Electric submersible pump well group management system and method based on digital twinning

Abstract

The invention belongs to the technical field of oil well production management, and discloses an electric submersible pump well group management system and method based on digital twinning. According to the method, operation data of an electric submersible pump unit and environmental data in a shaft are collected in real time, a multi-scale digital twinborn model is constructed for the received data, and the mechanical structure and electrical characteristics of the electric submersible pump unit, the multiphase flow dynamic state in the shaft and geological pressure field data are obtained; trend prediction is carried out on operation parameters, energy efficiency indexes and health states of the multi-scale digital twin model of each well; through a machine learning algorithm and an expert knowledge base, trend prediction data is associated with a historical health database, early warning and intelligent diagnosis of equipment faults are completed, and a maintenance strategy is generated. The method can assist managers to make decisions based on the historical health database. According to the invention, unified management and intelligent well patrol of multiple well sites can be realized, and the oil well production management efficiency is greatly improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of oil well production management, and particularly relates to a submersible electric pump well group management system and method based on digital twin. Background Art

[0002] Submersible electric pumps are the core equipment for efficient oil production in oil fields. However, traditional management methods rely on manual inspections and single-well data monitoring, resulting in problems such as lagging responses and weak fault prediction capabilities. There is insufficient well group collaborative optimization: existing systems mostly perform threshold alarms for single-well operating parameters (current, temperature, pressure), lacking dynamic correlation analysis between wells. Existing digital twin models are mostly based on high-fidelity simulations (such as ANSYS simulations), with high computational complexity and difficult to meet the real-time requirements of well group management. Summary of the Invention

[0003] To overcome the problems in the related art, the disclosed embodiments of the present invention provide a submersible electric pump well group management system and method based on digital twin.

[0004] The technical solution is as follows: A submersible electric pump well group management method based on digital twin, the method comprising the following steps: S1, real-time collect the operation data of the submersible electric pump unit and the environmental data in the wellbore, and after processing the collected data, transmit it to the cloud server; S2, the cloud server uses the integrated digital twin model construction module to construct a multi-scale digital twin model for the received data, and obtain the mechanical structure and electrical characteristics of the submersible electric pump unit, the multiphase flow dynamics in the wellbore, and the geological pressure field data; the multi-scale digital twin model includes: an equipment-level model, a wellbore-level model, and a reservoir-level model; S3, perform trend prediction on the operation parameters, energy efficiency indicators, and health status of the multi-scale digital twin models of each well through a Web-based three-dimensional visualization platform; S4, through machine learning algorithms and an expert knowledge base, associate the data of the trend prediction with the historical health database, complete early warning and intelligent diagnosis of equipment failures, and generate maintenance strategies.

[0005] In step S1, real-time collect the operation data of the submersible electric pump unit and the environmental data in the wellbore, including: collect current, voltage, vibration, and flow data through sensors arranged on the physical structures of the downhole motor, protector, and pump body; collect temperature, pressure, flow rate, and sand content data in the wellbore through various types of sensors arranged at the wellbore and reservoir levels.

[0006] In step S2, the cloud server uses the integrated digital twin model construction module to construct a multi-scale digital twin model for the received data, including: Construct an equipment-level model based on the geometric characteristic parameters of the submersible electric pump to simulate the mechanical structure and electrical characteristics of the submersible electric pump. The construction process includes: (1) Based on the design drawings or 3D scan data of the submersible electric pump, establish a geometric model, including the dimensions, shapes, and assembly relationships of the stator, rotor, impeller, and bearing components; (2) Assign material properties and electrical parameters to the geometric model, including density, elastic modulus, thermal conductivity, resistance, and inductance; (3) Conduct multi-physics field coupling simulation. Through finite element analysis, simulate the stress, deformation, and fatigue life of the electric pump under alternating loads, and analyze the temperature field change in combination with the CFD method; (4) Integrate the multi-physics field simulation results into the Simulink system-level model to simulate the dynamic response of the submersible electric pump under start-stop and variable load conditions.

