Quantitative evaluation method, system and electronic equipment for monitoring production state of natural gas well

Abstract

The application relates to the technical field of natural gas field development, and discloses a kind of quantitative evaluation method and system and electronic equipment for monitoring the production state of natural gas well.The method obtains the effective historical control data of gas well changing with time, without understanding the control mechanism of plunger gas lift and the actual gas production of gas well;Based on the time domain fluctuation of plunger oil pressure and plunger casing pressure in effective historical control data, and the frequency domain sidelobe connection condition, a normal rate evaluation quantitative criterion is constructed;Based on the amplitude stability length proportion of plunger oil pressure and plunger casing pressure in time domain, and the number of sidelobes in frequency domain, a stable operation time evaluation quantitative criterion is constructed.Finally, based on the normal rate evaluation quantitative criterion and the stable operation time evaluation quantitative criterion, the normal rate quantitative index and the stable operation time quantitative index for monitoring the production quality of gas well can be obtained.From the normal rate and the stable operation time, the actual gas well working state can be evaluated uniformly and quantitatively;It is effective and has strong generalization.

Description

Technical Field

[0001] This application relates to the field of natural gas field development technology, specifically to a quantitative evaluation method, system, and electronic equipment for monitoring the production status of natural gas wells. Background Technology

[0002] In the context of carbon neutrality, natural gas plays a vital role in the energy structure as a clean energy source. However, in the later stages of natural gas well production, insufficient formation energy makes it difficult to drain produced water from the formation, leading to fluid accumulation at the bottom of the well. In severe cases, this can even cause the well to "crush," resulting in production shutdown. To address this issue, plunger gas lift drainage and gas production technology has emerged. This technology utilizes the well's own energy to drive a plunger in a reciprocating motion to achieve periodic drainage and gas production. It has advantages such as ease of implementation and low cost, and has been widely applied in actual natural gas industry operations. Currently, plunger gas lift control algorithms mainly optimize controllable factors to artificially achieve efficient operation of plunger gas lift drainage and gas production. However, the quality of operation needs improvement. This necessitates real-time and quantitative evaluation of the plunger gas lift operating conditions. Therefore, how to quantitatively evaluate the operating conditions of the plunger gas lift is an effective prerequisite for stabilizing and increasing production.

[0003] In existing technologies, the operation of natural gas well control systems using plunger gas lift drainage gas production technology is mainly evaluated through the following two methods:

[0004] The first type of evaluation method requires prior understanding of the front-end control mechanism, which requires solid expert knowledge and theoretical foundation, is time-consuming, labor-intensive, and inefficient; moreover, most of the relevant evaluations remain at the qualitative level and cannot quantitatively evaluate the production quality of gas wells.

[0005] The second type of evaluation method uses the gas production of natural gas wells as the basis for judgment. However, in actual gas wells, there are often multiple gas wells sharing the same gas meter, which makes it difficult to accurately allocate the gas production. Inaccurate gas production of each gas well is the norm, which seriously restricts the evaluation accuracy of the plunger gas lift operation condition based on gas production and limits the promotion and application of related methods. Summary of the Invention

[0006] This application provides a quantitative evaluation method for monitoring the production status of natural gas wells, which solves the problems in the prior art. Existing evaluation methods require prior knowledge of the front-end control mechanism, and most of the related evaluations are at the qualitative level and cannot quantitatively evaluate the production quality of gas wells. In addition, because multiple wells in actual gas wells share the same gas meter, the gas production often cannot be accurately allocated, which seriously restricts the application of related methods.

[0007] Accordingly, embodiments of this application also provide a quantitative evaluation system for monitoring the production status of natural gas wells and an electronic device to ensure the implementation and application of the above methods.

[0008] To address the aforementioned technical problems, this application discloses a quantitative evaluation method for monitoring the production status of natural gas wells, the method comprising:

[0009] Acquire effective historical control data of gas wells over time; effective historical control data includes plunger oil pressure and plunger sleeve pressure.

[0010] A quantitative criterion for normality evaluation is constructed based on the time-domain fluctuations of plunger oil pressure and plunger sleeve pressure, as well as the frequency-domain sidelobe connectivity.

[0011] Based on the proportion of amplitude stability time of plunger oil pressure and plunger sleeve pressure in the time domain, and the number of side lobes in the frequency domain, a quantitative criterion for evaluating stable operating time is constructed.

[0012] Based on the quantitative criteria for normal operation rate evaluation and the quantitative criteria for stable operation time evaluation, quantitative indicators for normal operation rate and stable operation time are obtained to monitor the production quality of gas wells.

[0013] This application also discloses a quantitative evaluation system for monitoring the production status of natural gas wells, the system comprising:

[0014] The data acquisition module is used to acquire effective historical control data of gas wells over time; effective historical control data includes plunger oil pressure and plunger sleeve pressure.

[0015] The quantification criterion construction module is used to construct a normality evaluation quantification criterion based on the time-domain fluctuation of plunger oil pressure and plunger sleeve pressure, as well as the frequency-domain sidelobe connectivity.

