Method and device for determining ground indicator diagram of oil pumping unit

Abstract

The invention discloses a method and a device for determining a ground indicator diagram of an oil pumping unit. The method comprises the steps that to-be-determined electrical parameter data are obtained, and the electrical parameter data comprise power of a motor of a target oil pumping unit at multiple time points; a machine learning model is adopted to convert the to-be-determined electrical parameter data, and load values corresponding to multiple suspension point displacements of the target oil pumping unit are obtained; and drawing a ground indicator diagram of the target oil pumping unit according to the load values corresponding to the multiple suspension point displacements of the target oil pumping unit, wherein the ground indicator diagram is used for representing a relation curve graph between the suspension point displacements of the oil pumping unit and the load values of the oil pumping unit. The technical problem that the cost of obtaining the ground indicator diagram is high due to the fact that a sensor needs to be added to obtain data in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for determining a surface work diagram of an oil pumping unit. Background Art

[0002] The dynamometer diagram of the pumping unit consists of the displacement of the suspension point and the load, which is used to reflect the working conditions of the pumping unit well rod, pipe, and pump, and then analyze the working conditions of the oil well and calculate the daily liquid production and system efficiency of the oil well. With the development of digital oil fields, most oil fields use sensors (dynamometers) to measure the displacement and load of the suspension point, and collect the dynamometer data periodically through wireless sensor communication technology. However, the above method has the following disadvantages: First, the sensor obtains energy through the charging mode, and the maintenance is poor under long-term working conditions; second, the sensor requires operators to calibrate regularly, which is time-consuming and laborious; third, the load drift of the sensor will cause data inaccuracy during long-term work. In the related art, a method is proposed to establish a corresponding physical model by associating the suspension point load with the electrical parameter data to obtain the physical calculation formula of the dynamometer load, but it requires accurate physical parameters such as the weight of the balance block, the position of the balance block, the mechanical transmission ratio, and the transmission efficiency. Each parameter is difficult to quantify accurately and is greatly affected by the working conditions. Another method is to derive an empirical formula based on the measured electrical parameter data and dynamometer data of each well. Then, the load data is calculated from the current data according to the empirical formula, the upper and lower stroke dead points are determined by the position switch, the stroke displacement is evenly distributed to the two stroke conversion points to obtain the displacement data, and finally the dynamometer diagram is obtained. However, it is necessary to install sensors to obtain the measured dynamometer diagram, and recalibrate when the working conditions change, which is time-consuming and laborious. In addition, the working conditions of the same well may also vary within a day, so the accuracy of this method is extremely unstable.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method and device for determining a surface power diagram of an oil pumping unit, so as to at least solve the technical problem in the related art that the cost of obtaining the surface power diagram is high due to the need to increase sensors to obtain data.

[0005] According to one aspect of an embodiment of the present application, a method for determining a surface power diagram of an oil pumping unit is provided, comprising: obtaining electrical parameter data to be determined, the electrical parameter data including the power of a motor of a target oil pumping unit at multiple time points; using a machine learning model to convert the electrical parameter data to be determined, and obtaining load values ​​corresponding to multiple suspension point displacements of the target oil pumping unit; and drawing a surface power diagram of the target oil pumping unit according to the load values ​​corresponding to the multiple suspension point displacements of the target oil pumping unit, the surface power diagram being used to represent a curve diagram showing the relationship between the suspension point displacements of the oil pumping unit and the load value of the oil pumping unit.

[0006] Optionally, the machine learning module is determined in the following manner, including: obtaining a plurality of power diagrams of the oil pumping units and ground work diagrams corresponding to the plurality of power diagrams, the power diagram being used to represent a relationship curve diagram between the motor power of the oil pumping unit and the suspension point displacement of the oil pumping unit, and the ground work diagram being used to represent a relationship curve diagram between the suspension point displacement of the oil pumping unit and the load value of the oil pumping unit; converting the relationship curve diagram between the motor power of the oil pumping unit and the suspension point displacement of the oil pumping unit into a relationship curve diagram between the motor power of the oil pumping unit and time; converting the relationship curve diagram between the motor power of the plurality of oil pumping units and time and the ground work diagrams corresponding to the plurality of power diagrams Figure 1 One-to-one correspondence, a training set of the machine learning model is obtained; the machine learning model is trained using the training set of the machine learning model to obtain the machine learning model.

