Submersible pump and submersible electric pump stator cooling device

Abstract

The application is suitable for the technical field of submersible pumps, and particularly relates to a submersible pump and a submersible electric pump stator cooling device. The submersible electric pump stator cooling device comprises a switching valve group, an injection pump assembly and a controller. The controller is used for obtaining the wellbore temperature gradient of a target oil well, the liquid production water cut, the motor power fluctuation curve and the annular gap size between the stator and the casing, determining a composite cooling path suitable for the target oil well based on the above, alternately switching the dominant mode of the composite cooling path, and collecting the temperature distribution of the stator, the cooling medium temperature rise and the pressure change value under each composite cooling path in real time. The overheat data of the stator is identified according to the temperature distribution. The cooling state and the flow resistance of the composite cooling path are determined according to the cooling medium temperature rise and the pressure change value. The cooling parameter data is determined based on the overheat data, the cooling state and the flow resistance. The submersible electric pump stator cooling device provided by the application can solve the problem of poor local heat dissipation capacity of the stator.

Description

Technical Field

[0001] This application belongs to the field of submersible pump technology, and particularly relates to a submersible pump and a submersible electric pump stator cooling device. Background Technology

[0002] A submersible pump (SMP) is a pump that is submerged inside an oil well to lift crude oil (or a liquid mixture) to the surface. An electric submersible pump (ESP) is a type of pump powered by electricity, with the pump body directly driven by a downhole motor. The downhole unit consists of the pump body, a protector, and the ESP connected coaxially in series from top to bottom. The ESP directly converts the electrical energy supplied from the surface into mechanical torque, which drives the pump impeller to rotate via a spline sleeve, thus lifting the crude oil. The stator core and windings of the ESP are integrally cast with epoxy resin to form the stator assembly, which is then press-fitted into the motor housing. Furthermore, the space between the stator cavity and the rotor is filled with motor oil, which lubricates the bearings and transfers heat.

[0003] However, due to the special working environment of submersible electric pumps and the continuous increase in well depth, the well temperature rises and the motor power increases. In addition, as the well depth increases, the properties of the oil, water and gas mixture downhole also change. Coupled with the interaction between the unstable motor power and the spatial limitation of the gap between the stator and the casing, the heat flux density caused by the copper and iron losses of the stator windings increases significantly. This ultimately leads to poor local heat dissipation capacity of the stator and improper flow matching of the cooling medium. Moreover, it can be subjected to sudden thermal shocks, which accelerate the aging of the stator insulation layer and even cause burnout failure.

[0004] In related technologies, the coolant is usually continuously injected downwards from the annulus of the bushing cable and then returned through the pump outlet, or a circulation loop is set up in the motor cavity, relying on the built-in impeller to drive the cooling oil self-circulation. However, these two methods not only cannot completely solve the above-mentioned technical problems, but may also create other threats, such as the formation of annular laminar flow isolation. That is, constant injection easily forms a stable boundary layer on the stator surface, resulting in a decrease in the local heat exchange coefficient. Furthermore, during periods of high gas-oil ratio, the cooling oil in the cavity may be replaced by gas, causing a sharp drop in flow rate, resulting in local dry spots and a rapid increase in the stator enamel film. Therefore, these methods cannot solve the above-mentioned technical problems. Summary of the Invention

[0005] This application provides a stator cooling device for a submersible pump and a submersible electric pump, which can solve the problems of poor local heat dissipation capacity of the stator and improper flow matching of the cooling medium caused by changes in the properties of the mixture, unstable motor power, and the spatial limitation of the gap between the stator and the bushing, without posing other threats.

[0006] In a first aspect, embodiments of this application provide a stator cooling device for a submersible electric pump, the stator cooling device comprising a switching valve group, an injection pump assembly, and a controller; the controller is communicatively connected to the switching valve group and the injection pump assembly, and the controller is used for:

[0007] Obtain the wellbore temperature gradient, production fluid water cut, motor power fluctuation curve, and annular space clearance size between the stator and casing of the target oil well;

[0008] Based on the wellbore temperature gradient, the produced fluid water cut, the motor power fluctuation curve, and the annular space clearance size between the stator and the casing, a composite cooling path adapted to the target oil well is determined; wherein, the composite cooling path includes annular injection cooling path and stator cavity recirculation cooling path;

[0009] During the continuous operation of the submersible electric pump, the dominant mode of the composite cooling path is alternately switched, and the temperature distribution, cooling medium temperature rise and pressure change values ​​of the stator under each composite cooling path are collected in real time.

[0010] The overheating data of the stator is identified based on the temperature distribution; wherein the overheating data is used to indicate the overheating region of the stator;

[0011] The cooling state and flow resistance of the composite cooling path are determined based on the temperature rise of the cooling medium and the pressure change.

[0012] Based on the overheating data, the cooling state, and the flow resistance, cooling parameter data is determined; wherein, the cooling parameter data is used to indicate the cooling medium flow rate, cooling medium temperature, and cooling path switching that need to be adjusted when cooling the stator.

[0013] The submersible electric pump stator cooling device provided in this application acquires the wellbore temperature gradient, produced fluid water cut, motor power fluctuation curve, and annular space clearance size between the stator and casing of the target oil well, providing accurate data support and laying the foundation for subsequent processing. Based on the wellbore temperature gradient, produced fluid water cut, motor power fluctuation curve, and annular space clearance size between the stator and casing, the controller determines a composite cooling path adapted to the target oil well. During continuous operation of the submersible electric pump, the dominant mode of the composite cooling path is alternately switched, and the temperature distribution and cooling medium of the stator under each composite cooling path are collected in real time. The temperature rise and pressure change values ​​can dynamically adjust the cooling path parameters according to the real-time operating status of the oil well, so as to achieve the optimal cooling effect under different production rates, well depths and geological conditions, with higher selectivity and more targeted approach. It identifies stator overheating data based on temperature distribution; determines the cooling state and flow resistance of the composite cooling path based on the temperature rise and pressure change values ​​of the cooling medium; and automatically adjusts the flow rate and velocity of the cooling medium based on the identified overheating data to keep the stator temperature within a safe range, effectively preventing equipment damage and performance degradation caused by overheating. Based on overheating data, cooling state and flow resistance, it determines cooling parameter data, which can solve problems such as poor local heat dissipation capacity of the stator and improper flow matching of the cooling medium caused by changes in the properties of the mixture, unstable motor power, and the spatial limitation of the gap between the stator and casing.

[0014] Secondly, embodiments of this application provide a submersible pump, including the submersible electric pump stator cooling device described in the first aspect above.

[0015] It is understandable that the beneficial effects of the second aspect mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a cross-sectional view of a submersible pump provided in one embodiment of this application;

[0018] Figure 2 This is a schematic diagram of the working process of the controller of the submersible electric pump stator cooling device provided in one embodiment of this application;

[0019] Figure 3 This is a schematic diagram of the implementation process of step S200 executed by the controller in the stator cooling device of a submersible electric pump provided in an embodiment of this application;

[0020] Figure 4 This is a schematic diagram of the implementation process of step S250 executed by the controller in the submersible electric pump stator cooling device provided in an embodiment of this application;

[0021] Figure 5 This is a schematic diagram of the implementation process of step S400 performed by the controller in the submersible electric pump stator cooling device provided in an embodiment of this application;

[0022] Figure 6 This is a schematic diagram of the implementation process of step S500 executed by the controller in the submersible electric pump stator cooling device provided in an embodiment of this application;

[0023] Figure 7 This is a schematic diagram of the cooling control system provided in an embodiment of this application;

[0024] Figure 8 This is a schematic diagram of the controller provided in the embodiments of this application. Detailed Implementation

[0025] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0026] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0027] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0028] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrases "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0029] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0030] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0031] A submersible pump (SMP) is a pump that is submerged inside an oil well to lift crude oil (or a liquid mixture) to the surface. An electric submersible pump (ESP) is a type of pump powered by electricity, with the pump body directly driven by a downhole motor. The downhole unit consists of the pump body, a protector, and the ESP connected coaxially in series from top to bottom. The ESP directly converts the electrical energy supplied from the surface into mechanical torque, which drives the pump impeller to rotate via a spline sleeve, thus lifting the crude oil. The stator core and windings of the ESP are integrally cast with epoxy resin to form the stator assembly, which is then press-fitted into the motor housing. Furthermore, the space between the stator cavity and the rotor is filled with motor oil, which lubricates the bearings and transfers heat.

