Oil well yield prediction method based on artificial intelligence

Abstract

The invention relates to an oil well yield prediction method based on artificial intelligence. The prediction method comprises the following steps: acquiring underground fluid proportion, pressure, pipe diameter and temperature data in real time through underground and ground multi-mode sensors; calculating wellbore flow characteristic parameters based on a multiphase fluid mechanics formula; utilizing a multiphase flow simulation algorithm to couple multi-source data to generate a full-chain fluid distribution result; optimizing a full-chain fluid distribution result to generate a yield distribution predicted value; multi-source data are fused through a physical information neural network, and a full-chain fluid parameter simulation result is generated; and finally, realizing real-time data assimilation by adopting an ensemble Kalman filtering algorithm, and outputting a dynamic simulation result. According to the petroleum yield prediction method provided by the invention, the problems of underground and ground data separation, model static boundary lag, excessive simplification of a physical equation and the like in a traditional method are solved, the prediction precision and real-time performance in a complex oil well scene are improved, and intelligent decision support is provided for oilfield development.

Description

Technical Field

[0001] The present invention relates to the technical field of petroleum resource detection, and in particular to an oil well production prediction method based on artificial intelligence. Background Art

[0002] Oil well production prediction is a core link in oilfield development and production management. The key lies in the accurate modeling and dynamic analysis of the entire flow process from underground to the surface. Traditional oil well production prediction methods mainly rely on physical models and empirical formulas. By collecting limited parameters such as downhole pressure and temperature, combined with multiphase flow theory to simulate wellbore flow, the production distribution is then inferred. However, the oilfield production system is highly complex, involving downhole fluid dynamics, ground pipeline transmission and multi-parameter coupling effects. Traditional methods often find it difficult to take into account the integration of multi-source heterogeneous data and real-time requirements.

[0003] In the existing technology, oil well production prediction models usually face the following problems: First, the separation of underground and surface data makes it difficult to couple parameters, for example, it is difficult to calculate wellbore flow characteristics and pipeline pressure distribution simultaneously; second, traditional numerical simulation methods rely on static boundary conditions and cannot respond to changes in production data in real time, causing the prediction results to lag behind actual working conditions; third, the accuracy of multiphase flow models is limited by simplified assumptions in physical equations, making it difficult to accurately capture the dynamic interaction effects of oil, gas and water three-phase fluids. These problems make the traditional methods have large prediction errors in complex oil well scenarios and difficult to support real-time optimization decisions. Summary of the invention

[0004] Based on this, the purpose of the present invention is to provide an artificial intelligence-based oil well production prediction method that can achieve dynamic coupling and real-time synchronization of full-chain parameters.

[0005] The purpose of the present invention is achieved by the following scheme: In a first aspect, the present invention provides an oil well production prediction method based on artificial intelligence, comprising the following steps: S1: Based on the downhole multi-modal sensor and the ground pipe network multi-modal sensor, the downhole fluid ratio data, downhole pressure data, pipe diameter parameters and pipe network temperature data are collected in real time. The downhole fluid ratio data is used to indicate the three-phase fluid ratio of oil phase, gas phase and water phase; S2: Calculate the wellbore flow characteristic parameters based on the downhole fluid ratio data and the downhole pressure data based on the multiphase fluid mechanics formula to generate the wellbore flow characteristic parameters, which are used to indicate the velocity distribution and density distribution of the fluid in the wellbore; S3: Based on the multiphase flow simulation algorithm, the pressure and temperature coupling calculation is performed on the pipe network temperature data, pipe diameter parameters and wellbore flow characteristic parameters to generate the full chain fluid distribution results; S4: Based on the finite difference method and back propagation algorithm, dynamic boundary optimization processing is performed on the fluid distribution results of the entire chain to generate the optimized output distribution prediction value; S5: Based on the physical information neural network, multi-parameter fusion processing is performed on the downhole fluid ratio data, downhole pressure data, pipe diameter parameters and pipe network temperature data to generate the full-chain fluid parameter simulation results; S6: Based on the ensemble Kalman filter algorithm, data assimilation is performed on the production distribution prediction value and the full-chain fluid parameter simulation results to generate dynamic simulation results synchronized with actual production. The dynamic simulation results are used to predict the change trend of oil well production.

[0006] In one embodiment, S2 of an oil well production prediction method based on artificial intelligence provided by the present invention specifically includes the following steps: S21: Calculate the downhole pressure data based on the liquid holdup equation and the velocity gradient equation to obtain the initial velocity distribution data of the fluid in the wellbore; S22: performing sliding window averaging processing on the initial velocity distribution data based on the sliding window technology to generate smoothed fluid velocity distribution data; S23: performing fluid mechanics constraint processing on the fluid velocity distribution data and the downhole fluid ratio data based on the physical information neural network to generate fluid density distribution data in the wellbore; S24: Integrate and process the fluid velocity distribution data and the fluid density distribution data to generate wellbore flow characteristic parameters.

[0007] In one embodiment, S3 of an oil well production prediction method based on artificial intelligence provided by the present invention specifically includes the following steps: S31: Train the multiphase flow model based on the historical production data of oil wells and historical pipe network parameters based on machine learning algorithms to generate a multiphase flow simulation kernel; S32: Calculate the pipe section pressure drop based on the pipe network temperature data, pipe diameter parameters and wellbore flow characteristic parameters based on the multiphase flow simulation kernel to generate the pipe network fluid pressure distribution; S33: Identify whether the wellbore velocity distribution of the wellbore flow characteristic parameters exceeds a preset velocity safety threshold, and if so, perform wellhead flow constraint optimization on the pipeline network fluid pressure distribution based on an adaptive particle swarm algorithm to generate updated boundary conditions; S34: Based on the numerical iteration method, the pressure-flow rate is synchronously coupled to the updated boundary conditions and wellbore flow characteristic parameters to generate the full-chain fluid distribution results.