[0007] Optionally, the relationship curve graph between the motor power of the oil pumping unit and the suspension point displacement of the oil pumping unit is converted into a relationship curve graph between the motor power of the oil pumping unit and time, including: obtaining the suspension point displacements of multiple oil pumping units corresponding to multiple target time points; extracting the motor powers of multiple oil pumping units corresponding to the suspension point displacements of multiple oil pumping units from the relationship curve between the motor power of the oil pumping unit and the suspension point displacement of the oil pumping unit; and making a one-to-one correspondence between multiple target time points and the motor powers of multiple oil pumping units to obtain a relationship curve graph between the motor power of the oil pumping unit and time.

[0008] Optionally, multiple target time points are matched one-to-one with the motor powers of multiple oil pumps to obtain a relationship curve graph between the motor power of the oil pump and time, including: using time as the horizontal axis and the motor power as the vertical axis to construct a coordinate system corresponding to the relationship curve between the motor power of the oil pump and time, wherein the numerical range of the horizontal axis is a first interval, the numerical range of the vertical axis is a second interval, the minimum value of the first interval is zero, the maximum value of the first interval is a first preset value, the minimum value of the second interval is a second preset value, and the maximum value of the second interval is a third preset value; using multiple target time points as horizontal coordinates and multiple motor powers as vertical coordinates in turn to determine multiple points in the relationship curve graph between the motor power of the oil pump and time; connecting multiple points in the relationship curve graph between the motor power of the oil pump and time in turn to construct a relationship curve graph between the motor power of the oil pump and time.

[0009] Optionally, the suspension point displacements of multiple oil pumping units corresponding to multiple target time points are obtained, including: determining the suspension point displacement corresponding to a stroke of the oil pumping unit's piston as the amplitude of the simple harmonic motion formula; determining the stroke frequency of the oil pumping unit's piston as the frequency, and determining the angular frequency of the simple harmonic motion formula based on the frequency; determining the initial phase of the simple harmonic motion formula to be zero, so as to determine the suspension point displacements of multiple oil pumping units corresponding to multiple target time points.

[0010] Optionally, after obtaining the relationship curve graph between the motor power of the oil pump and time, the method also includes: determining the grayscale value of each pixel point in the relationship curve graph between the motor power of the oil pump and time; determining the grayscale pixel matrix of the relationship curve graph between the motor power of the oil pump and time according to the grayscale value of each pixel point in the relationship curve graph between the motor power of the oil pump and time.

[0011] Optionally, after a predetermined conversion model is obtained by training the conversion model using the conversion model training set, the method further includes: comparing the surface performance diagram of the oil pumping unit predicted by the machine learning model with the surface performance diagram of the oil pumping unit obtained by actual measurement to obtain an evaluation result; and optimizing the machine learning model according to the evaluation result until the numerical value corresponding to the evaluation result is lower than a preset evaluation value.

[0012] According to another aspect of an embodiment of the present application, a device for determining a surface power diagram of an oil pumping unit is also provided, including: a receiving module, used to obtain electrical parameter data to be determined, the electrical parameter data including the power of the motor of the target oil pumping unit at multiple time points; a conversion module, used to convert the electrical parameter data to be determined using a machine learning model to obtain load values ​​corresponding to multiple suspension point displacements of the target oil pumping unit; a drawing module, used to draw a surface power diagram of the target oil pumping unit according to the load values ​​corresponding to the multiple suspension point displacements of the target oil pumping unit, the surface power diagram being used to represent a curve diagram of the relationship between the suspension point displacements of the oil pumping unit and the load value of the oil pumping unit.

[0013] According to another aspect of the embodiment of the present application, a computer device is also provided, including: a memory for storing program instructions; a processor, connected to the memory, for executing the program instructions of the following functions: obtaining electrical parameter data to be determined, the electrical parameter data including the power of the motor of the target oil pump at multiple time points; using a machine learning model to convert the electrical parameter data to be determined, and obtaining load values ​​corresponding to multiple suspension point displacements of the target oil pump; drawing a surface power diagram of the target oil pump according to the load values ​​corresponding to the multiple suspension point displacements of the target oil pump, the surface power diagram being used to represent a curve diagram of the relationship between the suspension point displacement of the oil pump and the load value of the oil pump.