[0032] However, due to the special working environment of submersible electric pumps and the continuous increase in well depth, the well temperature rises and the motor power increases. In addition, as the well depth increases, the properties of the oil, water and gas mixture downhole also change. Coupled with the interaction between the unstable motor power and the spatial limitation of the gap between the stator and the casing, the heat flux density caused by the copper and iron losses of the stator windings increases significantly. This ultimately leads to poor local heat dissipation capacity of the stator and improper flow matching of the cooling medium. Moreover, it can be subjected to sudden thermal shocks, which accelerate the aging of the stator insulation layer and even cause burnout failure.

[0033] In related technologies, the coolant is usually continuously injected downwards from the annulus of the bushing cable and then returned through the pump outlet, or a circulation loop is set up in the motor cavity, relying on the built-in impeller to drive the cooling oil self-circulation. However, these two methods not only cannot completely solve the above-mentioned technical problems, but may also create other threats, such as the formation of annular laminar flow isolation. That is, constant injection easily forms a stable boundary layer on the stator surface, resulting in a decrease in the local heat exchange coefficient. Furthermore, during periods of high gas-oil ratio, the cooling oil in the cavity may be replaced by gas, causing a sharp drop in flow rate, resulting in local dry spots and a rapid increase in the stator enamel film. Therefore, these methods cannot solve the above-mentioned technical problems.

[0034] To address the aforementioned issues, this application provides a submersible pump and a stator cooling device for an electric submersible pump. The controller of the electric submersible pump stator cooling device acquires the wellbore temperature gradient, produced fluid water cut, motor power fluctuation curve, and annular space clearance between the stator and casing of the target oil well, providing accurate data support and laying the foundation for subsequent processing. Based on the wellbore temperature gradient, produced fluid water cut, motor power fluctuation curve, and annular space clearance between the stator and casing, the controller determines a composite cooling path suitable for the target oil well. During continuous operation of the electric submersible pump, the dominant mode of the composite cooling path is alternately switched, and the temperature distribution and cooling medium of the stator under each composite cooling path are collected in real time. The temperature rise and pressure change values ​​can dynamically adjust the cooling path parameters according to the real-time operating status of the oil well, so as to achieve the optimal cooling effect under different production rates, well depths and geological conditions, with higher selectivity and more targeted approach. It identifies stator overheating data based on temperature distribution; determines the cooling state and flow resistance of the composite cooling path based on the temperature rise and pressure change values ​​of the cooling medium; and automatically adjusts the flow rate and velocity of the cooling medium based on the identified overheating data to keep the stator temperature within a safe range, effectively preventing equipment damage and performance degradation caused by overheating. Based on overheating data, cooling state and flow resistance, it determines cooling parameter data, which can solve problems such as poor local heat dissipation capacity of the stator and improper flow matching of the cooling medium caused by changes in the properties of the mixture, unstable motor power, and the spatial limitation of the gap between the stator and casing.

[0035] The stator cooling device for submersible electric pumps provided in this application embodiment can be applied to submersible pumps. This application embodiment does not impose any restrictions on the specific type of submersible pump.

[0036] In the downhole transportation of oil and gas extraction in this embodiment, the submersible pump, as the core power equipment, undertakes the critical task of transporting crude oil from the oil layer to the surface gathering and transportation pipeline network. This submersible pump (electric submersible pump) mainly includes a pump body, rotor assembly (including impeller and main shaft), stator assembly (including stator core and windings), sealing assembly, and cable connectors. The stator assembly, as the core power source of the submersible pump, continuously generates heat during operation due to copper losses from the energized windings and hysteresis losses in the core. If this heat cannot be dissipated in time, it will accelerate the aging of the stator winding insulation layer and may even cause short-circuit faults. Therefore, a submersible pump stator cooling device needs to be designed to ensure the long-term stable operation of the submersible pump.

[0037] For example, please refer to Figure 1 The stator cooling device of the submersible electric pump includes a switching valve assembly 10, an injection pump assembly 20, and a controller; it also includes a bearing 30, a ball valve, a housing 40, and a handwheel 50. The switching valve assembly 10 is fixed to the outer side of the middle section of the submersible pump body via a bracket. The injection pump assembly 20 is fixed to the outer side of the base at the lower end of the submersible pump body via a clamp-type bracket. The injection pump assembly 20 provides power and typically uses a small positive displacement pump, comprising a pump housing, drive / driven gears, drive shaft, bearings, and other mechanical parts. Its structural features include high pressure resistance (suitable for downhole pressures of 10-30 MPa) and low pulsation, ensuring stable injection of the cooling medium into the annulus. The switching valve assembly 10 consists of multiple sets of slide valves (or ball valves), forming a precision-fit structure between the valve core and valve sleeve. Axial movement or rotation of the valve core changes the flow path of the cooling medium (e.g., switching the annulus path). The valve assembly material is mostly corrosion-resistant alloy (such as 316L stainless steel) to ensure no clogging in sulfur-containing, high-mineralization environments. The controller can be an embedded DSP controller, a programmable logic controller, or a field-programmable gate array, but is not limited to these.

[0038] The annular injection cooling path, also known as the annular cooling channel, is formed by the annular gap between the outer surface of the stator and the inner wall of the casing. Its structural form (such as the gap width and axial guide grooves) is designed according to the wellbore dimensions. Additionally, some designs incorporate spiral guide ribs machined on the stator shell to guide the cooling medium to flow spirally along the stator axis, increasing the heat exchange area. The stator cavity return cooling path, also known as the stator cavity return channel, is primarily a cavity structure integrated within the stator body. It typically consists of a pre-reserved gap between the stator core and the windings, and a guide cavity within the end cover. Furthermore, some designs incorporate axial or radial flow channels machined inside the stator core, allowing the cooling medium to flow directly through the area of ​​most severe heat generation in the windings, and then return through the converging cavity of the end cover.

[0039] To better understand the submersible electric pump stator cooling device provided in the embodiments of this application, the specific working process of the submersible electric pump stator cooling device provided in the embodiments of this application will be described by way of example below.

[0040] Figure 2 This diagram illustrates the operation of the controller for the stator cooling device of the submersible electric pump provided in an embodiment of this application. The controller of the submersible electric pump stator cooling device is used to perform the following steps:

[0041] S100 obtains the wellbore temperature gradient, production fluid water cut, motor power fluctuation curve, and annular space clearance size between the stator and casing of the target oil well.

[0042] It can be understood that the wellbore temperature gradient is used to reflect the temperature increase per unit degree Celsius decrease along the well depth direction; the water cut of the produced fluid is used to reflect the volume ratio of water phase in the produced fluid; the motor power fluctuation curve is used to reflect the real-time power change of the submersible motor during operation; the annular space clearance size between the stator and the casing is used to reflect the geometric width of the annular cross-section through which the cooling medium can flow; among these, the wellbore temperature gradient reflects the longitudinal temperature distribution trend of the wellbore; the water cut of the produced fluid can affect the heat exchange efficiency of the cooling medium; the motor power fluctuation curve reflects the dynamic changes in load; and the annular space clearance size between the stator and the casing mainly determines the flow capacity of the annular cooling path.

[0043] For example, the wellbore temperature gradient can be obtained by placing a distributed temperature sensor at the wellhead and then processing it according to set requirements. These requirements could include setting a spatial resolution of 0.5 m and a temporal resolution of 10 s, continuously collecting data for 30 minutes, reading the temperature value every 0.5 m back to the host computer, subtracting the previous temperature from the next and dividing by 0.5 m to calculate the temperature rise per meter, and connecting these values ​​to form a depth temperature rise array. The product fluid water content can be obtained by installing a microwave water content meter with a 0–100% range at the outlet of the surface three-phase separator, and then processing it according to set requirements. These requirements could include setting sampling once per second, continuously recording for 20 minutes, and then calculating after removing the first 3 minutes of fluctuation from 1200 data points. The motor power fluctuation curve can be obtained by connecting a three-phase electrical parameter module to the inverter output, and then processing it according to set requirements to obtain a power-time array, which is the motor power fluctuation curve. These requirements could include setting sampling at 10 Hz and continuously collecting data for 5 minutes. The total number of points is 3000. The annular space clearance size can be obtained by importing the well structure diagram into modeling software (such as SolidWorks), subtracting the stator outer diameter from the inner diameter of the casing, and then dividing by 2. Then, the centralizer measurement report from the previous logging run is called up, and the measured clearances at the four axial positions are averaged to obtain the annular space clearance size.

[0044] The S200 controller determines a composite cooling path adapted to the target oil well based on the wellbore temperature gradient, the water cut of the produced fluid, the motor power fluctuation curve, and the annular space clearance size between the stator and the casing. The composite cooling path includes an annular injection cooling path and a stator cavity recirculation cooling path.