[0008] In one embodiment, S4 of an oil well production prediction method based on artificial intelligence provided by the present invention specifically includes the following steps: S41: Divide the whole chain fluid distribution result into multiple space-time grid units, discretize the mass flow distribution of each space-time grid unit by finite difference method, and generate discretized flow distribution data; S42: dynamically adjusting the distribution weights of the flow distribution data and the downhole fluid ratio data based on the long short-term memory neural network to generate an initial prediction value of the production distribution; S43: Identify whether the deviation between the initial prediction value and the downhole fluid ratio data exceeds a preset deviation threshold. If so, iteratively update the weights allocated to the initial prediction value based on a back propagation algorithm to generate an optimized production distribution prediction value.

[0009] In one embodiment, S42 of an oil well production prediction method based on artificial intelligence provided by the present invention specifically includes the following steps: S421: normalizing the downhole fluid ratio data to generate standardized fluid ratio data; S422: inputting the standardized fluid ratio data into the long short-term memory neural network, extracting the time series characteristics of the wellbore and pipe network allocation through the gating mechanism, and generating the initial allocation ratio weight; S423: Optimize the wellbore-pipeline network allocation ratio by using a dynamic programming algorithm for the initial allocation ratio weights and flow distribution data to generate an initial prediction value for the production distribution.

[0010] In one embodiment, S6 of an oil well production prediction method based on artificial intelligence provided by the present invention specifically includes the following steps: S61: extract the main frequency components in the pressure and temperature change trends of the production distribution prediction value based on the Fourier transform algorithm to generate frequency domain feature data; S62: The missing data points of the frequency domain feature data are supplemented by the cubic spline interpolation method to generate complete digital twin model data; S63: The ensemble Kalman filter algorithm is used to fuse the full-chain fluid parameter simulation results and digital twin model data to generate dynamic simulation results synchronized with actual production.

[0011] In a second aspect, the present invention provides an oil well production prediction system based on artificial intelligence, comprising: A data acquisition module is used to collect downhole fluid ratio data, downhole pressure data, pipe diameter parameters and pipe network temperature data in real time based on downhole multimodal sensors and ground pipe network multimodal sensors. The downhole fluid ratio data is used to indicate the three-phase fluid ratio of oil phase, gas phase and water phase; A characteristic parameter calculation module is used to calculate wellbore flow characteristic parameters based on downhole fluid ratio data and downhole pressure data based on multiphase fluid mechanics formulas to generate wellbore flow characteristic parameters, which are used to indicate velocity distribution and density distribution of the fluid in the wellbore; The pressure-temperature coupling module is used to perform pressure-temperature coupling calculations on the pipe network temperature data, pipe diameter parameters, and wellbore flow characteristic parameters based on the multiphase flow simulation algorithm to generate full-chain fluid distribution results; Dynamic optimization module, which is used to perform dynamic boundary optimization processing on the fluid distribution results of the entire chain based on the finite difference method and back propagation algorithm to generate optimized production distribution prediction values; Multi-parameter fusion module, which is used to perform multi-parameter fusion processing on downhole fluid ratio data, downhole pressure data, pipe diameter parameters and pipe network temperature data based on physical information neural network to generate full-chain fluid parameter simulation results; The synchronous simulation generation module is used to perform data assimilation processing on the production distribution prediction value and the full-chain fluid parameter simulation results based on the ensemble Kalman filter algorithm, and generate dynamic simulation results synchronized with actual production. The dynamic simulation results are used to predict the change trend of oil well production.

[0012] In a third aspect, the present application provides a computer device including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements any of the above-mentioned artificial intelligence-based oil well production prediction methods.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned artificial intelligence-based oil well production prediction methods.

[0014] In summary, the oil well production prediction method based on artificial intelligence provided by the present invention can realize comprehensive, accurate and real-time simulation and prediction of the oil well production system through multimodal sensor data acquisition, multiphase fluid mechanics calculation, multiphase flow simulation, dynamic boundary optimization, multi-parameter fusion and data assimilation and other technical methods, thereby improving the accuracy of oil well production prediction and providing a reliable basis for production decision-making. At the same time, the method can realize dynamic monitoring and optimization adjustment of the production system, which helps to improve production efficiency and reduce production costs, and integrates physical models and data-driven methods to ensure the accuracy and reliability of simulation results, providing strong support for intelligent production management of oil wells.

[0015] For better understanding and implementation, the present invention is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1A schematic diagram of a flow chart of an oil well production prediction method based on artificial intelligence provided in an embodiment of the present application; Figure 2 A schematic diagram of a process for generating an optimized yield distribution prediction value provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of an oil well production prediction system based on artificial intelligence provided in another embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. The preferred embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the invention more thorough and comprehensive.

[0018] Unless otherwise defined, all technical terms and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0019] In one embodiment, Figure 1 As shown, an oil well production prediction method based on artificial intelligence is provided. This embodiment uses the method applied to a terminal as an example for illustration. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps: S1: Based on the downhole multimodal sensor and the ground pipe network multimodal sensor, the downhole fluid ratio data, downhole pressure data, pipe diameter parameters and pipe network temperature data are collected in real time. The downhole fluid ratio data is used to indicate the three-phase fluid ratio of oil phase, gas phase and water phase.

[0020] Specifically, various types of sensors, including but not limited to pressure sensors, temperature sensors, fluid composition sensors, etc., can be installed at different depths of the oil well to monitor the pressure, temperature, and ratio of oil, gas, and water in the well in real time. These sensors are connected to the ground data acquisition system through wired or wireless communication to transmit the collected data to the ground in real time.

[0021] At the same time, a variety of sensors are also installed in the ground oil and gas pipeline network, such as pressure sensors, temperature sensors, flow sensors, etc. The ground pipeline multimodal sensors mainly collect pipeline temperature data and pipe diameter parameters. Pipeline temperature data can reflect the temperature changes of the fluid in the pipeline network, which is of great significance for understanding the thermodynamic properties and flow characteristics of the fluid. The pipe diameter parameter is a structural parameter of the pipeline network, which directly affects the flow resistance and flow distribution of the fluid in the pipeline network. These sensors can obtain the above data in real time and accurately through high-precision measurement technology, and transmit it to the data processing system, providing reliable data support for subsequent calculations and analysis.

[0022] S2: Calculate the wellbore flow characteristic parameters based on the downhole fluid ratio data and the downhole pressure data based on the multiphase fluid mechanics formula to generate the wellbore flow characteristic parameters, which are used to indicate the velocity distribution and density distribution of the fluid in the wellbore.