[0016] The quantification criterion construction module is also used to construct a quantification criterion for evaluating stable operating time based on the proportion of amplitude stability time of plunger oil pressure and plunger sleeve pressure in the time domain, as well as the number of side lobes in the frequency domain.

[0017] The quantitative index generation module is used to obtain quantitative indicators of normal rate and stable operation time for monitoring the production quality of gas wells, based on the quantitative criteria for normal rate evaluation and the quantitative criteria for stable operation time evaluation.

[0018] This application also discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements one or more of the methods described in this application.

[0019] In this embodiment, considering that most related evaluations remain at the qualitative level and cannot quantitatively evaluate the production quality of gas wells, a quantitative criterion for normality rate evaluation and a quantitative criterion for stable operation time evaluation are proposed. Based on these criteria, quantitative indicators for normality rate and stable operation time are obtained to monitor the production quality of gas wells, enabling quantitative evaluation of gas well production quality. Furthermore, a unified evaluation of the actual working status of gas wells can be conducted, improving the accuracy of the evaluation. Specifically, the quantitative criteria for normality rate evaluation and stable operation time evaluation are constructed based on effective historical control data. First, effective historical control data of the gas well changing over time is obtained. Without needing to understand the control mechanism of the plunger gas lift or the actual gas production of the well, a quantitative evaluation of the natural gas well control system's operation can be performed. Then, the quantitative criteria for normality rate evaluation are constructed based on the time-domain fluctuations of plunger oil pressure and plunger sleeve pressure, as well as the frequency-domain sidelobe connectivity, from the effective historical control data. The quantitative criteria for stable operation time evaluation are constructed based on the proportion of stable amplitude duration of plunger oil pressure and plunger sleeve pressure in the time domain, and the number of sidelobes in the frequency domain. The quantitative criteria for normal operation rate evaluation and the quantitative criteria for stable operation time evaluation constructed using the above methods can be used to monitor the production quality of gas wells, which can also help improve the production quality of gas wells and effectively enhance the effectiveness and scalability of plunger gas lift control monitoring technology.

[0020] Additional aspects and advantages of the embodiments of this application will be set forth in the following description, and will become apparent from the description or may be learned by practice of this application. Attached Figure Description

[0021] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0022] Figure 1 A flowchart illustrating a quantitative evaluation method for monitoring the production status of natural gas wells provided in this application embodiment;

[0023] Figure 2 This is the original drawing of the hydraulic sleeve provided in the embodiment of this application;

[0024] Figure 3 Oil-casing differential pressure diagram provided for embodiments of this application;

[0025] Figure 4 This is a hydraulic sleeve pressure spectrum diagram provided in an embodiment of this application;

[0026] Figure 5 This is a spectrum of differential pressure between the oil jacket and casing provided in an embodiment of this application.

[0027] Figure 6 Explanatory diagram of side lobes provided for embodiments of this application;

[0028] Figure 7 A diagram illustrating sidelobe connectivity provided for embodiments of this application;

[0029] Figure 8 A graph showing the prediction results of a BP neural network provided in an embodiment of this application;

[0030] Figure 9 This is a random forest prediction result diagram provided in the embodiments of this application;

[0031] Figure 10 This is a diagram showing the prediction results of the BNN neural network provided in the embodiments of this application;

[0032] Figure 11 A CNN neural network prediction result diagram provided in the embodiments of this application;

[0033] Figure 12 A structural diagram of the stable runtime prediction model provided in the embodiments of this application;

[0034] Figure 13 A structural diagram of the accuracy prediction model provided in the embodiments of this application;

[0035] Figure 14 The training result diagram of the normality loss function provided in the embodiments of this application;

[0036] Figure 15 The training result diagram for normality training accuracy provided in the embodiments of this application;

[0037] Figure 16 The training result diagram of the stable runtime loss function provided in the embodiments of this application;

[0038] Figure 17 A graph showing the stable runtime training accuracy training results provided in the embodiments of this application;

[0039] Figure 18 A schematic diagram of the structure of a quantitative evaluation system for monitoring the production status of natural gas wells provided in an embodiment of this application;

[0040] Figure 19 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0041] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0042] Those skilled in the art will understand that, unless explicitly stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0043] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0044] The solutions provided in this application can be executed by any electronic device, such as a terminal device or a server. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The terminal and server can be directly or indirectly connected via wired or wireless communication, which is not limited herein. The quantitative evaluation method, system, and electronic device for monitoring the production status of natural gas wells provided in this application aim to solve at least one of the technical problems existing in the prior art.

[0045] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0046] This application provides a possible implementation method, such as... Figure 1As shown, a flowchart of a quantitative evaluation method for monitoring the production status of natural gas wells is provided. This method can be executed by any electronic device, optionally on a server or a terminal device.

[0047] like Figure 1 As shown, the method may include the following steps:

[0048] Step 101: Obtain effective historical control data of the gas well over time; effective historical control data includes plunger oil pressure and plunger sleeve pressure.

