A method, system, equipment and medium for multi-objective coordinated control of submersible electric pump wells.

Abstract

This invention relates to the field of intelligent development and process optimization control technology for oil and gas fields, and discloses a multi-objective collaborative control method, system, equipment, and medium for submersible electric pump wells. The method includes: collecting multi-source operational data; constructing a multi-objective optimization model integrating dynamic constraints on oil well inflow, with objective functions including maximizing oil production, minimizing energy consumption per ton of fluid, and minimizing equipment wear; establishing a set of physical constraints; using a hierarchical adaptive optimization algorithm to obtain the Pareto optimal solution set, the solution process including offline pre-calculation in the cloud, online matching at the edge, and local refinement; and selecting and outputting the optimal control scheme based on an economic benefit evaluation model. This invention embeds oil well fluid supply constraints into the optimization objectives, reduces computational complexity through a hierarchical architecture, utilizes multi-dimensional data such as vibration to assess wear, achieves collaborative optimization of production, energy consumption, and equipment lifespan, and supports autonomous operation of edge equipment when offline.

Description

Technical Field

[0001] This invention relates to the field of intelligent development and process optimization control technology for oil and gas fields, specifically to a multi-objective collaborative control method, system, equipment, and medium for submersible electric pump wells. Background Technology

[0002] Submersible electric pumps (ESPs) are the main artificial lift equipment in oilfields, boasting advantages such as large displacement, high head, and strong adaptability. Modern ESP wells are generally equipped with downhole multi-parameter sensor systems, which can collect parameters such as pressure, temperature, vibration, and current in real time, providing a data foundation for intelligent control.

[0003] The current production management of submersible electric pump wells faces the following three major problems:

[0004] Manual frequency adjustment cannot adapt to dynamic changes in reservoir fluid supply capacity, resulting in a production loss of 10% to 15%. The phenomenon of "oversized pumps pulling a small cart"—where the pump displacement exceeds the reservoir's fluid supply capacity—is common, resulting in energy waste of 20% to 30%. Operating under suboptimal conditions leads to premature equipment failure and shortens the pump inspection cycle.

[0005] Existing control technologies mainly include empirical rule methods, single-objective optimization methods, traditional multi-objective evolutionary algorithms, and static model methods. Their common shortcomings are: the optimization model does not embed dynamic fluid supply constraints of oil well inflow, and the optimized solution may exceed the actual fluid supply capacity of the reservoir; the computational complexity is high, making it difficult to deploy in real time on edge equipment; and the downhole vibration sensor data is not fully utilized for equipment wear assessment.

[0006] Therefore, this application provides a multi-objective coordinated control method for submersible electric pump wells to solve the above-mentioned technical problems. Summary of the Invention

[0007] The purpose of this invention is to provide a multi-objective collaborative control method, system, equipment, and medium for submersible electric pump wells, in order to solve the technical problems in existing submersible electric pump well control methods, such as the lack of integration of dynamic fluid supply constraints from well inflow, high computational complexity making edge deployment difficult, and the failure to effectively utilize vibration data for equipment wear assessment.

[0008] To address the aforementioned technical problems, this invention provides a multi-objective coordinated control method for submersible electric pump wells, comprising: Collect and preprocess multi-source operational data from submersible electric pump wells; Based on the multi-source operational data, a multi-objective optimization model integrating dynamic constraints of oil well inflow is constructed. The multi-objective optimization model includes the objectives of maximizing oil production, minimizing energy consumption per ton of fluid, and minimizing equipment wear. The objective of maximizing oil production is determined based on the actual fluid production, which is the smaller value between the reservoir's fluid supply capacity and the pump's fluid discharge capacity. The objective of minimizing energy consumption per ton of fluid is determined based on the ratio of motor input power to actual fluid production. The objective of minimizing equipment wear is determined based on a normalized weighted combination of vibration acceleration, motor operating temperature rise, and motor operating current. Establish a set of physical constraints, including pump operating frequency boundary constraints, dynamic liquid surface safety constraints, motor protection constraints, frequency change rate constraints, and pump efficiency lower limit constraints. The dynamic liquid surface safety constraint is that the dynamic liquid surface depth is not lower than a preset safety lower limit depth. The multi-objective optimization model is solved using a hierarchical adaptive optimization algorithm to obtain the Pareto optimal solution set. The solution process includes offline pre-computation in the cloud, online matching at the edge, and local refinement solution. In the local refinement solution, constraint repair is performed on the solutions that exceed the reservoir's fluid supply capacity. The optimal control scheme is determined from the Pareto optimal solution set according to the economic benefit evaluation model, and the optimal pump operating frequency in the optimal control scheme is output. The adjustment process of the optimal pump operating frequency satisfies the frequency change rate constraint.

[0009] In some specific embodiments, based on the multi-source operational data, a multi-objective optimization model integrating dynamic constraints of oil well inflow is constructed. This multi-objective optimization model includes objectives for maximizing oil production, minimizing energy consumption per ton of fluid, and minimizing equipment wear. The objective for maximizing oil production is determined based on the actual fluid production, which is the smaller of the reservoir's fluid supply capacity and the pump's fluid discharge capacity. The objective for minimizing energy consumption per ton of fluid is determined based on the ratio of motor input power to actual fluid production. The objective for minimizing equipment wear is determined based on a normalized weighted combination of vibration acceleration, motor operating temperature rise, and motor operating current. Further, it includes: The target for maximizing oil production is determined by the actual fluid production, water cut, and crude oil density. The actual fluid production is the smaller of a first calculated value and a second calculated value. The first calculated value is determined based on the oil production index, reservoir static pressure, and bottom hole flow pressure. The second calculated value is determined based on the pump rated displacement, the ratio of the current operating frequency to the rated frequency, and the pump's overall efficiency. The target of minimizing energy consumption per ton of liquid is determined based on the ratio of motor input power, daily operating time and actual liquid production. The motor input power is determined based on the density of the wellbore mixture, gravitational acceleration, lifting height, actual liquid production, pump overall efficiency, motor efficiency and frequency converter efficiency. The goal of minimizing equipment wear is determined based on the normalized square weighted sum of vibration acceleration, motor operating temperature rise, and motor operating current and their respective allowable upper limits. A correction relationship for the overall pump efficiency is introduced, wherein the overall pump efficiency is determined based on the rated pump efficiency and the operating condition correction parameters.

[0010] In some specific embodiments, the local refinement solution further includes a constraint verification step for frequency candidate solutions that do not satisfy the set of physical constraints, including: Verify whether the candidate frequency solution satisfies the pump operating frequency boundary constraint. If the candidate frequency solution does not satisfy the pump operating frequency boundary constraint, then correct the candidate frequency solution to the boundary value. Verify whether the dynamic liquid surface depth corresponding to the candidate frequency solution meets the dynamic liquid surface safety constraint. If the dynamic liquid surface depth corresponding to the candidate frequency solution does not meet the dynamic liquid surface safety constraint, adjust the candidate frequency solution until the dynamic liquid surface depth meets the safety lower limit. Verify whether the motor winding temperature and motor operating current corresponding to the candidate frequency solution meet the motor protection constraints. If the motor winding temperature or motor operating current corresponding to the candidate frequency solution does not meet the motor protection constraints, then limit the value range of the candidate frequency solution. The adjustment range of the candidate frequency solution is checked to see if it meets the frequency change rate constraint and the pump overall efficiency meets the pump efficiency lower limit constraint. If the adjustment range of the candidate frequency solution does not meet the frequency change rate constraint or the pump overall efficiency does not meet the pump efficiency lower limit constraint, the candidate frequency solution is corrected accordingly.

