Formation plugging identification method and device based on numerical simulation automatic history matching of oil and gas reservoirs
By using an automatic history fitting method based on numerical simulation of oil and gas reservoirs, combined with machine learning algorithms and surrogate models, the main controlling factors of formation blockage are identified, solving the problems of time-consuming, labor-intensive, and error-prone traditional methods, and achieving rapid and accurate formation blockage identification.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- PETROCHINA CO LTD
- Filing Date
- 2024-12-19
- Publication Date
- 2026-06-23
AI Technical Summary
Traditional methods for identifying formation blockages rely on manual intervention, which is time-consuming and labor-intensive, making it difficult to adapt to the needs of complex and unconventional oil and gas reservoirs. Furthermore, the interpretation results are prone to errors, and the degree of automation in identification is low.
An automatic history fitting method based on oil and gas reservoir numerical simulation is adopted, combined with machine learning algorithms and surrogate models. By establishing a three-dimensional numerical model and analyzing production dynamics, parameter optimization is performed using CNN convolutional network and non-dominated sorting genetic algorithm to identify the main controlling factors of formation blockage.
It achieves rapid and accurate identification of formation blockage, reduces computational complexity and time, improves the accuracy and automation of identification, and simplifies the workload of the model.
Smart Images
Figure CN122263191A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of petroleum exploration and development technology, specifically to a method and apparatus for identifying formation blockage based on automatic historical fitting of oil and gas reservoir numerical simulation. Background Technology
[0002] In numerical simulations of oil and gas reservoirs, history fitting involves inversely calculating reservoir physical properties based on known actual dynamic parameters, thereby correcting and adjusting the parameters in the model. Typically, the history fitting problem is transformed into solving a function extremum problem defined in a multidimensional space using nonlinear programming. The independent variables must satisfy constraints such as the seepage equation expressed by partial differential equations, boundary conditions, and initial conditions.
[0003] Formation blockage can affect the normal production of gas wells, reduce production and recovery rates, increase development costs and risks, cause secondary pollution of the gas reservoir, and induce changes in reservoir sensitivity, triggering water-sensitive, salt-sensitive, acid-sensitive, and alkali-sensitive reactions, thus exacerbating reservoir damage and leading to safety hazards in oil and gas wells. This increases the probability of accidents such as sand production, corrosion, hydrate blockage, wellbore scaling, blowouts, and well collapses. With the increasing demand for numerical simulation of oil and gas reservoirs in the petroleum engineering field, automatic history fitting has become a key tool for better identifying formation blockage in gas wells.
[0004] Traditional methods for identifying formation blockage mainly rely on production dynamic data analysis and well test analysis, requiring manual intervention and judgment, which is time-consuming and labor-intensive, and difficult to adapt to the special needs of complex and unconventional oil and gas reservoirs. Although some scholars have proposed establishing reservoir numerical simulation models to fit production history and predict and identify formation blockage, in field applications, they still heavily rely on the experience of interpreters. Judging based on well test analysis of skin coefficients, reservoir seepage characteristics, and combined with production dynamic characteristics results in low levels of automation. Furthermore, well test parameter interpretation mainly involves moving typical curve charts to coincide with measured double logarithmic curves to interpret wellbore and formation parameters. The human determination of the well test model introduces significant errors, and if the selected well test model does not match the actual oilfield conditions, the interpretation results will be inaccurate. Summary of the Invention
[0005] To address the problems and shortcomings of existing technologies, this invention proposes a method and apparatus for identifying formation blockage based on automatic history fitting in numerical simulation of oil and gas reservoirs. This invention reflects formation blockage indirectly through automatic history fitting, and then reduces the computational load and complexity of the numerical simulation model by using a surrogate model. This allows for faster and more accurate acquisition of relevant parameters without requiring extensive mathematical formula calculations and reasoning. This invention uses a predictive surrogate model to obtain important parameters from large-scale oil reservoir data, simplifying the overall model workload while ensuring model integrity. Through multi-objective optimization, it obtains more accurate influencing factors of formation blockage, thereby achieving accurate formation blockage prediction results.
