A method and system for intelligent intermittent operation of oil pumping wells

Abstract

This invention discloses a method and system for intelligent intermittent operation of pumping unit wells. The method includes the following steps: calculating the operating frequency control parameters for pumping unit shutdown using the stroke sampling method and the relative deviation method, and setting the well oil pressure for pumping unit startup; obtaining the influencing factors of the pumping unit's operating frequency; constructing a pumping unit operating frequency prediction model, building a dataset based on the influencing factors, and using the trained model to obtain predicted values ​​of the pumping unit's operating frequency control parameters; and controlling the pumping unit to intelligently intermittently operate based on the operating frequency control parameters for pumping unit shutdown, the well oil pressure for pumping unit startup, and the predicted values ​​of the operating frequency control parameters. This invention overcomes the problem of inaccurate pumping unit well startup and shutdown timing and avoids situations where the pumping capacity of the pumping unit exceeds the actual fluid supply capacity of the well, leading to poor pump efficiency, wasted energy, and damage to motor equipment.

Description

Technical Field

[0001] This invention relates to the field of intelligent control of oil pumping units, and specifically to an intelligent intermittent method and system for oil pumping unit wells. Background Technology

[0002] Traditional oil pumping wells often operate continuously, which, while ensuring sustained crude oil production, can lead to energy waste and accelerated equipment wear. To overcome these issues, intelligent intermittent operation methods and systems for oil pumping wells have emerged. This method integrates advanced sensors, controllers, and communication technologies to achieve real-time monitoring and intelligent control of the oil pumping well's operating status. Based on the well's actual production conditions and geological parameters, the intelligent intermittent operation system can automatically adjust the pumping unit's operating parameters and operating time to achieve optimal extraction results and energy efficiency.

[0003] Existing intelligent intermittent switching methods for oil wells use a threshold set during the downstroke to shut down the pumping unit via a controller. Specifically, when dry pumping occurs, the actual current drops below this threshold, triggering the shutdown. Furthermore, existing methods detect dry pumping by monitoring the average motor current and identifying its decrease, thus shutting down the pumping unit accordingly. However, the actual motor current is significantly affected by the pumping unit's counterweight, making a simple criterion insufficient for accurate well-start / stop timing. Moreover, if the pumping unit operates at a fixed frequency, its pumping capacity may exceed the well's actual fluid supply capacity, leading to poor pump efficiency and prolonged periods of ineffective operation. This wastes significant energy and increases the likelihood of equipment damage and maintenance costs. Summary of the Invention

[0004] To address the aforementioned shortcomings in the prior art, this invention provides a method and system for intelligent intermittent operation of pumping wells.

[0005] To achieve the above-mentioned objectives, the technical solution adopted by this invention is as follows:

[0006] A method for intelligent intermittent operation of oil pumping wells includes the following steps:

[0007] S1. Collect historical power consumption data and operating condition data of the pumping unit. Based on the historical power consumption data and operating condition data of the pumping unit, calculate the operating frequency control parameters for shutting down the pumping unit using the stroke sampling method and the relative deviation method, and set the oil well pressure for opening the pumping unit.

[0008] S2. Collect multi-index production data of oil wells and obtain the influencing factors of pumping unit operating frequency based on the multi-index production data of oil wells.

[0009] S3. Construct a pumping unit operating frequency prediction model. Based on the influencing factors of the pumping unit operating frequency in step S2, construct a dataset. Use the dataset to train the pumping unit operating frequency prediction model and use the trained pumping unit operating frequency prediction model to obtain the predicted values ​​of the pumping unit operating frequency control parameters.

[0010] S4. Based on the operating frequency control parameters for shutting down the pumping unit in step S1, the oil pressure of the well when the pumping unit is turned on, and the predicted value of the operating frequency control parameters for the pumping unit obtained in step S3, control the pumping unit to perform intelligent intermittent operation.

[0011] Further, in step S1, based on historical power consumption data and operating condition data of the pumping unit, the operating frequency control parameters for pumping unit shutdown are calculated using the stroke sampling method and the relative deviation method, including the following steps:

[0012] A1. Based on historical power consumption data and operating condition data of the pumping unit, and using the stroke sampling method, determine the standard value of the working frequency of the pumping unit's dry pumping cycle.