[0007] In step S2, construct a wellbore-level model based on the wellbore environment data, and reproduce the multiphase flow dynamics in the wellbore through computational fluid dynamics simulation. The construction process includes: (i) Establish a 3D wellbore geometric model according to the wellbore structure parameters; (ii) Set the multiphase flow parameters, input the real-time sensor data as boundary conditions, including pressure, temperature, and sand content; and define the fluid physical properties, including crude oil viscosity and gas solubility; (iii) Use the multiphase flow CDF to simulate and calculate the flow velocity distribution, pressure gradient, and sand grain deposition in the wellbore.

[0008] In step (iii), the continuous phase mathematical model of the multiphase flow dynamics is the continuity equation of the flow and the Navier-Stokers equation, and the expression is: ; ; In the formula, is the fluid volume fraction, with the unit of %; is the fluid density, with the unit of kg / m 3 ; is the fluid velocity, with the unit of m / s; is the pressure, with the unit of Pa; is the fluid viscosity, with the unit of Pa·s; is the source term between the continuous phase and the dispersed phase, with the unit of Pa / m; is the gravitational acceleration, m / s 2 , is the time, with the unit of s.

[0009] In step S2, the equipment-level model, wellbore-level model, and reservoir-level model are also dynamically coupled to complete the macro linkage analysis of micro-failures, including: the equipment-level model detects micro anomalies, diagnoses to determine the failure mode, and the equipment-level model transmits the failure parameters to the wellbore-level model, triggering the recalculation of flow rate and pressure, and transmitting them to the reservoir-level model to correct the pressure field in the near-wellbore area.

[0010] In step S3, the trend prediction of the operating parameters, energy efficiency indicators, and health status of the multi-scale digital twin models of each well is carried out through the Web-based 3D visualization platform, including: adopting virtual experiment technology to simulate the equipment operating status under different working conditions in the digital space, actively injecting typical failure modes into the virtual model, and completing the early fault location by comparing the differences between multi-dimensional sensor data and simulation data; the specific steps are as follows: S301. Feature extraction: Perform wavelet packet decomposition on the vibration signal, filter out most of the invalid frequency components, and extract the energy signal features of multiple sub-bands; calculate the total harmonic distortion rate of the motor current; calculate the temperature gradient according to the thermal grid model of the temperature field. S302. Data comparison: Compare the multi-dimensional data features extracted from the measured data with the feature data obtained from the simulation of the multi-dimensional digital twin model to identify the differences. S303. Fault location: Through the difference comparison of different frequency bands of the signal, the total harmonic distortion rate of the current, and the temperature gradient, initially locate different components of the equipment, and then match the specific fault type according to the characteristic frequency.

[0011] In step S4, through machine learning algorithms and expert knowledge bases, the data of trend prediction is associated with the historical health database to complete the early warning and intelligent diagnosis of equipment failures and generate maintenance strategies, including: Analyze the correlation between the real-time monitoring data and the historical health database through a regression model, use wavelet packet decomposition of the fault signal to extract features, and accurately identify potential failure modes through machine learning algorithms, and generate optimal maintenance strategy suggestions based on the risk assessment model; the risk assessment model includes three quantitative indicators: severity, probability, and detectability, and grades the risk, and gives multiple maintenance strategies according to the preset expert knowledge base in combination with the current risk level and failure mode.

[0012] Furthermore, the failure modes include bearing wear, motor overheating, tubing leakage, pump leakage, and pump jamming; the risk levels are high risk, medium risk, and low risk, and the multiple maintenance strategies include: immediate shutdown, planned maintenance, and continuous monitoring.