[0049] In this embodiment of the application, the inherent laws of the production process are explored by mining the inherent laws of historical gas well production data, and an evaluation system is proposed to evaluate the generation status of gas wells in a quantitative way from two aspects: normal rate and stable operation time.

[0050] Step 102: Construct a quantitative criterion for normality evaluation based on the time-domain fluctuations of plunger oil pressure and plunger sleeve pressure, as well as the frequency-domain sidelobe connectivity.

[0051] The changes in plunger oil pressure and plunger sleeve pressure over time are essentially nonlinear random signals. Therefore, the time-domain fluctuation can refer to the signal fluctuation of plunger oil pressure and plunger sleeve pressure in the time-domain diagram. For example, if the plunger oil pressure (or plunger sleeve pressure) signal value collected within period T shows an increasing trend, and the plunger oil pressure (or plunger sleeve pressure) signal value collected within the (T+1)th period shows a decreasing trend, then the time-domain fluctuation can be an increase followed by a decrease.

[0052] Frequency domain sidelobe connectivity refers to whether the sidelobes of the plunger oil pressure (or plunger sleeve pressure) are connected in the spectrum generated after mapping effective historical data from the time domain to the frequency domain. Specifically, it includes two cases: sidelobe connectivity and sidelobe non-connectivity.

[0053] Step 103: Construct a quantitative criterion for evaluating stable operating time based on the proportion of stable amplitude duration of plunger oil pressure and plunger sleeve pressure in the time domain and the number of side lobes in the frequency domain.

[0054] This application embodiment does not require exploring the control mechanism of natural gas well production. Instead, it analyzes effective historical control data in the time and frequency domains and constructs quantitative criteria for normal operation rate evaluation and quantitative criteria for stable operation time evaluation based on the characteristics of plunger oil pressure and plunger sleeve pressure in the time and frequency domains.

[0055] Step 104: Based on the normality rate evaluation quantification criteria and the stable operation time evaluation quantification criteria, obtain the normality rate quantification index and the stable operation time quantification index used to monitor the production quality of gas wells.

[0056] The evaluation system in this application embodiment, based on the normal operation rate and stable operating time, can effectively improve the effectiveness and scalability of plunger gas lift control monitoring technology.

[0057] In this embodiment, considering that most related evaluations remain at the qualitative level and cannot quantitatively evaluate the production quality of gas wells, a quantitative criterion for normality rate evaluation and a quantitative criterion for stable operation time evaluation are proposed. Based on these criteria, quantitative indicators for normality rate and stable operation time are obtained to monitor the production quality of gas wells, enabling quantitative evaluation of gas well production quality. Furthermore, a unified evaluation of the actual working status of gas wells can be conducted, improving the accuracy of the evaluation. Specifically, the quantitative criteria for normality rate evaluation and stable operation time evaluation are constructed based on effective historical control data. First, effective historical control data of the gas well changing over time is obtained. Without needing to understand the control mechanism of the plunger gas lift or the actual gas production of the well, a quantitative evaluation of the natural gas well control system's operation can be performed. Then, the quantitative criteria for normality rate evaluation are constructed based on the time-domain fluctuations of plunger oil pressure and plunger sleeve pressure, as well as the frequency-domain sidelobe connectivity, from the effective historical control data. The quantitative criteria for stable operation time are constructed based on the proportion of stable amplitude duration of plunger oil pressure and plunger sleeve pressure in the time domain, and the number of sidelobes in the frequency domain. The quantitative criteria for normality evaluation and stable operation time evaluation constructed using the above methods can be used to monitor the production quality of gas wells, which can also help improve the production quality of gas wells and effectively enhance the effectiveness and scalability of plunger gas lift control monitoring technology.

[0058] In an optional embodiment, acquiring effective historical control data of the gas well over time includes:

[0059] Based on preset key descriptors, key gas well production data are obtained by filtering from pre-acquired gas well production data; key descriptors include plunger sleeve pressure, plunger oil pressure, solenoid valve status, and production system.

[0060] A support vector machine is constructed based on key gas well production data, and then the support vector machine is used to filter normal operation data from the gas well production data to obtain effective historical data.

[0061] Because natural gas well production data is affected by numerous background factors such as equipment parameters, operating conditions, and operating status, many abnormal data points appear. This limits the accuracy of the evaluation system and seriously affects the accuracy and precision of monitoring the working status of gas wells. Therefore, in this embodiment, it is necessary to process the abnormal data of gas well production data to obtain valid historical data.

[0062] Specifically, controllable factors in natural gas well production include up to 17 descriptive terms. These terms collectively reflect factors in the gas well production process. However, not all descriptive terms are suitable for monitoring and evaluating gas wells. Therefore, it is necessary to exclude useless descriptive terms from historical data and select effective data descriptive terms as key data for gas well production. Production data from natural gas wells at certain time intervals was selected and analyzed. The resulting key production data included plunger sleeve pressure, plunger oil pressure, solenoid valve status, and production regime.

[0063] Based on the key gas well production data that vary over time using four descriptors—plunger sleeve pressure, plunger oil pressure, solenoid valve status, and production regime—a support vector machine is constructed to determine whether a gas well is operating normally. Data indicating normal gas well operation is selected as valid historical data, providing data support for further monitoring and evaluation of gas well control quality.

