Method and system for operating a dual frequency integrated booster gas lift integrated compressor

Abstract

The present application relates to the technical field of oil and gas exploitation, and discloses a dual-frequency integrated pressurization gas lift integrated compressor operation control method and system, which predicts the gas lift demand pressure change sequence and the pressurization demand pressure change sequence of each gas well through the gas well correlation characteristics, then generates an operation control instruction set in combination with the first group network information and the second group network information in the pipe network connection relationship, and drives and controls the gas lift frequency conversion cylinder pipeline unit and the pressurization frequency conversion cylinder pipeline unit of each dual-frequency integrated pressurization gas lift integrated compressor respectively to provide gas lift pressure output and pressurization pressure output. Thus, the present application establishes the well-machine adaptation rule by fusing the gas well correlation characteristics, the production fluctuation coefficient and the fracture interweaving influence factor, quantifying the compressor loss coefficient and combining the pipe network pressure chain fluctuation threshold, significantly improves the stability of the dual-frequency integrated pressurization gas lift integrated compressor operation and the accuracy of the pressure control, and guarantees the stable output of the gas well productivity.

Description

Technical Field

[0001] This invention relates to the field of oil and gas extraction technology, and in particular to a method and system for operating control of a dual-frequency integrated booster air lift compressor. Background Technology

[0002] When conducting multi-well group development of oil and gas in a target area, the multi-well group development task has the following characteristics because different well groups may have different characteristics and states at the same time: the number of gas wells in the target area is dense (usually 5-20), the gas well production capacity varies significantly (high-yield wells and low-yield liquid accumulation wells coexist), and the pipeline network adopts a manifold coupling connection (multiple wells share the gathering and transportation pipeline).

[0003] In the process of oil and gas extraction and operation, well groups typically require dual services: gas lift drainage and pressurized external transportation. Traditional well groups often use a single variable frequency compressor to independently drive these processes, necessitating more compressor units for the same well group scenario. This significantly complicates the management of these on-site compressor units. While some technologies have proposed the theoretical research of dual variable frequency integrated compressors, which can effectively reduce the number of on-site compressor units, in practical applications, the interwoven distribution of artificial and natural formation fractures leads to short-term fluctuations in gas well production. Furthermore, due to varying compressor wear conditions and pipeline coupling constraints, dual variable frequency integrated compressor units often encounter problems such as compressors with low wear tolerance bearing high-frequency fluctuating loads, and multiple well connections causing cascading pressure oscillations in the pipeline network. This increases the difficulty of dynamically adapting compressor pressure output and places stringent demands on the accuracy and stability of well rig coordinated control.

[0004] Therefore, how to consider the impact of factors such as changes in gas lift demand pressure and booster demand pressure caused by fluctuations in the production of different gas wells, compressor unit losses, and pipeline coupling constraints on the dynamic adaptation of dual-frequency integrated compressors to multi-well group scenarios, and improve the accuracy and stability of well rig collaborative control, is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] This invention provides a method and system for controlling the operation of a dual-frequency integrated booster air lift compressor, aiming to solve at least one of the above-mentioned technical problems.

[0006] To achieve the above objectives, the present invention provides a method for operating control of a dual-frequency integrated booster air-lift compressor, the method comprising:

[0007] Obtain operational condition association information for several gas wells within a target area; wherein, the operational condition association information includes gas well association characteristics and pipeline connection relationships;

[0008] Based on the gas well correlation characteristics, predict the gas lift demand pressure change sequence and pressurization demand pressure change sequence for each gas well during the target operating period;

[0009] Based on the gas lift demand pressure change sequence and the booster demand pressure change sequence, combined with the first network information between gas wells and the second network information between the dual-frequency integrated booster gas lift compressor and the gas well in the pipeline connection relationship, an operating control instruction set for each dual-frequency integrated booster gas lift compressor is generated.

[0010] According to the set of operation control instructions, the air lift variable frequency cylinder pipeline unit and the booster variable frequency cylinder pipeline unit of each dual-frequency integrated booster air lift compressor are driven and controlled respectively to provide air lift pressure output and booster pressure output.

[0011] Optionally, obtain the operational status correlation information of several gas wells within the target area, specifically including:

[0012] Collect formation parameters, historical production data, liquid accumulation change records, and historical response data of several gas wells within the target area to form a basic dataset of gas wells;

[0013] Based on the basic dataset of several gas wells, gas well correlation features are extracted; wherein, the gas well correlation features include the fracture connectivity coefficient between gas wells, the production capacity correlation coefficient, the pressure fluctuation synchronization rate, and the liquid accumulation volume cooperative change index.