[0013] Another object of the present invention is to provide a digital twin-based submersible electric pump well group management system, which implements the digital twin-based submersible electric pump well group management method, and the system includes: Downhole data acquisition and processing module, which is used to collect the operation data of the submersible electric pump unit and the environmental data in the wellbore in real time, and after processing the collected data, transmit it to the cloud server; Digital twin model construction module, integrated in the cloud server, constructs a multi-scale digital twin model for the received data, and obtains the mechanical structure and electrical characteristics of the submersible electric pump unit, the multiphase flow dynamics in the wellbore, and the geological pressure field data; the multi-scale digital twin model includes an equipment-level model, a wellbore-level model, and a reservoir-level model; Well group working condition online monitoring module, which is used to predict the trends of the operation parameters, energy efficiency indicators and health status of the multi-scale digital twin models of each well through a Web-based 3D visualization platform, and realize single-well remote control and well group status monitoring; Risk warning and auxiliary decision-making module, which is used to associate the data of trend prediction with the historical health database through machine learning algorithms and expert knowledge bases, complete early warning and intelligent diagnosis of equipment failures, and generate maintenance strategies.

[0014] Combining all the above technical solutions, the beneficial effects of the present invention are as follows: First, the system provided by the present invention includes a downhole data acquisition and processing module, a digital twin model construction module, a well group working condition online monitoring module, and a risk warning and auxiliary decision-making module; the downhole data acquisition and processing module uses a distributed sensor network to collect multi-source heterogeneous data at the electric pump unit, wellbore and reservoir levels in real time, and completes preprocessing at the collection end; the digital twin model construction module establishes an equipment-level, wellbore-level and reservoir-level multi-scale dynamic coupling model, supporting adaptive accuracy switching; the well group working condition online monitoring module realizes single-well remote control and well group status monitoring through a 3D visualization interface; the risk warning and auxiliary decision-making module integrates machine learning and expert knowledge bases to realize intelligent diagnosis and hierarchical warning based on historical health data. This system solves problems such as data islands, lagging fault prediction, and single-well independent operation in the existing submersible electric pump management system, and realizes well group collaborative optimization and intelligent management.

[0015] Second, the multi-dimensional digital twin model of the electric pump well group constructed by the system combines real-time downhole working condition data for virtual experiments to verify on-line monitoring, and can assist managers in making decisions based on the historical health database. The present invention can realize unified management and intelligent well patrol of multiple well sites, greatly improving the production management efficiency of oil wells. Compared with the prior art, the advantages of the present invention further include: the prior art usually only monitors the operation parameters of the electric pump, while this application combines multi-dimensional information such as reservoir pressure, fluid characteristics, and geological data to construct a more comprehensive monitoring system, improving the accuracy of fault diagnosis; the digital twin model proposed in the present invention includes three scales: equipment-level model, wellbore-level model, and well group-level model, which can optimize the production scheduling of the well group and improve the overall oil production efficiency; in the present invention, through the on-line detection module of the well group working condition, the real-time state of the well group is displayed through a three-dimensional digital twin interface, realizing unified visual monitoring of multiple well sites; the risk warning and auxiliary decision-making module proposed in the present invention introduces a historical health database, improves the fault prediction ability through a big data model, and the established expert system can provide fault cause analysis and maintenance strategies.

[0016] Third, through real-time monitoring, early fault warning and intelligent diagnosis, the present invention can greatly reduce the unplanned downtime, and at the same time reduce the costs of manual inspection and emergency repair, achieving direct economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure; Figure 1 It is a flow chart of a method for managing a submersible electric pump well group based on digital twin provided by an embodiment of the present invention; Figure 2 It is a structural diagram of wavelet packet decomposition provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention is provided in conjunction with the drawings. Many specific details are set forth in the following description to fully understand the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0019] The present invention realizes intelligent monitoring, fault warning, and collaborative optimization of a submersible electric pump well group by constructing a multi-scale dynamically coupled digital twin model. The innovation points of the present invention are: (1) A multi-scale digital twin coupling architecture is proposed to solve the data island problem of traditional single-well monitoring; (2)Integrate virtual experiments with real data to locate faults through data comparison; (3)Utilize health data fully through machine learning and expert databases to improve the system diagnosis ability.