[0014] According to another aspect of the embodiment of the present application, a non-volatile storage medium is also provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the above-mentioned method for determining the surface work diagram of the oil pump by running the computer program.

[0015] In an embodiment of the present application, the electrical parameter data to be determined is obtained, and the electrical parameter data includes the power of the motor of the target oil pump at multiple time points; the electrical parameter data to be determined is converted by a machine learning model to obtain the load values ​​corresponding to the multiple suspension point displacements of the target oil pump; the ground power diagram of the target oil pump is drawn according to the load values ​​corresponding to the multiple suspension point displacements of the target oil pump, and the ground power diagram is used to represent the relationship between the suspension point displacement of the oil pump and the load value of the oil pump. The electrical parameter data is converted by a pre-trained machine learning model to obtain the load values ​​corresponding to the multiple suspension point displacements, and then the ground power diagram is drawn, thereby achieving the purpose of avoiding the addition of sensor equipment, thereby realizing the technical effect of reducing the cost of obtaining the ground power diagram, and thus solving the technical problem in the related art that the cost of obtaining the ground power diagram is high due to the need to increase sensors to obtain data. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 It is a hardware structure block diagram of a computer terminal for implementing a method for determining a surface work diagram of an oil pumping unit according to an embodiment of the present application;

[0018] Figure 2 It is a flow chart of a method for determining a surface work diagram of an oil pumping unit of the present application;

[0019] Figure 3 It is a schematic diagram of a power diagram of an oil pumping unit in an embodiment of the present application and a schematic diagram of a ground power diagram corresponding to the power diagram;

[0020] Figure 4 is a time power curve diagram according to an embodiment of the present application;

[0021] Figure 5 is a schematic diagram of a process of converting time power data into a grayscale image pixel matrix according to an embodiment of the present application;

[0022] Figure 6 is a flow chart of another method for determining a surface work diagram of an oil pumping unit according to an embodiment of the present application;

[0023] Figure 7 It is a schematic diagram comparing the ground power diagram predicted by the machine learning model according to the embodiment of the present application and the measured power diagram;

[0024] Figure 8 It is a structural schematic diagram of a device for determining a surface work diagram of an oil pump according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] The method for determining the surface performance diagram of the oil pumping unit provided in the embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal for implementing a method for determining a surface power diagram of an oil pumping unit is shown. Figure 1 As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, and a BUS bus. A person skilled in the art can understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0028] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0029] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for determining the surface power diagram of the oil pumping unit in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned method for determining the surface power diagram of the oil pumping unit is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0030] The transmission module 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission module 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0031] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0032] It should be noted that, in some optional embodiments, the above Figure 1 The computer device shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. It should be noted that Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computer device described above.

[0033] Under the above-mentioned operating environment, an embodiment of the present application provides an embodiment of a method for determining a surface power diagram of an oil pump. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] Figure 2 is a flow chart of a method for determining a surface work diagram of an oil pumping unit according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0035] Step S202, obtaining electrical parameter data to be determined, the electrical parameter data including the power of the motor of the target oil pumping unit at multiple time points;

[0036] Figure 3 A power diagram of an oil pump and a ground power diagram corresponding to the power diagram are shown, such as 3. Figure 3 The right side of the figure is the power diagram of the oil pump. Figure 3 The left side of the figure is the ground power diagram corresponding to the power diagram of the oil pump.

[0037] The power maps corresponding to ground power maps with different shape characteristics also have different characteristics. Therefore, there is a potential correlation between the power map and the ground power map. Through the powerful fitting learning ability of the neural network and a large amount of data training, a mapping relationship model between the two can be found.

[0038] Step S204, using a machine learning model to convert the electrical parameter data to be determined, to obtain load values ​​corresponding to the displacements of multiple suspension points of the target pumping unit;

[0039] Step S206, drawing a surface work diagram of the target pumping unit according to the load values ​​corresponding to the multiple suspension point displacements of the target pumping unit, the surface work diagram is used to represent a curve diagram of the relationship between the suspension point displacement of the pumping unit and the load value of the pumping unit.