[0023] Specifically, the multiphase fluid mechanics formula is a mathematical expression that describes the flow law of multiphase fluids in pipelines or wellbores, which comprehensively considers factors such as the phase interaction, flow velocity, density, and pressure of the fluid. Specifically, the system can calculate key parameters such as the velocity distribution and density distribution of the fluid in the wellbore by substituting the collected proportion data of the oil phase, gas phase, and water phase and the downhole pressure data into these formulas. Among them, the velocity distribution parameters can reflect the change in the flow velocity of different phase fluids in the wellbore, which is directly meaningful for determining the flow state and flow rate of the fluid. The density distribution parameters reflect the density changes of the fluid at different positions and different phases, which is crucial for accurately calculating the volume flow rate and mass flow rate of the fluid. These wellbore flow characteristic parameters provide the necessary basic data for the subsequent pipe network pressure and temperature coupling calculations, ensuring the accurate modeling and analysis of the entire flow system.

[0024] S3: Based on the multiphase flow simulation algorithm, the pressure and temperature coupling calculation is performed on the pipeline network temperature data, pipe diameter parameters and wellbore flow characteristic parameters to generate the full-chain fluid distribution results.

[0025] Specifically, a multiphase flow simulation algorithm based on the finite element method or the multiphase flow network method can be selected. Taking the finite element method as an example, the pipe network system is divided into multiple tiny finite element units, the fluid flow in each unit is discretized, and the corresponding control equation is established. Specifically, the wellbore flow characteristic parameters (fluid velocity, density distribution) obtained by the system are used as the boundary conditions of the pipe network inlet, and the fluid flow in the pipe network is simulated and calculated in combination with the pipe network temperature data and pipe diameter parameters. In the calculation process, the influence of the physical parameters of the fluid (such as viscosity, specific heat capacity, etc.) changing with temperature is considered, and corrections are made through table lookup or empirical formulas.

[0026] For each pipe network unit, the pressure drop and temperature change of the fluid are calculated simultaneously. The pressure drop calculation takes into account factors such as the flow velocity, pipe diameter, and fluid viscosity of the fluid, and is calculated using the Darcy-Weisbach formula; the temperature change calculation takes into account factors such as the heat exchange between the fluid and the pipeline, the adiabatic compression or expansion of the fluid, and is solved using the energy conservation equation. The calculation results of all units are integrated to obtain the pressure and temperature distribution of the entire pipe network system, thereby generating the full-chain fluid distribution results, including the flow state, pressure, temperature, and other information of the fluid in the wellbore and pipe network.

[0027] S4: Based on the finite difference method and back propagation algorithm, dynamic boundary optimization processing is performed on the fluid distribution results of the entire chain to generate optimized production distribution prediction values.

[0028] Specifically, the finite difference method is used to discretize the fluid distribution results of the entire chain, converting continuous fluid distribution parameters (such as pressure, temperature, fluid velocity, etc.) into discrete grid point data, and establishing the corresponding differential equations; the back propagation algorithm is used to optimize the boundary condition parameters in the differential equations. The error between the predicted value of the production distribution and the actual measured production data is used as the objective function, and the boundary condition parameters are adjusted through the back propagation algorithm to minimize the objective function.

[0029] Specifically, the system uses the finite difference method to preliminarily process the fluid distribution results of the entire chain to obtain the initial output distribution prediction value. Then, the prediction value is compared with the actual output data to calculate the error. According to the error backpropagation to the boundary condition parameters, the boundary condition parameters are adjusted according to a certain learning rate and optimization algorithm (such as gradient descent method). This process is repeated until the error meets the preset threshold, and finally the optimized output distribution prediction value is obtained.

[0030] S5: Based on the physical information neural network, multi-parameter fusion processing is performed on the downhole fluid ratio data, downhole pressure data, pipe diameter parameters and pipe network temperature data to generate full-chain fluid parameter simulation results.

[0031] Specifically, the physical information neural network is a deep learning method that integrates physical laws into the neural network architecture. By adding the constraint terms of the physical equations to the loss function of the neural network, the network can meet the requirements of physical laws while learning data. In this step, the physical information neural network is used to perform multi-parameter fusion processing on the downhole fluid ratio data, downhole pressure data, pipe diameter parameters and pipe network temperature data.

[0032] Specifically, the system uses the above-mentioned multi-source data such as downhole fluid ratio data, downhole pressure data, pipe diameter parameters and pipe network temperature data as the input of the neural network, and learns the complex relationship and internal laws between the data through the network's forward propagation and back propagation process. During the training process, the network continuously adjusts the weight and bias parameters so that the output full-chain fluid parameter simulation results not only conform to the statistical characteristics of the data, but also meet the constraints of physical laws, thereby improving the accuracy and reliability of the simulation results.

[0033] S6: Based on the ensemble Kalman filter algorithm, data assimilation is performed on the production distribution prediction value and the full-chain fluid parameter simulation results to generate dynamic simulation results synchronized with actual production. The dynamic simulation results are used to predict the change trend of oil well production.

[0034] Specifically, the ensemble Kalman filter is a filtering algorithm based on Bayesian statistics, which can estimate and update the state of the system by fusing model prediction data and actual observation data. In this step, the ensemble Kalman filter algorithm is used to perform data assimilation processing on the production distribution prediction value and the full-chain fluid parameter simulation results. First, the state vector and covariance matrix of the system are constructed according to the production distribution prediction value and the full-chain fluid parameter simulation results. Then, the actual production data is used as the observation data, and the state vector is updated using the ensemble Kalman filter algorithm to obtain a dynamic simulation result synchronized with the actual production. The result can reflect the production status of the oil well in real time, and is used to predict the changing trend of the oil well production, providing a scientific basis for the development and production management of the oil field.

[0035] In summary, the oil well production prediction method based on artificial intelligence provided by the present invention can realize comprehensive, accurate and real-time simulation and prediction of the oil well production system through multimodal sensor data acquisition, multiphase fluid mechanics calculation, multiphase flow simulation, dynamic boundary optimization, multi-parameter fusion and data assimilation and other technical methods, thereby improving the accuracy of oil well production prediction and providing a reliable basis for production decision-making. At the same time, the method can realize dynamic monitoring and optimization adjustment of the production system, which helps to improve production efficiency and reduce production costs, and integrates physical models and data-driven methods to ensure the accuracy and reliability of simulation results, providing strong support for intelligent production management of oil wells.