[0013] A2. Based on historical power consumption data and operating condition data of the pumping unit, and according to the standard value of the working frequency of the pumping unit's dry pumping cycle in step A1, the stroke difference and the rate of change of the difference in the dry pumping cycle of the pumping unit are calculated using the relative deviation method.

[0014] A3. Based on historical power consumption data and operating condition data of the pumping unit, construct the membership matrix of the stroke difference and the membership matrix of the rate of change of the difference.

[0015] A4. Based on the stroke difference and rate of change of the stroke difference during the dry pumping cycle of the pumping unit in step A2, and the membership matrix of the stroke difference and the rate of change of the stroke difference in step A3, calculate the operating frequency control parameters for shutting down the pumping unit.

[0016] Further, in step A4, based on the stroke difference and rate of change of the pumping unit during the dry pumping cycle in step A2, and the membership matrix of the stroke difference and the rate of change of the difference in step A3, the operating frequency control parameters for shutting down the pumping unit are calculated, expressed as follows:

[0017]

[0018] in: These are the operating frequency control parameters for shutting down the oil pumping unit. This is a correction factor for the operating frequency control parameters of the pumping unit shutdown. This represents the stroke difference during the dry pumping cycle of the oil pumping unit. This is the membership matrix of the stroke difference. The rate of change of the difference between the dry pumping cycles of the oil pumping unit. This is the membership matrix of the rate of change of the difference.

[0019] Furthermore, in step S2, the factors affecting the operating frequency of the pumping unit include the wellbore height, casing pressure, pump efficiency, and flow rate.

[0020] Furthermore, in step S3, the pumping unit operating frequency prediction model includes a prediction sub-model and an evaluation sub-model.

[0021] Further, in step S3, the pumping unit operating frequency prediction model is trained using the dataset, including the following steps:

[0022] B1. Input the historical data of the dataset into the prediction sub-model to obtain the training prediction value of the pumping unit's operating frequency;

[0023] B2. Determine whether the error between the training prediction value of the pumping unit operating frequency in step B1 and the historical true value of the pumping unit operating frequency is greater than the maximum error value; if yes, proceed to step B3, otherwise return to step B2.

[0024] B3. Update the prediction sub-model using the evaluation sub-model until the set number of training iterations is reached.

[0025] Further, step B1 includes the following steps:

[0026] B11. Input the historical data of the dataset into the input layer, and use the input layer and the hidden layer to obtain the output value of the hidden layer, represented as:

[0027]

[0028] in: The hidden layer output value. Hidden layer neurons Activation function, The sequence number of the neuron in the input layer. This represents the total number of neurons in the input layer. The weights between the input layer and the hidden layer. For the first The input values ​​of each neuron. The threshold values ​​for the input layer and the hidden layer are... The sequence number of the neurons in the hidden layer. This represents the total number of neurons in the hidden layer;

[0029] B12. Based on the hidden layer output value in step B11, the training prediction value of the pumping unit operating frequency is obtained using the hidden layer and the output layer, expressed as:

[0030]

[0031] in: The training prediction value for the operating frequency of the oil pumping unit. The weights between the hidden layer and the output layer. The threshold between the hidden layer and the output layer. The neuron number in the output layer. This represents the total number of neurons in the output layer.

[0032] Furthermore, step B3 includes the following steps:

[0033] B31. Update the weights and thresholds between the hidden layer and the output layer using the evaluation sub-model, as follows:

[0034]

[0035]

[0036] in: The updated weights between the hidden layer and the output layer. To evaluate the learning rate of the sub-model, The hidden layer output value. Training prediction values ​​for the operating frequency of the oil pumping unit Historical true value of pumping unit operating frequency The error between them This is the threshold between the updated hidden layer and the output layer. The threshold between the hidden layer and the output layer

[0037] B32. Update the weights and thresholds between the input layer and the hidden layer using the evaluation sub-model, as follows:

[0038]

[0039]

[0040] in: The updated weights between the input layer and the hidden layer. The weights between the input layer and the hidden layer. For the first The input values ​​of each neuron. The neuron number in the output layer. This represents the total number of neurons in the output layer. The weights between the hidden layer and the output layer. The updated thresholds for the input layer and hidden layer. The threshold values ​​are for the input layer and the hidden layer.