[0011] In some specific embodiments, cloud-based offline pre-computation further includes: The operating parameters, including reservoir static pressure, oil production index, water cut, and downhole ambient temperature, are discretized according to their ranges and combined to obtain multiple typical operating conditions. For each typical working condition, a multi-objective evolutionary algorithm is used to calculate the Pareto optimal solution set; Clustering and compression processing is performed on the Pareto optimal solution set for each typical working condition; The compressed operating condition feature vectors and their corresponding Pareto solutions are constructed into a pre-computation database and stored on an edge computing device.

[0012] In some specific embodiments, edge-end online matching further includes: Extract the reservoir static pressure, oil production index, water cut, and downhole ambient temperature at the current moment to form a feature vector of the current operating condition; The similarity distance between the current working condition feature vector and the feature vectors of each working condition in the pre-calculated database is calculated using normalized Euclidean distance. Based on the similarity distance, select the three similar working conditions with the smallest distance and extract the corresponding pre-calculated Pareto solution set; An initial solution is determined from the extracted pre-computed Pareto solution set.

[0013] In some specific embodiments, the local refinement solution further includes: The population is initialized within a preset frequency neighborhood, centered on the initial solution. The differential evolution algorithm is used to perform an iterative search within the frequency neighborhood; For each frequency candidate solution generated iteratively, a constraint verification step is performed to eliminate frequency candidate solutions that do not meet the constraints. After constraint verification, the candidate frequency solution is subjected to reservoir fluid supply capacity constraint repair. The repair process includes solving for the critical frequency that makes the pump discharge capacity equal to the reservoir fluid supply capacity when the pump discharge capacity corresponding to the candidate frequency solution is greater than the reservoir fluid supply capacity, and then correcting the candidate frequency solution to the critical frequency.

[0014] In some specific embodiments, an optimal control scheme is determined from the Pareto optimal solution set according to an economic benefit evaluation model, and the optimal pump operating frequency in the optimal control scheme is output. The adjustment process of the optimal pump operating frequency satisfies the frequency change rate constraint, and further includes: A comprehensive daily economic benefit evaluation relationship for a single well is established, which is determined based on the economic value corresponding to the daily oil production, the economic cost corresponding to the daily electricity consumption, and the depreciation cost corresponding to equipment wear. Substitute the daily oil production, motor input power and equipment wear index corresponding to each solution in the Pareto optimal solution set into the evaluation relationship to calculate the daily comprehensive economic benefit value corresponding to each solution. Compare the daily comprehensive economic benefit values ​​corresponding to each solution, and determine the solution that maximizes the daily comprehensive economic benefit value as the optimal control scheme; Output the optimal pump operating frequency in the optimal control scheme, wherein the adjustment process of the optimal pump operating frequency satisfies the upper limit of the frequency adjustment range per unit time.

[0015] Based on the same concept, the present invention also provides a multi-objective coordinated control system for submersible electric pump wells, comprising: The data acquisition and preprocessing module is configured to acquire and preprocess multi-source operational data from submersible electric pump wells. The multi-objective optimization model construction module is configured to construct a multi-objective optimization model that integrates dynamic constraints of oil well inflow based on the multi-source operating data. The multi-objective optimization model includes the objectives of maximizing oil production, minimizing energy consumption per ton of fluid, and minimizing equipment wear. The objective of maximizing oil production is determined based on the actual fluid production, which is the smaller value between the reservoir's fluid supply capacity and the pump's fluid discharge capacity. The objective of minimizing energy consumption per ton of fluid is determined based on the ratio of motor input power to actual fluid production. The objective of minimizing equipment wear is determined based on a normalized weighted combination of vibration acceleration, motor operating temperature rise, and motor operating current. The physical constraint establishment module is configured to establish a set of physical constraint conditions, including pump operating frequency boundary constraints, dynamic liquid surface safety constraints, motor protection constraints, frequency change rate constraints, and pump efficiency lower limit constraints. The dynamic liquid surface safety constraint is that the dynamic liquid surface depth is not lower than a preset safety lower limit depth. The hierarchical adaptive optimization solution module is configured to use a hierarchical adaptive optimization algorithm to solve the multi-objective optimization model and obtain a Pareto optimal solution set. The solution includes offline pre-calculation in the cloud, online matching at the edge, and local refinement solution. In the local refinement solution, constraint repair is performed on the solution that exceeds the reservoir's fluid supply capacity. The optimal solution decision and output module is configured to determine the optimal control scheme from the Pareto optimal solution set according to the economic benefit evaluation model, and output the optimal pump operating frequency in the optimal control scheme, wherein the adjustment process of the optimal pump operating frequency satisfies the frequency change rate constraint.

[0016] Based on the same concept, the present invention also provides an electronic device, characterized in that it includes: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of a multi-objective coordinated control method for submersible electric pump wells.

[0017] Based on the same concept, the present invention also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a multi-objective coordinated control method for submersible electric pump wells.

[0018] Compared with existing technologies, its advantages are as follows: This invention discloses a multi-objective collaborative control method, system, equipment and medium for submersible electric pump wells. By embedding the dynamic fluid supply constraint of the well inflow into the optimization objective function, it ensures that the optimization solution is always within the actual fluid supply capacity of the reservoir, thus guaranteeing the engineering feasibility of the control scheme. It adopts a hierarchical adaptive optimization architecture to reduce computational complexity and support the deployment of edge computing devices; It has the ability to optimize for both limited and sufficient liquid supply scenarios. When the liquid supply is limited, it can reduce energy consumption by reducing the frequency, and when the liquid supply is sufficient, it can increase production by increasing the frequency. By introducing wear minimization targets based on vibration acceleration, motor operating temperature rise, and motor operating current, the pump inspection cycle of the equipment is extended. Edge devices store a complete pre-computed database, enabling them to operate autonomously during network outages and ensuring continuous control. Attached Figure Description