[0036] In one embodiment, S2 of an oil well production prediction method based on artificial intelligence provided by the present invention specifically includes the following steps: S21: Calculate the downhole pressure data based on the liquid holdup equation and the velocity gradient equation to obtain the initial velocity distribution data of the fluid in the wellbore.

[0037] Specifically, the liquid holdup equation is used to describe the volume fraction distribution of the fluid in the wellbore, and the velocity gradient equation is used to describe the variation of fluid velocity with position. By combining these two equations, a mathematical relationship between fluid velocity and downhole pressure can be established, where the liquid holdup equation and the velocity gradient equation can be expressed as: ; in, is the liquid holdup rate, is the liquid phase volume flow rate, is the wellbore cross-sectional area, is the fluid velocity, is the height direction, is the pressure gradient, is the fluid viscosity; the system substitutes the collected downhole pressure data into the above equation, solves the velocity distribution of the fluid by numerical calculation method, determines the volume fraction of the fluid according to the liquid holdup equation, and then combines the velocity gradient equation and uses numerical methods such as the finite difference method to calculate the fluid velocity at different heights of the wellbore to obtain the initial velocity distribution data.

[0038] S22: Perform sliding window averaging processing on the initial velocity distribution data based on the sliding window technology to generate smoothed fluid velocity distribution data.

[0039] Specifically, the sliding window technology is a data smoothing method that moves a fixed-size window on the data sequence and averages or performs other statistical processing on the data in the window to reduce data fluctuations and noise. In this step, the sliding window averaging process can effectively smooth short-term fluctuations and outliers in the initial velocity distribution data, making the data smoother and more stable. The system sets a fixed-size window, for example, the window size is 5 data points, and slides the window on the initial velocity distribution data sequence in turn. For each window position, the average value of the data points in the window is calculated, and the value of the data point at the center of the window is replaced with the average value. In this way, the entire initial velocity distribution data is smoothed to generate smoothed fluid velocity distribution data.

[0040] S23: Perform fluid mechanics constraint processing on the fluid velocity distribution data and the downhole fluid ratio data based on the physical information neural network to generate the fluid density distribution data in the wellbore.

[0041] Specifically, the physical information neural network is a deep learning method that incorporates physical laws into the neural network training process. By adding the constraint terms of the physical equations to the loss function, it ensures that the output results of the neural network not only meet the statistical characteristics of the data, but also meet the requirements of the physical laws. In this step, the physical information neural network is used to process the fluid velocity distribution data and the downhole fluid ratio data to ensure that the generated fluid density distribution data conforms to the basic principles of fluid mechanics. Specifically, the system uses the fluid velocity distribution data and the downhole fluid ratio data as the input of the neural network, and designs a network structure containing multiple hidden layers and neurons. In the training process of the network, in addition to using traditional loss functions (such as mean square error) to measure the difference between the predicted value and the true value, the basic equations of fluid mechanics (such as the mass conservation equation, the momentum conservation equation, etc.) are added as constraints. The weights and bias parameters of the network are adjusted through optimization algorithms (such as gradient descent method) so that the output results of the network not only meet the characteristics of the input data, but also meet the constraints of fluid mechanics, thereby generating the fluid density distribution data in the wellbore.

[0042] S24: Integrate and process the fluid velocity distribution data and the fluid density distribution data to generate wellbore flow characteristic parameters.

[0043] Specifically, the integration process includes aligning and fusing the velocity distribution data and density distribution data in space and time to ensure that the two are combined in the same coordinate system and time series. Through mathematical operations and data fusion technology, the velocity and density data are integrated into a comprehensive flow characteristic parameter. This parameter can fully describe the flow state of the fluid in the wellbore, including the velocity distribution, density distribution of the fluid and the relationship between the two. The wellbore flow characteristic parameter is an important basic data for subsequent oil production prediction. It can provide the model with detailed information on the fluid flow characteristics and help improve the accuracy and reliability of production prediction.

[0044] In one embodiment, S3 of an oil well production prediction method based on artificial intelligence provided by the present invention specifically includes the following steps: S31: Based on the machine learning algorithm, the multiphase flow model is trained on the historical production data of oil wells and the historical pipeline network parameters to generate the multiphase flow simulation kernel.

[0045] Specifically, the machine learning algorithm in the present invention mainly refers to algorithms such as neural networks and support vector machines that can learn patterns and rules from historical data. The historical production data of oil wells include past oil well production, fluid ratio, pressure, temperature and other information, and the historical pipeline network parameters cover the pipe diameter, length, material and corresponding temperature, pressure and other data of the pipeline network. These historical data are used as input, and after pre-processing steps such as cleaning and normalization, they are input into the machine learning model for training. During the training process, the model continuously adjusts its own parameters to minimize the error between the predicted value and the actual value, and finally generates a multiphase flow simulation kernel that can accurately describe the flow characteristics of multiphase fluids in the pipeline network. The kernel is essentially a trained model that can predict key information such as the flow state and pressure distribution of the fluid in the pipeline network based on the current input data.

[0046] S32: Based on the multiphase flow simulation kernel, the pipe network temperature data, pipe diameter parameters and wellbore flow characteristic parameters are used to calculate the pipe section pressure drop and generate the pipe network fluid pressure distribution.

[0047] Specifically, the system estimates the fluid pressure drop in each pipe section by inputting the above data into the multiphase flow simulation kernel and using the multiphase flow laws learned in the kernel. The pipe network temperature data affects the physical properties of the fluid, such as viscosity and density. The pipe diameter parameters determine the flow resistance of the fluid, and the wellbore flow characteristic parameters give the initial state of the fluid when it enters the pipe network. Combining these factors, the multiphase flow simulation kernel can calculate the pressure drop of each pipe section and generate a fluid pressure distribution map for the entire pipe network. The pressure distribution map intuitively shows the pressure changes of the fluid in various parts of the pipe network, providing a basis for subsequent flow constraint optimization and generation of full-chain fluid distribution results.

