CN115577645B - Construction method and prediction method of combustion and explosion fracturing fracture range prediction model - Google Patents
Construction method and prediction method of combustion and explosion fracturing fracture range prediction model Download PDFInfo
- Publication number
- CN115577645B CN115577645B CN202211568186.1A CN202211568186A CN115577645B CN 115577645 B CN115577645 B CN 115577645B CN 202211568186 A CN202211568186 A CN 202211568186A CN 115577645 B CN115577645 B CN 115577645B
- Authority
- CN
- China
- Prior art keywords
- fracture
- model
- fracturing
- result
- combustion
- 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 61
- 238000010276 construction Methods 0.000 title claims abstract description 21
- 238000004880 explosion Methods 0.000 title claims description 50
- 238000002485 combustion reaction Methods 0.000 title claims description 29
- 238000005422 blasting Methods 0.000 claims abstract description 25
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 46
- 230000000694 effects Effects 0.000 claims description 27
- 238000004088 simulation Methods 0.000 claims description 23
- 238000013461 design Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 238000003066 decision tree Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 238000005336 cracking Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 abstract description 3
- 238000005474 detonation Methods 0.000 description 18
- 238000012360 testing method Methods 0.000 description 9
- 238000010801 machine learning Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 239000011435 rock Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000004927 clay Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- -1 poisson ratio Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000003079 shale oil Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Computer Hardware Design (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a construction method and a prediction method of a blasting fracturing fracture range prediction model, belonging to the technical field of oil and gas field development.
Description
Technical Field
The invention belongs to the technical field of oil and gas field development, and particularly relates to a construction method and a prediction method of a combustion and explosion fracturing fracture range prediction model.
Background
The hydraulic fracturing technology is the shale reservoir transformation technology which is most widely applied and mature in process at present, but the problems that a good seepage channel is difficult to form in conventional fracturing, water resources are short, water lock and clay expansion are caused, reservoir pollution is serious and the like exist, so that methane in-situ explosion is utilized to reduce reservoir pollution and promote multiple crack expansion which is not controlled by stress. Methane explosion fracturing is used as a new method for shale gas reservoir reconstruction, and has many difficulties and challenges in the aspects of development mode and parameter optimization, so that further research is needed.
In shale oil and gas reservoirs, the traditional hydraulic fracturing production increase aims to realize the maximization of oil and gas yield by creating an effective reservoir modification volume (SRV) around a well, in the blasting fracturing operation, the fracturing effect is evaluated by calculating the range of a fracturing zone generated near a blasting point, however, the factors influencing the fracturing effect are more, including reservoir geological static parameters, fracturing construction parameters, production dynamic parameters and other factors, the relationship among the parameters is complicated, the multiple parameters and the fracturing effect are not simple functional relationships, and the relationship among the parameters is difficult to express by a single expression.
Normally, a numerical simulation model is continuously called to design and optimize a fracturing process, wherein the methane explosion fracturing fracture expansion numerical simulation model created based on a continuous discontinuous unit method has certain correctness, but has the following problems: firstly, the evaluation can be performed only after the fracturing stimulation operation process is completed, and some construction parameters such as peak pressure (explosion source density) and the like cannot be dynamically modified in real time, which is not beneficial to timely adjusting the scheme. Secondly, the method has the limitations of long numerical simulation time, inaccurate fracture parameter description, single seepage mechanism and the like.
Disclosure of Invention
The invention provides a construction method and a prediction method of a combustion and explosion fracturing fracture range prediction model, and aims to solve the problems in the prior art.
In order to achieve the purpose, the invention provides a construction method of a combustion and explosion fracturing range prediction model, which comprises the following steps:
acquiring parameter data of expansion of a plurality of methane combustion-explosion fracturing fractures;
determining a crack propagation result according to the acquired parameter data to form an original data set;
preprocessing the original data set;
and (4) inputting the data set obtained after pretreatment into a gradient lifting grid XGboost, and constructing a model for predicting the blasting fracturing range.