[0041] Furthermore, an improved weight training module is added between the hidden layer and the output layer using the evaluation sub-model. The data processing formula for the improved weight training module is expressed as follows:

[0042]

[0043] in: The output value of the hidden layer is the result of the improved weight training module. The coefficient of the first bias term. The symbol for the Hadamarda product. It is the hyperbolic tangent function. This is the coefficient of the second bias term.

[0044] A smart intermittent opening system for pumping wells using the above method includes a pumping unit start / stop calculation unit, a pumping unit operating frequency analysis unit, a pumping unit operating frequency prediction unit, and a pumping unit smart intermittent opening control unit.

[0045] The pumping unit start-stop calculation unit is used to collect historical power consumption data and operating condition data of the pumping unit, calculate the operating frequency control parameters for shutting down the pumping unit based on the historical power consumption data and operating condition data, and set the oil well pressure for starting the pumping unit.

[0046] The pumping unit operating frequency analysis unit is used to collect multi-index production data of oil wells and obtain the influencing factors of pumping unit operating frequency based on the multi-index production data of oil wells.

[0047] The pumping unit operating frequency prediction unit is used to build a pumping unit operating frequency prediction model. It constructs a dataset based on the influencing factors of the pumping unit operating frequency, uses the dataset to train the pumping unit operating frequency prediction model, and uses the trained pumping unit operating frequency prediction model to obtain the predicted values ​​of the pumping unit operating frequency control parameters.

[0048] The intelligent intermittent opening and closing control unit of the pumping unit is used to control the pumping unit to intelligently intermittently open and close based on the operating frequency control parameters for the pumping unit closing, the oil pressure of the well when the pumping unit is opened, and the predicted value of the operating frequency control parameters for the pumping unit.

[0049] The present invention has the following beneficial effects:

[0050] (1) This invention collects historical power consumption data and operating condition data of pumping units, and calculates the working frequency control parameters for shutting down the pumping unit using the stroke sampling method and the relative deviation method based on the historical power consumption data and operating condition data of pumping units. This can overcome the problem that the timing of pumping unit well opening and closing is not accurate enough by simply setting a threshold during the downstroke to shut down the pumping unit.

[0051] (2) This invention obtains the influencing factors of the working frequency of the pumping unit and constructs a prediction model of the working frequency of the pumping unit. Based on the influencing factors of the working frequency of the pumping unit, a dataset is constructed. The dataset is used to train the prediction model of the working frequency of the pumping unit. The predicted value of the working frequency control parameter of the pumping unit is obtained by using the trained prediction model of the working frequency of the pumping unit. This enables the working frequency of the pumping unit to be adjusted according to the actual working conditions, avoiding the problem that the pumping capacity of the pumping unit is greater than the actual liquid supply capacity of the oil well, which leads to poor pump efficiency, waste of power, and damage to motor equipment.

[0052] (3) This invention proposes an intelligent intermittent opening system for pumping wells using the above method, comprising a pumping well start / stop calculation unit, a pumping well operating frequency analysis unit, a pumping well operating frequency prediction unit, and an intelligent intermittent opening control unit for the pumping well; the pumping well start / stop calculation unit can collect historical pumping well power consumption data and pumping well operating condition data, calculate the operating frequency control parameters for pumping well shutdown based on the historical pumping well power consumption data and pumping well operating condition data, and set the oil pressure of the oil well when the pumping well is opened; the pumping well operating frequency analysis unit can collect multi-index production data of the oil well, and calculate the operating frequency control parameters for pumping well shutdown based on the multi-index production data of the oil well. The system obtains data on factors influencing the operating frequency of the pumping unit; the pumping unit operating frequency prediction unit can construct a pumping unit operating frequency prediction model, build a dataset based on the influencing factors, train the pumping unit operating frequency prediction model using the dataset, and use the trained pumping unit operating frequency prediction model to obtain predicted values ​​of the pumping unit operating frequency control parameters; the pumping unit intelligent intermittent opening control unit can control the pumping unit to intelligently intermittently open based on the pumping unit closing operating frequency control parameters, the oil well pressure when the pumping unit is opened, and the predicted values ​​of the pumping unit operating frequency control parameters. Attached Figure Description