[0048] S33: Identify whether the wellbore velocity distribution of the wellbore flow characteristic parameters exceeds a preset velocity safety threshold. If so, optimize the wellhead flow constraint of the pipeline network fluid pressure distribution based on an adaptive particle swarm algorithm to generate updated boundary conditions.

[0049] Specifically, the system extracts wellbore velocity distribution data from wellbore flow characteristic parameters and compares it with a preset velocity safety threshold. The velocity safety threshold is set according to the production requirements and safety standards of the oil well. Exceeding this threshold may cause flow instability or other production problems in the wellbore.

[0050] If it is identified that the wellbore velocity distribution exceeds the safety threshold, the fluid pressure distribution of the pipeline network needs to be optimized. Preferably, an adaptive particle swarm algorithm can be used. The adaptive particle swarm algorithm is an intelligent optimization algorithm that dynamically adjusts the speed and position of particles by simulating the flight and optimization process of particles in the search space to find the optimal solution. In the present invention, the system uses this algorithm to perform constraint optimization on the wellhead flow rate, and adjusts the wellhead flow rate to return the flow velocity in the wellbore to a safe range while minimizing the impact on the overall production efficiency. The optimized result is the updated boundary condition, which will serve as an important basis for subsequent calculations.

[0051] S34: Based on the numerical iteration method, the pressure-flow rate is synchronously coupled to the updated boundary conditions and wellbore flow characteristic parameters to generate the full-chain fluid distribution results.

[0052] Specifically, the numerical iteration method is a numerical method that approaches the true solution through continuous iterative calculations. In this step, the updated boundary conditions and wellbore flow characteristic parameters are used as the initial input, and the pressure and flow distribution of the fluid in the wellbore and pipeline network are gradually calculated through the numerical iteration method. During the iteration process, the estimated values ​​of pressure and flow are continuously adjusted so that the pressure and flow distribution after iteration satisfies the basic equations and boundary conditions of fluid mechanics until the set convergence accuracy is reached. The final generated full-chain fluid distribution result comprehensively considers multiple factors such as the pressure, flow, velocity, density, etc. of the fluid in the wellbore and pipeline network, and can accurately reflect the distribution of the fluid in the entire production system. This result provides comprehensive and accurate fluid flow information for subsequent oil production forecasts, helps to improve the accuracy and reliability of the forecast, thereby providing a scientific basis for oilfield production management and guiding the formulation and optimization of production decisions.

[0053] In one embodiment, if Figure 2 As shown, S4 of an oil well production prediction method based on artificial intelligence provided by the present invention specifically includes the following steps: S41: Divide the whole chain fluid distribution result into multiple space-time grid units, discretize the mass flow distribution of each space-time grid unit by finite difference method, and generate discretized flow distribution data.

[0054] Specifically, the Long Short-Term Memory Neural Network (LSTM) is a neural network structure that can effectively process time series data. It controls the flow of information through a gating mechanism and can capture long-term dependencies in the data. In this step, the system uses the discretized flow distribution data and downhole fluid ratio data as the input of the LSTM network. The network dynamically adjusts the production distribution ratio weights of each grid unit at different time steps by learning the patterns and rules in the historical data. This means that the network can automatically determine the contribution ratio of each grid unit to the total production at different times based on the dynamic changes in fluid flow and the proportion of different phase fluids. In this way, the LSTM network can generate an initial prediction value of the production distribution that takes into account time and space factors, providing preliminary results for subsequent prediction optimization.

[0055] S42: Based on the long short-term memory neural network, the flow distribution data and the downhole fluid ratio data are dynamically adjusted to generate an initial prediction value of the production distribution.

[0056] Specifically, the initial forecast value of the yield distribution is generated by the following steps: S421: normalize the downhole fluid ratio data to generate standardized fluid ratio data.

[0057] Specifically, normalization is to convert data of different ranges and dimensions into a unified standard range, usually [0, 1] or [-1, 1]. In the present invention, a suitable normalization method, such as minimum-maximum normalization, can be used to process the downhole fluid ratio data. Minimum-maximum normalization linearly maps the data to a specified range, and the formula is: ; in, is the normalized data, is the original data, and are the minimum and maximum values ​​of the data respectively. The normalized fluid ratio data can eliminate the dimensional differences between the ratio data of different phase fluids and improve the training efficiency and prediction accuracy of the neural network.

[0058] S422: Input the standardized fluid ratio data into the long short-term memory neural network, extract the time series characteristics of the wellbore and pipeline network allocation through the gating mechanism, and generate the initial allocation ratio weight.

[0059] Specifically, the gating mechanism of the long short-term memory neural network includes an input gate, a forget gate, and an output gate. The long short-term memory neural network controls the information input at the current moment, the retention of previous information, and the output of the information at the current moment through the gating mechanism. During the training process, the network automatically learns how to extract the key features of fluid distribution in the wellbore and pipeline network based on the temporal changes of the standardized fluid ratio data. These features reflect the flow trends and interactions of different phases of fluid at different times. Based on the extracted features, the network further generates the initial production distribution ratio weight, which represents the contribution ratio of each phase of fluid to the total production at different times and spatial locations.

[0060] S423: Optimize the wellbore-pipeline network allocation ratio by using a dynamic programming algorithm for the initial allocation ratio weights and flow distribution data to generate an initial prediction value for the production distribution.

[0061] Specifically, the dynamic programming algorithm is a method for solving the optimal solution by decomposing a complex problem into multiple sub-problems. In this step, the dynamic programming algorithm is used to optimize the initial allocation ratio weights and flow distribution data. The algorithm can take into account the flow distribution at different locations and times, as well as the proportional relationship of each phase of fluid, to find the optimal allocation ratio weight that makes the overall production forecast value closest to the actual situation. Specifically, the system uses the initial allocation ratio weights and flow distribution data as the input of the dynamic programming algorithm, and iteratively solves the optimal allocation ratio weights by establishing the state transfer equation and the optimization objective function. Then, based on the optimized weights and flow distribution data, the production distribution at each location and time is calculated to generate the initial prediction value of the production distribution. This prediction value comprehensively considers the flow characteristics and proportional relationship of the fluid, providing a basis for subsequent optimization of the prediction value.