[0019] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a flowchart illustrating some specific embodiments of the multi-objective coordinated control method for submersible electric pump wells according to the present invention; Figure 2 This is a schematic diagram of the structure of a multi-objective coordinated control system for submersible electric pump wells according to some specific embodiments of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device according to some specific embodiments of the present invention; In the diagram, 710 is the processor; 720 is the memory; 730 is the input device; and 740 is the output device. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0022] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0023] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0024] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0025] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0026] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0027] Reference Figure 1 A multi-objective coordinated control method for submersible electric pump wells, comprising: S101, collect multi-source operational data from submersible electric pump wells and perform preprocessing; Specifically, in this embodiment of the invention, multi-source operational data of the submersible electric pump well is collected. This multi-source operational data includes pump operating frequency, bottom hole flowing pressure, dynamic fluid level depth, production rate, water cut, downhole temperature, motor current, and vibration acceleration. The pump operating frequency is obtained from the inverter output; the bottom hole flowing pressure is measured by a downhole pressure sensor; the dynamic fluid level depth is obtained through echo sounder or downhole pressure gradient calculation; the production rate is obtained by wellhead flow meter or separator measurement; the water cut is determined by wellhead sampling and testing or an online water cut analyzer; the downhole temperature is measured by a downhole temperature sensor; the motor current is obtained from the inverter or current transformer in the distribution cabinet; and the vibration acceleration is collected by a downhole vibration sensor at a sampling frequency of not less than 1 kHz. The collected multi-source operational data is preprocessed, including outlier removal and noise filtering. Outlier removal uses statistical criteria, identifying data points that deviate from the data mean by more than a preset multiple of the standard deviation as outliers and removing them. Noise filtering uses a moving average method, replacing the current sampling point value with the average of multiple consecutive sampling points to eliminate high-frequency random noise interference and improve data smoothness and the stability of subsequent calculations.

[0028] S102, Based on the multi-source operation data, a multi-objective optimization model integrating dynamic constraints of oil well inflow is constructed. The multi-objective optimization model includes the objectives of maximizing oil production, minimizing energy consumption per ton of fluid, and minimizing equipment wear. The objective of maximizing oil production is determined based on the actual fluid production, which is the smaller value between the reservoir's fluid supply capacity and the pump's fluid discharge capacity. The objective of minimizing energy consumption per ton of fluid is determined based on the ratio of motor input power to actual fluid production. The objective of minimizing equipment wear is determined based on a normalized weighted combination of vibration acceleration, motor operating temperature rise, and motor operating current. S102 further includes: The target for maximizing oil production is determined by the actual fluid production, water cut, and crude oil density. The actual fluid production is the smaller of a first calculated value and a second calculated value. The first calculated value is determined based on the oil production index, reservoir static pressure, and bottom hole flow pressure. The second calculated value is determined based on the pump rated displacement, the ratio of the current operating frequency to the rated frequency, and the pump's overall efficiency. The target of minimizing energy consumption per ton of liquid is determined based on the ratio of motor input power, daily operating time and actual liquid production. The motor input power is determined based on the density of the wellbore mixture, gravitational acceleration, lifting height, actual liquid production, pump overall efficiency, motor efficiency and frequency converter efficiency. The goal of minimizing equipment wear is determined based on the normalized square weighted sum of vibration acceleration, motor operating temperature rise, and motor operating current and their respective allowable upper limits. A correction relationship for the overall pump efficiency is introduced, wherein the overall pump efficiency is determined based on the rated pump efficiency and the operating condition correction parameters.

[0029] Specifically, in this embodiment of the invention, a multi-objective optimization model integrating dynamic constraints on oil well inflow is constructed based on preprocessed multi-source operational data. The multi-objective optimization model includes objectives for maximizing oil production, minimizing energy consumption per ton of fluid, and minimizing equipment wear.

[0030] The target for maximizing oil production is determined jointly by the actual fluid production, water cut, and crude oil density. The actual fluid production is taken as the smaller of a first calculated value and a second calculated value. The first calculated value is the reservoir fluid supply capacity, determined based on the production index, reservoir static pressure, and bottom hole flowing pressure; specifically, it is the product of the production index and the difference between the reservoir static pressure and the bottom hole flowing pressure. The second calculated value is the pump discharge capacity, determined based on the pump's rated discharge capacity, the ratio of the current operating frequency to the rated frequency, and the pump's overall efficiency; specifically, it is the product of these three factors. When the pump discharge capacity is less than the reservoir fluid supply capacity, the actual fluid production is determined by the pump discharge capacity, and increasing the frequency can increase the fluid production. When the pump discharge capacity is greater than or equal to the reservoir fluid supply capacity, the actual fluid production is determined by the reservoir fluid supply capacity, and the production is limited by the formation fluid supply capacity. In this case, the optimization target automatically shifts to energy saving and consumption reduction.

[0031] The goal of minimizing energy consumption per ton of fluid is determined based on the ratio of motor input power, daily operating time, and actual fluid production. Motor input power is determined based on the wellbore mixed fluid density, gravitational acceleration, lift height, actual fluid production, pump overall efficiency, motor efficiency, and inverter efficiency. Specifically, motor input power is directly proportional to the product of wellbore mixed fluid density, gravitational acceleration, lift height, and actual fluid production, and inversely proportional to the product of pump overall efficiency, motor efficiency, and inverter efficiency. Wellbore mixed fluid density is determined by adding the product of formation water density and water cut to the product of crude oil density and oil cut.

[0032] The goal of minimizing equipment wear is determined by a normalized, weighted sum of the squared values ​​of vibration acceleration, motor operating temperature rise, and motor operating current, along with their respective allowable upper limits. The allowable upper limit for vibration acceleration is determined according to rotating machinery vibration standards; the allowable upper limit for motor operating temperature rise is determined based on the allowable temperature rise value corresponding to the motor's insulation class; and the allowable upper limit for motor operating current is based on the rated current. The vibration acceleration, motor operating temperature rise, and motor operating current terms are multiplied by their respective weighting coefficients and then summed. These weighting coefficients are obtained through regression calibration using historical operating data.

[0033] A comprehensive pump efficiency correction relationship is introduced to more accurately describe the actual pump efficiency under varying operating conditions. The comprehensive pump efficiency is determined based on the rated pump efficiency and operating condition correction parameters, including flow rate deviation correction coefficient, head deviation correction coefficient, and viscosity correction coefficient. The flow rate deviation correction coefficient is related to the degree to which the actual produced fluid deviates from the pump's optimal efficiency flow rate. The head deviation correction coefficient is related to the degree to which the actual lift height deviates from the pump's rated head. The viscosity correction coefficient is related to the degree to which the kinematic viscosity of the wellbore produced fluid deviates from the design value. Each correction coefficient is obtained based on regression analysis of pump characteristic curves and field operating data.

[0034] S103, establish a set of physical constraints, including pump operating frequency boundary constraints, dynamic liquid surface safety constraints, motor protection constraints, frequency change rate constraints, and pump efficiency lower limit constraints, wherein the dynamic liquid surface safety constraint is that the dynamic liquid surface depth is not lower than the preset safety lower limit depth. Specifically, in this embodiment of the invention, a set of physical constraints is established to limit the optimization search space and ensure the engineering feasibility of the control scheme. The set of physical constraints includes pump operating frequency boundary constraints, dynamic liquid level safety constraints, motor protection constraints, frequency change rate constraints, and pump efficiency lower limit constraints.