[0020] Example 1, as Figure 1 shown, the method for managing a group of submersible electric pump wells based on digital twin provided by the embodiment of the present invention includes: S1. Real-time collect the operation data of the submersible electric pump unit and the environmental data in the wellbore. After processing the collected data, transmit it to the cloud server; S2. The cloud server uses the integrated digital twin model construction module to construct a multi-scale digital twin model for the received data, and obtain the mechanical structure and electrical characteristics of the submersible electric pump unit, the multiphase flow dynamics in the wellbore, and the geological pressure field data; the multi-scale digital twin model includes: an equipment-level model, a wellbore-level model, and a reservoir-level model; S3. Through the Web-side three-dimensional visualization platform, conduct trend prediction on the operation parameters, energy efficiency indicators, and health status of the multi-scale digital twin models of each well; S4. Through machine learning algorithms and expert knowledge bases, associate the data of trend prediction with the historical health database, complete the early warning and intelligent diagnosis of equipment faults, and generate maintenance strategies.

[0021] Exemplarily, in step S1, there are various key devices and components (motor, protector, pump body) underground. Sensors are arranged on their physical structures to collect the operation status data of physical objects in real time. The collected data includes data such as current, voltage, vibration, and flow rate; collect the environmental data in the wellbore, including data such as temperature, pressure, flow velocity, and sand content.

[0022] Exemplarily, in step S1, the underground data acquisition and processing module adopts a distributed sensor network architecture. Through multi-type sensors deployed at the electric pump unit, wellbore, and reservoir levels, multi-source heterogeneous data including current, voltage, vibration, temperature, pressure, flow rate, etc. are collected in real time.

[0023] The underground data acquisition and processing module completes data preprocessing, feature extraction, and anomaly detection at the data acquisition end, improving the real-time performance and reliability of data processing.

[0024] Exemplarily, in the process of constructing a multi-scale digital twin model through the digital twin model construction module in step S2, an equipment-level model is established based on the geometric feature parameters of the submersible electric pump to accurately simulate the mechanical structure and electrical characteristics of the submersible electric pump. The construction process is as follows: (1)Based on the design drawings or 3D scan data of the submersible electric pump, establish a geometric model, including the dimensions, shapes, and assembly relationships of key components such as the stator, rotor, impeller, and bearings.

[0025] (2)Assign material properties and electrical parameters to the geometric model, including density, elastic modulus, thermal conductivity, resistance, inductance, etc.

[0026] (3)Conduct multi-physics field coupling simulation. Through finite element analysis, simulate the stress, deformation, and fatigue life of the electric pump under alternating loads, and analyze the temperature field change situation in combination with the CFD method.

[0027] (4)Integrate the multi-physics field simulation results into the Simulink system-level model to simulate the dynamic response of the submersible electric pump under conditions such as starting, stopping, and variable loads; Exemplarily, in step S2, establish a wellbore-level model based on wellbore environment data, and reproduce the multiphase flow dynamics in the wellbore through computational fluid dynamics simulation. The construction process is as follows: (i)Establish a three-dimensional wellbore geometric model according to wellbore structure parameters (such as casing diameter, slope of the deviated well section).

[0028] (ii)Set multiphase flow parameters, input real-time sensor data as boundary conditions, including pressure, temperature, sand content, etc., and define fluid physical properties (such as crude oil viscosity, gas solubility).

[0029] (iii)Use multiphase flow CFD simulation to calculate the flow velocity distribution, pressure gradient, and sand particle deposition in the wellbore; Among them, the mathematical model of the continuous phase of the flow is the continuity equation of the flow and the Navier-Stokers equation: ; ; In the formula, is the fluid volume fraction, with the unit of %; is the fluid density, with the unit of kg / m 3 ; is the fluid velocity, with the unit of m / s; is the pressure, with the unit of Pa; is the fluid viscosity, with the unit of Pa·s; is the source term between the continuous phase and the dispersed phase, with the unit of Pa / m; is the acceleration of gravity, m / s 2 , is the time, with the unit of s.