Preferably, in the method for constructing the combustion and explosion fracture range prediction model, the result of fracture propagation comprises fracture range length and width values of the fracture;
correspondingly, the step of inputting the preprocessed data set into the gradient lifting grid XGboost and constructing a combustion and explosion fracturing fracture range prediction model comprises the following steps:
and taking the preprocessed data as the input of the gradient lifting grid XGboost, and taking the fracture range length and the width value of the crack corresponding to the parameter data as the output for training so as to obtain an initial model for predicting the fracture range of the blasting fracture.
Preferably, in the method for constructing the combustion and explosion fracturing range prediction model, the model of the gradient lifting grid XGBoost is as follows:
wherein x is i Is an input sample;
f m (x i ) The predicted result of the m-th tree is obtained;
Preferably, in the method for constructing the combustion and explosion fracturing range prediction model, model parameters in the initial model are adjusted to obtain a target model, and the adjustment parameters include the number n _ estimators of decision trees in the model, the maximum tree depth max _ depth, the minimum sample weight min child _ weight required by leaf nodes and the descending value gamma of the minimum loss function, and the proportion subsample of sample data randomly taken by each decision tree.
Preferably, in the method for constructing the combustion and explosion fracturing range prediction model, n _ estimators =200, max_depth =10, min child _ weight =3, gamma =0.1, and subsample =0.8.
Preferably, in the method for constructing the combustion and explosion fracturing range prediction model, after the step of adjusting the model parameters in the initial model to obtain the target model, the method further includes:
and evaluating the target model, wherein an evaluation formula is as follows:
wherein R is 2 As a result of the evaluation;
y i is the true result of the crack propagation;
n is the number of samples;
Preferably, in the construction method of the combustion and explosion fracture range prediction model, the fracture expansion result comprises fracture range length and width values of the fracture;
accordingly, the step of preprocessing the raw data set comprises:
calculating the correlation between factors influencing the fracturing effect and the fracture range length and width value of the fracture, and determining main control factors influencing the methane explosion fracturing effect;
carrying out data normalization processing on the determined main control factors influencing the methane combustion and explosion fracturing effect;
wherein, the calculation formula of the correlation is as follows:
wherein x is i Is the inputted parameter data;
y i as parameter data x i The true result of the corresponding crack propagation;
In order to achieve the above object, the present invention further provides a prediction method of a combustion and explosion fracturing range prediction model, where the prediction method includes the following steps:
and predicting the fracture range in the fracturing process under the scheme to be predicted according to the model constructed by the construction method.
In order to achieve the above object, the present invention further provides a terminal, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of constructing a blast fracture rupture zone prediction model described above.
In order to achieve the above object, the present invention further provides a computer readable storage medium storing a computer program, wherein the computer program is configured to implement the above method for constructing a blasting fracture range prediction model when executed by a processor.
The invention has the following beneficial effects:
according to the method, parameter data of multiple methane explosion fracturing crack expansions are obtained, the crack expansion result is determined according to the obtained parameter data, an original data set is formed, the original data set is preprocessed, the preprocessed data set is input into a gradient lifting grid XGboost, a model for explosion fracturing range prediction is constructed, and therefore a prediction model is constructed based on a machine learning XGboost method, on the premise that prediction accuracy is guaranteed, the efficiency of fracturing range calculation is effectively improved, and the fracturing effect can be evaluated in real time;
furthermore, a plurality of blasting fracturing samples are determined by using an orthogonal test design method, a proxy model which can screen out the original numerical simulation model influencing the fracturing effect and accurately describing the fracturing effect by using a positive numerical method is constructed by using fewer sample points, and the precision of the model is ensured; based on the main control factors of Pearson (Pearson) correlation results and eliminating irrelevant features, the time can be saved, the model efficiency can be improved, and the model can be simplified.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments or the technical solutions in the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic diagram of a first embodiment of a method for constructing a blasting fracture cracking range prediction model according to the invention;
FIG. 2 is a sample distribution plot of predicted values for a sample of a data set;
FIG. 3 is a graph showing the predicted result of the width of the rupture range of the embodiment;
fig. 4 is a schematic diagram of an embodiment of a terminal.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The term "and/or" in the embodiments of the present invention describes an association relationship of associated objects, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The term "plurality" in the embodiments of the present invention means two or more, and other terms are similar thereto.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that in various embodiments of the invention, numerous technical details are set forth in order to provide a better understanding of the present invention. However, the claimed invention may be practiced without these specific details or with various changes and modifications based on the following embodiments. The following embodiments are divided for convenience of description, and should not constitute any limitation to the specific implementation manner of the present invention, and the embodiments may be mutually incorporated and referred to without contradiction.