[0006] To achieve the above-mentioned objectives, the technical solution of the present invention is as follows:
[0007] This invention discloses a method for identifying formation plugging based on automatic historical fitting of oil and gas reservoir numerical simulation, the method comprising the following steps:
[0008] Step S1. Based on the geological modeling results, establish a three-dimensional numerical model of the oil and gas reservoir;
[0009] Step S2. Conduct production dynamic analysis on the oil and gas reservoir to identify the dynamic and static characteristic parameters of the oil and gas reservoir production stage;
[0010] Step S3. Use the numerical model and dynamic and static characteristic parameters of the production stage to perform automatic historical fitting. In the numerical simulation results, select the dynamic and static characteristic parameters of the production stage corresponding to the blockage condition to establish a dataset.
[0011] Step S4. Use machine learning algorithms to build a proxy prediction model and train the proxy model using a dataset; after training, use the trained model to identify the main controlling factors causing formation blockage.
[0012] Step S5. Introduce the main control factors into the three-dimensional numerical model of the oil and gas reservoir for automatic history fitting, use the non-dominated sorting genetic algorithm to optimize the numerical simulation results in the overall solution space, and finally obtain the optimal solution set to identify formation blockage.
[0013] Preferably, the method further includes: step S6. comparing the formation blockage identified by the numerical simulation results with the well test interpretation to evaluate and verify the accuracy and rationality of the model in identifying formation blockage.
[0014] Preferably, the production dynamics analysis includes geological feature recognition, connectivity analysis, fluid analysis, daily output analysis, and water body analysis.
[0015] Preferably, in step S1, the dynamic characteristic parameters include daily gas production, daily water production, daily oil production, wellhead pressure, bottom hole pressure, formation pressure, wellhead temperature, and bottom hole temperature.
[0016] Preferably, the static characteristic parameters include permeability, porosity, fluid saturation, fluid viscosity, formation conductivity, initial formation pressure, rock compressibility, capillary pressure, and net-to-capillary ratio.
[0017] Preferably, the proxy prediction model is a CNN convolutional network.
[0018] Preferably, the training and inversion process of the CNN convolutional network is as follows:
[0019] Step a. Input the standardized dataset into the constructed model. The model's convolutional layers perform convolution operations on the input data using convolution kernels to extract the spatial features of the data. The calculation expression is as follows:
[0020]
[0021] Where, x i,j,k For input data; w m,n,p y is the kernel weight; b is the bias, y is the weight of the convolution kernel. i,j,k This is the output of a convolution;
[0022] Step b applies the ReLU activation function to the input of the convolutional layer to introduce nonlinearity, and the calculation expression is as follows:
[0023] f(x) = max(0,x);
[0024] By reducing data dimensionality through pooling operations, the calculation expression is as follows:
[0025] y i,j,k =max(x i+m,j+n,k+p );
[0026] Where m, n, and p are the sizes of the pooling window, respectively;
[0027] Step c. Based on the trained CNN model, input new parameters and predict the impact of these parameters on production data. By repeatedly adjusting the input parameters, find the parameter combination that best matches the historical data. These combinations are the main controlling factors of formation blockage.
[0028] Based on the same inventive concept, another aspect of the present invention proposes a formation plugging identification device based on automatic history fitting of oil and gas reservoir numerical simulation. The device is used to implement the aforementioned formation plugging identification method, comprising:
[0029] The geological modeling module establishes a three-dimensional numerical model of the oil and gas reservoir based on the geological modeling results.
[0030] The production dynamics analysis module performs production dynamics analysis on oil and gas reservoirs, clarifying the dynamic and static characteristic parameters of the oil and gas reservoir production stages;
[0031] The automatic history fitting module uses numerical models and dynamic and static characteristic parameters of the production stage to automatically fit the history. In the numerical simulation results, it selects the dynamic and static characteristic parameters of the production stage corresponding to the blockage condition to establish a dataset.
[0032] The machine learning module uses machine learning algorithms to build a proxy prediction model and trains the proxy model using a dataset. After training, the trained model is used to invert the historical fitting accuracy to determine the main controlling factors causing congestion identification.
