CN113705878B - Method and device for determining water yield of horizontal well, computer equipment and storage medium - Google Patents
Method and device for determining water yield of horizontal well, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113705878B CN113705878B CN202110972566.0A CN202110972566A CN113705878B CN 113705878 B CN113705878 B CN 113705878B CN 202110972566 A CN202110972566 A CN 202110972566A CN 113705878 B CN113705878 B CN 113705878B
- Authority
- CN
- China
- Prior art keywords
- neural network
- network model
- horizontal well
- deep neural
- water yield
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 113
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000003860 storage Methods 0.000 title claims abstract description 25
- 238000003062 neural network model Methods 0.000 claims abstract description 101
- 230000000306 recurrent effect Effects 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 66
- 238000005457 optimization Methods 0.000 claims description 47
- 238000004422 calculation algorithm Methods 0.000 claims description 42
- 230000006870 function Effects 0.000 claims description 24
- 230000007246 mechanism Effects 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 6
- 239000007788 liquid Substances 0.000 claims description 5
- 230000035699 permeability Effects 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000011478 gradient descent method Methods 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 235000020681 well water Nutrition 0.000 claims description 3
- 239000002349 well water Substances 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 239000011229 interlayer Substances 0.000 claims 8
- 239000010410 layer Substances 0.000 claims 4
- 230000002457 bidirectional effect Effects 0.000 claims 2
- 238000004519 manufacturing process Methods 0.000 claims 1
- 238000013135 deep learning Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 4
- 239000002609 medium Substances 0.000 description 20
- 238000005553 drilling Methods 0.000 description 9
- 125000006850 spacer group Chemical group 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000010606 normalization Methods 0.000 description 6
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 210000002569 neuron Anatomy 0.000 description 5
- 125000004122 cyclic group Chemical group 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 239000008398 formation water Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000013100 final test Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 239000012120 mounting media Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a method and a device for determining the water yield of a horizontal well, computer equipment and a storage medium. The method comprises the following steps: acquiring an influence parameter of water yield of a horizontal well; inputting the influence parameters into a trained deep neural network model to obtain a prediction result of the water yield of the horizontal well; wherein the deep neural network model comprises a recurrent neural network model. According to the technical scheme provided by the embodiment of the invention, the deep learning technology is used for predicting the water yield of the horizontal well, various complex data features can be fused, and the circulating neural network model is more in line with the front-back association characteristics of the horizontal well, so that the prediction error is obviously reduced, and compared with the traditional prediction method, the prediction method has great improvement, and a user can better utilize the predicted water yield value.
Description
Technical Field
The embodiment of the invention relates to the technical field of drilling, in particular to a method and a device for determining the water yield of a horizontal well, computer equipment and a storage medium.
Background
At present, gas drilling has great potential and is an effective drilling mode for solving the problem of drilling in an easy-to-leak stratum, protecting a low-pressure low-permeability reservoir and improving the drilling speed. However, formation water out problems are an important bottleneck that limits the gas drilling benefits. By quantitatively predicting the formation water outlet before drilling, reliable basis can be provided for reasonable zone selection and layer selection of gas drilling.
In the traditional horizontal well water output prediction process, the water output is usually calculated according to the seepage mechanics theory. Because the geological parameter description is inaccurate, larger errors are easy to occur, the system cannot be a complete system, meanwhile, the traditional prediction mode is low in intelligent degree, the functions are relatively incomplete, and the actual requirements of industry cannot be met.
Disclosure of Invention
The embodiment of the invention provides a method, a device, computer equipment and a storage medium for determining the water yield of a horizontal well, so as to reduce the prediction error of the water yield of the horizontal well, and further enable a user to better utilize the predicted water yield value.
In a first aspect, an embodiment of the present invention provides a method for determining a water yield of a horizontal well, where the method includes:
acquiring an influence parameter of water yield of a horizontal well;
inputting the influence parameters into a trained deep neural network model to obtain a prediction result of the water yield of the horizontal well; wherein the deep neural network model comprises a recurrent neural network model.
Optionally, before the step of inputting the influence parameters into the trained deep neural network model to obtain the predicted result of the water yield of the horizontal well, the method further includes:
obtaining a training sample of the deep neural network model;
constructing the deep neural network model;
and according to the training sample, performing optimization training on the deep neural network model by using a target optimization learning algorithm.