[0045] For example, by performing piecewise linear fitting on the wellbore temperature gradient, analyzing the water cut of the produced fluid, performing frequency domain analysis on the motor power fluctuation curve, and simulating the annular space clearance size between the stator and the casing, result data corresponding to the wellbore temperature gradient, the water cut of the produced fluid, the motor power fluctuation curve, and the annular space clearance size between the stator and the casing can be obtained. Then, a composite cooling path adapted to the target oil well can be obtained based on the result data.

[0046] In one possible implementation, please refer to Figure 3 S200, based on the wellbore temperature gradient, produced fluid water cut, motor power fluctuation curve, and the annular space clearance size between the stator and casing, determines a composite cooling path adapted to the target oil well, including:

[0047] S210, the temperature gradient curve is obtained by piecewise linear fitting of the wellbore temperature gradient; the temperature gradient curve is used to characterize the rate of temperature change at different depths.

[0048] It is understandable that piecewise linear fitting divides the entire wellbore depth into multiple intervals according to formation or temperature change characteristics, and uses a straight line to approximate the temperature gradient change within each interval; the temperature gradient curve is a continuous curve formed after fitting, which can show the difference in the rate of temperature change at different depths.

[0049] For example, the acquired temperature gradient data at each depth point is first divided into intervals. Taking the main formation interface of the oil well (such as the formation boundary at a depth of 200 meters and 500 meters) as the segment point, the wellbore is divided into three depth segments: 0-200 meters, 200-500 meters, and below 500 meters. Then, for each depth segment, the fitted linear equation is calculated with depth as the x-axis and temperature gradient as the y-axis (e.g., the fitted equation for the 0-200 meter segment is y=0.0005x+0.1, where x is the depth and y is the gradient). The fitted linear equations of the three segments are connected in order of depth to form a temperature gradient curve covering the entire wellbore. The y-axis of each point in the curve is the temperature change rate at the corresponding depth, i.e., the temperature gradient curve.

[0050] S220, the water content of the product liquid is analyzed to obtain a stable water content value; the stable water content value is used to indicate the value to eliminate the influence of instantaneous fluctuations on the selection of cooling path.

[0051] For example, the analysis of the product liquid water content can be performed by smoothing the collected water content data sequence using a moving average method, with the moving window size set to 10 data points (corresponding to 100 seconds). Starting from the 10th data point, the average value of each data point and the previous 9 data points is calculated sequentially (for example, the stable value of the 10th point is (the sum of data points 1-10) / 10, and the stable value of the 11th point is (the sum of data points 2-11) / 10, resulting in 351 smoothed intermediate values. The overall average of these 351 intermediate values ​​is then taken to obtain the final stable water content value (for example, 65.2%), which is the representative value after eliminating instantaneous fluctuations.

[0052] S230, frequency domain analysis is performed on the motor power fluctuation curve to obtain the power fluctuation main frequency; whereby the power fluctuation main frequency is used to reflect the dynamic change characteristics of the motor load.

[0053] For example, the motor power fluctuation curve is converted into standard time series data, and then frequency domain conversion is performed to generate a frequency amplitude spectrum. The horizontal axis of the spectrum is frequency, and the vertical axis is amplitude. The spectrum is scanned to find the frequency value corresponding to the maximum amplitude value. This frequency is the main frequency of motor power fluctuation, which means that the motor load fluctuates periodically every 20 seconds (1 / 0.05).

[0054] S240, the equivalent diameter of the annular space is obtained by simulating the size of the annular space clearance between the stator and the bushing; the equivalent diameter of the annular space is used to calculate the flow resistance of the cooling medium.

[0055] For example, based on the annular clearance size data of each depth segment, the data is imported into fluid dynamics simulation software. The equivalent diameter is calculated using the rule of dividing the flow cross-sectional area by 4 times the wetted perimeter. First, the flow cross-sectional area of ​​the annulus at that depth is calculated based on each set of circumferential clearance values ​​(for example, it can be calculated using the formula for irregular annular area) and the wetted perimeter (the sum of the contact perimeters of the inner and outer walls of the annulus). Then, the equivalent diameter of a single set is calculated by substituting it into the formula. The arithmetic mean of the equivalent diameters of all depth segments is taken to obtain the equivalent diameter of the annulus.

[0056] S250 determines a composite cooling path adapted to the target oil well conditions based on the temperature gradient curve, water cut stability value, power fluctuation frequency, and annular equivalent diameter.

[0057] For example, the four parameters are first classified into levels, and then combined and judged according to the preset decision logic. The judgment results are integrated to clarify the start-up timing, duty cycle, and other parameters of the two paths, forming the final composite cooling path scheme. Among them, the preset decision logic can be that if the annular equivalent diameter is large, the temperature gradient is high, the water content is medium, and the main frequency is low, then the annular injection path is determined to be dominant (accounting for 70%), and the stator cavity return path is auxiliary (accounting for 30%); if the annular equivalent diameter is small and the main frequency is high, then the stator cavity return path is dominant (accounting for 60%), and the annular path is auxiliary (accounting for 40%).

[0058] This configuration, through multi-parameter collaborative decision-making, avoids the one-sidedness of single-parameter judgment, enabling the composite cooling path to match the wellbore temperature distribution, adapt to medium characteristics and load fluctuations, and take into account the annular flow capacity, thereby improving the adaptability and effectiveness of the cooling scheme.

[0059] In one possible implementation, please refer to Figure 4 S250, based on the temperature gradient curve, water cut stability value, power fluctuation frequency, and annular equivalent diameter, determines a composite cooling path adapted to the target oil well conditions, including:

[0060] S251, a cooling path matrix is ​​constructed based on the temperature gradient curve, the stable value of water content, the main frequency of power fluctuation, and the equivalent diameter of the annulus. Among them, the row vectors correspond to the annular injection cooling path and the stator cavity recirculation cooling path, respectively, and the column vectors correspond to the temperature gradient curve, the stable value of water content, the main frequency of power fluctuation, and the equivalent diameter of the annulus, respectively.

[0061] For example, the matrix can be constructed by creating a 2x4 two-dimensional matrix in the controller's data processing module, and then defining the row vectors: the first row is the annular injection cooling path, and the second row is the stator cavity recirculation cooling path; the column vectors are: the first column is the temperature gradient curve characteristic value (taking the maximum value of the curve, 0.28℃ / m), the second column is the water content stability value (65.2%), the third column is the power fluctuation frequency (0.05Hz), and the fourth column is the annular equivalent diameter (92mm). Each cell is filled with the path's adaptation coefficient for the parameters (set based on historical data, for example, the adaptation coefficient for the annular path to the large equivalent diameter is 0.9, and for the cavity path it is 0.6; the adaptation coefficient for the annular path to the high frequency is 0.4, and for the cavity path it is 0.8), to finally form the matrix.

[0062] S252, calculate the weights of each column vector to obtain the environmental parameter weight vector; where the environmental parameter weight vector is the degree of influence of the parameter on the cooling effect.

[0063] For example, the weights can be calculated using the analytic hierarchy process (AHP). First, a judgment matrix is ​​constructed, and the four parameters—temperature gradient curve, stable water content, dominant power fluctuation frequency, and equivalent annular diameter—are compared pairwise. Appropriate scores are assigned based on their importance to the cooling effect. For instance, the temperature gradient curve has a greater impact on the cooling effect and can be assigned a higher score when compared with the stable water content. Then, the largest eigenvalue of the judgment matrix and its corresponding eigenvector are calculated. Processing the eigenvector yields the environmental parameter weight vector, where each element represents the weight of the temperature gradient curve, stable water content, dominant power fluctuation frequency, and equivalent annular diameter on the cooling effect. The environmental parameter weight vector is an ordered set of all parameter weights.

[0064] S253, the annular equivalent diameter and the environmental parameter weight vector are weighted and summed, and the dominant cooling path is obtained according to the conflict resolution rule. The conflict resolution rule is that if the annular equivalent diameter is greater than or equal to the critical value, the annular injection cooling path is preferentially determined as the dominant cooling path; if the annular equivalent diameter is less than the critical value, the stator cavity recirculation cooling path is preferentially determined as the dominant cooling path.

[0065] For example, a critical value for the equivalent diameter of the annulus is preset, the adaptation coefficient and weight vector in the matrix are retrieved, the weighted score of the two paths is calculated, and then the conflict resolution rule is triggered by determining whether the actual value of the equivalent diameter of the annulus triggers the conflict resolution rule, so as to ultimately determine whether the recirculation cooling path in the stator cavity is the dominant cooling path or the recirculation cooling path in the stator cavity is determined to be the dominant cooling path.