[0040] Through the method for determining the surface power diagram of the oil pumping unit in the above-mentioned steps S202 to S206, the electrical parameter data to be determined is obtained, and the electrical parameter data includes the power of the motor of the target oil pumping unit at multiple time points; the electrical parameter data to be determined is converted by a machine learning model to obtain the load values ​​corresponding to the multiple suspension point displacements of the target oil pumping unit; the surface power diagram of the target oil pumping unit is drawn according to the load values ​​corresponding to the multiple suspension point displacements of the target oil pumping unit, and the surface power diagram is used to represent the relationship curve diagram between the suspension point displacement of the oil pumping unit and the load value of the oil pumping unit. The electrical parameter data is converted by a pre-trained machine learning model to obtain the load values ​​corresponding to the multiple suspension point displacements, and then the surface power diagram is drawn, thereby achieving the purpose of avoiding the addition of sensor equipment, thereby achieving the technical effect of reducing the cost of obtaining the surface power diagram, and thus solving the technical problem of the high cost of obtaining the surface power diagram due to the need to increase sensors to obtain data in the related technology. The following is a detailed description.

[0041] In step S204 of the above-mentioned method for determining the ground power diagram of the oil pumping unit, the machine learning model can be trained in the following manner: obtain multiple power diagrams of the oil pumping units and the ground power diagrams corresponding to the multiple power diagrams, the power diagram is used to represent the relationship curve diagram between the motor power of the oil pumping unit and the suspension point displacement of the oil pumping unit, and the ground power diagram is used to represent the relationship curve diagram between the suspension point displacement of the oil pumping unit and the load value of the oil pumping unit; convert the relationship curve diagram between the motor power of the oil pumping unit and the suspension point displacement of the oil pumping unit into a relationship curve diagram between the motor power of the oil pumping unit and time; convert the relationship curve diagram between the motor power of multiple oil pumping units and time and the ground power diagrams corresponding to the multiple power diagrams. Figure 1 One-to-one correspondence, a training set of the machine learning model is obtained; the machine learning model is trained using the training set of the machine learning model to obtain the machine learning model.

[0042] In some embodiments of the present application, the process of converting the relationship curve graph between the motor power of the oil pumping unit and the suspension point displacement of the oil pumping unit into the relationship curve graph between the motor power of the oil pumping unit and time is as follows: obtain the suspension point displacements of multiple oil pumping units corresponding to multiple target time points; extract the motor powers of multiple oil pumping units corresponding to the suspension point displacements of multiple oil pumping units from the relationship curve between the motor power of the oil pumping unit and the suspension point displacement of the oil pumping unit; correspond multiple target time points to the motor powers of multiple oil pumping units one by one, and obtain the relationship curve graph between the motor power of the oil pumping unit and time.

[0043] In an optional manner, the interval between multiple target time points is 0.1 second.

[0044] The specific process of drawing the relationship curve graph between the motor power and time of the oil pump is as follows: using time as the horizontal axis and the motor power as the vertical axis to construct a coordinate system corresponding to the relationship curve between the motor power and time of the oil pump, wherein the numerical range of the horizontal axis is a first interval, the numerical range of the vertical axis is a second interval, the minimum value of the first interval is zero, the maximum value of the first interval is a first preset value, the minimum value of the second interval is a second preset value, and the maximum value of the second interval is a third preset value; using multiple target time points as horizontal coordinates and multiple motor powers as vertical coordinates in turn to determine multiple points in the relationship curve graph between the motor power and time of the oil pump; connecting multiple points in the relationship curve graph between the motor power and time of the oil pump in turn to construct the relationship curve graph between the motor power and time of the oil pump.

[0045] It should be noted that, considering that the stroke frequency of the current oil pump is between 0.8 times / minute and 5 times / minute, and the motor power is between -15kw and 15kw, the first preset value can be 80 seconds, the second preset value can be -15kw, and the third preset value can be 15kw. The pixel size of the drawn graph is consistent, for example: the pixel size of the graph can be set to 700*200.

[0046] Figure 4 A time power curve diagram is shown, such as Figure 4 As shown, the ordinate represents motor power and the abscissa represents time.

[0047] In actual application scenarios, one stroke of the pump will generate a ground work diagram A and a corresponding power diagram B. The power diagram B is converted into a time-power diagram C of time and power and then corresponds to the work diagram A, which is regarded as a set of training data (A, C).