Optionally, the obtaining a training sample of the deep neural network model includes:
establishing a first preset number of Eclipse mechanism models and a second preset number of Eclipse actual models, and acquiring a field water finding result of the horizontal well;
and generating a plurality of groups of training samples according to the Eclipse mechanism model, the Eclipse actual model and the on-site water finding result.
Optionally, the constructing the deep neural network model includes:
determining that the number of hidden layers of the deep neural network model is 3, and the number of each layer is 8, 32 and 64 respectively;
determining an activation function used by a hidden layer and an output layer of the deep neural network model as a sigmoid function;
and determining the loss function for training the deep neural network model as a mean square error.
Optionally, before the optimizing training of the deep neural network model according to the training sample using a target optimizing learning algorithm, the method further includes:
determining super parameters of a plurality of preset optimization learning algorithms;
according to the training samples, respectively carrying out optimization training on the deep neural network model by using each preset optimization learning algorithm;
and comparing training results of the preset optimization learning algorithms to determine the target optimization learning algorithm.
Optionally, the preset optimization learning algorithm includes a small batch gradient descent method, a momentum method, a root mean square transfer method and an adaptive moment estimation optimization method.
Optionally, the influencing parameters include: at least one of horizontal well length, water avoidance height, well type, distance of a spacer from the horizontal well, width of the spacer, type of hypertonic zone, ratio of permeability of the spacer, oil-water viscosity ratio, water energy, liquid yield, water content and section number.
In a second aspect, an embodiment of the present invention further provides a device for determining a water yield of a horizontal well, where the device includes:
the influence parameter acquisition module is used for acquiring influence parameters of the water yield of the horizontal well;
the water yield prediction module is used for inputting the influence parameters into the trained deep neural network model to obtain a prediction result of the water yield of the horizontal well; wherein the deep neural network model comprises a recurrent neural network model.
In a third aspect, an embodiment of the present invention further provides a computer apparatus, including:
one or more processors;
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the water yield of the horizontal well provided by any embodiment of the present invention.
In a fourth aspect, the embodiment of the present invention further provides a computer readable storage medium, where a computer program is stored, where the program when executed by a processor implements the method for determining the water yield of a horizontal well provided by any embodiment of the present invention.
The embodiment of the invention provides a method for determining the water yield of a horizontal well, which comprises the steps of firstly obtaining an influence parameter of the water yield of the horizontal well, and then inputting the obtained influence parameter into a trained deep neural network model so as to output a prediction result of the water yield of the horizontal well through the deep neural network model, wherein the deep neural network model can be a circulating neural network model. According to the method for determining the water yield of the horizontal well, provided by the embodiment of the invention, the water yield of the horizontal well is predicted by using a deep learning technology, various complex data features can be fused, and the front-back association characteristics of the horizontal well are more met by using a cyclic neural network model, so that the prediction error is obviously reduced, and compared with the traditional prediction method, the method for determining the water yield of the horizontal well is greatly improved, and a user can better utilize the predicted water yield value.
Drawings
FIG. 1 is a flow chart of a method for determining water yield of a horizontal well according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a device for determining water yield of a horizontal well according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a computer device according to a third embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts steps as a sequential process, many of the steps may be implemented in parallel, concurrently, or with other steps. Furthermore, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figures. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Example 1
Fig. 1 is a flowchart of a method for determining water yield of a horizontal well according to an embodiment of the present invention. The embodiment is applicable to the situation that the water yield of the horizontal well is predicted before drilling, the method can be executed by the device for determining the water yield of the horizontal well, and the device can be realized by hardware and/or software and can be generally integrated in computer equipment. As shown in fig. 1, the method specifically comprises the following steps:
s11, acquiring influence parameters of water yield of the horizontal well.
Optionally, the influencing parameters include: at least one of horizontal well length, water avoidance height, well type, distance of a spacer from the horizontal well, width of the spacer, type of hypertonic zone, ratio of permeability of the spacer, oil-water viscosity ratio, water energy, liquid yield, water content and section number. Specifically, there are many influencing factors of the water yield of the horizontal well, wherein the main factors include the above 13 types, from which the required influencing parameters can be determined, and in particular, all the above 13 types can be used, and the 13 influencing parameters are used as the input of the subsequent deep neural network model. Any conventional method may be used to obtain the various influencing parameters, and the method is not particularly limited in this embodiment.