[0066] S254 dynamically adjusts the dominant cooling path and the remaining paths to obtain a composite cooling path; the dynamic adjustment is achieved by dynamically adjusting the duty cycle of each path through power fluctuations and the main frequency.

[0067] It is understandable that dynamic adjustment is to change the opening ratio of both in real time according to the fluctuation of motor load, so that the cooling intensity is synchronized with the load change.

[0068] For example, an initial duty cycle is first set, with the dominant path occupying 70% and the remaining path occupying 30%. That is, every 10 minutes, the cavity path is open for 7 minutes and the annular path is open for 3 minutes. The power fluctuation frequency is retrieved to be 0.05Hz (period of 20 seconds), which is judged as a low-frequency fluctuation. The correspondence between the frequency and the duty cycle adjustment coefficient is set, with the adjustment coefficient for low frequency (≤0.1Hz) being 1.0 and the adjustment coefficient for high frequency (>0.1Hz) being 1.2 (the auxiliary path proportion is increased by 20%, and since the current frequency is low, the initial duty cycle is maintained at the adjustment coefficient of 1.0). At the same time, the duty cycle is set to be updated every 5 minutes according to the latest frequency, forming a dynamic composite cooling path. The above is only an example and is not limited to the above implementation method.

[0069] This configuration allows the path duty cycle to be dynamically adjusted by the main frequency of power fluctuations, enabling the composite cooling path to adapt to changes in motor load in real time. This reduces the problem of insufficient cooling when the load increases or excessive cooling when the load decreases, thereby improving the energy efficiency of the submersible pump stator cooling device.

[0070] In one possible implementation, S254 dynamically adjusts the dominant cooling path and the remaining paths to obtain a composite cooling path, including:

[0071] S2541, based on the power fluctuation main frequency, determines the power fluctuation energy coefficient under the current operating condition, and obtains the duty cycle correction coefficient; among which, the duty cycle correction coefficient is used to characterize the degree of influence of power fluctuation on cooling path switching.

[0072] For example, the duty cycle correction factor can be obtained by retrieving the main frequency and amplitude of the power fluctuation, multiplying the main frequency by the fluctuation amplitude according to the formula, and obtaining the energy factor. A pre-defined correspondence table between the energy factor and the correction factor is then used. For example, an energy factor ≤ 0.5 can be matched with a correction factor of 1.0; 0.5 < energy factor ≤ 1.0 can be matched with a correction factor of 1.1; and an energy factor greater than 1.0 can be matched with a correction factor of 1.2. Thus, the duty cycle correction factor can be obtained.

[0073] S2542, based on the duty cycle correction coefficient, analyzes the initial duty cycle of the dominant cooling path and the remaining paths to obtain the real-time path duty cycle sequence; the real-time path duty cycle sequence is used to characterize the opening ratio of each cooling path at different times.

[0074] For example, given an initial duty cycle, the dominant path has a duty cycle of 70%, the remaining path has a duty cycle correction factor of 1.1. The adjustment rule is set as follows: the auxiliary path duty cycle equals the initial duty cycle multiplied by the correction factor, and the dominant path duty cycle equals 1 minus the auxiliary path duty cycle. The adjusted duty cycle is calculated as follows: auxiliary path = 30% × 1.1 = 33%, dominant path = 1 - 33% = 67%. Then, by setting the data update cycle to 5 minutes, a real-time duty cycle sequence is generated for 2 hours: 0-5 minutes (67% / 33%), 5-10 minutes (67% / 33%), 10-15 minutes (due to the main frequency changing to 0.06Hz, energy coefficient 0.9, correction factor 1.1, maintaining 67% / 33%)... a total of 24 time points of duty cycle data to form a real-time path duty cycle sequence.

[0075] S2543 compares the real-time path duty cycle sequence with the preset minimum switching time threshold. When the adjacent switching time is greater than or equal to the minimum switching time threshold, it directly outputs a composite cooling path.

[0076] For example, a preset minimum switching time threshold of 3 minutes can be set. Adjacent switching time points in the real-time path duty cycle sequence can be extracted. For instance, the switching intervals of minutes 0-5, 5-10, 10-15, etc., are all 5 minutes, all greater than the preset threshold of 3 minutes. Therefore, the sequence is directly determined to meet the switching time requirement, and the entire real-time path duty cycle sequence is output as the activation timing parameter for the composite cooling path. If there are adjacent switching times less than the threshold, such as minutes 8-10 (interval of 2 minutes) being less than 3 minutes in a certain sequence, this time period needs to be merged. Minutes 8-10 and 5-8 are merged into 5-10 minutes, the duty cycle is recalculated, and a new sequence is formed. This process continues until all adjacent switching times meet the threshold requirement, and finally, the adjusted composite cooling path is output.

[0077] During continuous operation of the submersible electric pump, the S300 alternately switches between the dominant modes of the composite cooling path and collects the stator temperature distribution, cooling medium temperature rise, and pressure change values ​​under each composite cooling path in real time.

[0078] For example, during the operation of the submersible electric pump, the dominant mode of the composite cooling path is alternately switched according to a preset switching cycle (e.g., every 30 minutes), i.e., switching from annular injection cooling path to stator cavity recirculation cooling path, or vice versa. In each dominant mode, temperature distribution data of the stator is collected in real time by temperature sensors installed at different depths of the stator (e.g., a thermocouple is placed every 50 meters); simultaneously, temperature rise and pressure change values ​​of the cooling medium are collected by thermometers and pressure gauges installed at the inlet and outlet of the cooling medium, respectively. The collected data is uploaded to the ground monitoring system in real time via a wireless transmission module. The ground monitoring system stores and analyzes the uploaded data, generating temperature distribution curves, temperature rise change curves, and pressure fluctuation curves, providing data support for subsequent optimization of the cooling path.

[0079] S400 identifies stator overheating data based on temperature distribution; the overheating data is used to indicate the overheated areas of the stator.

[0080] It is understandable that overheating data refers to information about areas where the temperature exceeds the material's limit, including location, temperature value, area, etc., which is used to locate potential thermal damage sites.

[0081] For example, the collected stator temperature distribution data is organized into a position temperature correspondence table. The thermal limit threshold of the stator insulation material (Class B) is preset to 130 degrees. The measuring points in the temperature table that exceed 130 degrees are identified, such as the second point in the axial direction (135 degrees) and the third point in the circumferential direction (132 degrees). The location (300 meters in axial depth, 270 degrees in circumferential angle, etc.), temperature value, and temperature difference with adjacent measuring points are marked, thereby generating overheating data.

[0082] In one possible implementation, please refer to Figure 5 S400 identifies stator overheating data based on temperature distribution, including:

[0083] S410, the temperature distribution is meshed to obtain the axial and circumferential temperature matrices of the stator; wherein, the temperature matrix is ​​used to characterize the temperature value of each micro-element region on the surface of the stator.

[0084] It can be understood that grid mapping divides the stator surface into regular small regions (grids), and the temperature matrix is ​​grid temperature data arranged in the axial and circumferential directions, which can intuitively show the two-dimensional distribution characteristics of temperature.

[0085] For example, the stator is divided into multiple (X) grids along the axial direction and multiple (Y) grids along the circumference direction, forming an X×Y two-dimensional grid (with XY micro-regions). Temperature values ​​at the center of each grid are then collected, with the axial direction as rows and the circumference as columns, and all grid temperature values ​​are filled into a two-dimensional matrix to obtain the axial and circumferential temperature matrices of the stator. For instance, the stator is divided into 20 grids along the axial direction and 8 grids along the circumference direction (each grid is 45°, totaling 360°), forming a 20×8 two-dimensional grid (160 micro-regions). Temperature values ​​at the center of each grid are then collected (if some grids do not have direct measurement points, interpolation between adjacent measurement points can be used for calculation). For example, the temperature of the 5th grid along the axial direction and the 2nd grid along the circumference direction is 128°C, and the temperature of the 6th grid along the axial direction and the 3rd grid along the circumference direction is 135°C. All grid temperature values ​​are then filled into a two-dimensional matrix with the axial direction as rows and the circumference as columns to obtain the axial and circumferential temperature matrices of the stator.

[0086] S420 compares the temperature matrix with the preset stator material thermal limit threshold matrix point by point to obtain the overheating risk matrix; wherein, the thermal limit threshold matrix is ​​dynamically updated according to the stator insulation material grade and aging curve.