[0030] Exemplarily, in step S2, the reservoir-level model integrates geological data to realize the visualization of the pressure field.

[0031] Exemplarily, in step S2, the digital twin models at each level in the digital twin model construction module are dynamically coupled to realize macro linkage analysis of micro faults, that is, the equipment-level model detects micro anomalies and diagnoses them to determine the fault mode. The equipment-level model passes the fault parameters to the wellbore-level model, triggering the recalculation of flow rate and pressure, and passes them to the reservoir-level model to correct the pressure field in the near-wellbore area.

[0032] The digital twin model construction module can automatically select the model accuracy level based on the operating condition characteristics, such as using a reduced-order model under normal operating conditions and switching to a high-precision mode under abnormal conditions to improve the simulation speed.

[0033] The digital twin model construction module constructs a lightweight digital twin model locally in each well site (single well), that is, the equipment-level model is an adaptive reduced-order finite element model, and the wellbore flow field model can use empirical formulas to improve calculation efficiency. At the same time, the model parameters are uploaded to the unified dispatching center server for analysis and calculation, and the results are displayed in the visualization interface of the well group operating condition online monitoring module.

[0034] For example, in step S3, the well group operating condition online monitoring module is used to intuitively display the operating parameters, energy efficiency indicators and health status of each well through a three-dimensional visualization interface, supporting multi-dimensional data comparison analysis and trend prediction. The downhole data acquisition and processing module uses virtual experiment technology to simulate the equipment operating status under different working conditions in digital space. A high-fidelity digital twin is created for each submersible electric pump well in the cloud server, integrating equipment-level (motor, bearing, impeller), wellbore-level (multiphase flow dynamics) and reservoir-level (pressure field) models. The model is updated synchronously through real-time data streams (such as current, vibration, temperature, and pressure) to ensure that the virtual environment is consistent with the physical equipment status.

[0035] A multi-physics coupling simulation platform (such as COMSOL or ANSYS) is used to build a configurable virtual experiment module, which supports users to customize input parameters (such as pump speed, oil viscosity, sand content) or automatically import historical operating data.

[0036] Actively inject typical fault modes (such as bearing wear and motor turn-to-turn short circuit) into the virtual model, and compare the differences between multi-dimensional sensor data and simulation data to achieve early fault location. S301, feature extraction: perform wavelet packet decomposition on the vibration signal, filter most of the invalid frequency components, and extract the energy signal characteristics of multiple sub-bands; calculate the total harmonic distortion rate of the motor current; calculate the temperature gradient based on the temperature field thermal grid model.

[0037] S302, data comparison: compare the multi-dimensional data features extracted from the measured data with the feature data obtained by simulating the multi-dimensional digital twin model to identify differences.

[0038] S303. Fault location: By comparing the differences in different frequency bands of signals, the total harmonic distortion rate of current, and the temperature gradient, different components of the equipment are initially located, and then specific fault types are matched according to the characteristic frequencies.

[0039] For example, a vibration sensor captures high-frequency impact signals of the bearing (characteristic frequency > 5 kHz), and the equipment-level model diagnoses it as "outer ring spalling of the bearing" (microscopic fault).

[0040] Exemplarily, in step S3, the visualization interface of the well group working condition online monitoring module is divided into a single well control interface and a well group status interface. The single well control interface can observe the operating status of key components in the digital space and remotely control the electric pump using artificial instruments. The well group status interface integrates GIS maps to mark the real-time risk levels of each single well.

[0041] Exemplarily, in step S4, the risk early warning and auxiliary decision-making module integrates machine learning algorithms and an expert knowledge base to achieve early warning and intelligent diagnosis of equipment failures.