S12, inputting the influence parameters into a trained deep neural network model to obtain a prediction result of the water yield of the horizontal well; wherein the deep neural network model comprises a recurrent neural network model.
Specifically, after the required influence parameters are obtained, the influence parameters can be input into the trained deep neural network model, so that the prediction result of the water yield of the horizontal well is output through the deep neural network model. The deep neural network model can be a cyclic neural network model, and the water yield of each section depends on the information of the previous section, so that the deep neural network model has obvious transmissibility, namely accords with the Markov characteristic, and the prediction error can be reduced by utilizing the characteristic that the cyclic neural network model is more in line with the front-back association of a horizontal well. Alternatively, the deep neural network model may also be a bi-directional recurrent neural network, a deep recurrent neural network, a convolutional neural network, or the like.
On the basis of the above technical solution, optionally, before the inputting the influence parameter into the trained deep neural network model to obtain the prediction result of the water yield of the horizontal well, the method further includes: obtaining a training sample of the deep neural network model; constructing the deep neural network model; and according to the training sample, performing optimization training on the deep neural network model by using a target optimization learning algorithm.
Wherein, optionally, the obtaining the training sample of the deep neural network model includes: establishing a first preset number of Eclipse mechanism models and a second preset number of Eclipse actual models, and acquiring a field water finding result of the horizontal well; and generating a plurality of groups of training samples according to the Eclipse mechanism model, the Eclipse actual model and the on-site water finding result. Specifically, 10000 Eclipse mechanism models and 8 Eclipse actual models can be built firstly, then a field water finding result of 1 horizontal well is obtained, 46 balance sets of effective data can be generated according to the data for analysis, the first 70% of the effective data can be used as training samples, and the last 30% of the effective data can be used as test samples. In order to eliminate the influence of different dimension on the model and improve the operation efficiency and the prediction precision of the neural network, after the training sample is acquired, the training sample is firstly subjected to pretreatment such as normalization, and specifically, the min-max normalization can be used for mapping the original data to between [0-1], and a specific calculation formula is as follows:
where x represents the data before normalization and y represents the data after normalization. Accordingly, the inverse normalization can be performed using the following calculation formula:
x＝y(max(x)-min(x))+min(x)
after normalization is completed, the data can be screened to remove useless noise points, the rest data is used as a final training sample, and a final test sample and the like can be obtained through the same method.
Optionally, the constructing the deep neural network model includes: determining that the number of hidden layers of the deep neural network model is 3, and the number of each layer is 8, 32 and 64 respectively; determining an activation function used by a hidden layer and an output layer of the deep neural network model as a sigmoid function; and determining the loss function for training the deep neural network model as a mean square error. Specifically, the input layer and the output layer of the deep neural network model may be determined according to the set input and output, for example, when the input of the deep neural network model is the above 13 influencing parameters and the output is the water output value of the horizontal well, the number of neurons of the input layer may be determined to be 13, and the number of neurons of the output layer may be determined to be 1. The number of hidden layers and the number of neurons are too small to deeply dig a deep relation between the feature and the target, too many model parameters are caused, the training is long, and the model is easy to excessively fit, so that the number of hidden layers and the number of hidden layer neurons can be determined by adopting a trial-and-error method and combining with the Hecht-Nielsen theory, the number of hidden layers is finally determined to be 3 through repeated experiments, the number of neurons of each layer is respectively 8, 32 and 64, and the network structure of the deep neural network model can be finally determined to be 13-8-32-64-1. After the network structure is determined, modeling can be performed based on a python3.7 environment and a Tensorflow deep learning framework, an activation function used by a hidden layer is determined to be a sigmoid function, a sigmoid function is also adopted by an output layer, and the water yield of a horizontal well belongs to a regression problem, so that a selected loss function is a mean square error.