[0087] It is understandable that the overheating risk matrix is ​​a matrix of risk labels formed after comparison, which can be used to show the risk distribution.

[0088] For example, the stator insulation material is Class B with an initial thermal limit of 130℃. The equipment has been running for 5000 hours. According to the aging curve (the threshold decreases by 2℃ for every 1000 hours of operation), the current threshold is 130-(5000 / 1000)×2=120℃. A 20×8 threshold matrix is ​​constructed (all grids have a threshold of 120℃). The temperature matrix and the threshold matrix are compared grid by grid. If a grid value in the temperature matrix is ​​greater than the corresponding grid value in the threshold matrix, it is marked as "1" (overheating risk); otherwise, it is marked as "0" (no risk). For example, if the temperature of the axial grids 5-7 and the circumferential grids 2-4 are both greater than 120℃, the corresponding positions are marked as "1", and the rest are marked as "0" to form an overheating risk matrix.

[0089] S430 performs connected component analysis on the overheating risk matrix to extract continuous overheating regions; where continuous overheating regions are used to indicate overheating clusters whose temperatures exceed the threshold and are spatially adjacent.

[0090] For example, continuous overheating regions are concentrated overheating clusters, which can distinguish between localized concentrated overheating and isolated overheating points. For instance, an eight-neighbor connected component labeling algorithm (i.e., adjacent grids in the vertical, horizontal, and diagonal directions of a certain grid are considered connected) is used to scan the overheating risk matrix and identify two connected components. Connected component 1 consists of the 5th-6th grid in the axial direction and the 2nd-3rd grid in the circumferential direction (a total of 4 grids, all labeled "1" and adjacent); connected component 2 consists of the 7th grid in the axial direction and the 4th grid in the circumferential direction (1 grid, with no adjacent "1" values, which can be considered an isolated point). By excluding isolated points, connected component 1 is extracted as the continuous overheating region to mark its boundary range.

[0091] S440 calculates the superheating characteristic parameters of each continuous overheated region; among which, the superheating characteristic parameters include the region peak temperature, the maximum temperature gradient, the region area percentage, and the temperature rise rate.

[0092] For example, calculating the overheating characteristic parameters of each continuous overheated region can be done by determining the peak temperature of the region, calculating the maximum temperature gradient, determining the region area percentage, and determining the temperature rise rate, thus obtaining the overheating characteristic parameters. Specifically, the peak temperature of the region can be determined by examining the temperature values ​​of the four grids within connected domain 1 (128℃, 132℃, 135℃, 130℃) and taking the maximum value of 135℃. The maximum temperature gradient can be calculated as the ratio of the temperature difference between adjacent grids to their distance (grid side length 5cm). For example, the gradient between the 135℃ and 128℃ grids is (135-128) / 0.05 = 140℃ / meter, and the maximum value of all gradients, 140℃ / meter, is taken. The region area percentage can be calculated as follows: connected domain 1 contains 4 grids, and the stator has a total of 160 grids; the percentage is 4 / 160 × 100% = 2.5%. The temperature rise rate can be calculated by comparing the average temperature of the area 10 minutes ago (125℃) with the current average temperature (131.25℃). The temperature rise rate is calculated as (131.25-125) / 10 = 0.625℃ / minute.

[0093] S450 determines superheat data based on regional peak temperature, maximum temperature gradient, regional area percentage, and temperature rise rate.

[0094] For example, determining overheating data can be achieved by organizing basic information on continuous overheating areas, assessing risk levels according to calculated characteristic parameters and preset rules, and finally generating overheating data. The preset rules for assessing risk levels include, for example, a peak temperature greater than 130℃ and a temperature rise rate greater than 0.5℃ / minute being classified as medium risk. The final overheating data could be defined as follows: a continuous overheating area exists in the stator axial direction (25-35cm) and circumferential direction (45-135°), with a peak temperature of 135℃, a temperature gradient of 140℃ / meter, an area ratio of 2.5%, and a temperature rise rate of 0.625℃ / minute, with a risk level of medium.

[0095] This setup allows for a more intuitive display of the location, severity, and risk level of overheated areas, providing an accurate basis for subsequent targeted cooling measures. Detailed analysis of the overheating data enables rapid identification of areas in the stator at risk of overheating, determining the severity and potential development trend of the overheating. For example, if a continuous overheating zone is found to have a persistently rising peak temperature and a large rate of temperature increase, timely measures can be taken, such as adjusting the dominant cooling path mode or increasing the flow rate of the cooling medium, to prevent stator damage due to overheating and ensure the stable operation of the submersible pump.

[0096] In one possible implementation, after identifying the stator overheating data based on the temperature distribution, the process includes:

[0097] S401, based on the distribution location of the overheated area on the stator, distinguishes between end overheating mode, middle overheating mode and uniform overheating mode.

[0098] For example, the distribution of overheated areas on the stator can be determined by first dividing the stator structure into regions, such as 10% of the length at each end of the axial direction as the end and 80% in the middle as the middle. The location of the overheated areas is then examined. For instance, if a continuous overheated area is located in the 0-10cm or 90-100cm range and its area percentage is greater than 60%, it is determined to be an end overheating mode; if it is located in the 10-90cm range and its area percentage is greater than 60%, it is determined to be a middle overheating mode; if it is distributed in both the end and middle ranges and the area percentage difference between each region is ≤10%, it is determined to be a uniform overheating mode. Currently, the overheated area is located in the 25-35cm range and its area percentage is 100%, thus it is determined to be a middle overheating mode.

[0099] In one possible implementation, S401 distinguishes between end overheating mode, middle overheating mode, and uniform overheating mode, including:

[0100] S4011, for end overheating mode, marks the relative distance between the overheated area and the motor junction box or bearing location.

[0101] For example, for the end-heating mode, the specific axial positions of the motor junction box and bearing in the stator are determined, such as the junction box being located at 0-5 cm axially and the bearing at 95-100 cm axially. The relative distance values ​​can be calculated by measuring the axial distance between the center point of the continuous overheating zone and these critical components. For example, if the center of the overheating zone is 30 cm from the junction box and 5 cm from the bearing, it is ultimately marked as 30 cm from the junction box / 5 cm from the bearing. If the overheating zone covers multiple critical components, the minimum distance to each component is marked separately, forming a complete description of the relative positions.

[0102] S4012 calculates the overlap between the overheated area and the axial position with the highest stator core temperature for the central overheating mode.

[0103] For example, for the central overheating mode, the axial position of the highest stator core temperature is determined. This can be located by recording temperature peaks in historical operating data or the highest temperature point in real-time monitoring data. For instance, if the highest temperature is recorded at 50 cm axially in the stator core, this position is used as a reference point. Next, the overlap between the continuous overheating region and this reference point is calculated. Specifically, this can be done by measuring the axial distance between the boundary of the overheating region and the reference point, and assessing the extent to which the overheating region covers the reference point. If the overheating region completely encompasses the reference point, the overlap is 100%; if it partially encompasses it, the overlap is calculated based on the proportion of inclusion, for example, if it includes 50%, the overlap is 50%.

[0104] S4013 records the temperature distribution uniformity index of the overheated area along the entire length of the stator for the uniform overheating mode.

[0105] For example, for a uniform overheating mode, the total length of the stator is determined and divided into multiple equal-length measurement segments along the axial direction. For instance, if the total stator length is 100cm, it can be divided into 10 equal-length 10cm measurement segments. One or more representative points are selected within each measurement segment for temperature measurement, obtaining the temperature values ​​for each segment. The standard deviation or coefficient of variation of all measurement segment temperature values ​​is calculated as an indicator of temperature distribution uniformity. A smaller standard deviation or lower coefficient of variation indicates a more uniform temperature distribution; conversely, a larger standard deviation or higher coefficient of variation indicates a greater variation in temperature distribution. For example, if the calculated standard deviation is 2℃ and the coefficient of variation relative to the average temperature is 5%, the temperature distribution can be considered relatively uniform. Furthermore, the uniformity of temperature distribution can be demonstrated by plotting a temperature distribution curve along the axial direction.

[0106] This setup, by employing differentiated analysis methods for different overheating modes, allows for more precise identification of the root cause of overheating. For end-stage overheating modes, the relative distance between the marker and key components can quickly determine whether it is caused by poor contact in the junction box or heat generated by bearing friction; for mid-stage overheating modes, calculating the overlap with the high-temperature zone of the core can identify whether it is caused by localized core losses; for uniform overheating modes, recording the temperature distribution uniformity index can distinguish whether it is caused by a decrease in the overall efficiency of the submersible pump stator cooling system or by abnormal load distribution. This stratified analysis strategy not only improves the efficiency of overheating diagnosis but also provides data support for the subsequent development of targeted cooling solutions.