The embodiment relates to a construction method of a combustion and explosion fracturing fracture range prediction model.
The following describes implementation details of the method for constructing a blasting fracture cracking range prediction model according to the first embodiment of the present invention, and the following description is provided only for convenience of understanding and is not necessary to implement the present invention.
The specific flow of the present embodiment is shown in fig. 1, and specifically includes:
s100, acquiring parameter data of expansion of a plurality of methane combustion-explosion fracturing fractures;
specifically, the parameter data of the expansion of the methane combustion and explosion fracturing fractures comprises reservoir geological parameters influencing combustion and explosion fracturing effects and fracturing construction parameters. The reservoir geological parameters comprise original ground stress field, young modulus of rock, poisson ratio, rock density and the like; the fracturing construction parameters include: detonation source density, detonation velocity, detonation heat, and the like. The details are shown in Table 1.
More specifically, step S100 includes obtaining reservoir geological parameters and fracturing construction parameters affecting the blasting fracturing effect according to the logging data, the seismic data, the fracturing design data, and the investigation analysis.
TABLE 1 parameter data
| Parameter(s) | Parameter range |
| Elastic modulus GPa | 20~50 |
| Poisson ratio | 0.15~0.3 |
| Cohesion MPa | 5~20 |
| |
3~10 |
| Internal friction angle ° | 20~50 |
| Minimum ground stress MPa | 10~60 |
| |
0~20 |
| Density of detonation source kg/ |
50~250 |
| Detonation velocity m/s | 100~800 |
| Detonation heat J/kg | 5E+07~9E+07 |
S200, determining a crack expansion result according to the acquired parameter data to form an original data set;
specifically, step S200 includes:
step S210, determining a plurality of methane combustion explosion fracturing fracture expansion simulation schemes according to the acquired parameter data;
step S220, determining a fracture expansion result according to a plurality of methane combustion explosion fracture expansion simulation schemes to form an original data set.
The method for determining the multiple methane blasting fracture expansion simulation schemes comprises the steps of conducting horizontal selection and orthogonal design on parameters, and designing multiple orthogonal numerical simulation schemes according to horizontal values of all factors.
Specifically, taking the parameters provided in table 1 as an example, an appropriate orthogonal table is selected for scheme design according to the above parameters, the determined horizontal number and the factor number, and it is assumed that L is selected 4 (2 3 ) And in the orthogonal test table, L represents an orthogonal table, 4 represents that 4 times of tests are required, 2 represents that each factor is divided into 2 levels, and 3 represents that 3 factors are required, and the three parameters of the elastic modulus, the detonation source density and the detonation velocity are subjected to level selection and scheme design. The levels of each factor are shown in table 2.
TABLE 2 levels of the factors
| Factors of the fact | Elastic modulus GPa | Density of detonation source kg/m 3 | Detonation velocity m/s |
| Level 1 | 40 | 100 | 400 |
| Level 2 | 30 | 200 | 600 |
Specifically, step S220 includes performing multiple simulations using a fracture numerical simulation model based on a CDEM (Continuous-Discontinuous Element Method) Method to obtain a simulation result under each fracture propagation simulation scheme. The results include length and width values of the reservoir fracture field. A plurality of simulation schemes are in one-to-one correspondence with the simulation results to form an original data set.