[0048] There are many ways to obtain the suspension point displacements of multiple pumping units corresponding to multiple target time points. Since the upper and lower dead point speeds of the pumping unit in a stroke are zero, the suspension point motion of the pumping unit is simplified to simple harmonic motion. The suspension point displacement corresponding to each time point is calculated according to the law of simple harmonic motion, and then the motor power corresponding to each time point is determined. An optional method in the embodiment of the present application is: the suspension point displacement corresponding to the piston of the pumping unit completing a stroke is determined as the amplitude of the simple harmonic motion formula; the stroke frequency of the piston of the pumping unit is determined as the frequency, and the angular frequency of the simple harmonic motion formula is determined based on the frequency; the initial phase of the simple harmonic motion formula is determined to be zero to determine the suspension point displacements of multiple pumping units corresponding to multiple target time points, wherein the simple harmonic motion formula is as follows:

[0049]

[0050] In the formula, X represents the suspension point displacement, A represents the amplitude, and ω represents the angular frequency. Indicates the initial phase.

[0051] In some embodiments of the present application, after obtaining the relationship curve graph between the motor power and time of the oil pump, the grayscale value of each pixel point in the relationship curve graph between the motor power and time of the oil pump is determined; the grayscale pixel matrix of the relationship curve graph between the motor power and time of the oil pump is determined according to the grayscale value of each pixel point in the relationship curve graph between the motor power and time of the oil pump.

[0052] Figure 5 A schematic diagram of a process of converting time power data into a grayscale image pixel matrix is ​​shown, Figure 5 As shown, Figure 5 The left side of the figure is the power value data sequence, the middle is the time power curve, and the right side is the grayscale pixel matrix.

[0053] After the machine learning model is trained using the training set of the machine learning model, the surface power diagram of the oil pumping unit predicted by the machine learning model is compared with the surface power diagram of the oil pumping unit obtained by actual measurement to obtain an evaluation result; the machine learning model is optimized according to the evaluation result until the numerical value corresponding to the evaluation result is lower than the preset evaluation value.

[0054] Specifically, the evaluation result can be determined by the following formula:

[0055]

[0056] In the formula, is the measured dynamometer data, y i It is the predicted output data of the electrical parameter conversion to the ground dynamometer diagram.

[0057] It should be noted that the smaller the value of the evaluation result M, the better the performance of the machine learning model. In an optional manner, the preset evaluation value can be set to 3.5%.

[0058] In an optional way, the machine learning model is mainly composed of a convolutional neural network, a long short-term memory neural network and a fully connected layer. After the model is built, it is trained using a training data set to obtain the final electric parameter to ground power diagram model. Based on the powerful generalization and fitting capabilities of the deep learning algorithm, the model can learn the potential mapping relationship between the electric parameter data and the indicator diagram data from the electric parameter data. Even new sample data that has not been trained can obtain the corresponding indicator diagram data through the model. According to the trained electric parameter to ground power diagram model, the pixel matrix of the measured time power curve image is input into the model to obtain the output, which is the displacement load data corresponding to the ground power diagram.

[0059] Figure 6 A flow chart showing another method for determining a surface power diagram of an oil pumping unit is shown. Figure 6 As shown, including:

[0060] Step S601: Collecting power diagram data of several oil wells and corresponding ground power diagram data;

[0061] Step S602: Calculate the power data corresponding to each time point by the law of simple harmonic motion (the time interval between each data point is 0.1 seconds), and convert the displacement power diagram data into time power data;

[0062] Step S603: plotting the time power data into a grayscale image of uniform size, and obtaining pixel matrix values ​​of the image;

[0063] Step S604: The pixel matrix values ​​of the power curve image and the load and displacement data of the dynamometer diagram are matched one by one to construct a training data set;

[0064] Step S605: Build a neural network model and conduct training to obtain a trained deep learning model. Input a new measured power data image into the model to convert it into a corresponding power indicator diagram.

[0065] The machine learning model consists of two parts: the first part is the CNN model, which has the ability to extract image features. The grayscale image of the time power curve is input into the CNN network, and the feature data extracted by CNN is input into the second part of the LSTM network to capture the potential connection of the power diagram data in time. The final output is 400 data representing the displacement and load of the power diagram, the first 200 of which are displacement data, and the last 200 are load data. The specific input values, structural parameters and output value parameters of the entire model are shown in Table 1.