[0107] S500 determines the cooling state and flow resistance of the composite cooling path based on the temperature rise and pressure change of the cooling medium.

[0108] For example, a time-series difference analysis is performed on the temperature rise of the cooling medium to obtain the temperature rise rate per unit time. The cooling efficiency level is determined based on the temperature rise rate. The pressure change value is frequency-domain filtered to extract the steady-state pressure drop component value. The cooling state and flow resistance of the composite cooling path are determined based on the cooling efficiency level and the steady-state pressure drop component value.

[0109] In one possible implementation, please refer to Figure 6 S500 determines the cooling state and flow resistance of the composite cooling path based on the temperature rise and pressure change of the cooling medium, including:

[0110] S510, performs time-series difference analysis on the temperature rise of the cooling medium to obtain the temperature rise rate per unit time; whereby the temperature rise rate is used to characterize the heat absorption intensity of the cooling medium.

[0111] For example, by collecting the temperature values ​​of the cooling medium at different time points, calculating the temperature difference between adjacent time points, and dividing by the time interval, the temperature rise rate per unit time is obtained. For instance, if the temperature is T1 at time t1 and T2 at time t2, and t2-t1=Δt, then the temperature rise rate v=(T2-T1) / Δt. If the temperature of the cooling medium rises from 30℃ to 35℃ within 10 minutes, then the temperature rise rate is (35-30) / 10=0.5℃ / minute. This rate reflects the cooling medium's ability to absorb heat per unit time. A higher temperature rise rate indicates stronger heat absorption by the cooling medium, which may mean a greater stator heat dissipation demand or insufficient cooling medium flow.

[0112] S520 compares the rate of temperature rise per unit time with a preset heat absorption efficiency threshold range to obtain a cooling efficiency level; the cooling efficiency level is used to quantify the heat dissipation capacity of the path.

[0113] For example, the preset heat absorption efficiency threshold range can be set according to the equipment operating requirements and the characteristics of the cooling medium, such as dividing it into a low-efficiency zone (v < 0.3℃ / min), a medium-efficiency zone (0.3 ≤ v < 0.7℃ / min), and a high-efficiency zone (v ≥ 0.7℃ / min). The calculated temperature rise rate is compared with the threshold range, for example, by checking each range one by one to determine which range the temperature rise rate falls into. If the temperature rise rate is 0.5℃ / min, it is determined to be in the medium-efficiency zone, corresponding to a cooling efficiency level of two. This level reflects the heat dissipation capacity of the composite cooling path under the current operating conditions.

[0114] S530 performs frequency domain filtering on the pressure change value to extract the steady-state pressure drop component value; the steady-state pressure drop component value is used to indicate the value to eliminate the influence of pulsation interference.

[0115] For example, based on the pressure change value sequence, the time domain data is converted to the frequency domain using a fast Fourier transform. Then, by identifying and filtering high-frequency components and retaining low-frequency components, the filtered frequency domain data is converted back to the time domain to obtain a smooth pressure sequence. The average value of this sequence is then calculated as the steady-state pressure drop component value to obtain the steady-state pressure drop component value.

[0116] S540 determines the cooling state and flow resistance of the composite cooling path based on the cooling efficiency level and steady-state pressure drop component.

[0117] For example, the process of determining the cooling state and flow resistance of a composite cooling path based on the cooling efficiency level and steady-state pressure drop component can be comprehensively evaluated using pre-defined judgment rules. For instance, when the cooling efficiency level is level two (medium efficiency zone) and the steady-state pressure drop component is within the range of 0.2-0.5 MPa, the cooling state is determined to be "partially effective," and the flow resistance is "medium." If the cooling efficiency level is level one (low efficiency zone) and the steady-state pressure drop component exceeds 0.5 MPa, the cooling state is determined to be "inefficient," and the flow resistance is "high." In practice, a two-dimensional matrix of cooling efficiency level and steady-state pressure drop component can be established, and the final state can be determined through cross-comparison. For example, if the cooling efficiency level is level two (temperature rise rate 0.5℃ / min) and the steady-state pressure drop component is 0.3 MPa, then according to the matrix rules, the cooling state is determined to be "partially effective," and the flow resistance is "medium," indicating that the current cooling path can meet some heat dissipation requirements, but the flow resistance has already limited the cooling effect.

[0118] This setup allows for a comprehensive evaluation of cooling performance. By combining heat dissipation and resistance factors, and using a simple rule base, the system can quickly identify abnormal states, facilitating timely intervention. The resistance value directly uses filtered data to ensure accuracy, avoid redundant calculations, and improve efficiency.

[0119] S600 determines cooling parameter data based on overheating data, cooling status, and flow resistance; the cooling parameter data is used to indicate the cooling medium flow rate, cooling medium temperature, and cooling path switching that need to be adjusted when cooling the stator.

[0120] For example, when determining cooling parameter data based on overheating data, cooling status, and flow resistance, the severity of stator overheating is judged according to the risk level and overheating characteristic parameters in the overheating data. For instance, if the overheating data shows that the stator has a moderate risk and a high temperature rise rate, the cooling parameters should be adjusted first to suppress the temperature rise. The heat dissipation capacity of the current cooling path is determined by combining the cooling status assessment results (e.g., "partially effective" or "inefficient"). If the cooling status is "inefficient," the cooling effect needs to be enhanced, and the flow resistance (e.g., "medium" or "high") is used to determine whether the flow of the cooling medium is obstructed. If the flow resistance is "high," the cooling path needs to be optimized or the medium flow rate increased. In practice, a rule base for the association of overheating data, cooling status, and flow resistance can be established. For example, when the overheating data is of medium risk and the temperature rise rate is greater than 0.5℃ / min, and the cooling status is "partially effective" and the flow resistance is "medium," the rule base can recommend increasing the cooling medium flow rate by 20% and switching the cooling path, etc., but is not limited to this.

[0121] This configuration can solve the problems of poor local heat dissipation capacity of the stator and improper flow matching of the cooling medium caused by changes in the properties of the mixture, unstable motor power, and the spatial limitation of the gap between the stator and the bushing.

[0122] In one possible implementation, S600 determines cooling parameter data based on superheat data, cooling conditions, and flow resistance, including:

[0123] S610 determines the overheating feature vector based on the overheating data and the cooling performance vector based on the cooling state; wherein, the overheating feature vector is used to quantify the degree of stator overheating risk, and the cooling performance vector is used to characterize the heat dissipation capacity and flow resistance characteristics of the path.

[0124] For example, constructing the overheating feature vector can be achieved by calculating the average overheating value, calculating the overheating rate, recording the overheating duration, and then arranging the data in the order of average overheating value, overheating rate, and overheating duration. For instance, calculating the average overheating value can be done by taking overheating data from three measuring points on the stator (4℃, 3.8℃, 4.2℃) and obtaining an average value of 4℃. Calculating the overheating rate can be done by comparing the overheating value of 2℃ 10 minutes ago with an increase of (4-2)℃ ÷ 10min = 0.2℃ / min. Recording the overheating duration can be done from when the temperature exceeds the safe temperature until now, a period of 8 minutes. Arranging the data in the order of average overheating value, overheating rate, and overheating duration yields the overheating feature vector [4, 0.2, 8]. Constructing the cooling performance vector can be achieved by using a cooling efficiency level of 1 and a steady-state pressure drop of 0.9MPa, and arranging the data in the order of cooling efficiency level and steady-state pressure drop to obtain the cooling performance vector [1, 0.9].

[0125] S620 inputs the overheating feature vector and cooling performance vector into the cooling parameter prediction model to obtain the initial cooling parameter set; wherein, the cooling parameter prediction model is used to establish the nonlinear mapping relationship between overheating, cooling state and cooling parameters.