Orthogonal numerical simulation schemes are designed according to the values of the levels of the factors provided in the table 2, and each scheme is simulated for multiple times to obtain the length and the width of the blasting rupture range under the design of each scheme, and partial scheme results are shown in the table 3 and fig. 2 and 3.
TABLE 3 respective simulation scenarios
| Factors of the design | Elastic modulus GPa | Detonation source density kg/m 3 | Detonation velocity m/s | Width of rupture m | Length of rupture m |
| Scheme 1 | 40 | 100 | 400 | 0.47 | 0.24 |
| Scheme 2 | 40 | 200 | 600 | 1.97 | 0.63 |
| |
300 | 100 | 600 | 1.25 | 0.75 |
| |
300 | 200 | 400 | 0.63 | 0.42 |
Step S300, preprocessing the original data set;
specifically, the fracture propagation result comprises fracture range length and width values of the fracture;
accordingly, the step of preprocessing the raw data set comprises:
step S310, calculating the correlation between factors influencing the fracturing effect and the fracture range length and width value of the fracture, and determining main control factors influencing the methane explosion fracturing effect;
step S320, performing data normalization processing on the determined main control factors influencing the methane burning explosion fracturing effect;
wherein, the calculation formula of the correlation is as follows:
wherein x is i Is the input parameter data;
y i as parameter data x i The true result of the corresponding crack propagation;
It should be noted that, in step S310, correlation between the factor affecting the fracturing effect and the length and width of the fracture range is mainly analyzed by using Pearson correlation coefficient method, and the main factor affecting the methane explosion fracturing effect is screened out. Wherein r is between-1 and 1, and the larger the absolute value of the r is, the stronger the correlation is. The closer the correlation coefficient is to 1 or-1, the stronger the correlation degree is; the closer the correlation coefficient is to 0, the weaker the correlation.
Calculating correlation coefficient r values between each parameter variable and a fracture range, taking the data as an example, the correlation between the detonation source density and the minimum ground stress and the length and width of the fracture range is strong, r is greater than 0.8, certain correlation also exists between stress difference, detonation velocity and the like and an objective function, r is about 0.5, the correlation between cohesion and detonation heat and the objective function is weak, and r is less than 0.2, so eight main control factors influencing the fracturing effect are preferably selected from the detonation source density, the detonation velocity, the minimum ground stress, the stress difference, the elastic modulus, the poisson ratio, the tensile strength and the detonation iteration time.
In the step S320, the data normalization process may be performed by the following method.
Data normalization formula:
wherein, x is original data and the value range is x ∈ [ x [ ] min ,x max ]；
x norm The data processed by the normalization method;
x max is the maximum value in the original data;
x min is the minimum value in the raw data.
And S400, inputting the preprocessed data set into a gradient lifting grid XGboost, and constructing a model for predicting the explosion fracturing range.
Specifically, the fracture propagation result comprises fracture range length and width values of the fracture;
correspondingly, the step of inputting the preprocessed data set into the gradient lifting grid XGboost and constructing a combustion and explosion fracturing fracture range prediction model comprises the following steps:
and taking the preprocessed data as the input of the gradient lifting grid XGboost, and taking the fracture range length and the width value of the crack corresponding to the parameter data as the output for training so as to obtain an initial model for predicting the fracture range of the blasting fracture.
In addition, the preprocessed data can be divided into a training set and a test set, and an initialization parameter is set by using a training model of the training set, wherein the initialization parameter comprises a learning rate, a base tree, a maximum tree depth and an iteration number. The main control parameters are used as input, the length and the width value of the rupture range are used as output to train and obtain an initial rupture range prediction model,
the initial model was adjusted with the test set and the fracture range prediction model was evaluated with R2_ score. And obtaining a final blasting fracturing range prediction model.
More specifically, the data set after S3 preprocessing is divided into 80% of training set and the remaining 20% of training set as test set.