[0066] Table 1

[0067]

[0068] Figure 7 A schematic diagram showing the comparison between the ground power diagram (indicator diagram) predicted by the machine learning model and the measured indicator diagram.

[0069] Figure 8 is a schematic diagram of the structure of a device for determining a surface work diagram of an oil pumping unit according to an embodiment of the present application, such as Figure 8 As shown, the device comprises:

[0070] A receiving module 80 is used to obtain electrical parameter data to be determined, the electrical parameter data including the power of the motor of the target pumping unit at multiple time points;

[0071] A conversion module 82, used to convert the electrical parameter data to be determined using a machine learning model to obtain load values ​​corresponding to the displacements of multiple suspension points of the target pumping unit;

[0072] The drawing module 84 is used to draw a surface work diagram of the target pumping unit according to the load values ​​corresponding to the multiple suspension point displacements of the target pumping unit. The surface work diagram is used to represent a curve diagram showing the relationship between the suspension point displacement of the pumping unit and the load value of the pumping unit.

[0073] The conversion module 42 of the apparatus for determining the surface power diagram of the oil pumping unit includes: a training submodule for obtaining a plurality of power diagrams of the oil pumping unit and surface power diagrams corresponding to the plurality of power diagrams, wherein the power diagram is used to represent a relationship curve diagram between the motor power of the oil pumping unit and the suspension point displacement of the oil pumping unit, and the surface power diagram is used to represent a relationship curve diagram between the suspension point displacement of the oil pumping unit and the load value of the oil pumping unit; converting the relationship curve diagram between the motor power of the oil pumping unit and the suspension point displacement of the oil pumping unit into a relationship curve diagram between the motor power of the oil pumping unit and time; converting the relationship curve diagram between the motor power of the oil pumping unit and time and the surface power diagrams corresponding to the plurality of power diagrams into a relationship curve diagram between the motor power of the oil pumping unit and time; Figure 1 One-to-one correspondence, a training set of a machine learning model is obtained; the machine learning model is trained by using the training set of the machine learning model to obtain a machine learning model;

[0074] The training submodule includes: a conversion unit, which is used to obtain the suspension point displacements of multiple pumping units corresponding to multiple target time points; extract the motor powers of multiple pumping units corresponding to the suspension point displacements of multiple pumping units from the relationship curve between the motor power of the pumping units and the suspension point displacement of the pumping units; one-to-one correspondence between multiple target time points and the motor powers of multiple pumping units is obtained to obtain a relationship curve between the motor power of the pumping units and time;

[0075] The conversion unit includes: a drawing subunit, which is used to construct a coordinate system corresponding to the relationship curve between the motor power and time of the oil pumping unit by taking time as the horizontal axis and the motor power as the vertical axis, wherein the numerical range of the horizontal axis is a first interval, the numerical range of the vertical axis is a second interval, the minimum value of the first interval is zero, the maximum value of the first interval is a first preset value, the minimum value of the second interval is a second preset value, and the maximum value of the second interval is a third preset value; sequentially using multiple target time points as horizontal coordinates and multiple motor powers as vertical coordinates to determine multiple points in the relationship curve diagram between the motor power and time of the oil pumping unit; sequentially connecting multiple points in the relationship curve diagram between the motor power and time of the oil pumping unit to construct the relationship curve diagram between the motor power and time of the oil pumping unit;

[0076] The above-mentioned conversion unit also includes: an acquisition subunit, a grayscale subunit and an evaluation subunit. The acquisition subunit is used to determine the suspension point displacement corresponding to the completion of one stroke of the piston of the pumping unit as the amplitude of the simple harmonic motion formula; determine the stroke frequency of the piston of the pumping unit as the frequency, and determine the angular frequency of the simple harmonic motion formula based on the frequency; determine the initial phase of the simple harmonic motion formula as zero, so as to determine the suspension point displacements of multiple pumping units corresponding to multiple target time points;

[0077] A grayscale subunit is used to determine the grayscale value of each pixel in the relationship curve diagram between the motor power and time of the oil pump; determine the grayscale pixel matrix of the relationship curve diagram between the motor power and time of the oil pump according to the grayscale value of each pixel in the relationship curve diagram between the motor power and time of the oil pump;

[0078] The evaluation subunit is used to compare the surface power diagram of the oil pumping unit predicted by using a predetermined conversion model with the surface power diagram of the oil pumping unit obtained by actual measurement to obtain an evaluation result; and optimize the predetermined conversion model according to the evaluation result until the numerical value corresponding to the evaluation result is lower than the preset evaluation value.