[0035] The pump operating frequency boundary constraint limits the allowable range of frequency adjustment. The frequency value must not be lower than the preset lower frequency limit to ensure the normal start-up and stable operation of the pump, and at the same time, it must not be higher than the preset upper frequency limit to prevent inverter overload and equipment overspeed damage.

[0036] The dynamic liquid level safety constraint defines the minimum permissible depth of the dynamic liquid level, which must be greater than or equal to the lower safety limit depth. This constraint is used to prevent the pump inlet from being exposed to gas due to excessive submersion, thus avoiding pump cavitation or airlock failure.

[0037] Motor protection constraints include motor winding temperature constraints and motor operating current constraints. The motor winding temperature must be less than or equal to the maximum allowable winding temperature, which is determined according to the motor insulation class. The motor operating current must be less than or equal to a preset upper limit of the rated current to prevent the motor from operating under overload for extended periods, which could lead to accelerated insulation aging or burnout.

[0038] The frequency change rate constraint limits the maximum permissible amplitude of frequency regulation per unit time. During frequency regulation, the frequency change between adjacent moments must be less than or equal to the preset upper limit of the change rate to prevent sudden frequency changes from impacting the power grid and underground equipment.

[0039] The pump efficiency lower limit constraint defines the minimum allowable value for the overall pump efficiency. The overall pump efficiency corresponding to any candidate solution at any frequency must be greater than or equal to the preset pump efficiency lower limit value to ensure that the system is in the economic operating range and avoid continuous operation under conditions that are significantly deviated from the high-efficiency range.

[0040] The aforementioned physical constraints together constitute the basis for determining the feasibility of the solution during the optimization process. If any constraint is not satisfied, the solution is determined to be infeasible and is eliminated or modified.

[0041] S104, The hierarchical adaptive optimization algorithm is used to solve the multi-objective optimization model to obtain the Pareto optimal solution set. The solution includes offline pre-calculation in the cloud, online matching at the edge, and local refinement solution. In the local refinement solution, constraint repair is performed on the solution that exceeds the reservoir's fluid supply capacity. S104 further includes: The local refinement solution further includes a constraint verification step for frequency candidate solutions that do not satisfy the set of physical constraints, including: Verify whether the candidate frequency solution satisfies the pump operating frequency boundary constraint. If the candidate frequency solution does not satisfy the pump operating frequency boundary constraint, then correct the candidate frequency solution to the boundary value. Verify whether the dynamic liquid surface depth corresponding to the candidate frequency solution meets the dynamic liquid surface safety constraint. If the dynamic liquid surface depth corresponding to the candidate frequency solution does not meet the dynamic liquid surface safety constraint, adjust the candidate frequency solution until the dynamic liquid surface depth meets the safety lower limit. Verify whether the motor winding temperature and motor operating current corresponding to the candidate frequency solution meet the motor protection constraints. If the motor winding temperature or motor operating current corresponding to the candidate frequency solution does not meet the motor protection constraints, then limit the value range of the candidate frequency solution. The adjustment range of the candidate frequency solution is checked to see if it meets the frequency change rate constraint and the pump overall efficiency meets the pump efficiency lower limit constraint. If the adjustment range of the candidate frequency solution does not meet the frequency change rate constraint or the pump overall efficiency does not meet the pump efficiency lower limit constraint, the candidate frequency solution is corrected accordingly.

[0042] S104 further includes: Cloud-based offline pre-computation further includes: The operating parameters, including reservoir static pressure, oil production index, water cut, and downhole ambient temperature, are discretized according to their ranges and combined to obtain multiple typical operating conditions. For each typical working condition, a multi-objective evolutionary algorithm is used to calculate the Pareto optimal solution set; Clustering and compression processing is performed on the Pareto optimal solution set for each typical working condition; The compressed operating condition feature vectors and their corresponding Pareto solutions are constructed into a pre-computation database and stored on an edge computing device.

[0043] S104 further includes: Edge-based online matching further includes: Extract the reservoir static pressure, oil production index, water cut, and downhole ambient temperature at the current moment to form a feature vector of the current operating condition; The similarity distance between the current working condition feature vector and the feature vectors of each working condition in the pre-calculated database is calculated using normalized Euclidean distance. Based on the similarity distance, select the three similar working conditions with the smallest distance and extract the corresponding pre-calculated Pareto solution set; An initial solution is determined from the extracted pre-computed Pareto solution set.

[0044] S104 further includes: Local refinement solution, further including: The population is initialized within a preset frequency neighborhood, centered on the initial solution. The differential evolution algorithm is used to perform an iterative search within the frequency neighborhood; For each frequency candidate solution generated iteratively, a constraint verification step is performed to eliminate frequency candidate solutions that do not meet the constraints. After constraint verification, the candidate frequency solution is subjected to reservoir fluid supply capacity constraint repair. The repair process includes solving for the critical frequency that makes the pump discharge capacity equal to the reservoir fluid supply capacity when the pump discharge capacity corresponding to the candidate frequency solution is greater than the reservoir fluid supply capacity, and then correcting the candidate frequency solution to the critical frequency.

[0045] Specifically, in this embodiment of the invention, a hierarchical adaptive optimization algorithm is used to solve the multi-objective optimization model to obtain the Pareto optimal solution set. The solution process includes three stages: offline pre-computation in the cloud, online matching at the edge, and local refinement solution.

[0046] In the cloud-based offline pre-computation stage, reservoir static pressure, oil production index, water cut, and downhole ambient temperature are discretized and combined according to levels to obtain multiple typical operating conditions. For each typical operating condition, a multi-objective evolutionary algorithm is used to calculate the Pareto optimal solution set satisfying the set of physical constraints. The Pareto optimal solution set for each typical operating condition is then clustered and compressed to reduce data storage. The compressed operating condition feature vectors and corresponding Pareto solution sets are used to construct a pre-computation database, which is stored on an edge computing device. The pre-computation database supports incremental updates at predetermined periods or when changes in operating condition parameters exceed preset thresholds.

[0047] In the edge-end online matching stage, the reservoir static pressure, oil production index, water cut, and downhole ambient temperature at the current moment are extracted to form the current operating condition feature vector. Normalized Euclidean distance is used to calculate the similarity distance between the current operating condition feature vector and the feature vectors of each operating condition in the pre-calculated database, with the standard deviation of each operating condition feature parameter used as the normalization parameter. The three similar operating conditions with the smallest similarity distance are selected, and their corresponding pre-calculated Pareto solutions are extracted. An initial solution is determined from the extracted pre-calculated Pareto solution set as the center point for subsequent local refinement searches.

[0048] In the local refinement solution stage, the population is initialized within a preset frequency neighborhood centered on the initial solution. A differential evolution algorithm is used for iterative searching within the frequency neighborhood, significantly reducing the population size and number of iterations compared to the standard differential evolution algorithm. A constraint verification step is performed on each frequency candidate solution generated iteratively.