Optionally, before the optimizing training of the deep neural network model according to the training sample using a target optimizing learning algorithm, the method further includes: determining super parameters of a plurality of preset optimization learning algorithms; according to the training samples, respectively carrying out optimization training on the deep neural network model by using each preset optimization learning algorithm; and comparing training results of the preset optimization learning algorithms to determine the target optimization learning algorithm. Wherein, optionally, the preset optimization learning algorithm comprises a small batch gradient descent Method (MBGD), a momentum method (momentum), a root mean square transfer method (RMSprop) and an adaptive moment estimation optimization method (Adam). Specifically, 4 different preset optimization learning algorithms such as MBGD, momentum method, RMSprop algorithm and Adam algorithm can be selected for debugging the deep neural network model in multiple rounds to determine the hyper-parameters of each algorithmAfter multiple rounds of debugging, the optimal learning rate can be finally determined to be 0.001, the momentum method factor gamma is 0.9, the RMSprop algorithm factor rho is 0.95, and the factor delta adopts a default value of 1 x 10 -6 Adam algorithm factor delta adopts default value 1 x 10 -8 The factors P1 and P2 are respectively 0.9 and 0.99, the intermediate variable defaults to 0, and each initial parameter is randomly selected. After the super parameters of each preset optimization learning algorithm are determined, the obtained training samples and the set 4 optimization learning algorithms can be utilized to perform optimization training on the deep neural network model, the change curve of the training loss function value is observed, the Adam algorithm can be determined to be the optimal deep learning algorithm, namely the target optimization learning algorithm, the Adam algorithm has high convergence rate and high efficiency, the final loss value is reduced to the minimum value 0.0706, and then the model for predicting the water yield of the horizontal well based on the circulating neural network of the target optimization learning algorithm can be constructed. The training process can adopt a double-layer cycle, the internal-layer cycle sets the batch-size to 512, 10 groups of training samples can be randomly extracted in each iteration process to update parameters, 25 cycles of training can be carried out by the external-layer cycle epoch-num, and training data can be randomly disturbed before each iteration begins.
According to the technical scheme provided by the embodiment of the invention, firstly, the influence parameters of the water yield of the horizontal well are obtained, then the obtained influence parameters are input into the trained deep neural network model, so that the prediction result of the water yield of the horizontal well is output through the deep neural network model, wherein the deep neural network model can be a circulating neural network model. By predicting the water yield of the horizontal well by using a deep learning technology, various complex data features can be fused, and the circulating neural network model is more in line with the front-back association characteristics of the horizontal well, so that the prediction error is obviously reduced, and compared with the traditional prediction method, the prediction method has great promotion, and a user can better utilize the predicted water yield value.
Example two
Fig. 2 is a schematic structural diagram of a device for determining water yield of a horizontal well according to a second embodiment of the present invention, where the device may be implemented by hardware and/or software, and may be generally integrated in a computer device, for executing the method for determining water yield of a horizontal well according to any embodiment of the present invention. As shown in fig. 2, the apparatus includes:
an influence parameter obtaining module 21, configured to obtain an influence parameter of the water yield of the horizontal well;
the water yield prediction module 22 is configured to input the influence parameter into a trained deep neural network model, so as to obtain a prediction result of the water yield of the horizontal well; wherein the deep neural network model comprises a recurrent neural network model.
According to the technical scheme provided by the embodiment of the invention, firstly, the influence parameters of the water yield of the horizontal well are obtained, then the obtained influence parameters are input into the trained deep neural network model, so that the prediction result of the water yield of the horizontal well is output through the deep neural network model, wherein the deep neural network model can be a circulating neural network model. By predicting the water yield of the horizontal well by using a deep learning technology, various complex data features can be fused, and the circulating neural network model is more in line with the front-back association characteristics of the horizontal well, so that the prediction error is obviously reduced, and compared with the traditional prediction method, the prediction method has great promotion, and a user can better utilize the predicted water yield value.
On the basis of the technical scheme, the device for determining the water yield of the horizontal well comprises:
the training sample acquisition module is used for acquiring a training sample of the deep neural network model before the influence parameters are input into the trained deep neural network model to obtain a predicted result of the water yield of the horizontal well;
the model construction module is used for constructing the deep neural network model;
and the model training module is used for carrying out optimization training on the deep neural network model by using a target optimization learning algorithm according to the training sample.
On the basis of the above technical solution, optionally, the training sample obtaining module includes:
the data acquisition unit is used for establishing a first preset number of Eclipse mechanism models and a second preset number of Eclipse actual models and acquiring on-site water finding results of the horizontal well;
and the sample generation unit is used for generating a plurality of groups of training samples according to the Eclipse mechanism model, the Eclipse actual model and the on-site water finding result.