[0079] It should be noted that Figure 8 The device for determining the surface power diagram of the oil pumping unit shown is used to perform Figure 2 A method for determining a surface power diagram of an oil pumping unit is shown, so the relevant explanations in the method for determining a surface power diagram of an oil pumping unit are also applicable to the device for determining a surface power diagram of this type of oil pumping unit, and will not be repeated here.

[0080] An embodiment of the present application also provides a computer device, including: a memory, for storing program instructions; a processor, connected to the memory, for executing the program instructions of the following functions: obtaining electrical parameter data to be determined, the electrical parameter data including the power of the motor of the target oil pump at multiple time points; using a machine learning model to convert the electrical parameter data to be determined, and obtaining load values ​​corresponding to multiple suspension point displacements of the target oil pump; drawing a surface power diagram of the target oil pump according to the load values ​​corresponding to the multiple suspension point displacements of the target oil pump, the surface power diagram being used to represent a curve diagram of the relationship between the suspension point displacement of the oil pump and the load value of the oil pump.

[0081] It should be noted that the above-mentioned computer equipment is used to execute Figure 2 The method for determining the surface work diagram of the oil pumping unit shown in the figure, therefore the relevant explanations in the above-mentioned virtual machine migration method are also applicable to the computer device and will not be repeated here.

[0082] An embodiment of the present application also provides a non-volatile storage medium, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the following method for determining a surface power diagram of an oil pump by running the computer program: obtaining electrical parameter data to be determined, the electrical parameter data including the power of a motor of a target oil pump at multiple time points; using a machine learning model to convert the electrical parameter data to be determined to obtain load values ​​corresponding to multiple suspension point displacements of the target oil pump; drawing a surface power diagram of the target oil pump according to the load values ​​corresponding to the multiple suspension point displacements of the target oil pump, the surface power diagram being used to represent a curve diagram of the relationship between the suspension point displacements of the oil pump and the load value of the oil pump.

[0083] It should be noted that the above non-volatile storage medium is used to execute Figure 2 The method for determining the surface power diagram of the oil pumping unit is shown, so the relevant explanations in the above-mentioned method for determining the surface power diagram of the oil pumping unit are also applicable to the non-volatile storage medium, and will not be repeated here.

[0084] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0085] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0086] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0087] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0088] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0089] If the integrated unit is implemented in the form of 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, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0090] The above are only preferred implementations of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining a surface performance diagram of an oil pumping unit, characterized in that: include: Acquiring electrical parameter data to be determined, the electrical parameter data including power of a motor of a target oil pumping unit at multiple time points; The electrical parameter data to be determined are converted using a machine learning model to obtain load values ​​corresponding to the displacements of multiple suspension points of the target pumping unit; A surface work diagram of the target pumping unit is drawn according to load values ​​corresponding to multiple suspension point displacements of the target pumping unit, and the surface work diagram is used to represent a curve diagram showing the relationship between the suspension point displacement of the pumping unit and the load value of the pumping unit.

2. The method according to claim 1, characterized in that The machine learning module is determined by: Acquire a plurality of power diagrams of the oil pumping units and ground work diagrams corresponding to the power diagrams of the oil pumping units, wherein the power diagram of the oil pumping unit is used to represent a curve diagram of the relationship between the motor power of the oil pumping unit and the suspension point displacement of the oil pumping unit, and the ground work diagram is used to represent a curve diagram of the relationship between the suspension point displacement of the oil pumping unit and the load value of the oil pumping unit; Converting the relationship curve diagram between the motor power of the oil pumping unit and the suspension point displacement of the oil pumping unit into a relationship curve diagram between the motor power of the oil pumping unit and time; The relationship curve graphs between the motor power and time of the plurality of pumping units are matched one by one with the ground power diagrams corresponding to the power diagrams of the plurality of pumping units to obtain a training set of the machine learning model; The machine learning model is obtained by training using the training set of the machine learning model.