[0014] Collect data on the manifold layout, pipeline diameter, pressure transmission coefficient, and valve connection status of the pipeline network within the target area, and construct a pipeline network connection relationship consisting of the first group of network information between gas wells and the second group of network information between the dual-frequency integrated booster gas lift compressor and the gas wells.

[0015] The first network information is a manifold coupling relationship matrix between gas wells, and the first matrix element in the manifold coupling relationship matrix includes the pressure transmission efficiency between gas wells and the pipeline load superposition coefficient; the second network information is a connectability matrix between the dual-frequency integrated booster gas lift compressor and the gas well, and the second matrix element in the connectability matrix includes the passage existence identifier, the maximum pipeline pressure value, and the upper limit of flow rate.

[0016] Optionally, based on the gas well correlation characteristics, the steps for predicting the gas lift demand pressure change sequence and the booster demand pressure change sequence for each gas well during the target operating period specifically include:

[0017] The gas well-related features are normalized to generate a standardized feature vector;

[0018] By incorporating short-term fluctuations in gas well production and the interplay of artificial and natural fractures into the standardized feature vector, a dual-pressure time-series prediction model based on LSTM is constructed.

[0019] The standardized feature vector, historical gas well pressure data, and dynamic formation fracture monitoring data are input into the dual-pressure time-series prediction model for training, thereby obtaining the trained pressure demand prediction model.

[0020] The trained model outputs the gas lift demand pressure change sequence and the booster demand pressure change sequence for each gas well during the target operating period.

[0021] Optionally, the steps of constructing a dual-pressure time-series prediction model based on LSTM are as follows: Incorporating short-term fluctuations in gas well production and the interplay of artificial and natural fractures into the standardized feature vector.

[0022] Based on historical gas well production data, the production fluctuation coefficient per unit time is calculated to quantify the impact weight of short-term production fluctuations on pressure demand.

[0023] By capturing the formation fracture propagation status through microseismic monitoring data, a fracture interweaving influence factor is generated; wherein, the fracture interweaving influence factor is used to characterize the dynamic effect of the connection between artificial fractures and natural fractures on gas well production capacity and pressure demand.

[0024] The production fluctuation coefficient and crack interweaving influence factor are used as additional input features and fused with the standardized feature vector to construct the input layer of the LSTM-based dual-pressure time series prediction model.

[0025] The number of hidden layer nodes, number of iterations and learning rate of the LSTM-based dual-pressure time series prediction model are preset. The actual pressure change sequence of the gas well is used as the output label. The Adam optimizer used to train the model is preset to obtain the LSTM-based dual-pressure time series prediction model.

[0026] Optionally, based on the gas lift demand pressure change sequence and the booster demand pressure change sequence, and combined with the first network information between gas wells and the second network information between the dual-frequency integrated booster gas lift compressor and the gas well in the pipeline connection relationship, the steps for generating the operation control instruction set for each dual-frequency integrated booster gas lift compressor specifically include:

[0027] Acquire historical operating data for each dual-frequency integrated booster air-lift compressor; wherein, the historical operating data includes speed adjustment frequency, fluctuation amplitude, fault records, and cumulative operating time;

[0028] Based on the historical operating data, the compressor loss coefficient is calculated, and the expression is as follows:

[0029] ;

[0030] In the formula, L is the loss coefficient. For cumulative runtime, For the total design duration, Fault frequency Total number of operating days This represents the largest fluctuation in history. This is the rated maximum fluctuation range;

[0031] Based on the first network information, calculate the pipeline pressure chain fluctuation threshold when multiple wells are connected to the same compressor, and establish well rig adaptation rules by combining the connectivity identifier of the second network information.

[0032] According to the well rig adaptation rules, the pressure change sequence of each gas well is assigned to the corresponding dual-frequency integrated booster air lift compressor, generating a set of operating control instructions containing target speed and pressure output values.

[0033] Optionally, based on the first network information, the threshold for pipeline pressure cascading fluctuations when multiple wells are connected to the same compressor is calculated. Combined with the connectivity identifier of the second network information, a well rig adaptation rule is established, specifically including:

[0034] Extract the pressure transmission efficiency and manifold load superposition coefficient of the gas wells that the target compressor can access from the gas well coupling relationship matrix of the first group of network information;

[0035] Obtain the fluctuation amplitude of the pressure change sequence of each connected gas well's boosting demand. Based on the pressure transmission efficiency, manifold load superposition coefficient, and fluctuation amplitude, calculate the pipeline network pressure cascading fluctuation threshold, expressed as:

[0036] ;

[0037] In the formula, Let be the pressure transmission efficiency of the i-th gas well. This is the load superposition factor for the manifold. Let T be the fluctuation amplitude of the i-th gas well, and T be the threshold for pipeline pressure cascading fluctuations.