[0049] The constraint verification steps specifically include: verifying whether the frequency candidate solution meets the pump operating frequency boundary constraints; if the frequency candidate solution does not meet the pump operating frequency boundary constraints, the frequency candidate solution is corrected to the nearest boundary value. Verifying whether the dynamic liquid level depth corresponding to the frequency candidate solution meets the dynamic liquid level safety constraints; if the dynamic liquid level depth corresponding to the frequency candidate solution does not meet the dynamic liquid level safety constraints, the frequency candidate solution is adjusted until the dynamic liquid level depth meets the safety lower limit. Verifying whether the motor winding temperature and motor operating current corresponding to the frequency candidate solution meet the motor protection constraints; if the motor winding temperature or motor operating current corresponding to the frequency candidate solution does not meet the motor protection constraints, the value range of the frequency candidate solution is restricted. Verifying whether the adjustment range of the frequency candidate solution meets the frequency change rate constraint and whether the pump overall efficiency meets the pump efficiency lower limit constraint; if the adjustment range of the frequency candidate solution does not meet the frequency change rate constraint or the pump overall efficiency does not meet the pump efficiency lower limit constraint, the frequency candidate solution is corrected accordingly.

[0050] After constraint verification, the candidate frequency solutions undergo reservoir fluid supply capacity constraint repair. The repair process is as follows: when the pump discharge capacity corresponding to the candidate frequency solution is greater than the reservoir fluid supply capacity, the critical frequency that makes the pump discharge capacity equal to the reservoir fluid supply capacity is calculated, and the candidate frequency solution is corrected to this critical frequency. If the critical frequency is lower than the lower limit of the pump operating frequency, the candidate frequency solution is corrected to the lower limit of the pump operating frequency, and a pump type mismatch warning is generated. After the iteration terminates, the final Pareto optimal solution set is obtained.

[0051] S105, determine the optimal control scheme from the Pareto optimal solution set according to the economic benefit evaluation model, and output the optimal pump operating frequency in the optimal control scheme, wherein the adjustment process of the optimal pump operating frequency satisfies the frequency change rate constraint.

[0052] S105 further includes: A comprehensive daily economic benefit evaluation relationship for a single well is established, which is determined based on the economic value corresponding to the daily oil production, the economic cost corresponding to the daily electricity consumption, and the depreciation cost corresponding to equipment wear. Substitute the daily oil production, motor input power and equipment wear index corresponding to each solution in the Pareto optimal solution set into the evaluation relationship to calculate the daily comprehensive economic benefit value corresponding to each solution. Compare the daily comprehensive economic benefit values ​​corresponding to each solution, and determine the solution that maximizes the daily comprehensive economic benefit value as the optimal control scheme; Output the optimal pump operating frequency in the optimal control scheme, wherein the adjustment process of the optimal pump operating frequency satisfies the upper limit of the frequency adjustment range per unit time.

[0053] Specifically, in this embodiment of the invention, the optimal control scheme is determined from the Pareto optimal solution set based on the economic benefit evaluation model. A comprehensive daily economic benefit evaluation relationship for a single well is established, which is determined based on the economic value corresponding to daily oil production, the economic cost corresponding to daily electricity consumption, and the depreciation cost corresponding to equipment wear. The economic value corresponding to daily oil production is obtained by multiplying the daily oil production by the crude oil sales price. The economic cost corresponding to daily electricity consumption is obtained by multiplying the motor input power, daily operating time, and industrial electricity price. The depreciation cost corresponding to equipment wear is obtained by multiplying the equipment wear index by the unit wear depreciation coefficient. The comprehensive daily economic benefit value is the economic value corresponding to daily oil production minus the economic cost corresponding to daily electricity consumption, and then minus the depreciation cost corresponding to equipment wear.

[0054] Substituting the daily oil production, motor input power, and equipment wear index corresponding to each solution in the Pareto optimal solution set into the evaluation relationship, the daily comprehensive economic benefit value corresponding to each solution is calculated one by one. The daily comprehensive economic benefit values ​​corresponding to each solution are compared, and the solution that maximizes the daily comprehensive economic benefit value is selected as the optimal control scheme. The optimal pump operating frequency in the optimal control scheme is output. The adjustment process of the optimal pump operating frequency satisfies the upper limit of the frequency adjustment range per unit time; that is, the frequency adjustment is executed step by step according to the preset rate of change limit, rather than an instantaneous jump to the target frequency.

[0055] When multiple solutions in the Pareto optimal solution set have equal or different economic benefit values, the solution with the smaller equipment wear index is selected first to further extend the equipment service life.

[0056] The following describes another embodiment of the multi-objective coordinated control method for submersible electric pump wells according to the present invention: Multi-source data acquisition and preprocessing: Pump operating frequency is collected via downhole sensors. Bottom-hole flowing pressure Dynamic liquid level depth, liquid production rate Moisture content Downhole temperature Motor current Vibration acceleration There are a total of 8 types of parameters. Data preprocessing uses the 3σ criterion to remove outliers and a 5-point moving average filter.

[0057] Construct a multi-objective optimization model that incorporates IPR constraints: Objective function 1: Maximize oil production. ; The actual liquid production rate is obtained by solving the IPR curve and the pump characteristic curve simultaneously to find the minimum value: ; ; when At times, increasing frequency can increase production; when At that time, production was limited by IPR, and the optimization goal automatically shifted to energy saving and consumption reduction.

[0058] in, Daily oil production at different operating frequencies; Daily oil production; This represents the actual daily liquid production at different operating frequencies; The water content of the wellbore produced fluid; Density of crude oil; The maximum fluid supply capacity of the reservoir is calculated based on the inflow dynamics (IPR) curve of the oil well. The pump discharge capacity at different operating frequencies; Oil well production index; For reservoir static pressure; This refers to the bottom-well flow pressure.

[0059] Objective function 2, minimizing energy consumption per ton of liquid: ; Input power is calculated using a hydraulic power model: ; In the formula, 86400 is the unit conversion factor, and the formula for calculating the density of the mixture is: ; in, Energy consumption per ton of liquid lifted at different operating frequencies; Input power to the motor at different operating frequencies; This represents the actual daily liquid production at different operating frequencies; The density of the wellbore mixture; It is the acceleration due to gravity; This refers to the fluid lift height. For the overall pump efficiency of centrifugal pumps; To improve the operating efficiency of the submersible motor; To improve the operating efficiency of the frequency converter; Density of formation water; The water content of the wellbore produced fluid; This refers to the density of crude oil.

[0060] Objective function 3, minimizing equipment wear: ; In the formula, , , , , The weighting coefficients are used for ridge regression calibration.

[0061] in, The cumulative wear index of equipment at different operating frequencies; These are the weighting coefficients for the three wear factors: vibration, temperature rise, and current impact. This represents the effective value of downhole vibration acceleration. This represents the upper limit of permissible vibration acceleration. This represents the actual operating temperature rise of the motor. This is the upper limit of the allowable temperature rise of the motor windings; This refers to the real-time operating current of the motor. This is the rated current of the motor.