[0033] The formation blockage identification module incorporates the main controlling factors into the three-dimensional numerical model of the oil and gas reservoir for automatic history fitting. It uses a non-dominated sorting genetic algorithm to optimize the numerical simulation results in the overall solution space, and finally obtains the optimal solution set to identify formation blockage.
[0034] A computer device includes a memory, a processor, and a computer program stored in the memory and executable in the processor, wherein when the processor executes the computer program, it implements the steps of the above-described formation blockage identification method.
[0035] A computer-readable storage medium storing a computer program that, when executed in a computer processor, implements the steps of the above-described formation blockage identification method.
[0036] The beneficial effects of this invention are:
[0037] 1. This invention reflects formation blockage indirectly through automatic historical data fitting, and then reduces the computational load and complexity of the numerical simulation model by using a surrogate model. This enables faster and more accurate acquisition of relevant parameters without requiring extensive mathematical formula calculations and reasoning. This invention uses a surrogate model to obtain important parameters from large reservoir data, simplifying the overall model workload while ensuring model integrity. Through multi-objective optimization, it obtains more accurate influencing factors of formation blockage, thereby achieving accurate formation blockage prediction results.
[0038] 2. This invention uses the non-dominated sorting genetic algorithm (NSGA-III) to search for the optimal solution set in the overall solution space, which can help optimize resource allocation, make efficient use of computing resources, and reduce computation time. Attached Figure Description
[0039] The foregoing and hereinafter detailed description of the invention becomes clearer when read in conjunction with the following drawings, in which:
[0040] Figure 1 This is a schematic diagram of the method flow of the present invention;
[0041] Figure 2 This is a diagram showing the device composition of the present invention.
[0042] In the attached image:
[0043] 201. Geological Modeling Module; 202. Production Dynamics Analysis Module; 203. Automatic History Fitting Module; 204. Machine Learning Module; 205. Formation Blockage Identification Module. Detailed Implementation
[0044] To enable those skilled in the art to better understand the technical solutions of this invention, several specific embodiments will be used to further illustrate the technical solutions for achieving the objectives of this invention. It should be noted that the technical solutions claimed by this invention include, but are not limited to, the following embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort should fall within the scope of protection of this invention.
[0045] As one of the most basic embodiments of the present invention, this embodiment first discloses a method for identifying formation blockage based on automatic historical fitting of oil and gas reservoir numerical simulation. Figure 1 This is a flowchart of the method of the present invention, with reference to the appendix to the specification. Figure 1 The method mainly includes the following steps:
[0046] Step S1. Based on the geological modeling results, establish a three-dimensional numerical model of the oil and gas reservoir.
[0047] Step S2. Conduct production dynamic analysis on the oil and gas reservoir to identify the dynamic and static characteristic parameters of the oil and gas reservoir production stage.
[0048] In the embodiments described in this invention, the production dynamics analysis of oil and gas reservoirs typically includes geological feature recognition, connectivity analysis, fluid analysis, daily production analysis, and water body analysis. The dynamic feature parameters obtained from the production dynamics analysis are typically production-related parameters, including daily gas production, daily water production, daily oil production, wellhead pressure, bottom hole pressure, formation pressure, wellhead temperature, and bottom hole temperature. Furthermore, the static feature parameters are typically geological feature parameters, generally including permeability, porosity, fluid saturation, fluid viscosity, formation conductivity, initial formation pressure, rock compressibility coefficient, capillary pressure, and net-to-capillary ratio.
[0049] Step S3. Use the numerical model and dynamic and static characteristic parameters of the production stage to perform automatic historical fitting. In the numerical simulation results, select the dynamic and static characteristic parameters of the production stage corresponding to the blockage condition to establish a dataset.
[0050] In the embodiments described in this invention, the dataset is typically standardized, and the specific standardization calculation formula is as follows:
[0051]
[0052] Where x represents the original data; μ represents the mean; σ represents the standard deviation; and x′ represents the standardized data.
