturing construction parameter optimization method |
Non-Patent Citations (2)
Title |
---|
体积压裂水平井产量影响因素及裂缝参数优化研究;靳国栋;中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑;20200715;全文 * |
天然断裂带干扰下的复合暂堵压裂工艺参数优化;宋志同 等;石油地质与工程;20230930;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117574755A (en) | 2024-02-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Artus et al. | Optimization of nonconventional wells under uncertainty using statistical proxies | |
CN102041995B (en) | System for monitoring complicated oil deposit flooding conditions | |
US9026416B2 (en) | System and method of grid generation for discrete fracture modeling | |
CN104615862B (en) | Method for determining well position of high-water-content oil field based on evolutionary algorithm | |
US10846443B2 (en) | Discrete irregular cellular models for simulating the development of fractured reservoirs | |
Nasrabadi et al. | Well placement optimization: A survey with special focus on application for gas/gas-condensate reservoirs | |
CN117574755B (en) | Hierarchical multistage optimization method for fracturing parameters of horizontal well of shale reservoir well factory | |
CN106104590A (en) | Multistage oil field design optimization under Bu Quedingxing | |
CN109543828A (en) | A kind of intake profile prediction technique based under condition of small sample | |
Wang et al. | Fast history matching and optimization using a novel physics-based data-driven model: an application to a diatomite reservoir | |
CN113610945B (en) | Ground stress curve prediction method based on hybrid neural network | |
US20120059634A1 (en) | Method for optimizing the positioning of wells in an oil reservoir | |
Zhang et al. | Surrogate-assisted multiobjective optimization of a hydraulically fractured well in a naturally fractured shale reservoir with geological uncertainty | |
Maschio et al. | Data assimilation for uncertainty reduction using different fidelity numerical models | |
Sankaran et al. | Data Analytics in Reservoir Engineering | |
CN113343574A (en) | Mishrif group lithology logging identification method based on neural network | |
CN116911216B (en) | Reservoir oil well productivity factor assessment and prediction method | |
Vaseghi et al. | Generalized Multi-Scale Stochastic Reservoir Opportunity Index for enhanced well placement optimization under uncertainty in green and brownfields | |
Harb et al. | BHPSO combined with statistical net hydrocarbon thickness map for well placement optimization under uncertainty | |
AlAmeri et al. | History matching under geological constraints coupled with multiobjective optimization to optimize MWAG performance: a case study in a giant onshore carbonate reservoir in the Middle East | |
Luo et al. | Optimization Method of Hydraulic Fracturing Design for Horizontal Shale Gas Well Based on Artificial Neural Network and Genetic Algorithm | |
CN114004100B (en) | Oil reservoir assisted history fitting and optimization simulation method | |
CN114755744A (en) | Total organic carbon well logging interpretation method and system based on mud shale heterogeneity characteristics | |
Al-Aghbari et al. | Hybrid approach of using bi-objective genetic programming in well control optimization of waterflood management | |
CN117454755B (en) | Shale oil three-dimensional well pattern fracturing multi-element parameter optimization design method |
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 |