On the basis of the technical scheme, the optional model building module comprises:
the hidden layer determining unit is used for determining that the number of hidden layers of the deep neural network model is 3, and the number of each layer is 8, 32 and 64 respectively;
an activation function determining unit, configured to determine an activation function used by a hidden layer and an output layer of the deep neural network model as a sigmoid function;
and the loss function determining unit is used for determining the loss function for training the deep neural network model as a mean square error.
On the basis of the technical scheme, the device for determining the water yield of the horizontal well comprises:
the super-parameter determining module is used for determining super-parameters of a plurality of preset optimization learning algorithms before the target optimization learning algorithm is used for performing optimization training on the deep neural network model according to the training sample;
the pre-training module is used for carrying out optimization training on the deep neural network model by using each preset optimization learning algorithm according to the training samples;
and the target optimization learning algorithm determining module is used for comparing training results of the preset optimization learning algorithms to determine the target optimization learning algorithm.
On the basis of the technical scheme, optionally, the preset optimization learning algorithm comprises a small batch gradient descent method, a momentum method, a root mean square transfer method and an adaptive moment estimation optimization method.
On the basis of the above technical solution, optionally, the influencing parameters include: at least one of horizontal well length, water avoidance height, well type, distance of a spacer from the horizontal well, width of the spacer, type of hypertonic zone, ratio of permeability of the spacer, oil-water viscosity ratio, water energy, liquid yield, water content and section number.
The device for determining the water yield of the horizontal well provided by the embodiment of the invention can execute the method for determining the water yield of the horizontal well provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
It should be noted that, in the embodiment of the determination device for water output of a horizontal well, each unit and module included are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.
Example III
Fig. 3 is a schematic structural diagram of a computer device provided in a third embodiment of the present invention, and shows a block diagram of an exemplary computer device suitable for implementing an embodiment of the present invention. The computer device shown in fig. 3 is only an example and should not be construed as limiting the functionality and scope of use of embodiments of the invention. As shown in fig. 3, the computer apparatus includes a processor 31, a memory 32, an input device 33, and an output device 34; the number of processors 31 in the computer device may be one or more, in fig. 3, one processor 31 is taken as an example, and the processors 31, the memory 32, the input device 33, and the output device 34 in the computer device may be connected by a bus or other means, in fig. 3, by a bus connection is taken as an example.
The memory 32 is a computer readable storage medium, and may be used to store a software program, a computer executable program, and a module, such as program instructions/modules corresponding to a method for determining a water yield of a horizontal well in an embodiment of the present invention (for example, the influencing parameter obtaining module 21 and the water yield prediction module 22 in a device for determining a water yield of a horizontal well). The processor 31 executes various functional applications of the computer device and data processing by running software programs, instructions and modules stored in the memory 32, i.e. implements the above-described method of determining the water output of a horizontal well.
The memory 32 may mainly include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created according to the use of the computer device, etc. In addition, memory 32 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, memory 32 may further include memory located remotely from processor 31, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 33 may be used for obtaining influencing parameters of the water output of the horizontal well, generating key signal inputs related to user settings and function control of the computer device, etc. The output device 34 includes a display screen or the like, and may be used to present the prediction of the final horizontal well water output to the user.
Example IV
A fourth embodiment of the present invention also provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are for performing a method of determining the water output of a horizontal well, the method comprising:
acquiring an influence parameter of water yield of a horizontal well;
inputting the influence parameters into a trained deep neural network model to obtain a prediction result of the water yield of the horizontal well; wherein the deep neural network model comprises a recurrent neural network model.
The storage medium may be any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, lanbus (Rambus) RAM, etc.; nonvolatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a computer system in which the program is executed, or may be located in a different second computer system connected to the computer system through a network (such as the internet). The second computer system may provide program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations (e.g., in different computer systems connected by a network). The storage medium may store program instructions (e.g., embodied as a computer program) executable by one or more processors.