[0062] S43: Identify whether the deviation between the initial prediction value and the downhole fluid ratio data exceeds a preset deviation threshold. If so, iteratively update the weights allocated to the initial prediction value based on a back propagation algorithm to generate an optimized production distribution prediction value.

[0063] Specifically, the system compares the generated initial prediction value with the actual downhole fluid ratio data and calculates the deviation between the two. The system also verifies the deviation between the initial prediction value and the downhole fluid ratio data through a preset deviation threshold determined based on production experience and accuracy requirements. If the deviation between the two exceeds the preset deviation threshold, it means that there is a large difference between the initial prediction value and the actual situation, and optimization is required.

[0064] The back propagation algorithm is an optimization algorithm based on gradient descent, which is commonly used in neural network training. In this step, the back propagation algorithm is applied to the optimization of the initial prediction value. By calculating the error gradient between the initial prediction value and the actual value, the weight parameters in the LSTM network are adjusted by back propagation. The weights are continuously updated iteratively to reduce the deviation between the optimized production distribution prediction value and the actual downhole fluid ratio data until the convergence condition is met or the preset number of iterations is reached, and finally a more accurate optimized production distribution prediction value is obtained.

[0065] The above-mentioned artificial intelligence-based oil well production prediction method can realize dynamic boundary optimization processing of the fluid distribution results of the whole chain through the comprehensive application of multiple technical methods such as finite difference method, long short-term memory neural network, dynamic programming algorithm and back propagation algorithm, and can dynamically adjust the production distribution prediction according to real-time data to improve the accuracy and timeliness of the prediction structure; at the same time, this method fully mines the time series characteristics and spatial distribution laws in the data through the combination of neural network and optimization algorithm, provides more reliable data support for oil well production prediction, and combines with the iterative update mechanism to ensure that the prediction results can continue to approach the actual production situation, providing a strong basis for production decision-making.

[0066] In one embodiment, S6 of an oil well production prediction method based on artificial intelligence provided by the present invention specifically includes the following steps: S61: Extract the main frequency components in the pressure and temperature change trends of the production distribution prediction value based on the Fourier transform algorithm to generate frequency domain feature data.

[0067] Specifically, Fourier transform is a mathematical transformation method that converts time domain signals into frequency domain signals. In this step, the system uses the output distribution prediction value as a time domain signal and converts it into a frequency domain signal using the Fourier transform algorithm. By analyzing the frequency domain signal, the main frequency components in the pressure and temperature change trends can be identified. These main frequency components represent the most significant frequency components in the change trend. In the frequency domain, the system extracts the main frequency components as frequency domain feature data based on the energy distribution and amplitude of the signal. These frequency domain feature data can reflect the main periodicity and regularity of pressure and temperature changes in the output distribution prediction value, and provide a basis for the subsequent digital twin model data generation.

[0068] S62: The missing data points of the frequency domain feature data are supplemented by the cubic spline interpolation method to generate complete digital twin model data.

[0069] Specifically, cubic spline interpolation is an interpolation method based on cubic polynomials. The algorithm can accurately estimate the values ​​of missing data points while maintaining the smoothness of the interpolation function. In the present invention, the system analyzes the frequency domain feature data, determines the location and number of missing data points, and uses known data points to establish a cubic spline interpolation function, which is composed of a cubic polynomial between each adjacent known data point and satisfies the conditions of continuity of the function value, first-order derivative, and second-order derivative at the known data point. Subsequently, the system calculates the frequency domain feature values ​​at the missing data points by solving the interpolation function, thereby generating complete digital twin model data. The digital twin model data is an accurate mapping of the actual production system in the virtual space, which contains comprehensive information on the predicted value of the output distribution in the frequency domain and time domain, and provides complete data support for subsequent data fusion and dynamic simulation.

[0070] S63: The ensemble Kalman filter algorithm is used to fuse the full-chain fluid parameter simulation results and digital twin model data to generate dynamic simulation results synchronized with actual production.

[0071] Specifically, the ensemble Kalman filter is a filtering algorithm based on Bayesian statistics, which can estimate and update the state of the system by fusing model prediction data and actual observation data. In this step, the system uses the simulation results of the full-chain fluid parameters as the model prediction data, and the digital twin model data as the actual observation data, and applies the ensemble Kalman filter algorithm for data fusion. The system uses the ensemble Kalman filter algorithm to fuse the simulation results of the full-chain fluid parameters and the digital twin model data. The algorithm calculates the optimal state estimate based on the covariance relationship and observation noise characteristics of the two, and generates dynamic simulation results synchronized with actual production. This result combines the information of model prediction and actual observation, and can more accurately reflect the production status and change trend of the oil well, providing strong support for real-time optimization decision-making.

[0072] In summary, the oil well production prediction method based on artificial intelligence provided by the present invention can realize the frequency domain feature extraction, data supplementation and data fusion of the production distribution prediction value through the comprehensive application of multiple technical methods such as Fourier transform, cubic spline interpolation and ensemble Kalman filtering, and finally generate dynamic simulation results synchronized with actual production. Through this process, the present invention can extract key frequency domain features from the production prediction data to provide important frequency information for subsequent analysis; and through interpolation to supplement missing data, it can improve the integrity and availability of data; at the same time, through the data fusion method, data from different sources are effectively combined, thereby enhancing the accuracy and reliability of the simulation results. In addition, this aspect also responds to the state changes of the oil well production system in real time through dynamic simulation results, providing strong support for production decisions and production predictions, and helping to improve production efficiency and economic benefits.