[0053] Step S4. Use machine learning algorithms to build a proxy prediction model. Use the standardized dataset from step S3 as the training set for the model. Use the training set to train the proxy model. After training, select the optimal model as the final prediction proxy model. Then use the trained model to invert and identify the main controlling factors causing formation blockage.
[0054] In the embodiments described in this invention, a CNN convolutional neural network is typically used as the surrogate prediction model, and the specific training and prediction process of the model is as follows:
[0055] a. Input data through the model input layer, and then use a convolutional layer to perform convolution operations on the input data using convolutional kernels to extract the spatial features of the data. The specific calculation formula is as follows:
[0056]
[0057] Where, x i,j,k For input data; w m,n,p y is the kernel weight; b is the bias, y is the weight of the convolution kernel. i,j,k This is the output of the convolution.
[0058] b. Apply the ReLU activation function to the input of the convolutional layer to introduce nonlinearity. The specific calculation formula is as follows:
[0059] f(x) = max(0,x);
[0060] Pooling operations (such as max pooling) reduce data dimensionality and computational complexity. The calculation formula is as follows:
[0061] y i,j,k =max(x i+m,j+n,k+p );
[0062] Where m, n, and p are the sizes of the pooling window.
[0063] The output of the convolutional layer is flattened by a fully connected layer and then fed back into the fully connected layer to obtain the prediction result. Finally, the predicted value corresponding to the actual historical production data is output through the output layer.
[0064] c. Inversion process
[0065] By using a trained CNN model and inputting new parameters, the impact of these parameters on production data is predicted. Through repeated adjustments to the input parameters, the parameter combinations that best match historical data are identified; these combinations are the controlling factors of formation blockage.
[0066] In other words, by analyzing the sensitivity of the model output to different input parameters, we can determine which parameters have the greatest impact on the historical fitting results. These parameters are the main control factors that need to be inverted.
[0067] Step S5. Introduce the main control factors into the three-dimensional numerical model of the oil and gas reservoir for automatic history fitting, use the non-dominated sorting genetic algorithm (NSGA-III) to optimize the numerical simulation results in the overall solution space, and finally obtain the optimal solution set to identify formation blockage.
[0068] In the embodiments described in this invention, the specific implementation steps of NSGA-III are as follows:
[0069] ① Initialize a population P of size N, and generate a set of reference points Z according to the objective dimension of the problem;
[0070] ② Perform non-dominated sorting on P to obtain different non-dominated layers F1, F2, ..., Fk;
[0071] ③ Starting from F1, individuals in the non-dominated layer are sequentially added to a new population Q until the size of Q reaches or exceeds N;
[0072] ④ If the size of Q exceeds N, then reference point association selection is performed on the last added non-dominated layer Fl. That is, based on the distance and angle between the individual and the reference point, the individual most related to the reference point is selected until the size of Q equals N.
[0073] ⑤ Perform crossover and mutation operations on each individual in Q to generate a progeny population R of size N;
[0074] ⑥ Merge P and R to obtain a population T of size 2N;
[0075] ⑦ Perform non-dominated sorting on T to obtain different non-dominated layers F1, F2, ..., Fk;
[0076] ⑧ Repeat steps ③ and ④, starting from F1, and add individuals from the non-dominated layer to a new population P in turn until the size of P is equal to N;
[0077] ⑨ If the preset termination condition (such as the maximum number of generations or the convergence index) is met, the algorithm stops and all individuals in P are output as the final solution set; otherwise, return to step ⑤ to continue evolution.
[0078] Step S6. Taking the formation pressure distribution and skin coefficient changes as the starting point, compare the formation blockage identified by the numerical simulation results with the well test interpretation to evaluate and verify the accuracy and rationality of the model in identifying formation blockage.
[0079] In the embodiments described in this invention, the solutions in the optimal solution set are used to simulate the formation pressure distribution and skin coefficient changes, and their impact on reservoir production is analyzed; the simulation results are compared with actual well test data to verify the accuracy and rationality of the model.