[0042] Exemplarily, as Figure 2 shown, by analyzing the correlation between real-time monitoring data and the historical health database through a regression model, decomposing fault signals using wavelet packets, extracting features, and accurately identifying potential fault modes (such as bearing wear, motor overheating, tubing leakage, pump leakage, pump jamming, etc.) through machine learning algorithms, and generating optimal maintenance strategy suggestions based on a risk assessment model. The risk assessment model includes three quantitative indicators: severity (production loss caused by the fault), probability (historical fault frequency and working condition deterioration rate), and detectability (accuracy rate of the diagnostic model), and classifies the risk (high risk, medium risk, low risk). According to the preset expert knowledge base, multiple maintenance strategies are given in combination with the current risk level and fault mode, such as immediate shutdown, planned maintenance, continuous monitoring, etc.

[0043] Exemplarily, in step S4, the risk early warning and auxiliary decision-making module is equipped with a historical health database, which integrates expert experience, historical maintenance records, equipment parameters, and healthy working condition data, provides a data set for machine learning algorithms, and accurately identifies potential fault modes.

[0044] The early warning methods in the risk early warning and auxiliary decision-making module can be sound warning and light warning.

[0045] Embodiment 2. The digital twin-based submersible electric pump well group management system provided by the embodiment of the present invention includes a downhole data acquisition and processing module, a digital twin model construction module, a well group working condition online monitoring module, and a risk early warning and auxiliary decision-making module.

[0046] Downhole data acquisition and processing module, which is used to collect the operation data of the submersible electric pump unit and the environmental data in the wellbore in real time, and after processing the collected data, transmit it to the cloud server; Digital twin model construction module, integrated in the cloud server, constructs a multi-scale digital twin model for the received data to obtain the mechanical structure and electrical characteristics of the submersible electric pump unit, the multiphase flow dynamics in the wellbore, and the geological pressure field data; the multi-scale digital twin model includes an equipment-level model, a wellbore-level model, and a reservoir-level model; Well group working condition online monitoring module, which is used to predict the trends of the operation parameters, energy efficiency indicators, and health status of the multi-scale digital twin models of each well through a Web-based 3D visualization platform, and realize remote control of a single well and monitoring of the well group status; Risk warning and auxiliary decision-making module, which is used to associate the data predicted by the trend with the historical health database through machine learning algorithms and an expert knowledge base, complete early warning and intelligent diagnosis of equipment failures, and generate maintenance strategies. This system solves problems such as data islands, lag in fault prediction, and independent operation of single wells in the existing submersible electric pump management system, and realizes collaborative optimization and intelligent management of the well group.

[0047] Exemplarily, the downhole data acquisition and processing module adopts a distributed sensor network architecture, deploys multiple types of sensors at the levels of the electric pump unit, wellbore, and reservoir, and collects multi-source heterogeneous data such as current, voltage, vibration, temperature, pressure, and flow in real time. And preprocessing is completed at the acquisition end; The equipment-level model, wellbore-level model, and reservoir-level model perform dynamic coupling of each level model to realize the linkage analysis of microscopic faults and macroscopic working conditions.

[0048] Exemplarily, the digital twin model construction module can automatically select the model accuracy level according to the working condition characteristics. For example, a reduced-order model is used in normal working conditions to improve the calculation speed, and it switches to a high-precision mode when abnormal.

[0049] Furthermore, the risk warning and auxiliary decision-making module is provided with a historical health database, which integrates expert experience, historical maintenance records, equipment parameters, and healthy working condition data, provides a training set for machine learning algorithms, and improves the accuracy of fault identification.

[0050] To further illustrate the relevant effects of the embodiments of the present invention, the present invention takes "sand plugging in the wellbore caused by wear of the motor bearing" as an example to illustrate the linkage analysis process: The device-level model conducts bearing wear detection. In the initial stage of motor bearing wear, the vibration sensor will capture high-frequency impact signals, and their energy values exceed the normal threshold. At the same time, the digital twin model simulates the increase in bearing clearance through finite element simulation and compares it with the measured vibration spectrum. If the correlation coefficient exceeds the determination value, the bearing wear fault is confirmed; this triggers the wellbore-level model to recalculate the flow rate and sand particle distribution. As the simulated deposition amount increases, the reservoir-level model adjusts the pressure field accordingly. The system comprehensively evaluates the risk level and generates a maintenance strategy from the preset expert knowledge base: immediately stop the machine to replace the bearing and conduct well flushing.