[0073] Second, as Figure 3 As shown, the present invention provides an oil well production prediction system 700 based on artificial intelligence, which is configured with the following modules: The data acquisition module 710 is used to collect downhole fluid ratio data, downhole pressure data, pipe diameter parameters and pipe network temperature data in real time based on the downhole multi-modal sensor and the ground pipe network multi-modal sensor. The downhole fluid ratio data is used to indicate the ratio of the three-phase fluid of the oil phase, the gas phase and the water phase. The characteristic parameter calculation module 720 is used to calculate the wellbore flow characteristic parameters based on the downhole fluid ratio data and the downhole pressure data based on the multiphase fluid mechanics formula to generate the wellbore flow characteristic parameters, and the wellbore flow characteristic parameters are used to indicate the velocity distribution and density distribution of the fluid in the wellbore; The pressure-temperature coupling module 730 is used to perform pressure-temperature coupling calculation on the pipe network temperature data, pipe diameter parameters and wellbore flow characteristic parameters based on the multiphase flow simulation algorithm to generate the full-chain fluid distribution results; Dynamic optimization module 740, used to perform dynamic boundary optimization processing on the whole chain fluid distribution results based on finite difference method and back propagation algorithm to generate optimized output distribution prediction value; The multi-parameter fusion module 750 is used to perform multi-parameter fusion processing on the downhole fluid ratio data, downhole pressure data, pipe diameter parameters and pipe network temperature data based on the physical information neural network to generate the full-chain fluid parameter simulation results; The synchronous simulation generation module 760 is used to perform data assimilation processing on the production distribution prediction value and the full-chain fluid parameter simulation results based on the ensemble Kalman filter algorithm, and generate dynamic simulation results synchronized with actual production. The dynamic simulation results are used to predict the change trend of oil well production.

[0074] In summary, the artificial intelligence-based oil well production prediction system provided by the present invention can realize comprehensive, accurate and real-time simulation and prediction of the oil well production system through multimodal sensor data acquisition, multiphase fluid mechanics calculation, multiphase flow simulation, dynamic boundary optimization, multi-parameter fusion and data assimilation and other technical methods, thereby improving the accuracy of oil well production prediction and providing a reliable basis for production decision-making. At the same time, the system can realize dynamic monitoring and optimization adjustment of the production system, which helps to improve production efficiency and reduce production costs, and integrates physical models and data-driven methods to ensure the accuracy and reliability of simulation results, providing strong support for intelligent production management of oil wells.

[0075] Preferably, the characteristic parameter calculation module 720 provided by the present invention is configured with the following units: The velocity calculation unit 721 is used to calculate the downhole pressure data based on the liquid holdup equation and the velocity gradient equation to obtain the initial velocity distribution data of the fluid in the wellbore; The velocity smoothing unit 722 is used to perform sliding window averaging processing on the initial velocity distribution data based on the sliding window technology to generate smoothed fluid velocity distribution data; The density generating unit 723 is used to perform fluid mechanics constraint processing on the fluid velocity distribution data and the downhole fluid ratio data based on the physical information neural network to generate the fluid density distribution data in the wellbore; The parameter integration unit 724 is used to integrate the fluid velocity distribution data and the fluid density distribution data to generate wellbore flow characteristic parameters.

[0076] Preferably, the pressure-temperature coupling module 730 provided by the present invention is configured with the following units: The multiphase flow model training unit 731 is used to train the multiphase flow model based on the historical production data of the oil well and the historical pipe network parameters based on the machine learning algorithm to generate a multiphase flow simulation kernel; The pipe section pressure drop calculation unit 732 is used to calculate the pipe section pressure drop based on the pipe network temperature data, pipe diameter parameters and wellbore flow characteristic parameters based on the multiphase flow simulation kernel to generate the pipe network fluid pressure distribution; The boundary condition optimization unit 733 is used to identify whether the wellbore velocity distribution of the wellbore flow characteristic parameters exceeds a preset velocity safety threshold. If so, the wellhead flow constraint optimization is performed on the pipeline network fluid pressure distribution based on an adaptive particle swarm algorithm to generate an updated boundary condition. The coupling result generating unit 734 is used to perform pressure-flow synchronous coupling on the updated boundary conditions and wellbore flow characteristic parameters based on the numerical iteration method to generate the full-chain fluid distribution result.

[0077] Preferably, the dynamic optimization module 740 provided by the present invention is configured with the following units: The flow discretization unit 741 is used to divide the whole chain fluid distribution result into a plurality of space-time grid units, discretize the mass flow distribution of each space-time grid unit by finite difference method, and generate discretized flow distribution data; The production prediction generation unit 742 is used to dynamically adjust the distribution weight of the flow distribution data and the downhole fluid ratio data based on the long short-term memory neural network to generate an initial prediction value of the production distribution; Preferably, the yield prediction generation unit 742 is configured with the following subunits: The data normalization unit 7421 is used to perform normalization processing on the downhole fluid ratio data to generate standardized fluid ratio data; The weight generation unit 7422 is used to input the standardized fluid ratio data into the long short-term memory neural network, extract the time series characteristics of the wellbore and pipe network allocation through the gating mechanism, and generate the initial allocation ratio weight; The prediction value generating unit 7423 is used to optimize the wellbore-pipeline network allocation ratio for the initial allocation ratio weight and flow distribution data through a dynamic programming algorithm to generate an initial prediction value for the production distribution.

[0078] The production prediction optimization unit 743 is used to identify whether the deviation between the initial prediction value and the downhole fluid ratio data exceeds a preset deviation threshold. If so, the initial prediction value is iteratively updated by allocating weights based on the back propagation algorithm to generate an optimized production distribution prediction value.

[0079] Preferably, the synchronous simulation generation module 760 provided by the present invention is configured with the following units: The frequency domain feature extraction unit 761 is used to extract the main frequency component in the pressure and temperature change trend of the output distribution prediction value based on the Fourier transform algorithm to generate frequency domain feature data; A data supplementation unit 762 is used to supplement the missing data points of the frequency domain feature data by using a cubic spline interpolation method to generate complete digital twin model data; The data fusion unit 763 is used to use the ensemble Kalman filter algorithm to fuse the full-chain fluid parameter simulation results and the digital twin model data to generate dynamic simulation results synchronized with actual production.

[0080] In one embodiment, the present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the above-mentioned artificial intelligence-based oil well production prediction method is implemented.

[0081] In one embodiment, the present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the above-mentioned artificial intelligence-based oil well production prediction method is implemented.