[0064] In an optional embodiment, a normality evaluation quantification criterion is constructed based on the time-domain fluctuations of plunger oil pressure and plunger sleeve pressure, as well as the frequency-domain sidelobe connectivity, including:

[0065] The temporal fluctuations of plunger oil pressure and plunger sleeve pressure were determined based on valid historical data from multiple gas wells.

[0066] A preset transformation method is used to map the plunger oil pressure, plunger sleeve pressure, and oil-sleeve pressure difference to the frequency domain to obtain a spectrum diagram; wherein, the transformation method includes Fourier transform method and short-time Fourier transform method; the oil-sleeve pressure difference is the difference between plunger oil pressure and plunger sleeve pressure;

[0067] The frequency domain sidelobe connectivity of the plunger oil pressure and plunger sleeve pressure is determined based on the spectrum diagram; the sidelobe connectivity includes sidelobe connectivity and sidelobe non-connectivity.

[0068] A quantitative criterion for evaluating normality rate was constructed based on the time-domain fluctuations and frequency-domain sidelobe connectivity of multiple gas wells.

[0069] Historical control data on the changes in key descriptors of plunger sleeve pressure and plunger oil pressure over time contain detailed information that is difficult to observe with the naked eye, such as fluctuations during well opening and fluctuations in the gas well during each cycle. By performing time-frequency domain analysis on the historical control data, the changes in each key descriptor of the plunger gas well can be reflected in the frequency domain. Existing mature methods such as Fourier transform and short-time Fourier transform can be used to map the historical control data from the time domain to the frequency domain, and an overall normality evaluation criterion can be constructed based on the time-domain fluctuations and frequency-domain sidelobe connectivity of plunger sleeve pressure and plunger oil pressure.

[0070] The changes in plunger oil pressure (hereinafter referred to as oil pressure) and plunger sleeve pressure (hereinafter referred to as sleeve pressure) over time are essentially nonlinear random signals. Let the oil pressure be denoted as o(t) and the sleeve pressure as c(t), and introduce a new variable, the oil-sleeve pressure difference d(t): d(t) = o(t) - c(t). Simultaneously, frequency domain analysis is performed on the oil pressure and sleeve pressure to remove noise and unwanted frequency components, allowing for a clearer observation of the signal variation characteristics. Optionally, in this embodiment, the Fourier transform method is used to transform the signal from the time domain to the frequency domain. One-dimensional Fourier transforms are performed on the three sets of data: oil pressure, sleeve pressure, and oil-sleeve pressure difference, as shown in the following formula:

[0071]

[0072]

[0073]

[0074] Select a gas well sample and its time-domain plot and spectrum, such as... Figures 2 to 5 As shown, where, Figure 2 This is the original diagram of hydraulic and sleeve pressure, i.e., the time-domain diagram of hydraulic and sleeve pressure. Figure 3 This is a time-domain plot of the oil-casing pressure difference. Figure 4 This is a spectrum diagram of hydraulic sleeve pressure. Figure 5 This is a spectrum diagram of the differential pressure between the oil jacket and the casing.

[0075] In the frequency domain, the fluctuations in oil pressure and casing pressure signals can accurately reflect the fluctuation situation. Analysis of the spectrum diagrams reveals the sidelobe connectivity. Specifically, in the oil pressure and casing pressure spectrum diagrams, two or more peaks connected together indicate sidelobe connectivity, such as... Figure 7 As shown.

[0076] In an optional embodiment, the condition for sidelobe connectivity is:

[0077]

[0078] Among them, y i This represents the spectral amplitude at a frequency of i Hz, where i ∈ N.

[0079] In this embodiment, multiple connected side lobes are considered as one side lobe.

[0080] In an optional embodiment, a normality rate evaluation quantification criterion is constructed based on the time-domain fluctuations and frequency-domain sidelobe connectivity of multiple gas wells, including:

[0081] The basic quantitative score range of the normality rate is determined based on the time-domain fluctuations of multiple gas wells;

[0082] The first bonus quantitative score for normality is determined based on the frequency domain sidelobe connectivity of multiple gas wells;

[0083] The second bonus quantification range of the normality rate is determined based on the oil-casing pressure difference of multiple gas wells;

[0084] A normality rate evaluation criterion is constructed to quantify the normality rate of gas wells based on the basic quantitative score range, the first bonus quantitative score, and the second bonus quantitative range of the normality rate, thereby obtaining a quantitative index of the normality rate of gas wells.

[0085] In this embodiment, based on the time-domain fluctuations of multiple gas wells, the basic quantitative score range of the normality rate can be divided into three categories: (0, Y1], (Y1, Y2], and (Y2, 1]. Wherein, (0, Y1] indicates that the waveform of the signal value in the time-domain graph differs greatly across different periods; (Y1, Y2] indicates that the waveform of the signal value in the time-domain graph shows significant differences across different periods, but the differences are not significant; and (Y2, 1] indicates that the waveform of the signal value in the time-domain graph tends to be consistent across different periods. The first bonus quantitative score of the normality rate can be determined by statistically analyzing the frequency domain sidelobe connectivity of multiple gas wells. The second bonus quantitative range of the normality rate can be determined by statistically analyzing the oil-casing pressure difference of multiple gas wells, such as (0, H1], (H1, H2], and (H2, +∞).