[0053] Figure 1 This is a schematic diagram of a method for intelligent intermittent operation of oil pumping wells;

[0054] Figure 2 This is a schematic diagram of an intelligent intermittent system for oil pumping wells. Detailed Implementation

[0055] The specific embodiments of the present invention are described below to enable those skilled in the art to understand the present invention. However, it should be understood that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, various changes are obvious as long as they are within the spirit and scope of the present invention as defined and determined by the appended claims. All inventions utilizing the concept of the present invention are protected.

[0056] like Figure 1 As shown, a method for intelligent intermittent opening of a pumping unit well includes the following steps:

[0057] S1. Collect historical power consumption data and operating condition data of the pumping unit. Based on the historical power consumption data and operating condition data of the pumping unit, calculate the operating frequency control parameters for shutting down the pumping unit using the stroke sampling method and the relative deviation method, and set the oil well pressure for starting the pumping unit.

[0058] In an optional embodiment of the present invention, a pumping unit start-up and shutdown calculation unit is provided. This unit collects historical power consumption data and operating condition data of the pumping unit. Based on this data, it calculates the operating frequency control parameters for pumping unit shutdown using a stroke sampling method and a relative deviation method, and sets the well oil pressure for pumping unit startup. The present invention calculates the operating frequency control parameters for pumping unit shutdown using a stroke sampling method and a relative deviation method based on historical power consumption data and operating condition data, including the following steps:

[0059] A1. Based on historical power consumption and operating condition data of the pumping unit, and using the stroke sampling method, the standard value of the operating frequency of the pumping unit during the dry pumping cycle is determined, and expressed as:

[0060]

[0061] in: This refers to the standard operating frequency for the dry pumping cycle of the oil pumping unit. This represents the average operating frequency of the sampling points during the first stroke of the pumping unit's dry pumping cycle. This represents the average operating frequency at the sampling points during the second stroke of the pumping unit's dry pumping cycle. This represents the average operating frequency at the sampling points during the third stroke of the pumping unit's dry pumping cycle. The first dry pumping cycle of the oil pumping unit Average operating frequency of each stroke sampling point This represents the number of sampling points during the dry pumping cycle of the oil pumping unit.

[0062] A2. Based on historical power consumption data and operating condition data of the pumping unit, and according to the standard value of the working frequency of the pumping unit's dry pumping cycle in step A1, the stroke difference and rate of change of the difference in the dry pumping cycle are calculated using the relative deviation method, and expressed as:

[0063]

[0064]

[0065]

[0066]

[0067] in: This represents the stroke difference during the dry pumping cycle of the oil pumping unit. This represents the stroke difference at the sampling point of the first stroke during the dry pumping cycle of the oil pumping unit. This represents the stroke difference at the sampling point of the second stroke during the dry pumping cycle of the oil pumping unit. This represents the stroke difference at the sampling point of the third stroke during the dry pumping cycle of the oil pumping unit. The first dry pumping cycle of the oil pumping unit Stroke difference at each stroke sampling point The first dry pumping cycle of the oil pumping unit Stroke difference at each stroke sampling point The first dry pumping cycle of the oil pumping unit The operating frequency of each stroke sampling point The first dry pumping cycle of the oil pumping unit The standard value of the operating frequency at each stroke sampling point The rate of change of the difference between the dry pumping cycles of the oil pumping unit. This represents the rate of change of the difference between sampling points during the first stroke of the pumping cycle of the oil pumping unit. The rate of change of the difference between the sampling points during the second stroke of the pumping cycle is the value of the oil pumping unit. This represents the rate of change of the difference between sampling points during the third stroke of the pumping cycle. The first dry pumping cycle of the oil pumping unit The rate of change of the difference between the sampling points of each stroke The first dry pumping cycle of the oil pumping unit Rate of change of difference between sampling points of each stroke.