[0126] For example, the cooling parameter prediction model can be constructed using a neural network algorithm, which is trained with a large amount of historical data to obtain the mapping relationship between overheating characteristics, cooling performance, and cooling parameters. For instance, the overheating feature vector [4, 0.2, 8] and the cooling performance vector [1, 0.9] are input into the trained model, and the model outputs an initial cooling parameter set through nonlinear transformation of the hidden layer, which includes the suggested value of cooling medium flow rate, temperature adjustment value, and cooling path switching instruction. When establishing a cooling parameter prediction model, historical operating data is collected and preprocessed as training samples. The data should cover, but is not limited to, overheating characteristics under different operating conditions (e.g., average superheat value, overheating rate, overheating duration), cooling performance indicators (e.g., cooling efficiency level, steady-state pressure drop component), and corresponding actual cooling parameters (e.g., cooling medium flow rate, temperature adjustment value, cooling path switching command). Data preprocessing includes missing value imputation, outlier removal, and standardization, such as converting temperature values ​​to Celsius and normalizing flow rate values ​​to the 0-1 range. The model architecture can employ a multilayer perceptron or a long short-term memory network. The model architecture handles static feature mapping, while the long short-term memory network captures temporal dependencies. The input layer receives the concatenation of the overheating feature vector and the cooling performance vector. The hidden layer introduces nonlinearity through the ReLU activation function, and the output layer outputs the cooling parameter set. During training, mean squared error is used as the loss function, weights are adjusted using the backpropagation algorithm, and early stopping is employed to prevent overfitting. During the validation phase, the dataset needs to be divided into training, validation, and test sets, for example, in a 7:1:2 ratio. Model performance is monitored on the validation set, and training is terminated when the validation loss does not decrease after five consecutive epochs. Final test set evaluation shows that the model's predicted cooling medium flow rate has an average error within ±5% of the actual value, the temperature adjustment error does not exceed ±1℃, and the accuracy of cooling path switching commands reaches 92%, indicating that the model can effectively establish a nonlinear mapping relationship between overheating, cooling states, and cooling parameters.

[0127] S630 performs multi-objective optimization on the initial cooling parameter set to obtain the optimal cooling parameter combination; among which, the multi-objective optimization aims to minimize the risk of overheating, maximize the cooling efficiency, and minimize the flow resistance.

[0128] For example, obtaining the optimal cooling parameter combination can be achieved by using an initial set of cooling parameters (e.g., flow rate 200 L / min, temperature 25 °C, path A) as the initial population, defining three optimization objective functions: an overheating risk minimization function (based on the temperature rise rate predicted by the overheating feature vector), a cooling efficiency maximization function (based on the heat dissipation capacity score based on the cooling performance vector), and a flow resistance minimization function (based on the resistance coefficient based on the steady-state pressure drop). Offspring are generated through crossover (e.g., single-point crossover to generate new flow rates of 190 L / min and 210 L / min) and mutation (e.g., random perturbation of temperature value ±1 °C), and better individuals are selected. For example, in a certain generation of the population, parameter combination 1 (flow rate 180 L / min, temperature 24℃, path B) is better than combination 2 (flow rate 220 L / min, temperature 26℃, path A) in terms of overheating risk, but the flow resistance is higher. After multiple iterations, the optimal solution set is finally obtained, which includes the optimal combination such as flow rate 195 L / min, temperature 24.5℃, and path B. This combination is verified in the test set to reduce overheating risk by 18%, improve cooling efficiency by 12%, and reduce flow resistance by 9%, thus meeting the requirements of multi-objective optimization.

[0129] S640 performs engineering mapping of the optimal combination of cooling parameters to generate cooling parameter data.

[0130] For example, when engineering-mapping the optimal cooling parameter combination, the actual hardware parameters and operational constraints of the submersible electric pump stator are considered. For instance, when the cooling medium flow rate in the optimal parameter combination is 195 L / min, it is verified whether the maximum output capacity of the current submersible electric pump stator cooling device meets this flow rate requirement. If the pump's rated flow rate is 200 L / min, it can be directly mapped; if the pump's maximum flow rate is only 180 L / min, the parameters need to be adjusted to the pump's maximum capacity boundary (e.g., flow rate 180 L / min), and the balance between overheating risk and cooling efficiency needs to be reassessed. For a temperature adjustment value of 24.5℃, the accuracy range of the cooling medium temperature control system is checked. If the system's adjustable accuracy is ±0.5℃, it is mapped to an executable range of 24.5℃ ±0.5℃; if the system only supports integer temperature adjustment, it needs to be rounded to 25℃, and the impact of this adjustment on cooling efficiency (e.g., efficiency may decrease by 2%) needs to be explained. For the cooling path switching command, the physical structure of the submersible electric pump stator is used to confirm whether the path can be switched. If the path cannot be used due to mechanical limitations, the suboptimal path must be selected, and the multi-objective optimization model must be run again to verify whether the parameter combination under the path still meets the optimization objective. The final generated cooling parameter data should include executable flow rate values ​​(e.g., 180L / min), temperature values ​​(e.g., 25℃), and path identifiers (e.g., path C).

[0131] This configuration, through engineering mapping, transforms theoretically calculated optimal parameters into practically operable cooling parameter data. This ensures the cooling solution aligns with the equipment's hardware capabilities while effectively addressing the risk of stator overheating. For example, if the flow rate in the optimal parameters exceeds the pump's rated capacity, the system automatically adjusts to the pump's maximum output flow rate and simultaneously recalculates the adjusted overheating risk and cooling efficiency, preventing cooling failure due to unexecutable parameters. Furthermore, to address the precision limitations of temperature regulation values, interval mapping ensures that temperature control commands match the actual hardware precision. Additionally, for cooling path switching commands, the system performs feasibility verification based on the physical structure of the submersible pump stator. If the primary path is unusable due to mechanical limitations, a secondary path is automatically selected, and the parameter combination is re-optimized. This ensures that the cooling path switching still meets multi-objective optimization requirements, improving the practicality and reliability of cooling parameter data. This avoids the disconnect between theoretical models and actual hardware, providing a more stable and efficient cooling guarantee for the submersible pump stator.

[0132] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0133] Corresponding to the submersible electric pump stator cooling device described in the above embodiments, this application also provides a cooling control system, the various modules of which can realize the various steps executed by the controller of the submersible electric pump stator cooling device. Figure 7 A structural block diagram of the cooling control system provided in an embodiment of this application is shown. For ease of explanation, only the parts related to the embodiment of this application are shown.

[0134] Reference Figure 7 The cooling control system includes:

[0135] The acquisition module is used to acquire the wellbore temperature gradient, production fluid water cut, motor power fluctuation curve, and annular space clearance size between the stator and casing of the target oil well.

[0136] The first determining module is used to determine a composite cooling path adapted to the target oil well based on the wellbore temperature gradient, the water cut of the produced fluid, the motor power fluctuation curve, and the annular space clearance size between the stator and the casing; wherein, the composite cooling path includes an annular injection cooling path and a stator cavity recirculation cooling path;

[0137] The processing module is used to alternately switch the dominant mode of the composite cooling path during the continuous operation of the submersible electric pump, and to collect the temperature distribution, cooling medium temperature rise and pressure change values ​​of the stator under each composite cooling path in real time.

[0138] The identification module is used to identify the overheating data of the stator based on the temperature distribution; wherein, the overheating data is used to indicate the overheating area of ​​the stator;

[0139] The second determining module is used to determine the cooling state and flow resistance of the composite cooling path based on the temperature rise and pressure change values ​​of the cooling medium.

[0140] The results module is used to determine cooling parameter data based on overheating data, cooling status, and flow resistance; the cooling parameter data is used to indicate the cooling medium flow rate, cooling medium temperature, and cooling path switching that need to be adjusted when cooling the stator.

[0141] It should be noted that the information interaction and execution process between the above-mentioned devices / modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0142] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0143] Figure 8 This is a schematic diagram of the controller provided in one embodiment of this application. Figure 8 As shown, the controller 6 in this embodiment includes: at least one processor 60 ( Figure 8 Only one is shown in the image), at least one memory 61 ( Figure 8 (Only one is shown in the image) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60, wherein when the processor 60 executes the computer program 62, it causes the controller 6 to perform the steps in the embodiments of the steps performed by the controller of any of the above-described submersible electric pump stator cooling devices, or causes the controller 6 to perform the functions of each module / unit in the above-described system embodiments.

[0144] For example, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 62 in the controller 6.

[0145] The controller may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 8 The example shown is merely of controller 6 and does not constitute a limitation on controller 6. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0146] The processor 60 can be a Central Processing Unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0147] In some embodiments, the memory 61 may be an internal storage unit of the controller 6, such as a hard disk or memory of the controller 6. In other embodiments, the memory 61 may be an external storage device of the controller 6, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the controller 6. Furthermore, the memory 61 may include both internal storage units and external storage devices of the controller 6. The memory 61 is used to store operating systems, applications, bootloaders, data, and other programs, such as the program code of computer programs. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0148] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0149] This application provides a computer program product that, when run on a submersible pump, causes the submersible pump to perform the steps in any of the above method embodiments.

[0150] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-described embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to the submersible pump, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, such as a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk.