[0086] When evaluating the normality rate of any gas well, the basic quantitative score of the normality rate (a value determined within the range of the basic quantitative score of the normality rate), the first bonus quantitative score of the normality rate, and the second bonus quantitative score of the normality rate (a value determined within the range of the second bonus quantitative score of the normality rate) can be added together to obtain the normality rate quantitative index of the gas well.

[0087] In an optional embodiment, a quantitative criterion for evaluating stable operating time is constructed based on the proportion of amplitude stability time of plunger oil pressure and plunger sleeve pressure in the time domain, and the number of sidelobes in the frequency domain, including:

[0088] The proportion of time-domain amplitude stability duration of plunger oil pressure and plunger sleeve pressure was determined based on effective historical data from multiple gas wells.

[0089] The number of side lobes in the frequency domain of plunger oil pressure and plunger sleeve pressure is determined based on the spectrum diagram.

[0090] A quantitative criterion for evaluating stable operating time was constructed based on the proportion of stable amplitude duration in the time domain and the number of sidelobes in the frequency domain of multiple gas wells.

[0091] In this embodiment of the application, the number of side lobes can also be obtained by analyzing the spectrum diagram. In the hydraulic sleeve pressure spectrum diagram, one peak represents one side lobe, such as... Figure 6 As shown.

[0092] The percentage of amplitude stabilization time for plunger oil pressure and plunger sleeve pressure can be obtained by analyzing the time domain diagram.

[0093] In an optional embodiment, a quantitative criterion for evaluating stable operating time is constructed based on the proportion of stable duration in the time domain amplitude of multiple gas wells and the number of sidelobes in the frequency domain, including:

[0094] The basic quantitative score range for stable operating time is determined based on the proportion of time-domain amplitude stability duration of multiple gas wells;

[0095] The first bonus quantification range for stable operating time is determined based on the number of side lobes of multiple gas wells;

[0096] The second bonus quantification range for stable operating time is determined based on the oil-casing pressure difference of multiple gas wells;

[0097] A normal operation rate evaluation criterion is constructed to quantify the stable operation time of gas wells by adding points based on the basic quantitative score range, the first bonus quantitative range, and the second bonus quantitative range of stable operation time, thereby obtaining a quantitative index of stable operation time of gas wells.

[0098] In this embodiment, based on the proportion of stable duration of time-domain amplitude of multiple gas wells, the basic quantitative score range of stable operating time can be divided into three categories: (0, X1], (X1, X2], and (X2, 1). The first bonus quantitative range of stable operating time can be obtained by statistically analyzing the number of side lobes of multiple gas wells, such as [0, K1], (K1, K2], and (K2, +∞). The second bonus quantitative range of stable operating time can be obtained by statistically analyzing the oil-casing pressure difference of multiple gas wells, such as (0, H1], (H1, H2], and (H2, +∞).

[0099] When evaluating the stable operating time of any gas well, the basic quantitative score of the stable operating time (a value determined within the range of the basic quantitative score of stable operating time), the first bonus quantitative score of the stable operating time (a value determined within the range of the first bonus quantitative score of stable operating time), and the second bonus quantitative score of the stable operating time (a value determined within the range of the second bonus quantitative score of stable operating time) can be added together to obtain the stable operating time quantitative index of the gas well.

[0100] As a first example, 2000 sets of sample gas well data (effective historical control data of gas wells) were taken. Labels were constructed for the data in terms of normal operation rate and stable operating time. Based on the constructed dataset, normal operation rate discrimination condition analysis was performed, dividing the data into two categories: excellent operating status and poor operating status. Sidelobe connectivity was calculated for each category. According to the statistical results:

[0101] In the samples with poor operating performance, 83% of the gas wells had connected side lobes, while 17% of the gas wells had unconnected side lobes.

[0102] In the sample with excellent operating performance, the proportion of gas wells with connected side lobes was 5%, while the proportion of gas wells with unconnected side lobes was 95%.

[0103] Based on the above analysis, quantitative indicators for normal operation rate and stable running time are constructed, as shown in Table 1:

[0104] Table 1. Criteria for constructing quantitative indicators of normal operation rate and stable operation time

[0105]

[0106]

[0107] The values ​​of Y1, Y2, X1, and X2 in Table 1 are given based on the actual situation and the statistical results in the first example of the dataset. The values ​​are different for natural gas wells in different regions and at different production stages. The values ​​of H1, H2, K1, and K2 are given based on the statistical results and the actual situation. In this embodiment of the application, data from 2000 gas wells in the First Gas Production Plant of Changqing Oilfield, PetroChina (June 12, 2021 - June 19, 2021) were analyzed to obtain the corresponding parameter values, as shown in Table 2.