[0080] Based on the same inventive concept, another aspect of the embodiments of the present invention discloses a formation blockage identification device based on automatic history fitting of oil and gas reservoir numerical simulation. Since the principle by which this device solves the problem is similar to the formation blockage identification method based on automatic history fitting of oil and gas reservoir numerical simulation, the implementation of this device can refer to the implementation of the method, and repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated. Figure 2 This is a schematic diagram of a formation blockage identification device based on automatic history fitting of oil and gas reservoir numerical simulation provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the device may include: a geological modeling module 201, a production dynamics analysis module 202, an automatic history fitting module 203, a machine learning module 204, and a formation blockage identification module 205.
[0081] The structure of the device will be described in detail below.
[0082] Geological Modeling Module 201: Based on the results of geological modeling, establish a three-dimensional numerical model of oil and gas reservoirs.
[0083] The production dynamics analysis module 202 performs production dynamics analysis on oil and gas reservoirs to identify the dynamic and static characteristic parameters of the oil and gas reservoir production stages.
[0084] The automatic history fitting module 203 uses the numerical model and dynamic and static characteristic parameters of the production stage to automatically fit the history. In the numerical simulation results, it selects the dynamic and static characteristic parameters of the production stage corresponding to the blockage condition to establish a dataset.
[0085] Machine learning module 204 uses machine learning algorithms to build a proxy prediction model and trains the proxy model using a dataset. After training, the trained model is used to invert the historical fitting accuracy to determine the main controlling factors causing congestion identification.
[0086] The formation blockage identification module 205 incorporates the main controlling factors into the three-dimensional numerical model of the oil and gas reservoir for automatic history fitting, and uses a non-dominated sorting genetic algorithm to optimize the numerical simulation results in the overall solution space, finally obtaining the optimal solution set and identifying formation blockage.
[0087] It should be noted that the systems, devices, models, or units described in the above embodiments can be implemented by computer chips or physical entities, or by products with certain functions. For ease of description, the above devices are described in this specification as various units based on their functions. Of course, in implementing this invention, the functions of each unit can be implemented in one or more software and / or hardware.
[0088] Furthermore, in this specification, adjectives such as first and second may only be used to distinguish an element or action, without necessarily implying any actual such relationship or order.
[0089] Furthermore, this embodiment also provides a computer device, which includes a processor, an input device, an output device, and a memory, all interconnected. The memory stores a computer program, which includes program instructions, and the processor is configured to invoke the program instructions to execute the steps described in the above embodiments.
[0090] Furthermore, another aspect of this embodiment provides a computer-readable storage medium, characterized in that: the computer-readable storage medium stores a computer program, the computer program including program instructions, which, when executed by a processor, cause the processor to perform the steps in the above embodiments.
[0091] In this embodiment, the processor can be a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips.
[0092] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and units, such as the program units corresponding to the above-described method embodiments of the present invention. The processor executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions, and modules stored in the memory, thereby implementing the methods described in the above-described method embodiments.
[0093] The memory may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the processor, etc. Furthermore, the memory may include high-speed random access memory and non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the processor, which can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0094] The one or more units are stored in the memory and, when executed by the processor, perform the methods described in the above embodiments.
[0095] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects.
[0096] The above description is merely a preferred embodiment of the present invention and is not intended to hinder the present invention in any way. Any simple modifications or equivalent changes made to the above embodiments based on the technical essence of the present invention shall fall within the protection scope of the present invention.
Claims
1. A method for identifying formation plugging based on automatic history fitting in numerical simulation of oil and gas reservoirs, characterized in that, The method includes the following steps: Step S1. Based on the geological modeling results, establish a three-dimensional numerical model of the oil and gas reservoir; Step S2. Conduct production dynamic analysis on the oil and gas reservoir to identify the dynamic and static characteristic parameters of the oil and gas reservoir production stage; Step S3. Use the numerical model and dynamic and static characteristic parameters of the production stage to perform automatic historical fitting. In the numerical simulation results, select the dynamic and static characteristic parameters of the production stage corresponding to the blockage condition to establish a dataset. Step S4. Use machine learning algorithms to build a proxy prediction model and train the proxy model using a dataset; after training, use the trained model to identify the main controlling factors causing formation blockage. Step S5. Introduce the main control factors into the three-dimensional numerical model of the oil and gas reservoir for automatic history fitting, use the non-dominated sorting genetic algorithm to optimize the numerical simulation results in the overall solution space, and finally obtain the optimal solution set to identify formation blockage.