Of course, the storage medium containing the computer executable instructions provided in the embodiments of the present invention is not limited to the above-described method operations, and may also perform the related operations in the method for determining the water yield of the horizontal well provided in any embodiment of the present invention.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
From the above description of embodiments, it will be clear to a person skilled in the art that the present invention may be implemented by means of software and necessary general purpose hardware, but of course also by means of hardware, although in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, etc., and include several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments of the present invention.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (7)
1. The method for determining the water yield of the horizontal well is characterized by comprising the following steps of:
acquiring an influence parameter of water yield of a horizontal well;
inputting the influence parameters into a trained deep neural network model to obtain a prediction result of the water yield of the horizontal well; wherein the deep neural network model comprises a recurrent neural network model;
wherein the influencing parameters include: horizontal well length, water-avoiding height, well type, distance between the interlayer and the horizontal well, interlayer width, interlayer type, hypertonic zone type, interlayer permeability ratio, oil-water viscosity ratio, water energy, liquid yield, water content and section number;
the deep neural network model further comprises a bidirectional circulating neural network, a deep circulating neural network and a convolutional neural network;
before the influence parameters are input into the trained deep neural network model to obtain the predicted result of the water yield of the horizontal well, the method further comprises the following steps:
obtaining a training sample of the deep neural network model;
constructing the deep neural network model;
according to the training sample, performing optimization training on the deep neural network model by using a target optimization learning algorithm;
the obtaining the training sample of the deep neural network model includes:
establishing a first preset number of Eclipse mechanism models and a second preset number of Eclipse actual models, and acquiring a field water finding result of the horizontal well;
and generating a plurality of groups of training samples according to the Eclipse mechanism model, the Eclipse actual model and the on-site water finding result.
2. The method for determining the water yield of the horizontal well according to claim 1, wherein the constructing the deep neural network model comprises:
determining that the number of hidden layers of the deep neural network model is 3, and the number of each layer is 8, 32 and 64 respectively;
determining an activation function used by a hidden layer and an output layer of the deep neural network model as a sigmoid function;
and determining the loss function for training the deep neural network model as a mean square error.
3. The method for determining the water yield of the horizontal well according to claim 1, further comprising, before the optimizing training of the deep neural network model using a target optimizing learning algorithm according to the training samples:
determining super parameters of a plurality of preset optimization learning algorithms;
according to the training samples, respectively carrying out optimization training on the deep neural network model by using each preset optimization learning algorithm;
and comparing training results of the preset optimization learning algorithms to determine the target optimization learning algorithm.
4. The method for determining the water yield of the horizontal well according to claim 3, wherein the preset optimization learning algorithm comprises a small batch gradient descent method, a momentum method, a root mean square transfer method and an adaptive moment estimation optimization method.
5. The utility model provides a determining device of horizontal well water yield which characterized in that includes:
the influence parameter acquisition module is used for acquiring influence parameters of the water yield of the horizontal well;
the water yield prediction module is used for inputting the influence parameters into the trained deep neural network model to obtain a prediction result of the water yield of the horizontal well; wherein the deep neural network model comprises a recurrent neural network model;
wherein the influencing parameters include: horizontal well length, water-avoiding height, well type, distance between the interlayer and the horizontal well, interlayer width, interlayer type, hypertonic zone type, interlayer permeability ratio, oil-water viscosity ratio, water energy, liquid yield, water content and section number;
the deep neural network model further comprises a bidirectional circulating neural network, a deep circulating neural network and a convolutional neural network;
the apparatus further comprises:
the training sample acquisition module is used for acquiring a training sample of the deep neural network model before the influence parameters are input into the trained deep neural network model to obtain a predicted result of the water yield of the horizontal well;
the model construction module is used for constructing the deep neural network model;
the model training module is used for carrying out optimization training on the deep neural network model by using a target optimization learning algorithm according to the training sample;
the training sample acquisition module comprises:
the data acquisition unit is used for establishing a first preset number of Eclipse mechanism models and a second preset number of Eclipse actual models and acquiring on-site water finding results of the horizontal well;
and the sample generation unit is used for generating a plurality of groups of training samples according to the Eclipse mechanism model, the Eclipse actual model and the on-site water finding result.
6. A computer device, comprising:
one or more processors;
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method of determining the water production of a horizontal well as claimed in any one of claims 1 to 4.