[0062] Pump efficiency calculation model: ; The correction factor is based on the APIRP11S2 standard and field data regression, and the calculation formula is as follows: ; ; ; in, For the overall pump efficiency of centrifugal pumps; The pump efficiency under rated operating conditions; This is the pump flow deviation correction factor; This is the pump head deviation correction factor; This is the pump fluid viscosity correction factor; This represents the actual daily liquid production. The flow rate corresponding to the pump's optimal efficiency point; This refers to the actual lifting height. This refers to the pump's rated head. The kinematic viscosity of the fluid produced from the wellbore.

[0063] Establish a set of physical constraints: Table 1: Set of Physical Constraints

[0064] in, These are the lower and upper limits of the pump's operating frequency; This refers to the depth of the dynamic fluid level in the wellbore. This is the lower limit of the safe depth for the dynamic liquid level; Real-time temperature of the motor windings, in units; This refers to the maximum allowable temperature of the motor windings. This refers to the real-time operating current of the motor. This is the rated current of the motor; The frequency adjustment amplitude per unit time; For the overall pump efficiency of centrifugal pumps; This represents the gas content at the pump inlet.

[0065] Hierarchical Adaptive Optimization (HAO) algorithm for solution: Offline pre-computation layer (executed in the cloud): Pareto solution sets are pre-calculated for typical operating condition combinations.

[0066] Operating condition discretization: Select 5 gears (8 / 10 / 12 / 14 / 16MPa). Select gear 4 (5 / 10 / 15 / 20). Select 5 gears (0.20 / 0.40 / 0.60 / 0.80 / 0.95). Three temperature settings (20 / 35 / 50°C) are available, covering a total of 300 typical operating conditions.

[0067] The NSGA-II algorithm (population N=100, 200 generations) is used to calculate the Pareto solution set for each working condition. After compression using K-means clustering (K=5, silhouette coefficient 0.72), the solution set is stored. The pre-calculated database size is approximately 48KB and can be stored on edge devices. Update mechanism: Monthly periodic updates, or incremental updates triggered when parameter changes exceed a threshold.

[0068] Online matching layer (executed at the edge): Extract the feature vector of the current working condition The pre-computed solution set of the most similar working condition is retrieved using the K-nearest neighbor algorithm (K=3). The distance metric used is normalized Euclidean distance. ; Normalization parameter: , , , .

[0069] in, The current working condition feature vector and the first Normalized Euclidean distance of each pre-calculated characteristic vector of the working condition; This is the feature vector of the current operating condition; Let be the feature vector of the i-th pre-calculated working condition; For the first The reservoir static pressure, oil production index, water cut, and ambient temperature for each pre-calculated working condition; This represents the normalized standard deviation of the corresponding feature parameter.

[0070] Local refinement layer (executed at the edge): The solution is refined using a lightweight differential evolution (LDE) algorithm within a ±5Hz neighborhood, centered on the matching solution.

[0071] LDE Lightweight Strategy Comparison Table:

[0072] The mutation uses the DE / best / 1 strategy, as shown in the following formula: ; In the formula, Crossover probability .

[0073] IPR constraint repair: If The critical frequency is solved using the bisection method. ,make and repair .

[0074] in, For the new individuals generated after mutation (frequency candidate values); The optimal individual (optimal frequency value) in the current population. This is the differential evolution scaling factor; Two distinct individuals are randomly selected from the current population, and... No repetition.

[0075] Algorithm termination conditions: 20 iterations, optimal solution change <0.1%, or timeout of 10 seconds.

[0076] Economic benefit evaluation and optimal solution selection: ; Select from Pareto solution set The largest solution is taken as the final optimal solution.

[0077] in, To achieve comprehensive economic benefits per well per day; Daily oil production; The selling price of crude oil; Input power to the motor; For industrial electricity prices; The cumulative wear index of the equipment; This represents the equipment depreciation cost per unit of wear and tear.

[0078] Optimal solution output and safe execution: Output optimal frequency The data is sent to the wellhead frequency converter via the SCADA system and smoothly adjusted according to the rate limited by constraint (C4).

[0079] Special case handling: Pump type matching early warning mechanism: when When this occurs, it indicates that the pump's rated displacement is too high, and the system will set the frequency to [a certain value]. It also generates a pump type mismatch warning and calculates the recommended rated displacement. .

[0080] Pareto degradation: When the pump displacement at all feasible frequencies exceeds the IPR limit, the optimization model automatically degenerates into a bi-objective optimization problem of "energy consumption-wear".

[0081] Wear coefficient calibration method: Collect complete operational cycle data and pump inspection records from at least 30 wells to establish a ridge regression calibration model: ; in, , , These are the dimensionless weighting coefficients for the average vibration acceleration, the average motor temperature rise, and the average current overload rate, respectively. , , All have been dimensionless, so the dimensions on both sides of the formula are consistent (both are the reciprocal dimension of time).

[0082] Ridge regression is used to solve ( (5-fold cross-validation), model validation criteria: MAPE ≤ 20%.

[0083] Calibration Example: Data Calibration Results of 36 Wells in an Oilfield , , ( After normalization, take , , .like The above default coefficients can be used.

[0084] in, The actual pump inspection cycle (operating life) of the equipment. These are the weighting coefficients for the three wear factors: vibration, temperature rise, and current impact. This is the time average of the effective value of vibration acceleration over the entire operating cycle; This represents the average time-based temperature rise of the motor throughout its entire operating cycle. This is the time average of the motor current overload rate over the entire operating cycle; This represents the residual term of the regression model; The ridge regression regularization coefficient; is the coefficient of determination for the regression model; MAPE is the mean absolute percentage error.

[0085] This embodiment adopts a three-layer architecture of "cloud-edge-device": Cloud-based: Performs offline pre-computation and model training, and distributes database updates to edge devices via the oilfield communication network. Edge computing: Stores a pre-computed database (48KB), performs online matching and local refinement, and has the ability to run autonomously offline; minimum configuration: ARM Cortex-A53, 256MB RAM. Terminal: Downhole multi-parameter sensor group (pressure, temperature, vibration (1kHz), current) and wellhead frequency converter.

[0086] The following example illustrates this embodiment: Liquid supply limited operation (energy saving optimization): Take the ESP well (well number ESP-2024-001) in a certain oil field as an example.

[0087] Basic parameters: Table 2: Basic Parameters of Test Wells

[0088] IPR Condition Diagnosis: IPR fluid supply capacity calculation: ; Pump efficiency calculation (45Hz operating condition): ; ; Pump displacement calculation: ; Diagnostic conclusion: This is a case of "overkill," with the pump displacement exceeding the IPR's liquid supply capacity by 60.9%.

[0089] Critical frequency This triggers a pump type mismatch warning.

[0090] Comparison of states before and after optimization: Table 3: Comparison of operating parameters before and after optimization:

[0091] HAO optimization solution: Due to limited liquid supply, the optimization model degenerates into a bi-objective optimization of "energy consumption-wear". The LDE algorithm refines the solution in the neighborhood of [30Hz, 35Hz] (15 generations, 3.2 seconds), obtaining the Pareto solution set as follows: Table 4: Solution set for Pareto optimization:

[0092] Economic benefit evaluation: Set boundary conditions: Yuan / ton Yuan / kWh Wear per unit (RMB).