[0068] A3. Based on historical power consumption data and operating condition data of the pumping unit, construct the membership matrix of the stroke difference and the membership matrix of the rate of change of the difference, as follows:

[0069]

[0070]

[0071] in: This is the membership matrix of the stroke difference. The membership degree of the stroke difference at the sampling point of the first stroke in the dry pumping cycle of the oil pumping unit. The membership degree of the stroke difference at the sampling point of the second stroke in the dry pumping cycle of the oil pumping unit. This represents the membership degree of the stroke difference at the sampling point of the third stroke in the dry pumping cycle of the oil pumping unit. The first dry pumping cycle of the oil pumping unit Membership degree of stroke difference at each stroke sampling point The first dry pumping cycle of the oil pumping unit Membership degree of stroke difference at each stroke sampling point This is the membership matrix of the rate of change of the difference. The membership degree represents the rate of change of the difference between the sampling points during the first stroke of the dry pumping cycle of the oil pumping unit. The membership degree represents the rate of change of the difference between sampling points during the third stroke of the pumping cycle of the oil pumping unit. The membership degree represents the rate of change of the difference between sampling points during the third stroke of the pumping cycle of the oil pumping unit. The first dry pumping cycle of the oil pumping unit Membership degree of the rate of change of the difference between sampling points of each stroke The first dry pumping cycle of the oil pumping unit Membership degree of the rate of change of the difference between the sampling points of each stroke.

[0072] This invention is based on historical power consumption data and operating condition data of pumping units, and uses the membership function method to calculate the membership degree of the stroke difference and the membership degree of the rate of change of the difference.

[0073] A4. Based on the stroke difference and rate of change of the stroke difference during the dry pumping cycle in step A2, and the membership matrix of the stroke difference and rate of change of the stroke difference in step A3, calculate the operating frequency control parameters for shutting down the pumping unit, expressed as:

[0074]

[0075] in: These are the operating frequency control parameters for shutting down the oil pumping unit. This is a correction factor for the operating frequency control parameters of the pumping unit during shutdown.

[0076] S2. Collect multi-indicator production data of oil wells, and obtain the influencing factors of pumping unit operating frequency based on the multi-indicator production data of oil wells.

[0077] In an optional embodiment of the present invention, a pumping unit operating frequency analysis unit is provided. This unit collects multi-index production data from the oil well and, based on this data, uses regression analysis to determine the influencing factors of the pumping unit operating frequency. These factors include the well's pavement height, casing pressure, pump efficiency, and flow rate.

[0078] S3. Construct a pumping unit operating frequency prediction model. Based on the influencing factors of the pumping unit operating frequency in step S2, construct a dataset. Use the dataset to train the pumping unit operating frequency prediction model, and use the trained pumping unit operating frequency prediction model to obtain the predicted values ​​of the pumping unit operating frequency control parameters.

[0079] In an optional embodiment of the present invention, a pumping unit operating frequency prediction unit is provided. The pumping unit operating frequency prediction unit constructs a pumping unit operating frequency prediction model, builds a dataset based on the influencing factors of the pumping unit operating frequency, trains the pumping unit operating frequency prediction model using the dataset, and uses the trained pumping unit operating frequency prediction model to obtain predicted values ​​of the pumping unit operating frequency control parameters. The pumping unit operating frequency prediction model includes a prediction sub-model and an evaluation sub-model.

[0080] This invention trains a prediction model for the operating frequency of an oil pumping unit using a dataset, and includes the following steps:

[0081] B1. Input the historical data of the dataset into the prediction sub-model to obtain the training prediction value of the pumping unit's operating frequency.

[0082] Step B1 includes the following steps:

[0083] B11. Input the historical data of the dataset into the input layer, and use the input layer and the hidden layer to obtain the output value of the hidden layer, represented as:

[0084]

[0085] in: The hidden layer output value. Hidden layer neurons Activation function, The sequence number of the neuron in the input layer. This represents the total number of neurons in the input layer. The weights between the input layer and the hidden layer. For the first The input values ​​of each neuron. The threshold values ​​for the input layer and the hidden layer are... The sequence number of the neurons in the hidden layer. This represents the total number of neurons in the hidden layer.