7. A computer readable storage medium having stored thereon a computer program, characterized in that the program, when executed by a processor, implements a method for determining the water yield of a horizontal well as claimed in any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110972566.0A CN113705878B (en) | 2021-08-24 | 2021-08-24 | Method and device for determining water yield of horizontal well, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110972566.0A CN113705878B (en) | 2021-08-24 | 2021-08-24 | Method and device for determining water yield of horizontal well, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113705878A CN113705878A (en) | 2021-11-26 |
| CN113705878B true CN113705878B (en) | 2024-02-09 |
Family
ID=78654239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110972566.0A Active CN113705878B (en) | 2021-08-24 | 2021-08-24 | Method and device for determining water yield of horizontal well, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113705878B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114422028B (en) * | 2021-12-29 | 2024-06-28 | 中国电信股份有限公司 | Signal demodulation method and device, electronic equipment and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108180013A (en) * | 2017-12-29 | 2018-06-19 | 中国石油天然气股份有限公司 | Method for judging water invasion direction of boundary water-gas reservoir |
| CN109214026A (en) * | 2017-07-07 | 2019-01-15 | 中国石油天然气股份有限公司 | Shale gas horizontal well initial-stage productivity prediction method |
| CN109799533A (en) * | 2018-12-28 | 2019-05-24 | 中国石油化工股份有限公司 | A kind of method for predicting reservoir based on bidirectional circulating neural network |
-
2021
- 2021-08-24 CN CN202110972566.0A patent/CN113705878B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214026A (en) * | 2017-07-07 | 2019-01-15 | 中国石油天然气股份有限公司 | Shale gas horizontal well initial-stage productivity prediction method |
| CN108180013A (en) * | 2017-12-29 | 2018-06-19 | 中国石油天然气股份有限公司 | Method for judging water invasion direction of boundary water-gas reservoir |
| CN109799533A (en) * | 2018-12-28 | 2019-05-24 | 中国石油化工股份有限公司 | A kind of method for predicting reservoir based on bidirectional circulating neural network |
Non-Patent Citations (3)
| Title |
|---|
| 人工神经网络在物探方法预测含水层含水量中的应用;宋洪伟;中国优秀硕士学位论文全文数据库 基础科学辑;正文第6、24、31-41页 * |
| 基于机器学习方法的油井日产油量预测;刘巍;石油钻采工艺;第42卷(第1期);正文第70-74页 * |
| 渤海油田水平井出水特征及控水效果评价方法;龚宁;特种油气藏;第26卷(第5期);正文第147-152页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113705878A (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7157154B2 (en) | Neural Architecture Search Using Performance Prediction Neural Networks | |
| CN106372402B (en) | The parallel method of fuzzy region convolutional neural networks under a kind of big data environment | |
| CN109543828B (en) | Water absorption profile prediction method based on small sample condition | |
| CN107239845B (en) | Construction method of oil reservoir development effect prediction model | |
| CN110222387B (en) | Multi-element drilling time sequence prediction method based on mixed leaky integration CRJ network | |
| CN103559537B (en) | Based on the template matching method of error back propagation in a kind of out of order data stream | |
| CN109725531A (en) | A kind of successive learning method based on gate making mechanism | |
| CN113236228B (en) | Method and system for rapidly predicting single well yield | |
| CN113705878B (en) | Method and device for determining water yield of horizontal well, computer equipment and storage medium | |
| CN114723095A (en) | Missing well logging curve prediction method and device | |
| CN111058840A (en) | Organic carbon content (TOC) evaluation method based on high-order neural network | |
| CN114254554A (en) | Long-time unstable well testing interpretation method based on LSTM model | |
| CN115481565A (en) | Earth pressure balance shield tunneling parameter prediction method based on LSTM and ant colony algorithm | |
| CN110991641B (en) | Oil reservoir type analysis method and device and electronic equipment | |
| CN115618987A (en) | Production well production data prediction method, device, equipment and storage medium | |
| CN111241749B (en) | Permanent magnet synchronous motor chaos prediction method based on reserve pool calculation | |
| CN110486009B (en) | Automatic parameter reverse solving method and system for infinite stratum | |
| Zheng et al. | Performance comparison of full-batch BP and mini-batch BP algorithm on spark framework | |
| CN110486008B (en) | Parameter interpretation method and system for radial composite oil reservoir | |
| CN106934075B (en) | Drilling fluid density determination method and static equivalent density determination method | |
| CN116663607A (en) | Method for constructing oilfield separate layer water injection prediction model based on LSTM | |
| CN113537354B (en) | Aquifer structure staged stochastic inversion identification method based on deep learning | |
| CN111738407B (en) | Clock error prediction method, device, medium and terminal based on deep learning | |
| CN117010260A (en) | Automatic history fit model prediction method, system and equipment for fractured reservoir | |
| CN114519291A (en) | Method for establishing working condition monitoring and control model and application method and device thereof |
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 |