[0151] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0152] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0153] In the embodiments provided in this application, it should be understood that the disclosed cooling control system, submersible pump, and submersible electric pump stator cooling device can be implemented in other ways. For example, the cooling control system and submersible pump embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0154] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0155] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application 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 of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A stator cooling device for a submersible electric pump, characterized in that, The submersible electric pump stator cooling device includes a switching valve group, an injection pump assembly, and a controller; the controller is communicatively connected to the switching valve group and the injection pump assembly, and the controller is used for: Obtain the wellbore temperature gradient, production fluid water cut, motor power fluctuation curve, and annular space clearance size between the stator and casing of the target oil well; Based on the wellbore temperature gradient, the produced fluid water cut, the motor power fluctuation curve, and the annular space clearance size between the stator and the casing, a composite cooling path adapted to the target oil well is determined; wherein, the composite cooling path includes annular injection cooling path and stator cavity recirculation cooling path; During the continuous operation of the submersible electric pump, the dominant mode of the composite cooling path is alternately switched, and the temperature distribution, cooling medium temperature rise and pressure change values ​​of the stator under each composite cooling path are collected in real time. The overheating data of the stator is identified based on the temperature distribution; wherein the overheating data is used to indicate the overheating region of the stator; The cooling state and flow resistance of the composite cooling path are determined based on the temperature rise of the cooling medium and the pressure change. Based on the overheating data, the cooling state, and the flow resistance, cooling parameter data is determined; wherein, the cooling parameter data is used to indicate the cooling medium flow rate, cooling medium temperature, and cooling path switching that need to be adjusted when cooling the stator; The step of determining a composite cooling path adapted to the target oil well based on the wellbore temperature gradient, the produced fluid water cut, the motor power fluctuation curve, and the annular space clearance size between the stator and casing includes: A piecewise linear fit is performed on the temperature gradient of the wellbore to obtain a temperature gradient curve; wherein, the temperature gradient curve is used to characterize the rate of temperature change at different depths; The water content of the product liquid is analyzed to obtain a stable water content value; wherein, the stable water content value is used to indicate the value for eliminating the influence of instantaneous fluctuations on the selection of cooling path; Frequency domain analysis is performed on the motor power fluctuation curve to obtain the dominant frequency of power fluctuation; wherein, the dominant frequency of power fluctuation is used to reflect the dynamic change characteristics of motor load; The equivalent diameter of the annular space is obtained by simulating the size of the annular space clearance between the stator and the sleeve; wherein, the equivalent diameter of the annular space is used to calculate the flow resistance of the cooling medium; The composite cooling path adapted to the target oil well conditions is determined based on the temperature gradient curve, water cut stability value, power fluctuation frequency, and annular equivalent diameter. The determination of the composite cooling path adapted to the target oil well conditions based on the temperature gradient curve, water cut stability value, power fluctuation frequency, and annular equivalent diameter includes: A cooling path matrix is ​​constructed based on the temperature gradient curve, the stable water content value, the dominant power fluctuation frequency, and the equivalent diameter of the annulus. The row vectors correspond to the annular injection cooling path and the stator cavity recirculation cooling path, respectively, and the column vectors correspond to the temperature gradient curve, the stable water content value, the dominant power fluctuation frequency, and the equivalent diameter of the annulus, respectively. The weights of each column vector are calculated to obtain the environmental parameter weight vector; wherein, the environmental parameter weight vector represents the degree of influence of the parameter on the cooling effect; The annular equivalent diameter and the environmental parameter weight vector are weighted and summed, and the dominant cooling path is obtained by analyzing according to the conflict resolution rules. The conflict resolution rules are as follows: if the annular equivalent diameter is greater than or equal to a critical value, the annular injection cooling path is preferentially determined as the dominant cooling path; if the annular equivalent diameter is less than the critical value, the stator cavity recirculation cooling path is preferentially determined as the dominant cooling path. The composite cooling path is obtained by dynamically adjusting the dominant cooling path and the remaining paths; wherein, the dynamic adjustment is achieved by dynamically adjusting the duty cycle of each path through power fluctuation frequency. The step of dynamically adjusting the dominant cooling path and the remaining paths to obtain the composite cooling path includes: Based on the power fluctuation frequency, the power fluctuation energy coefficient under the current operating condition is determined, and the duty cycle correction coefficient is obtained; wherein, the duty cycle correction coefficient is used to characterize the degree of influence of power fluctuation on cooling path switching; Based on the duty cycle correction coefficient, the initial duty cycles of the dominant cooling path and the remaining paths are analyzed to obtain a real-time path duty cycle sequence; the real-time path duty cycle sequence is used to characterize the activation ratio of each cooling path at different times. The real-time path duty cycle sequence is compared with a preset minimum switching time threshold. If the adjacent switching time is greater than or equal to the minimum switching time threshold, the composite cooling path is directly output.

2. The submersible electric pump stator cooling device as described in claim 1, characterized in that, The step of identifying the stator overheat data based on the temperature distribution includes: The temperature distribution is meshed to obtain the axial and circumferential temperature matrices of the stator; wherein the temperature matrix is ​​used to characterize the temperature value of each micro-element region on the surface of the stator; The temperature matrix is ​​compared point by point with the preset thermal limit threshold matrix of the stator material to obtain the overheating risk matrix; wherein, the thermal limit threshold matrix is ​​dynamically updated according to the stator insulation material grade and aging curve. Connectivity analysis is performed on the overheating risk matrix to extract continuous overheating regions; wherein, the continuous overheating regions are used to indicate overheating clusters whose temperatures exceed a threshold and are spatially adjacent. Calculate the overheating characteristic parameters of each of the continuous overheated regions; wherein, the overheating characteristic parameters include the region peak temperature, the maximum temperature gradient, the region area percentage, and the temperature rise rate. The overheating data is determined based on the peak temperature of the region, the maximum temperature gradient, the area ratio of the region, and the rate of temperature rise.

3. The submersible electric pump stator cooling device as described in claim 1, characterized in that, After identifying the stator overheating data based on the temperature distribution, the process includes: Based on the distribution location of the overheated area on the stator, the end overheating mode, the middle overheating mode, and the uniform overheating mode are distinguished.

4. The submersible electric pump stator cooling device as described in claim 3, characterized in that, Differentiate between end overheating mode, middle overheating mode, and uniform overheating mode, including: For the end overheating mode, mark the relative distance between the overheated area and the motor junction box or bearing location; For the overheating mode in the middle, calculate the degree of overlap between the overheated area and the axial position where the stator core temperature is highest; For the uniform overheating mode, the temperature distribution uniformity index of the overheated region over the entire length of the stator is recorded.

5. The submersible electric pump stator cooling device as described in claim 1, characterized in that, Determining the cooling state and flow resistance of the composite cooling path based on the temperature rise of the cooling medium and the pressure change includes: A time-series difference analysis is performed on the temperature rise of the cooling medium to obtain the temperature rise rate per unit time; wherein, the temperature rise rate is used to characterize the heat absorption intensity of the cooling medium. The cooling efficiency level is obtained by comparing the temperature rise rate per unit time with a preset heat absorption efficiency threshold range; wherein, the cooling efficiency level is used to quantify the heat dissipation capacity of the path. The pressure change value is frequency domain filtered to extract the steady-state pressure drop component value; wherein, the steady-state pressure drop component value is used to indicate the value to eliminate the influence of pulsation interference; The cooling state and flow resistance of the composite cooling path are determined based on the cooling efficiency level and the steady-state pressure drop component.

6. The submersible electric pump stator cooling device as described in claim 1, characterized in that, The determination of cooling parameter data based on the superheat data, the cooling state, and the flow resistance includes: An overheating feature vector is determined based on the overheating data, and a cooling performance vector is determined based on the cooling state; wherein, the overheating feature vector is used to quantify the degree of stator overheating risk, and the cooling performance vector is used to characterize the heat dissipation capacity and flow resistance characteristics of the path; The overheating feature vector and cooling performance vector are input into the cooling parameter prediction model to obtain an initial cooling parameter set; wherein, the cooling parameter prediction model is used to establish a nonlinear mapping relationship between overheating, cooling state and cooling parameters; The initial cooling parameter set is subjected to multi-objective optimization to obtain the optimal cooling parameter combination; wherein, the multi-objective optimization aims to minimize the overheating risk, maximize the cooling efficiency, and minimize the flow resistance. The optimal combination of cooling parameters is engineered and mapped to generate the cooling parameter data.

7. A submersible pump, characterized in that, Includes the submersible electric pump stator cooling device as described in any one of claims 1 to 6.

Images