[0108] Table 2. Parameters and corresponding values ​​for constructing indicators

[0109] numerical values 0.60 0.80 0.60 0.80 2 5 5 10

[0110] In an optional embodiment, after obtaining the quantitative indicators of normality rate and stable operating time for monitoring gas well production quality based on the quantitative criteria for normality rate evaluation and the quantitative criteria for stable operating time evaluation, the method further includes:

[0111] The effectiveness of the normality rate evaluation quantification criterion and the stable running time evaluation quantification criterion was verified based on a deep learning model.

[0112] In this embodiment, four types of neural networks—BP neural network, random forest, BNN neural network, and CNN neural network—were used to analyze 2000 sets of gas well data. The training set and the test set were divided into a 7:3 ratio. The prediction results are as follows: Figures 8-11 As shown. Among them, Figure 8 The result is the prediction from the BP neural network; Figure 9 This is the result of a random forest prediction. Figure 10 The prediction result of the BNN neural network; Figure 11 This is the prediction result from the CNN neural network.

[0113] The prediction accuracy of the four neural networks mentioned above is compared, and the results are shown in Figure 3:

[0114] Table 3. Comparison of Neural Network Prediction Accuracy

[0115]

[0116] As shown in Table 3, among the four types of neural networks, the CNN convolutional neural network has higher accuracy in both normal rate prediction and stable running time prediction.

[0117] The normality rate model achieves the highest prediction accuracy when using five convolutional layers and three fully connected layers, while the stable running time model achieves the highest prediction accuracy when using four convolutional layers and three fully connected layers.

[0118] Specifically, the process of training a CNN convolutional neural network accuracy prediction model is as follows: Figure 13 As shown. The normality prediction model uses 5 layers of convolution (i.e., Figure 13 The network structure consists of three layers: convolution 1, convolution 2, convolution 3, convolution 4, and convolution 5, forming a 3-layer fully connected network. Figure 14 The graph showing the normality loss function results indicates that the loss value gradually decreases as the number of training iterations increases, indicating model convergence. Figure 15 The graph showing the training accuracy results of the normal rate shows that the accuracy of the normal rate gradually increases with the number of iterations during the training process. After 600 iterations, the highest accuracy reaches 96.0%.

[0119] The process of training a stable runtime prediction model for a CNN convolutional neural network is as follows: Figure 12 As shown. The stable runtime prediction model uses 4 layers of convolution (i.e., Figure 12 The network structure consists of three fully connected layers: convolution 1, convolution 2, convolution 3, and convolution 4. Figure 16 The graph showing the stable runtime loss function results indicates that the loss value gradually decreases with increasing training iterations, indicating model convergence. Figure 17 The graph showing the stable running time training accuracy results indicates that the accuracy of the normality rate gradually increases with the number of iterations. After 700 iterations, the highest accuracy reaches 97.5%.

[0120] Based on the same principles as the methods provided in the embodiments of this application, the embodiments of this application also provide a quantitative evaluation system for monitoring the production status of natural gas wells, such as... Figure 18 As shown, the system includes:

[0121] Data acquisition module 1801 is used to acquire effective historical control data of gas wells over time; effective historical control data includes plunger oil pressure and plunger sleeve pressure;

[0122] The quantification criterion construction module 1802 is used to construct a normality evaluation quantification criterion based on the time-domain fluctuation of plunger oil pressure and plunger sleeve pressure, as well as the frequency-domain sidelobe connectivity.

[0123] The quantification criterion construction module 1802 is also used to construct a quantification criterion for evaluating stable operating time based on the proportion of amplitude stability time of plunger oil pressure and plunger sleeve pressure in the time domain and the number of side lobes in the frequency domain.

[0124] The quantitative index generation module 1803 is used to obtain quantitative indicators of normal rate and stable operation time for monitoring the production quality of gas wells based on the quantitative criteria for normal rate evaluation and the quantitative criteria for stable operation time evaluation.

[0125] In this embodiment, considering that most related evaluations remain at the qualitative level and cannot quantitatively evaluate the production quality of gas wells, a quantitative criterion for normality rate evaluation and a quantitative criterion for stable operating time evaluation are proposed. The quantitative index generation module, based on these criteria, acquires quantitative indicators for normality rate and stable operating time used to monitor gas well production quality. This enables quantitative evaluation of gas well production quality and allows for a unified evaluation of the actual gas well operating status, improving the accuracy of the evaluation. Specifically, the quantitative criteria for normality rate evaluation and stable operating time evaluation are constructed based on effective historical control data. That is, the data acquisition module first obtains effective historical control data of the gas well changing over time. This allows for quantitative evaluation of the natural gas well control system's operation without needing to understand the control mechanism of the plunger gas lift or the actual gas production of the well. Then, the quantitative index generation module constructs a normality rate evaluation quantification criterion based on the time-domain fluctuations of plunger oil pressure and plunger sleeve pressure in effective historical control data, as well as the frequency-domain sidelobe connectivity. It also constructs a stable operating time evaluation quantification criterion based on the proportion of stable amplitude duration of plunger oil pressure and plunger sleeve pressure in the time domain, and the number of sidelobes in the frequency domain. Using the normality rate evaluation quantification criterion and stable operating time evaluation quantification criterion constructed using the above methods to monitor the production quality of gas wells can further assist in improving gas well production quality and effectively enhance the effectiveness and scalability of plunger gas lift control monitoring technology.