[0086] B12. Based on the hidden layer output value in step B11, the training prediction value of the pumping unit operating frequency is obtained using the hidden layer and the output layer, expressed as:

[0087]

[0088] in: The training prediction value for the operating frequency of the oil pumping unit. The weights between the hidden layer and the output layer. The threshold between the hidden layer and the output layer. The neuron number in the output layer. This represents the total number of neurons in the output layer.

[0089] B2. Determine whether the error between the training prediction value of the pumping unit operating frequency in step B1 and the historical true value of the pumping unit operating frequency is greater than the maximum error value; if yes, proceed to step B3, otherwise return to step B2.

[0090] B3. Update the prediction sub-model using the evaluation sub-model until the set number of training iterations is reached.

[0091] Step B3 includes the following steps:

[0092] B31. Update the weights and thresholds between the hidden layer and the output layer using the evaluation sub-model, as follows:

[0093]

[0094]

[0095] in: The updated weights between the hidden layer and the output layer. To evaluate the learning rate of the sub-model, The hidden layer output value. Training prediction values ​​for the operating frequency of the oil pumping unit Historical true value of pumping unit operating frequency The error between them This is the threshold between the updated hidden layer and the output layer. This is the threshold between the hidden layer and the output layer.

[0096] This invention utilizes an evaluation sub-model to add an improved weight training module between the hidden layer and the output layer. The data processing formula for the improved weight training module is expressed as follows:

[0097]

[0098] in: The output value of the hidden layer is the result of the improved weight training module. The coefficient of the first bias term. The symbol for the Hadamarda complex. It is the hyperbolic tangent function. This is the coefficient of the second bias term.

[0099] This invention adds an improved weight training module between the hidden layer and the output layer, which can selectively control the flow of the hidden layer output value under different linear transformations, thereby accelerating the convergence speed of the weights between the hidden layer and the output layer and improving the training efficiency of the prediction sub-model.

[0100] B32. Update the weights and thresholds between the input layer and the hidden layer using the evaluation sub-model, as follows:

[0101]

[0102]

[0103] in: The updated weights between the input layer and the hidden layer. The weights between the input layer and the hidden layer. For the first The input values ​​of each neuron. The neuron number in the output layer. This represents the total number of neurons in the output layer. The weights between the hidden layer and the output layer. The updated thresholds for the input layer and hidden layer. The threshold values ​​are for the input layer and the hidden layer.

[0104] S4. Based on the operating frequency control parameters for shutting down the pumping unit in step S1, the oil pressure of the well when the pumping unit is turned on, and the predicted value of the operating frequency control parameters for the pumping unit obtained in step S3, control the pumping unit to perform intelligent intermittent operation.

[0105] In an optional embodiment of the present invention, an intelligent intermittent opening and closing control unit for the pumping unit is provided. The intelligent intermittent opening and closing control unit controls the pumping unit to intelligently intermittently open and close based on the operating frequency control parameters for pumping unit closure, the oil pressure of the well when the pumping unit is open, and the predicted value of the operating frequency control parameters for the pumping unit.

[0106] like Figure 2 As shown, an intelligent intermittent opening system for a pumping unit well using the above method includes a pumping unit start / stop calculation unit, a pumping unit operating frequency analysis unit, a pumping unit operating frequency prediction unit, and an intelligent intermittent opening control unit for the pumping unit.

[0107] In an optional embodiment of the present invention, the pumping unit start-stop calculation unit is used to collect historical power consumption data and operating condition data of the pumping unit, calculate the operating frequency control parameters for shutting down the pumping unit based on the historical power consumption data and operating condition data of the pumping unit, and set the oil well pressure for starting the pumping unit.

[0108] In an optional embodiment of the present invention, the pumping unit operating frequency analysis unit is used to collect multi-index production data of the oil well and obtain the influencing factors of the pumping unit operating frequency based on the multi-index production data of the oil well.