[0051] The above is only a relatively optimal specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention should be covered within the protection scope of the present invention.

Claims

1. A management method for a group of submersible electric pump wells based on digital twin, characterized in that, The method includes the following steps: S1. Collect the operation data of the submersible electric pump unit and the wellbore environment data in real time. After processing the collected data, transmit it to the cloud server; S2. The cloud server uses the integrated digital twin model construction module to construct a multi-scale digital twin model for the received data, and obtain the mechanical structure and electrical characteristics of the submersible electric pump unit, the multiphase flow dynamics in the wellbore, and the geological pressure field data; the multi-scale digital twin model includes: equipment-level model, wellbore-level model, and reservoir-level model; S3. Through the Web-side three-dimensional visualization platform, conduct trend prediction on the operation parameters, energy efficiency indicators, and health status of the multi-scale digital twin models of each well; S4. Through machine learning algorithms and expert knowledge bases, associate the data of the trend prediction with the historical health database, complete the early warning and intelligent diagnosis of equipment failures, and generate maintenance strategies.

2. The method for managing a group of submersible electric pump wells based on digital twin according to claim 1, wherein In step S1, collect the operation data of the submersible electric pump unit and the wellbore environment data in real time, including: collect current, voltage, vibration, and flow data through sensors arranged on the physical structures of the downhole motor, protector, and pump body; collect wellbore temperature, pressure, flow velocity, and sand content data through various types of sensors arranged at the wellbore and reservoir levels.

3. The method for managing a group of submersible electric pump wells based on digital twin according to claim 1, wherein In step S2, the cloud server uses the integrated digital twin model construction module to construct a multi-scale digital twin model for the received data, including: Construct an equipment-level model based on the geometric characteristic parameters of the submersible electric pump to simulate the mechanical structure and electrical characteristics of the submersible electric pump. The construction process includes: (1) Based on the design drawings or three-dimensional scan data of the submersible electric pump, establish a geometric model, including the dimensions, shapes, and assembly relationships of the stator, rotor, impeller, and bearing components; (2) Assign material properties and electrical parameters to the geometric model, including density, elastic modulus, thermal conductivity, resistance, and inductance; (3) Conduct multi-physics field coupling simulation, simulate the stress, deformation, and fatigue life of the electric pump under alternating loads through finite element analysis, and analyze the temperature field change in combination with the CFD method; (4) Integrate the multi-physics field simulation results into the Simulink system-level model to simulate the dynamic response of the submersible electric pump under start-stop and variable load conditions.

4. The method for managing a group of submersible electric pump wells based on digital twin according to claim 1, wherein, In step S2, construct a wellbore-level model based on the wellbore environment data, and reproduce the multiphase flow dynamics in the wellbore through computational fluid dynamics simulation. The construction process includes: (i) Establish a three-dimensional wellbore geometric model according to the wellbore structure parameters; (ii) Set the multiphase flow parameters, input the real-time sensor data as boundary conditions, including pressure, temperature, and sand content; and define the fluid physical properties, including crude oil viscosity and gas solubility; (iii) Use multi-phase flow CDF simulation to calculate the flow velocity distribution, pressure gradient, and sand grain deposition in the wellbore.

5. The method for managing a group of submersible electric pump wells based on digital twin according to claim 4, wherein, In step (iii), the continuous phase mathematical model of the multiphase flow dynamics is the continuity equation of flow and the Navier-Stokers equation, and the expression is: ； ； In the formula, is the fluid volume fraction, with the unit of %; is the fluid density, with the unit of kg / m 3 ; is the fluid velocity, with the unit of m / s; is the pressure, with the unit of Pa; is the fluid viscosity, with the unit of Pa·s; is the source term between the continuous phase and the dispersed phase, with the unit of Pa / m; is the gravitational acceleration, m / s 2 , is the time, with the unit of s.