[0126] The quantitative evaluation system for monitoring the production status of natural gas wells provided in this application embodiment can achieve... Figures 1 to 17 The various processes implemented in the method embodiments are not described in detail here to avoid repetition.

[0127] The quantitative evaluation system for monitoring the production status of natural gas wells in this application can execute the quantitative evaluation method for monitoring the production status of natural gas wells provided in this application. The implementation principles are similar. The actions performed by each module and unit in the quantitative evaluation system for monitoring the production status of natural gas wells in each embodiment of this application correspond to the steps in the quantitative evaluation method for monitoring the production status of natural gas wells in each embodiment of this application. For detailed functional descriptions of each module of the quantitative evaluation system for monitoring the production status of natural gas wells, please refer to the descriptions in the corresponding quantitative evaluation methods for monitoring the production status of natural gas wells shown above. They will not be repeated here.

[0128] Based on the same principles as the methods shown in the embodiments of this application, this application also provides an electronic device, which may include, but is not limited to, a processor and a memory; the memory is used to store computer programs; the processor is used to execute the quantitative evaluation method for monitoring the production status of natural gas wells shown in any optional embodiment of this application by calling the computer program. Compared with the prior art, the quantitative evaluation method for monitoring the production status of natural gas wells provided in this application, considering that most related evaluations remain at the qualitative level and cannot quantitatively evaluate the production quality of gas wells, proposes a normal rate evaluation quantitative criterion and a stable operating time evaluation quantitative criterion. Based on the normal rate evaluation quantitative criterion and the stable operating time evaluation quantitative criterion, quantitative indicators of normal rate and stable operating time used to monitor the production quality of gas wells are obtained, which can realize the quantitative evaluation of the production quality of gas wells, and can uniformly evaluate the actual working status of gas wells, thereby improving the accuracy of the evaluation of the production quality of gas wells. Among them, the normal rate evaluation quantitative criterion and the stable operating time evaluation quantitative criterion are constructed based on effective historical control data, that is, firstly, effective historical control data of gas wells changing over time are obtained, without needing to understand the control mechanism of plunger gas lift and the actual gas production of the gas well, so as to quantitatively evaluate the operation of the natural gas well control system. Then, based on the time-domain fluctuations of plunger oil pressure and plunger sleeve pressure in effective historical control data, as well as the frequency-domain sidelobe connectivity, a normality rate evaluation quantification criterion is constructed. Based on the proportion of stable amplitude duration of plunger oil pressure and plunger sleeve pressure in the time domain, and the number of sidelobes in the frequency domain, a stable operating time evaluation quantification criterion is constructed. Using the normality rate evaluation quantification criterion and stable operating time evaluation quantification criterion constructed using the above methods to monitor the production quality of gas wells can also help improve gas well production quality and effectively enhance the effectiveness and scalability of plunger gas lift control monitoring technology.

[0129] like Figure 19 As shown, Figure 19The illustrated electronic device 1900 can be a server, including a processor 1901 and a memory 1903. The processor 1901 and the memory 1903 are connected, for example, via a bus 1902. Optionally, the electronic device 1900 may also include a transceiver 1904. It should be noted that in practical applications, the transceiver 1904 is not limited to one unit, and the structure of this electronic device 1900 does not constitute a limitation on the embodiments of this application.

[0130] Processor 1901 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 1901 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0131] Bus 1902 may include a pathway for transmitting information between the aforementioned components. Bus 1902 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 1902 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 19 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0132] The memory 1903 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0133] The memory 1903 is used to store application code that executes the scheme of this application, and its execution is controlled by the processor 1901. The processor 1901 is used to execute the application code stored in the memory 1903 to implement the content shown in the foregoing method embodiments.

[0134] Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 19 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0135] The server provided in this application can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The terminal and server can be directly or indirectly connected via wired or wireless communication, which is not limited herein.