Training by using a training set to obtain an initial rupture range prediction model by taking main control parameters as input and taking rupture range length and width values as output, wherein the specific training process is as follows:
the XGboost is an integrated learning method of a base learner, and a plurality of weak learners are integrated into a strong learner by a certain method by adopting a step forward additive model. In the process of building a prediction model based on XGboost, feature splitting is continuously carried out to add decision trees, a plurality of trees make a decision together, the result of each tree is the difference between a target value and the prediction results of all the previous trees, and all the results are accumulated to obtain a final result, namely the prediction value of a sample.
The model of the gradient lifting grid XGboost is as follows:
wherein x is i Is an input sample;
f m (x i ) The predicted result of the m-th tree is obtained;
In addition, model parameters in the initial model are adjusted to obtain a target model, and the adjustment parameters comprise the number n _ estimators of decision trees in the model, the maximum tree depth max _ depth, the minimum sample weight min child _ weight required by leaf nodes, the descending value gamma of a minimum loss function, and the proportion subsample of sample data randomly taken by each decision tree.
In the present embodiment, n _ estimators =200, max _depth =10, min child _ weight =3, and gamma =0.1 and subsample =0.8.
After the step of adjusting the model parameters in the initial model to obtain the target model, the construction method further includes:
and evaluating the target model, wherein an evaluation formula is as follows:
wherein R is 2 As a result of the evaluation;
y i is the true result of the crack propagation;
n is the number of samples;
Obtaining an optimal combustion and explosion fracturing fracture range prediction model, inputting test set data into the optimal model to obtain a fracture range value predicted by the model, comparing the fracture range value with a true value, and calculating to obtain the R of the model 2 Is 0.952. The model can be regarded as a final explosion and rupture range prediction model.
According to the method, parameter data of multiple methane explosion fracturing crack expansions are obtained, the crack expansion result is determined according to the obtained parameter data, an original data set is formed, the original data set is preprocessed, the preprocessed data set is input into a gradient lifting grid XGboost, a model for explosion fracturing range prediction is constructed, and therefore a prediction model is constructed based on a machine learning XGboost method, on the premise that prediction accuracy is guaranteed, the efficiency of fracturing range calculation is effectively improved, and the fracturing effect can be evaluated in real time;
furthermore, a plurality of blasting fracturing samples are determined by an orthogonal test design method, a proxy model which can screen out an original numerical simulation model influencing fracturing effect and accurately describing the fracturing effect by a positive number method is constructed by using fewer sample points, and the precision of the model is ensured; based on the main control factors of Pearson (Pearson) correlation results and eliminating irrelevant features, the time can be saved, the model efficiency can be improved, and the model can be simplified.
In order to achieve the above object, the present invention further provides a prediction method of a combustion and explosion fracturing range prediction model, wherein the prediction method comprises the following steps:
and predicting the fracture range in the fracturing process under the scheme to be predicted according to the model constructed by the construction method.
It should be noted that the embodiment of the prediction method of the combustion and explosion fracturing range prediction model includes the embodiment of the above construction method.
According to the method, parameter data of multiple methane explosion fracturing crack expansions are obtained, the crack expansion result is determined according to the obtained parameter data, an original data set is formed, the original data set is preprocessed, the preprocessed data set is input into a gradient lifting grid XGboost, a model for explosion fracturing range prediction is constructed, and therefore a prediction model is constructed based on a machine learning XGboost method, on the premise that prediction accuracy is guaranteed, the efficiency of fracturing range calculation is effectively improved, and the fracturing effect can be evaluated in real time;
furthermore, a plurality of blasting fracturing samples are determined by an orthogonal test design method, a proxy model which can screen out an original numerical simulation model influencing fracturing effect and accurately describing the fracturing effect by a positive number method is constructed by using fewer sample points, and the precision of the model is ensured; based on the main control factors of Pearson (Pearson) correlation results and eliminating irrelevant features, the time can be saved, the model efficiency can be improved, and the model can be simplified.