[0093] Daily comprehensive benefit calculation: ; ; Optimal solution: ; Implementation results: Table 5: Comparison of Optimization Implementation Results

[0094] Benefits Summary: Production remains unchanged (limited by IPR fluid supply capacity), annual electricity savings of approximately RMB 12,000; equipment wear is reduced by 65.7%, pump inspection cycle is extended from 18 months to more than 36 months, and the comprehensive annual benefit per well is approximately RMB 87,000.

[0095] For the purpose of simplicity, the method steps disclosed in the above embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0096] like Figure 2 As shown, the present invention also provides a multi-objective coordinated control system for submersible electric pump wells, comprising: The data acquisition and preprocessing module 201 is configured to acquire and preprocess multi-source operational data from submersible electric pump wells. The multi-objective optimization model construction module 202 is configured to construct a multi-objective optimization model that integrates dynamic constraints of oil well inflow based on the multi-source operating data. The multi-objective optimization model includes the objectives of maximizing oil production, minimizing energy consumption per ton of fluid, and minimizing equipment wear. The objective of maximizing oil production is determined based on the actual fluid production, which is the smaller value between the reservoir's fluid supply capacity and the pump's fluid discharge capacity. The objective of minimizing energy consumption per ton of fluid is determined based on the ratio of motor input power to actual fluid production. The objective of minimizing equipment wear is determined based on a normalized weighted combination of vibration acceleration, motor operating temperature rise, and motor operating current. The physical constraint establishment module 203 is configured to establish a set of physical constraint conditions, including pump operating frequency boundary constraints, dynamic liquid surface safety constraints, motor protection constraints, frequency change rate constraints, and pump efficiency lower limit constraints. The dynamic liquid surface safety constraint is that the dynamic liquid surface depth is not lower than a preset safety lower limit depth. The hierarchical adaptive optimization solution module 204 is configured to use a hierarchical adaptive optimization algorithm to solve the multi-objective optimization model and obtain a Pareto optimal solution set. The solution includes cloud offline pre-calculation, edge online matching and local refinement solution, and in the local refinement solution, constraint repair is performed on the solution that exceeds the reservoir fluid supply capacity. The optimal solution decision and output module 205 is configured to determine the optimal control scheme from the Pareto optimal solution set according to the economic benefit evaluation model, and output the optimal pump operating frequency in the optimal control scheme, wherein the adjustment process of the optimal pump operating frequency satisfies the frequency change rate constraint.

[0097] It is worth noting that although only some basic functional modules are disclosed in the embodiments of this invention, it does not mean that the composition of this system is limited to the above-mentioned basic functional modules. On the contrary, what this embodiment intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with existing technology to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. The fact that this embodiment only discloses a few basic functional modules should not be considered as the scope of protection of the claims of this invention being limited to the disclosed basic functional modules. At the same time, for the convenience of description, the above device is described separately according to its functions as various units and modules. Of course, in implementing this invention, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0098] like Figure 3As shown, the present invention also provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of a multi-objective coordinated control method for submersible electric pump wells.

[0099] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. For example... Figure 3 The structure shown in this embodiment of the invention includes an electronic device comprising one or more processors 710 and a memory 720; the processors 710 in this electronic device may be one or more. Figure 3 Taking a processor 710 as an example; a memory 720 is used to store one or more programs; the one or more programs are executed by the one or more processors 710, so that the one or more processors 710 implement a multi-objective coordinated control method for submersible electric pump wells as described in any one of the embodiments of the present invention.

[0100] The electronic device may also include an input device 730 and an output device 740.

[0101] The processor 710, memory 720, input device 730, and output device 740 in this electronic device can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0102] The memory 720 in this electronic device serves as a computer-readable storage medium, capable of storing one or more programs. These programs can be software programs, computer-executable programs, or modules, such as the program instructions / modules corresponding to the multi-objective coordinated control method for submersible electric pump wells provided in this embodiment of the invention. The processor 710 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 720, thereby realizing the multi-objective coordinated control method for submersible electric pump wells described in the above embodiment.

[0103] The memory 720 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device. Furthermore, the memory 720 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 720 may further include memory remotely located relative to the processor 710, which can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0104] Input device 730 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the electronic device. Output device 740 may include display devices such as a display screen.

[0105] The present invention also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a multi-objective coordinated control method for submersible electric pump wells.

[0106] Specifically, the computer storage medium in this embodiment of the invention can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be—but is not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-objective coordinated control method for submersible electric pump wells, characterized in that, include: Collect and preprocess multi-source operational data from submersible electric pump wells; Based on the multi-source operational data, a multi-objective optimization model integrating dynamic constraints of oil well inflow is constructed. The multi-objective optimization model includes the objectives of maximizing oil production, minimizing energy consumption per ton of fluid, and minimizing equipment wear. The objective of maximizing oil production is determined based on the actual fluid production, which is the smaller value between the reservoir's fluid supply capacity and the pump's fluid discharge capacity. The objective of minimizing energy consumption per ton of fluid is determined based on the ratio of motor input power to actual fluid production. The objective of minimizing equipment wear is determined based on a normalized weighted combination of vibration acceleration, motor operating temperature rise, and motor operating current. Establish a set of physical constraints, including pump operating frequency boundary constraints, dynamic liquid surface safety constraints, motor protection constraints, frequency change rate constraints, and pump efficiency lower limit constraints. The dynamic liquid surface safety constraint is that the dynamic liquid surface depth is not lower than a preset safety lower limit depth. The multi-objective optimization model is solved using a hierarchical adaptive optimization algorithm to obtain the Pareto optimal solution set. The solution process includes offline pre-computation in the cloud, online matching at the edge, and local refinement solution. In the local refinement solution, constraint repair is performed on the solutions that exceed the reservoir's fluid supply capacity. The optimal control scheme is determined from the Pareto optimal solution set according to the economic benefit evaluation model, and the optimal pump operating frequency in the optimal control scheme is output. The adjustment process of the optimal pump operating frequency satisfies the frequency change rate constraint.

2. The multi-objective coordinated control method for submersible electric pump wells according to claim 1, characterized in that, Based on the aforementioned multi-source operational data, a multi-objective optimization model integrating dynamic constraints on oil well inflow is constructed. This multi-objective optimization model includes objectives for maximizing oil production, minimizing energy consumption per ton of fluid, and minimizing equipment wear. The oil production maximization objective is determined based on the actual fluid production, which is the smaller of the reservoir's fluid supply capacity and the pump's fluid discharge capacity. The energy consumption minimization objective is determined based on the ratio of motor input power to actual fluid production. The equipment wear minimization objective is determined based on a normalized weighted combination of vibration acceleration, motor operating temperature rise, and motor operating current. Further, it includes: The target for maximizing oil production is determined by the actual fluid production, water cut, and crude oil density. The actual fluid production is the smaller of a first calculated value and a second calculated value. The first calculated value is determined based on the oil production index, reservoir static pressure, and bottom hole flow pressure. The second calculated value is determined based on the pump rated displacement, the ratio of the current operating frequency to the rated frequency, and the pump's overall efficiency. The target of minimizing energy consumption per ton of liquid is determined based on the ratio of motor input power, daily operating time and actual liquid production. The motor input power is determined based on the density of the wellbore mixture, gravitational acceleration, lifting height, actual liquid production, pump overall efficiency, motor efficiency and frequency converter efficiency. The goal of minimizing equipment wear is determined based on the normalized square weighted sum of vibration acceleration, motor operating temperature rise, and motor operating current and their respective allowable upper limits. A correction relationship for the overall pump efficiency is introduced, wherein the overall pump efficiency is determined based on the rated pump efficiency and the operating condition correction parameters.