[0109] In an optional embodiment of the present invention, the pumping unit operating frequency prediction unit is used to construct a pumping unit operating frequency prediction model, construct a dataset based on the influencing factors of the pumping unit operating frequency, train the pumping unit operating frequency prediction model using the dataset, and obtain the predicted values ​​of the pumping unit operating frequency control parameters using the trained pumping unit operating frequency prediction model.

[0110] In an optional embodiment of the present invention, the pumping unit intelligent intermittent opening control unit is used to control the pumping unit to perform intelligent intermittent opening based on the pumping unit closing operating frequency control parameters, the oil well pressure when the pumping unit is opened, and the predicted value of the pumping unit operating frequency control parameters.

[0111] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0112] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0113] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0114] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

[0115] Those skilled in the art will recognize that the embodiments described herein are intended to help the reader understand the principles of the invention, and should be understood that the scope of protection of the invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific modifications and combinations based on the technical teachings disclosed in this invention without departing from the spirit of the invention, and these modifications and combinations are still within the scope of protection of this invention.

Claims

1. An intelligent interval opening method for pumping unit wells, characterized in that, The method comprises the following steps: S1, collecting historical pumping unit power consumption data and pumping unit working condition data, calculating the working frequency control parameter of the closed pumping unit based on the historical pumping unit power consumption data and the pumping unit working condition data by using the stroke sampling method and the relative deviation method, and setting the well pressure of the open pumping unit; The method for calculating the working frequency control parameter of the closed pumping unit based on the historical pumping unit power consumption data and the pumping unit working condition data by using the stroke sampling method and the relative deviation method comprises the following steps: A1, determining the working frequency standard value of the dry pumping period of the pumping unit based on the historical pumping unit power consumption data and the pumping unit working condition data and by using the stroke sampling method; A2, calculating the stroke difference value and the difference change rate of the dry pumping period of the pumping unit based on the historical pumping unit power consumption data and the pumping unit working condition data and according to the working frequency standard value of the dry pumping period of the pumping unit in step A1 by using the relative deviation method; A3, constructing the membership matrix of the stroke difference value and the membership matrix of the difference change rate based on the historical pumping unit power consumption data and the pumping unit working condition data; A4, calculating the working frequency control parameter of the closed pumping unit according to the stroke difference value and the difference change rate of the dry pumping period of the pumping unit in step A2 and the membership matrix of the stroke difference value and the membership matrix of the difference change rate in step A3, which is expressed as: wherein: is a working frequency control parameter for the shut-down of the pumping unit, is a correction factor for the working frequency control parameter for the shut-down of the pumping unit, is a stroke difference value for the dry pumping period of the pumping unit, is a membership matrix for the stroke difference value, is a difference change rate for the dry pumping period of the pumping unit, is a membership matrix for the difference change rate; S2, collecting multi-index production data of the well, and obtaining the influencing factors of the working frequency of the pumping unit according to the multi-index production data of the well; S3, constructing a pumping unit working frequency prediction model, constructing a data set based on the influencing factors of the working frequency of the pumping unit in step S2, training the pumping unit working frequency prediction model by using the data set, and obtaining the working frequency control parameter prediction value of the pumping unit by using the trained pumping unit working frequency prediction model; S4, controlling the intelligent interval opening of the pumping unit based on the working frequency control parameter of the closed pumping unit in step S1, the well pressure of the open pumping unit, and the working frequency control parameter prediction value of the pumping unit in step S3.

2. The intelligent off-cycle method for pumping unit wells of claim 1, wherein, The influencing factors of the working frequency of the pumping unit in step S2 include the page height of the well, the casing pressure, the pump efficiency, and the flow rate.

3. The intelligent off-cycle method for pumping unit wells of claim 1, wherein, In step S3, the pumping unit working frequency prediction model comprises a prediction sub-model and an evaluation sub-model.