6. The method for managing a group of submersible electric pump wells based on digital twin according to claim 1, wherein In step S2, the equipment-level model, wellbore-level model, and reservoir-level model are also dynamically coupled to complete the macroscopic linkage analysis of microscopic faults, including: the equipment-level model detects microscopic anomalies and diagnoses them to determine the fault mode. The equipment-level model transmits the fault parameters to the wellbore-level model, triggering the recalculation of flow rate and pressure, and transmits them to the reservoir-level model to correct the pressure field in the near-wellbore area.

7. The method for managing a group of submersible electric pump wells based on digital twins according to claim 1, wherein In step S3, the trend prediction of the operating parameters, energy efficiency indicators, and health status of the multi-scale digital twin models of each well is carried out through the Web-based 3D visualization platform, including: adopting virtual experiment technology to simulate the equipment operating status under different working conditions in the digital space, actively injecting typical fault modes into the virtual model, and completing the early fault location by comparing the differences between multi-dimensional sensor data and simulation data; the specific steps are as follows: S301. Feature extraction: Perform wavelet packet decomposition on the vibration signal, filter out most of the invalid frequency components, and extract the energy signal features of multiple sub-bands; calculate the total harmonic distortion rate of the motor current; calculate the temperature gradient according to the thermal grid model of the temperature field. S302. Data comparison: Compare the multi-dimensional data features extracted from the measured data with the feature data obtained by simulating the multi-dimensional digital twin model to identify the differences. S303. Fault location: Through the difference comparison of different frequency bands of the signal, the total harmonic distortion rate of the current, and the temperature gradient, the different components of the equipment are initially located, and then the specific fault type is matched according to the characteristic frequency.

8. The method for managing a group of submersible electric pump wells based on digital twin according to claim 1, characterized in that, In step S4, through the machine learning algorithm and the expert knowledge base, the data of the trend prediction is associated with the historical health database to complete the early warning and intelligent diagnosis of equipment faults and generate maintenance strategies, including: Analyze the relevance between the real-time monitoring data and the historical health database through the regression model, use wavelet packet decomposition to decompose the fault signal, extract features, and accurately identify potential fault modes through the machine learning algorithm, and generate optimal maintenance strategy suggestions based on the risk assessment model; the risk assessment model includes three quantitative indicators: severity, probability, and detectability, and grades the risk, and gives multiple maintenance strategies according to the preset expert knowledge base, combined with the current risk level and fault mode.

9. The method for managing a group of submersible electric pump wells based on digital twin according to claim 7, wherein The fault modes include bearing wear, motor overheating, tubing leakage, pump leakage, and pump jamming. The risk levels are high risk, medium risk, and low risk. The multiple maintenance strategies include: immediate shutdown, planned maintenance, and continuous monitoring.

10. A management system for a group of submersible electric pump wells based on digital twin, characterized in that, The system implements the digital twin-based submersible electric pump well group management method according to any one of claims 1-9. The system includes: The downhole data acquisition and processing module is used to collect the operating data of the submersible electric pump unit and the wellbore environment data in real time, and after processing the collected data, transmit it to the cloud server. The digital twin model construction module is integrated in the cloud server to construct a multi-scale digital twin model for the received data, and obtain the mechanical structure and electrical characteristics of the submersible electric pump unit, the multiphase flow dynamics in the wellbore, and the geological pressure field data; the multi-scale digital twin model includes an equipment-level model, a wellbore-level model, and a reservoir-level model. The online monitoring module for well group operating conditions is used to perform trend prediction on the operating parameters, energy efficiency indicators, and health status of the multi-scale digital twin models of each well through the Web-based 3D visualization platform, and achieve remote control of individual wells and monitoring of well group status; The risk warning and auxiliary decision-making module is used to associate the data of trend prediction with the historical health database through machine learning algorithms and expert knowledge bases, complete early warning and intelligent diagnosis of equipment failures, and generate maintenance strategies.

Images