3. The method according to claim 2, characterized in that Converting the relationship curve diagram between the motor power of the oil pumping unit and the suspension point displacement of the oil pumping unit into a relationship curve diagram between the motor power of the oil pumping unit and time includes: Obtaining the suspension point displacements of multiple pumping units corresponding to multiple target time points; Extracting the motor powers of the plurality of pumping units corresponding to the suspension point displacements of the plurality of pumping units from a relationship curve between the motor power of the pumping unit and the suspension point displacement of the pumping unit; The multiple target time points are matched one by one with the motor powers of the multiple oil pumping units, and a relationship curve diagram between the motor powers of the oil pumping units and time is obtained.

4. The method according to claim 3, characterized in that The plurality of target time points are matched one by one with the motor powers of the plurality of pumping units to obtain a relationship curve diagram between the motor powers of the pumping units and time, including: A coordinate system corresponding to a curve of a relationship between the motor power and time of the pumping unit is constructed by taking time as the horizontal axis and motor power as the vertical axis, wherein the numerical range of the horizontal axis is a first interval, the numerical range of the vertical axis is a second interval, the minimum value of the first interval is zero, the maximum value of the first interval is a first preset value, the minimum value of the second interval is a second preset value, and the maximum value of the second interval is a third preset value; sequentially using the multiple target time points as abscissas and the motor powers of the multiple pumping units as ordinates to determine multiple points in a curve diagram of a relationship between the motor powers of the pumping units and time; The plurality of points in the relationship curve diagram between the motor power and time of the oil pump are connected in sequence to construct the relationship curve diagram between the motor power and time of the oil pump.

5. The method according to claim 3, characterized in that: Obtaining the suspension point displacements of the plurality of pumping units corresponding to the plurality of target time points includes: The displacement of the suspension point corresponding to one stroke of the piston of the pumping unit is determined as the amplitude of the simple harmonic motion formula; Determine the stroke frequency of the piston of the pumping unit as the frequency, and determine the angular frequency of the simple harmonic motion formula based on the frequency; The initial phase of the simple harmonic motion formula is determined to be zero, so as to determine the suspension point displacements of the multiple pumping units corresponding to the multiple target time points.

6. The method according to claim 4, characterized in that After obtaining the relationship curve diagram between the motor power and time of the oil pump, the method further includes: Determine the gray value of each pixel in the relationship curve diagram between the motor power and time of the oil pumping unit; The grayscale pixel matrix of the relationship curve diagram between the motor power of the oil engine and time is determined according to the grayscale value of each pixel point in the relationship curve diagram between the motor power of the oil engine and time.

7. The method according to claim 1, characterized in that After converting the electrical parameter data to be determined by using a machine learning model to obtain load values ​​corresponding to the displacements of multiple suspension points of the target pumping unit, the method further includes: Comparing the surface power diagram of the oil pumping unit predicted by the machine learning model with the surface power diagram of the oil pumping unit obtained by actual measurement to obtain an evaluation result; The machine learning model is optimized according to the evaluation result until the numerical value corresponding to the evaluation result is lower than the preset evaluation value.

8. A device for determining a surface performance diagram of an oil pumping unit, characterized in that: include: A receiving module, used for acquiring electrical parameter data to be determined, wherein the electrical parameter data includes the power of the motor of the target oil pump at multiple time points; A conversion module, used to convert the electrical parameter data to be determined by using a machine learning model to obtain load values ​​corresponding to the displacements of multiple suspension points of the target oil pumping unit; A drawing module is used to draw a surface work diagram of the target pumping unit according to the load values ​​corresponding to the multiple suspension point displacements of the target pumping unit, and the surface work diagram is used to represent a curve diagram of the relationship between the suspension point displacement of the pumping unit and the load value of the pumping unit.

9. A computer device, characterized in that: include: A memory for storing program instructions; A processor is connected to the memory and is used to execute program instructions for the following functions: obtaining electrical parameter data to be determined, the electrical parameter data including the power of the motor of the target oil pump at multiple time points; using a machine learning model to convert the electrical parameter data to be determined to obtain load values ​​corresponding to multiple suspension point displacements of the target oil pump; and drawing a surface power diagram of the target oil pump according to the load values ​​corresponding to the multiple suspension point displacements of the target oil pump, wherein the surface power diagram is used to represent a curve diagram showing the relationship between the suspension point displacement of the oil pump and the load value of the oil pump.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the method for determining the surface performance diagram of the oil pumping unit according to any one of claims 1 to 7 by running the computer program.

Images