By way of example, three embodiments of the fracture range to be predicted are generated by using a fracture numerical simulation model, and the three embodiments are respectively input into the prediction model to obtain the fracture range prediction result of the scheme to be predicted. The main control factors of the three embodiments are distributed as shown in table 4, the processed data is input into a prediction model, and a blasting rupture range result is obtained, wherein the rupture range prediction result comprises the length and the width of a rupture range area at each moment in the blasting fracturing process.
TABLE 4 three examples
In order to achieve the above object, the present invention also provides a terminal, as shown in fig. 4, including at least one processor 901; and a memory 902 communicatively connected to the at least one processor 901; the memory 902 stores instructions executable by the at least one processor 901, and the instructions are executed by the at least one processor 901, so that the at least one processor 901 can execute the method for constructing the combustion and explosion fracture range prediction model according to the first to eighth embodiments.
The memory 902 and the processor 901 are coupled by a bus, which may comprise any number of interconnected buses and bridges that interconnect one or more of the various circuits of the processor 901 and the memory 902. The bus may also connect various other circuits such as peripherals, voltage regulators, power management circuits, etc., which are well known in the art, and therefore, will not be described any further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor 901 is transmitted over a wireless medium via an antenna, which further receives the data and transmits the data to the processor 901.
The processor 901 is responsible for managing the bus and general processing, and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And memory 902 may be used for storing data used by processor 901 in performing operations.
In order to achieve the above object, the present invention further provides a computer-readable storage medium storing a computer program, wherein the computer program is configured to implement the above method for constructing a blasting fracture range prediction model when executed by a processor.
That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the above embodiments may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
It is to be understood that the above-described embodiments are only a few, but not all, embodiments of the present invention. Based on the embodiments of the present invention, those skilled in the art may make other changes or modifications without creative efforts, and all of them should fall into the protection scope of the present invention.
Claims (5)
1. A construction method of a combustion and explosion fracturing range prediction model is characterized by comprising the following steps:
acquiring parameter data of expansion of a plurality of methane combustion-explosion fracturing fractures, wherein the parameter data comprises reservoir geological parameters and fracturing construction parameters which influence combustion-explosion fracturing effects;
determining a crack propagation result according to the acquired parameter data to form an original data set;
preprocessing the original data set;
inputting the preprocessed data set into a gradient lifting grid XGboost, and constructing a model for predicting the blasting fracturing fracture range;
wherein the step of determining a result of fracture propagation to form an original data set according to the acquired parameter data comprises:
determining a plurality of methane combustion explosion fracturing crack expansion simulation schemes according to the acquired parameter data;
determining a fracture expansion result according to a plurality of methane burning and blasting fracture expansion simulation schemes to form an original data set, wherein the method for determining the plurality of methane burning and blasting fracture expansion simulation schemes comprises the steps of carrying out horizontal selection and orthogonal design on parameters, and designing a plurality of orthogonal numerical simulation schemes according to horizontal values of all factors;
the result of the crack propagation comprises the fracture range length and the width value of the crack;
correspondingly, the step of inputting the preprocessed data set into the gradient lifting grid XGboost and constructing a combustion and explosion fracturing fracture range prediction model comprises the following steps:
taking the preprocessed data as the input of a gradient lifting grid XGboost, and taking the fracture range length and the width value of the crack corresponding to the parameter data as the output for training to obtain an initial model for predicting the fracture range of the blasting fracture;
adjusting model parameters in the initial model to obtain a target model, wherein the adjustment parameters comprise the number n _ estimators of decision trees in the model, the maximum tree depth max _ depth, the minimum sample weight min child _ weight required by leaf nodes, the reduction value gamma of a minimum loss function, and the proportion subsample of sample data randomly taken by each decision tree; n _ estimators =200, max _depth =10, min child _ weight =3, and gamma =0.1 and subsample =0.8;
after the step of adjusting the model parameters in the initial model to obtain the target model, the construction method further includes: and evaluating the target model, wherein an evaluation formula is as follows:
wherein R is 2 As a result of the evaluation;
y i is the true result of the crack propagation;
n is the number of samples;
the result of the crack propagation comprises the fracture range length and the width value of the crack;
accordingly, the step of preprocessing the raw data set comprises:
calculating the correlation between factors influencing the fracturing effect and the fracture range length and width value of the fracture, and determining main control factors influencing the methane explosion fracturing effect;
carrying out data normalization processing on the determined main control factors influencing the methane combustion and explosion fracturing effect;
wherein, the calculation formula of the correlation is as follows:
wherein x is i Is the input parameter data;
y i as parameter data x i The true result of the corresponding crack propagation;
`
average of true results for crack propagation;
2. The method for constructing the blasting fracturing fracture range prediction model according to claim 1, wherein the gradient lifting grid XGboost model is as follows:
wherein x is i Is an input sample;
f m (x i ) The predicted result of the m-th tree is obtained;
3. A prediction method of a combustion and explosion fracturing range prediction model is characterized by comprising the following steps:
the model constructed according to the construction method of claim 1 or 2, which predicts the fracture extent in the fracturing process under the scheme to be predicted.
4. A terminal, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of constructing a blast fracture extent prediction model according to claim 1 or 2.
5. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method for constructing a blasting fracture cracking range prediction model according to claim 1 or 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211568186.1A CN115577645B (en) | 2022-12-08 | 2022-12-08 | Construction method and prediction method of combustion and explosion fracturing fracture range prediction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211568186.1A CN115577645B (en) | 2022-12-08 | 2022-12-08 | Construction method and prediction method of combustion and explosion fracturing fracture range prediction model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115577645A CN115577645A (en) | 2023-01-06 |
| CN115577645B true CN115577645B (en) | 2023-04-18 |
Family
ID=84590134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211568186.1A Active CN115577645B (en) | 2022-12-08 | 2022-12-08 | Construction method and prediction method of combustion and explosion fracturing fracture range prediction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115577645B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116877039B (en) * | 2023-07-10 | 2024-03-22 | 中国科学院武汉岩土力学研究所 | Method and equipment for constructing prediction model of number and length of blasting cracks |
| CN117108261B (en) * | 2023-10-24 | 2024-01-19 | 四川大学 | Shale fracturing method based on energy-containing liquid-gas-fluid composite control blasting |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110454127A (en) * | 2019-07-04 | 2019-11-15 | 成都理工大学 | A kind of advantageous encryption times window of untraditional reservoir Encryption Well determines method |
| CN110472276A (en) * | 2019-07-04 | 2019-11-19 | 成都理工大学 | A kind of slit formation oil and gas reservoir Encryption Well transformation and optimization method |
| CN114638147A (en) * | 2020-12-16 | 2022-06-17 | 中国石油化工股份有限公司 | Method for determining fracturing process parameters of oil and gas reservoir |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106869896B (en) * | 2017-04-26 | 2018-05-08 | 西南石油大学 | A kind of Low permeable oil and gas reservoirs straight well volume fracturing reservoir reconstruction volume Forecasting Methodology |
| CN107742020A (en) * | 2017-10-09 | 2018-02-27 | 中国石油集团川庆钻探工程有限公司地球物理勘探公司 | Shale gas reservoir fracturing improvement method for predicting volume |