[0082] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0083] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial description of the method embodiments. The device embodiments described above are only schematic, wherein the components described as separate parts may or may not be physically separated, and the parts displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0084] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An oil well production prediction method based on artificial intelligence, characterized in that: The following steps are involved: S1: Based on the downhole multimodal sensor and the ground pipe network multimodal sensor, downhole fluid ratio data, downhole pressure data, pipe diameter parameters and pipe network temperature data are collected in real time, and the downhole fluid ratio data is used to indicate the ratio of the three-phase fluid of the oil phase, the gas phase and the water phase; S2: calculating wellbore flow characteristic parameters on the downhole fluid ratio data and the downhole pressure data based on a multiphase fluid mechanics formula to generate wellbore flow characteristic parameters, wherein the wellbore flow characteristic parameters are used to indicate velocity distribution and density distribution of the fluid in the wellbore; S3: performing pressure and temperature coupling calculation on the pipe network temperature data, the pipe diameter parameters and the wellbore flow characteristic parameters based on a multiphase flow simulation algorithm to generate a full-chain fluid distribution result; S4: Based on the finite difference method and the back propagation algorithm, dynamic boundary optimization processing is performed on the fluid distribution result of the whole chain to generate an optimized output distribution prediction value; S5: performing multi-parameter fusion processing on the downhole fluid ratio data, the downhole pressure data, the pipe diameter parameter and the pipe network temperature data based on a physical information neural network to generate a full-chain fluid parameter simulation result; S6: Based on the ensemble Kalman filter algorithm, data assimilation processing is performed on the production distribution prediction value and the full-chain fluid parameter simulation results to generate dynamic simulation results synchronized with actual production, and the dynamic simulation results are used to predict the change trend of oil well production.

2. The oil well production prediction method according to claim 1, characterized in that: The S2 includes: S21: Calculating the downhole pressure data based on the liquid holdup equation and the velocity gradient equation to obtain initial velocity distribution data of the fluid in the wellbore; S22: performing sliding window averaging processing on the initial velocity distribution data based on a sliding window technique to generate smoothed fluid velocity distribution data; S23: performing fluid mechanics constraint processing on the fluid velocity distribution data and the downhole fluid ratio data based on a physical information neural network to generate fluid density distribution data in the wellbore; S24: Integrate the fluid velocity distribution data and the fluid density distribution data to generate wellbore flow characteristic parameters.

3. The oil well production prediction method according to claim 1, characterized in that: The S3 includes: S31: Train the multiphase flow model based on the historical production data of oil wells and historical pipe network parameters based on machine learning algorithms to generate a multiphase flow simulation kernel; S32: Calculating the pipe section pressure drop based on the pipe network temperature data, the pipe diameter parameters and the wellbore flow characteristic parameters based on the multiphase flow simulation kernel to generate a pipe network fluid pressure distribution; S33: Identify whether the wellbore velocity distribution of the wellbore flow characteristic parameter exceeds a preset velocity safety threshold, and if so, perform wellhead flow constraint optimization on the pipeline network fluid pressure distribution based on an adaptive particle swarm algorithm to generate updated boundary conditions; S34: Based on the numerical iteration method, the updated boundary conditions and the wellbore flow characteristic parameters are subjected to pressure-flow synchronous coupling to generate the full-chain fluid distribution result.

4. The oil well production prediction method according to claim 1, characterized in that: The S4 includes: S41: Divide the whole chain fluid distribution result into a plurality of space-time grid units, discretize the mass flow distribution of each space-time grid unit by finite difference method, and generate discretized flow distribution data; S42: dynamically adjusting the distribution weights of the flow distribution data and the downhole fluid ratio data based on a long short-term memory neural network to generate an initial prediction value of the production distribution; S43: Identify whether the deviation between the initial prediction value and the downhole fluid ratio data exceeds a preset deviation threshold. If so, iteratively update the weights assigned to the initial prediction value based on a back propagation algorithm to generate an optimized production distribution prediction value.

5. The oil well production prediction method according to claim 4, characterized in that: The S42 includes: S421: performing normalization processing on the downhole fluid ratio data to generate standardized fluid ratio data; S422: inputting the standardized fluid ratio data into a long short-term memory neural network, extracting the time series characteristics of the wellbore and pipe network allocation through a gating mechanism, and generating an initial allocation ratio weight; S423: Optimizing the wellbore-pipeline network allocation ratio of the initial allocation ratio weight and the flow distribution data through a dynamic programming algorithm to generate an initial predicted value of the production distribution.

6. The oil well production prediction method according to any one of claims 1 to 5, characterized in that: The S6 includes: S61: extracting the main frequency components in the pressure and temperature change trends of the production distribution prediction value based on the Fourier transform algorithm to generate frequency domain feature data; S62: Supplement the missing data points of the frequency domain feature data by using a cubic spline interpolation method to generate complete digital twin model data; S63: Using the ensemble Kalman filter algorithm to fuse the full-chain fluid parameter simulation results and the digital twin model data, to generate dynamic simulation results synchronized with actual production.

7. An oil well production prediction system based on artificial intelligence, characterized in that: The system comprises: A data acquisition module, used to collect downhole fluid ratio data, downhole pressure data, pipe diameter parameters and pipe network temperature data in real time based on downhole multimodal sensors and ground pipe network multimodal sensors, wherein the downhole fluid ratio data is used to indicate the ratio of three-phase fluids of oil phase, gas phase and water phase; a characteristic parameter calculation module, used to calculate wellbore flow characteristic parameters on the downhole fluid ratio data and the downhole pressure data based on a multiphase fluid mechanics formula, and generate wellbore flow characteristic parameters, wherein the wellbore flow characteristic parameters are used to indicate velocity distribution and density distribution of the fluid in the wellbore; A pressure-temperature coupling module, used to perform pressure-temperature coupling calculation on the pipe network temperature data, the pipe diameter parameters and the wellbore flow characteristic parameters based on a multiphase flow simulation algorithm to generate a full-chain fluid distribution result; A dynamic optimization module, used for performing dynamic boundary optimization processing on the fluid distribution results of the whole chain based on the finite difference method and the back propagation algorithm to generate an optimized output distribution prediction value; A multi-parameter fusion module, used for performing multi-parameter fusion processing on the downhole fluid ratio data, the downhole pressure data, the pipe diameter parameter and the pipe network temperature data based on a physical information neural network to generate a full-chain fluid parameter simulation result; The synchronous simulation generation module is used to perform data assimilation processing on the production distribution prediction value and the full-chain fluid parameter simulation results based on the ensemble Kalman filter algorithm to generate dynamic simulation results synchronized with actual production. The dynamic simulation results are used to predict the change trend of oil well production.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images