2. The formation plugging identification method based on automatic history fitting of oil and gas reservoir numerical simulation according to claim 1, characterized in that, The method further includes: step S6. Comparing the formation blockage identified by the numerical simulation results with the well test interpretation to evaluate and verify the accuracy and rationality of the model in identifying formation blockage.
3. The formation plugging identification method based on automatic history fitting of oil and gas reservoir numerical simulation according to claim 1, characterized in that, The production dynamics analysis includes geological feature recognition, connectivity analysis, fluid analysis, daily output analysis, and water body analysis.
4. The formation plugging identification method based on automatic history fitting of oil and gas reservoir numerical simulation according to claim 1, characterized in that, In step S1, the dynamic characteristic parameters include daily gas production, daily water production, daily oil production, wellhead pressure, bottom hole pressure, formation pressure, wellhead temperature, and bottom hole temperature.
5. The formation plugging identification method based on automatic history fitting of oil and gas reservoir numerical simulation according to claim 1, characterized in that, The static characteristic parameters include permeability, porosity, fluid saturation, fluid viscosity, formation conductivity, initial formation pressure, rock compressibility, capillary pressure, and net-to-capillary ratio.
6. The formation plugging identification method based on automatic history fitting of oil and gas reservoir numerical simulation according to claim 1, characterized in that, The proxy prediction model is a CNN convolutional network.
7. The formation plugging identification method based on automatic history fitting of oil and gas reservoir numerical simulation according to claim 5, characterized in that, The training and inversion process of the CNN convolutional network is as follows: Step a. Standardize the dataset, and then input the standardized data into the constructed CNN model. The convolutional layers of the model perform convolution operations on the input data through convolution kernels to extract the spatial features of the data. The calculation expression is as follows: Where, x i,j,k For input data; w m,n,p y is the kernel weight; b is the bias, y is the weight of the convolution kernel. i,j,k This is the output of a convolution; Step b. Apply the ReLU activation function to the input of the convolutional layer to introduce nonlinearity. The calculation expression is as follows: f(x) = max(0,x); By reducing data dimensionality through pooling operations, the calculation expression is as follows: and i,j,k =max(x i+m,j+n,k+p ); Where m, n, and p are the sizes of the pooling window, respectively; Step c. Based on the trained CNN model, input new parameters and predict the impact of these parameters on production data. By repeatedly adjusting the input parameters, find the parameter combination that best matches the historical data. These combinations are the main controlling factors of formation blockage.
8. A formation plugging identification device based on automatic history fitting of oil and gas reservoir numerical simulation, the device being used to implement the formation plugging identification method according to any one of claims 1-7, characterized in that, include: The geological modeling module establishes a three-dimensional numerical model of the oil and gas reservoir based on the geological modeling results. The production dynamics analysis module performs production dynamics analysis on oil and gas reservoirs, clarifying the dynamic and static characteristic parameters of the oil and gas reservoir production stages; The automatic history fitting module uses numerical models and dynamic and static characteristic parameters of the production stage to automatically fit the history. In the numerical simulation results, it selects the dynamic and static characteristic parameters of the production stage corresponding to the blockage condition to establish a dataset. The machine learning module uses machine learning algorithms to build a proxy prediction model and trains the proxy model using a dataset. After training, the trained model is used to invert the historical fitting accuracy to determine the main controlling factors causing congestion identification. The formation blockage identification module incorporates the main controlling factors into the three-dimensional numerical model of the oil and gas reservoir for automatic history fitting. It uses a non-dominated sorting genetic algorithm to optimize the numerical simulation results in the overall solution space, and finally obtains the optimal solution set to identify formation blockage.
9. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable in the processor. When the processor executes the computer program, it implements the formation blockage identification method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed in a computer processor, implements the formation blockage identification method according to any one of claims 1-7.