3. The multi-objective coordinated control method for submersible electric pump wells according to claim 1, characterized in that, The local refinement solution further includes a constraint verification step for frequency candidate solutions that do not satisfy the set of physical constraints, including: Verify whether the candidate frequency solution satisfies the pump operating frequency boundary constraint. If the candidate frequency solution does not satisfy the pump operating frequency boundary constraint, then correct the candidate frequency solution to the boundary value. Verify whether the dynamic liquid surface depth corresponding to the candidate frequency solution meets the dynamic liquid surface safety constraint. If the dynamic liquid surface depth corresponding to the candidate frequency solution does not meet the dynamic liquid surface safety constraint, adjust the candidate frequency solution until the dynamic liquid surface depth meets the safety lower limit. Verify whether the motor winding temperature and motor operating current corresponding to the candidate frequency solution meet the motor protection constraints. If the motor winding temperature or motor operating current corresponding to the candidate frequency solution does not meet the motor protection constraints, then limit the value range of the candidate frequency solution. The adjustment range of the candidate frequency solution is checked to see if it meets the frequency change rate constraint and the pump overall efficiency meets the pump efficiency lower limit constraint. If the adjustment range of the candidate frequency solution does not meet the frequency change rate constraint or the pump overall efficiency does not meet the pump efficiency lower limit constraint, the candidate frequency solution is corrected accordingly.

4. The multi-objective coordinated control method for submersible electric pump wells according to claim 1, characterized in that, Cloud-based offline pre-computation further includes: The operating parameters, including reservoir static pressure, oil production index, water cut, and downhole ambient temperature, are discretized according to their ranges and combined to obtain multiple typical operating conditions. For each typical working condition, a multi-objective evolutionary algorithm is used to calculate the Pareto optimal solution set; Clustering and compression processing is performed on the Pareto optimal solution set for each typical working condition; The compressed operating condition feature vectors and their corresponding Pareto solutions are constructed into a pre-computation database and stored on an edge computing device.

5. The multi-objective coordinated control method for submersible electric pump wells according to claim 3, characterized in that, Edge-based online matching further includes: Extract the reservoir static pressure, oil production index, water cut, and downhole ambient temperature at the current moment to form a feature vector of the current operating condition; The similarity distance between the current working condition feature vector and the feature vectors of each working condition in the pre-calculated database is calculated using normalized Euclidean distance. Based on the similarity distance, select the three similar working conditions with the smallest distance and extract the corresponding pre-calculated Pareto solution set; An initial solution is determined from the extracted pre-computed Pareto solution set.

6. The multi-objective coordinated control method for submersible electric pump wells according to claim 5, characterized in that, Local refinement solution, further including: The population is initialized within a preset frequency neighborhood, centered on the initial solution. The differential evolution algorithm is used to perform an iterative search within the frequency neighborhood; For each frequency candidate solution generated iteratively, a constraint verification step is performed to eliminate frequency candidate solutions that do not meet the constraints. After constraint verification, the candidate frequency solution is subjected to reservoir fluid supply capacity constraint repair. The repair process includes solving for the critical frequency that makes the pump discharge capacity equal to the reservoir fluid supply capacity when the pump discharge capacity corresponding to the candidate frequency solution is greater than the reservoir fluid supply capacity, and then correcting the candidate frequency solution to the critical frequency.

7. The multi-objective coordinated control method for submersible electric pump wells according to claim 1, characterized in that, The optimal control scheme is determined from the Pareto optimal solution set according to the economic benefit evaluation model, and the optimal pump operating frequency in the optimal control scheme is output. The adjustment process of the optimal pump operating frequency satisfies the frequency change rate constraint, and further includes: A comprehensive economic benefit evaluation relationship for a single well is established, which is determined based on the economic value corresponding to the daily oil production, the economic cost corresponding to the daily electricity consumption, and the depreciation cost corresponding to equipment wear. Substitute the daily oil production, motor input power and equipment wear index corresponding to each solution in the Pareto optimal solution set into the evaluation relationship to calculate the daily comprehensive economic benefit value corresponding to each solution. Compare the daily comprehensive economic benefit values ​​corresponding to each solution, and determine the solution that maximizes the daily comprehensive economic benefit value as the optimal control scheme; Output the optimal pump operating frequency in the optimal control scheme, wherein the adjustment process of the optimal pump operating frequency satisfies the upper limit of the frequency adjustment range per unit time.

8. A multi-objective coordinated control system for submersible electric pump wells, characterized in that, include: The data acquisition and preprocessing module is configured to acquire and preprocess multi-source operational data from submersible electric pump wells. The multi-objective optimization model construction module is configured to construct a multi-objective optimization model that integrates dynamic constraints of oil well inflow based on the multi-source operating data. The multi-objective optimization model includes the objectives of maximizing oil production, minimizing energy consumption per ton of fluid, and minimizing equipment wear. The objective of maximizing oil production is determined based on the actual fluid production, which is the smaller value between the reservoir's fluid supply capacity and the pump's fluid discharge capacity. The objective of minimizing energy consumption per ton of fluid is determined based on the ratio of motor input power to actual fluid production. The objective of minimizing equipment wear is determined based on a normalized weighted combination of vibration acceleration, motor operating temperature rise, and motor operating current. The physical constraint establishment module is configured to establish a set of physical constraint conditions, including pump operating frequency boundary constraints, dynamic liquid surface safety constraints, motor protection constraints, frequency change rate constraints, and pump efficiency lower limit constraints. The dynamic liquid surface safety constraint is that the dynamic liquid surface depth is not lower than a preset safety lower limit depth. The hierarchical adaptive optimization solution module is configured to use a hierarchical adaptive optimization algorithm to solve the multi-objective optimization model and obtain a Pareto optimal solution set. The solution includes offline pre-calculation in the cloud, online matching at the edge, and local refinement solution. In the local refinement solution, constraint repair is performed on the solution that exceeds the reservoir's fluid supply capacity. The optimal solution decision and output module is configured to determine the optimal control scheme from the Pareto optimal solution set according to the economic benefit evaluation model, and output the optimal pump operating frequency in the optimal control scheme, wherein the adjustment process of the optimal pump operating frequency satisfies the frequency change rate constraint.

9. An electronic device, characterized in that, include: The system includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; the memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the method according to any one of claims 1 to 7.

Images