| CN112257304B (en) * | 2020-09-15 | 2021-11-30 | 中国石油天然气股份有限公司 | Shale stratum vertical well hydraulic fracture height prediction method |
| WO2022241444A1 (en) * | 2021-05-11 | 2022-11-17 | Liberty Oilfield Services Llc | Systems and methods for hybrid model hydraulic fracture pressure forecasting |
| CN113792479B (en) * | 2021-08-23 | 2023-09-22 | 北京科技大学 | Coal bed methane reservoir fracturing effect evaluation method based on physical constraint |
| CN114021466B (en) * | 2021-11-10 | 2022-08-23 | 西南石油大学 | Shale gas effective gap net volume prediction method based on flowback data and machine learning |
| CN114154427B (en) * | 2022-02-08 | 2022-04-19 | 中国石油大学(华东) | Volume fracturing fracture expansion prediction method and system based on deep learning |
| CN114595608B (en) * | 2022-03-11 | 2023-06-27 | 中国石油大学(华东) | Fracturing construction parameter and working system parameter optimization method and system |
| CN114912703A (en) * | 2022-05-31 | 2022-08-16 | 中国石油天然气集团有限公司 | Method, device and equipment for predicting rupture pressure and storage medium |
-
2022
- 2022-12-08 CN CN202211568186.1A patent/CN115577645B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110454127A (en) * | 2019-07-04 | 2019-11-15 | 成都理工大学 | A kind of advantageous encryption times window of untraditional reservoir Encryption Well determines method |
| CN110472276A (en) * | 2019-07-04 | 2019-11-19 | 成都理工大学 | A kind of slit formation oil and gas reservoir Encryption Well transformation and optimization method |
| CN114638147A (en) * | 2020-12-16 | 2022-06-17 | 中国石油化工股份有限公司 | Method for determining fracturing process parameters of oil and gas reservoir |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115577645A (en) | 2023-01-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115577645B (en) | Construction method and prediction method of combustion and explosion fracturing fracture range prediction model | |
| RU2669948C2 (en) | Multistage oil field design optimisation under uncertainty | |
| CN113901681B (en) | Three-dimensional compressibility evaluation method for dual desserts of shale gas reservoir in whole life cycle | |
| Salimi et al. | Evaluating the suitability of existing rock mass classification systems for TBM performance prediction by using a regression tree | |
| CN110469303B (en) | Volume fracturing parameter optimization design method based on four types of transformation volumes | |
| CN109241588A (en) | A kind of analogy method of the monolete extension based on quasi-continuous geomechanics model | |
| Shi et al. | Brittleness index prediction in shale gas reservoirs based on efficient network models | |
| CN106291755B (en) | A kind of areas Long Sheng low-grade fault law of development quantitative forecasting technique | |
| CN103617147A (en) | Method for identifying mine water-inrush source | |
| CN109655903A (en) | Rammell S-Wave Velocity Predicted Method and system | |
| CN112765791A (en) | TBM card-sticking risk prediction method based on numerical value sample and random forest | |
| CN103628816B (en) | The method of seismic properties Guidance Levels well guiding and device thereof | |
| CN115166853A (en) | Shale gas reservoir natural fracture model establishing method and device, electronic equipment and medium | |
| CN111027249B (en) | Machine learning-based inter-well connectivity evaluation method | |
| CN109236255A (en) | A kind of fractured horizontal well Assessment Method on Potential and device | |
| CN110717270B (en) | Oil and gas reservoir simulation method based on data | |
| CN112365054A (en) | Comprehensive grading prediction method for deep well roadway surrounding rock | |
| CN115481565A (en) | Earth pressure balance shield tunneling parameter prediction method based on LSTM and ant colony algorithm | |
| CN113946790A (en) | Method, system, equipment and terminal for predicting height of water flowing fractured zone | |
| CN115705454A (en) | Crack propagation simulation fracturing design optimization method based on phase field method | |
| Idris | Probabilistic stability analysis of underground mine excavations | |
| Sarkheil et al. | The fracture network modeling in naturally fractured reservoirs using artificial neural network based on image loges and core measurements | |
| Anifowose et al. | A functional networks-type-2 fuzzy logic hybrid model for the prediction of porosity and permeability of oil and gas reservoirs | |
| CN115526114A (en) | Hydraulic fracture morphology inversion method and system based on ensemble Kalman filtering method | |
| Tang et al. | Combining machine learning and physics modelling to determine the natural cave property with fracturing curves |
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 |