4. The intelligent off-cycle method for pumping unit wells of claim 3, wherein, In step S3, the pumping unit working frequency prediction model is trained by using the data set, which comprises the following steps: B1, inputting the historical data of the data set into the prediction sub-model to obtain the training prediction value of the working frequency of the pumping unit; B2, determining whether the error between the training prediction value of the working frequency of the pumping unit in step B1 and the historical true value of the working frequency of the pumping unit is greater than the maximum error value; if yes, proceed to step B3, otherwise, return to step B2; B3, updating the prediction sub-model by using the evaluation sub-model until the set training iteration number is reached.

5. The intelligent off-cycle method for pumping unit wells of claim 4, wherein, Step B1 comprises the following steps: B11, inputting the historical data of the data set into the input layer, and obtaining the hidden layer output value by using the input layer and the hidden layer, which is expressed as: wherein: is the output value of the hidden layer, is the activation function of the hidden layer neuron is the activation function of the hidden layer neuron is the neuron number in the input layer, is the total number of neurons in the input layer, is the weight value between the input layer and the hidden layer, is the input value of the th neuron, is the threshold value between the input layer and the hidden layer, is the neuron number in the hidden layer, is the total number of neurons in the hidden layer. B12, obtaining the training prediction value of the working frequency of the pumping unit by using the hidden layer and the output layer according to the hidden layer output value in step B11, which is expressed as: wherein: is the training prediction value for the frequency of the pumping unit, is the weight between the hidden layer and the output layer, is the threshold value between the hidden layer and the output layer, is the neuron number in the output layer, is the total number of neurons in the output layer.

6. The intelligent off-cycle method for pumping unit wells of claim 4, wherein, Step B3 comprises the following steps: B31, the weights and thresholds between the hidden layer and the output layer are updated by using the evaluation sub-model, which is expressed as: wherein: is the updated weight between the hidden layer and the output layer, is the learning rate of the evaluation sub-model, is the hidden layer output value, is the pumping unit operating frequency training prediction value and the pumping unit operating frequency historical true value between the error, is the updated threshold between the hidden layer and the output layer, is the threshold between the hidden layer and the output layer B32, the weights and thresholds between the input layer and the hidden layer are updated by using the evaluation sub-model, which is expressed as: wherein: is the updated weight between the input layer and the hidden layer, is the weight between the input layer and the hidden layer, is the input value of the th neuron, is the neuron number in the output layer, is the total number of neurons in the output layer, is the weight between the hidden layer and the output layer, is the updated threshold value between the input layer and the hidden layer, is the threshold value between the input layer and the hidden layer.

7. The intelligent off-cycle method for pumping unit wells of claim 6, wherein, An improved weight training module is added between the hidden layer and the output layer by using the evaluation sub-model, and the data processing formula of the improved weight training module is expressed as: wherein: is an output value of the improved weight training module for the hidden layer output value, is a first bias term coefficient, is a Hadamard product symbol, is a hyperbolic tangent function, is a second bias term coefficient.

8. An intelligent off-cycle system for pumping unit wells using the method of any one of claims 1-7, characterized in that, A pumping unit start-stop calculation unit, a pumping unit working frequency analysis unit, a pumping unit working frequency prediction unit and a pumping unit intelligent interval opening control unit; The pumping unit start-stop calculation unit is used to collect historical pumping unit power consumption data and pumping unit working condition data, calculate the working frequency control parameters of the pumping unit shutdown based on the historical pumping unit power consumption data and pumping unit working condition data, and set the oil well pressure of the pumping unit start-up; The pumping unit working frequency analysis unit is used to collect multi-index production data of the oil well, and obtain the influencing factors of the pumping unit working frequency according to the multi-index production data of the oil well; The pumping unit working frequency prediction unit is used to construct a pumping unit working frequency prediction model, construct a data set based on the influencing factors of the pumping unit working frequency, train the pumping unit working frequency prediction model by using the data set, and obtain the working frequency control parameter prediction value of the pumping unit by using the trained pumping unit working frequency prediction model; The pumping unit intelligent interval opening control unit is used to control the pumping unit to perform intelligent interval opening according to the working frequency control parameters of the pumping unit shutdown, the oil well pressure of the pumping unit start-up and the working frequency control parameter prediction value of the pumping unit.

Images