[0136] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A quantitative evaluation method for monitoring the production status of natural gas wells, characterized in that, The method includes: Acquire effective historical control data of the gas well over time; the effective historical control data includes plunger oil pressure and plunger sleeve pressure. Based on the time-domain fluctuations of the plunger oil pressure and the plunger sleeve pressure, and the frequency-domain sidelobe connectivity, a normality rate evaluation quantification criterion is constructed, including: determining the time-domain fluctuations of the plunger oil pressure and the plunger sleeve pressure based on the effective historical control data of multiple gas wells; mapping the plunger oil pressure, the plunger sleeve pressure, and the oil-sleeve pressure difference to the frequency domain using a preset transformation method to obtain a spectrum diagram; wherein, the transformation method includes Fourier transform and short-time Fourier transform; the oil-sleeve pressure difference is the difference between the plunger oil pressure and the plunger sleeve pressure; determining the frequency-domain sidelobe connectivity of the plunger oil pressure and the plunger sleeve pressure based on the spectrum diagram; the sidelobe connectivity includes sidelobe connectivity and... The side lobes are not connected. The normality rate evaluation quantification criterion is constructed based on the time-domain fluctuations and frequency-domain side lobe connectivity of multiple gas wells, including: determining the basic quantification score range of the normality rate based on the time-domain fluctuations of multiple gas wells; determining the second bonus quantification score of the normality rate based on the frequency-domain side lobe connectivity of multiple gas wells; determining the first bonus quantification range of the normality rate based on the oil-casing pressure difference of multiple gas wells; and constructing the normality rate evaluation criterion to perform bonus quantification on the normality rate of gas wells based on the basic quantification score range, the first bonus quantification score, and the second bonus quantification range of the normality rate, thereby obtaining the normality rate quantification index of the gas wells. Based on the proportion of the amplitude stability time of the plunger oil pressure and the plunger sleeve pressure in the time domain, and the number of side lobes in the frequency domain, a quantitative criterion for evaluating stable operating time is constructed. Based on the normality rate evaluation quantification criteria and the stable operation time evaluation quantification criteria, normality rate quantification indicators and stable operation time quantification indicators are obtained to monitor the production quality of gas wells.

2. The quantitative evaluation method for monitoring the production status of natural gas wells according to claim 1, characterized in that, The acquisition of effective historical control data of gas wells over time includes: Based on preset key descriptors, key gas well production data are obtained by filtering from pre-acquired gas well production data; the key descriptors include the plunger sleeve pressure, the plunger oil pressure, the solenoid valve status, and the production system. A support vector machine is constructed based on the key production data of the gas wells, and the support vector machine is used to filter normal operation data from the gas well production data to obtain the effective historical control data.

3. The quantitative evaluation method for monitoring the production status of natural gas wells according to claim 1, characterized in that, The condition for the sidelobe to be connected is: Where yi represents the spectral amplitude at a frequency of i Hz, i∈N.

4. The quantitative evaluation method for monitoring the production status of natural gas wells according to claim 1, characterized in that, Based on the proportion of the amplitude stability time of the plunger oil pressure and the plunger sleeve pressure in the time domain, and the number of sidelobes in the frequency domain, a quantitative criterion for evaluating stable operating time is constructed, including: The percentage of time-domain amplitude stability of the plunger oil pressure and the plunger sleeve pressure is determined based on the effective historical control data of multiple gas wells. The number of sidelobes in the frequency domain of the plunger oil pressure and the plunger sleeve pressure is determined based on the spectrum diagram. The quantitative criteria for evaluating stable operating time are constructed based on the proportion of stable amplitude duration in the time domain and the number of sidelobes in the frequency domain of multiple gas wells.

5. The quantitative evaluation method for monitoring the production status of natural gas wells according to claim 4, characterized in that, The method of constructing the quantitative criteria for evaluating stable operating time based on the proportion of stable duration in the time domain and the number of sidelobes in the frequency domain of multiple gas wells includes: The basic quantitative score range for stable operating time is determined based on the proportion of stable time duration of multiple gas wells in the time domain amplitude. The second bonus quantification range for stable operating time is determined based on the number of side lobes of multiple gas wells; The first bonus quantification range for stable operating time is determined based on the oil-casing pressure difference of multiple gas wells; The normality rate evaluation criterion is constructed to add points to the stable operating time of the gas well based on the basic quantitative score range of the stable operating time, the second quantitative score range of the stable operating time, and the first quantitative score range of the stable operating time, so as to obtain the quantitative index of the stable operating time of the gas well.

6. The quantitative evaluation method for monitoring the production status of natural gas wells according to claim 1, characterized in that, After obtaining the normality rate quantitative index and the stable operating time quantitative index for monitoring gas well production quality based on the normality rate evaluation quantification criterion and the stable operating time evaluation quantification criterion, the method further includes: The effectiveness of the normality rate evaluation quantification criterion and the stable running time evaluation quantification criterion was verified based on a deep learning model.

7. A quantitative evaluation system for monitoring the production status of natural gas wells, implemented according to any one of claims 1 to 6, characterized in that, The system includes: The data acquisition module is used to acquire effective historical control data of the gas well over time; the effective historical control data includes plunger oil pressure and plunger sleeve pressure. The quantification criterion construction module is used to construct a normality evaluation quantification criterion based on the time-domain fluctuation of the plunger oil pressure and the plunger sleeve pressure, as well as the frequency-domain sidelobe connectivity. The quantification criterion construction module is also used to construct a quantification criterion for evaluating stable operating time based on the proportion of amplitude stability time of the plunger oil pressure and the plunger sleeve pressure in the time domain, and the number of side lobes in the frequency domain. The quantitative index generation module is used to obtain quantitative indicators of normal rate and quantitative indicators of stable operation time for monitoring the production quality of gas wells, based on the normal rate evaluation quantitative criteria and the stable operation time evaluation quantitative criteria.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method of any one of claims 1 to 6.

Images