[0038] From the connectivity matrix of the second network information, select the set of compressors that have a path to the target gas well, and calculate the fit degree of each compressor in the set. The expression is:

[0039] ;

[0040] In the formula, F represents the fitness level. The score represents the matching between the loss coefficient and the fluctuation amplitude. Score for pressure-bearing compatibility of the pipeline;

[0041] Based on the compatibility of each compressor in the set, a well rig compatibility rule is established; wherein, the well rig compatibility rule is configured as follows: select the compressor with the highest compatibility as the access device for the target gas well; if there are multiple compressors with the same compatibility, a secondary screening is performed based on the principle of minimizing the pipeline pressure transmission loss calculated by pressure transmission efficiency and pipeline length.

[0042] Optionally, according to the well rig adaptation rules, the pressure change sequence of each gas well is assigned to the corresponding dual-frequency integrated booster gas lift compressor, and an operation control instruction set containing the target speed and pressure output value is generated. This specifically includes the following steps:

[0043] All gas wells are sorted according to their production capacity priority to form a gas well allocation priority sequence;

[0044] Based on the priority sequence, the gas lift demand pressure change sequence and the boosting demand pressure change sequence of each gas well are sequentially assigned to the gas lift variable frequency compression pipeline unit or the boosting variable frequency compression pipeline unit of the dual variable frequency integrated boosting gas lift compressor with the highest compatibility.

[0045] The pressure change sequences of multiple gas wells connected to the same compressor within the same time period are aligned on the time axis and superimposed with the load. The target speed of each pipeline unit is calculated based on the superimposed pressure. The expression is as follows:

[0046] ;

[0047] In the formula, For the target speed, This is the compressor's rated speed. The pressure after superposition, This refers to the compressor's rated pressure output value.

[0048] Verify whether the superimposed pipeline pressure chain fluctuation prediction value exceeds the threshold T. If so, the gas well with the lowest priority is reassigned to the gas lift variable frequency compression pipeline unit or the booster variable frequency compression pipeline unit of the second-best matching compressor.

[0049] The target speed, the superimposed pressure output value, and the pipeline unit type are integrated to generate a standardized set of operation control instructions.

[0050] Optionally, according to the set of operating control instructions, the air lift variable frequency cylinder pipeline unit and the booster variable frequency cylinder pipeline unit of each dual-frequency integrated booster air lift compressor are driven and controlled respectively to provide air lift pressure output and booster pressure output steps, specifically including:

[0051] The set of operation control commands is distributed to the dual-frequency integrated booster air-lift compressor according to the type of pipeline unit. The target pressure value is converted into the speed control signal of the frequency converter, which drives the compressor cylinder of the air-lift variable frequency compression pipeline unit and the booster variable frequency compression pipeline unit to run at the target speed.

[0052] Real-time acquisition of actual gas lift pressure and actual boost pressure at the wellhead of the gas well; calculation of the deviation between the commanded target value and the actual value; and determination of whether the gas lift pressure deviation or boost pressure deviation meets the error requirements.

[0053] If so, the inverter speed signal is dynamically corrected by combining the pressure transmission efficiency and the influence factor of crack interweaving until the deviation falls back to the error requirement range.

[0054] Optionally, the inverter speed signal is dynamically corrected by combining pressure transmission efficiency and crack interweaving influence factors until the deviation falls back to the required error range. This includes the following steps:

[0055] Determine the cause of the deviation; the determination method is as follows: determine whether it is caused by gas well production fluctuation based on the actual pressure fluctuation frequency of the gas well and the predicted content fluctuation frequency, and determine whether it is caused by pipeline network cascading fluctuation based on the actual pressure fluctuation of the gas well and the pressure fluctuation of adjacent gas wells.

[0056] When the deviation is caused by fluctuations in gas well production, the first formula is used to correct the inverter speed signal; when the deviation is caused by fluctuations in pipeline network, the second formula is used to correct the inverter speed signal.

[0057] The expression for the first formula is:

[0058] ;

[0059] The expression for the second formula is:

[0060] ;

[0061] In the formula, For the corrected rotational speed, The current rotational speed, This is the pressure deviation value. The influencing factor of crack interweaving, For pressure transmission efficiency.

[0062] Furthermore, to achieve the above objectives, the present invention also provides a dual-frequency conversion integrated booster air lift compressor operation control system, comprising:

[0063] Several dual-frequency integrated booster air-lift compressors are configured to have air-lift variable frequency cylinder pipeline units and booster variable frequency cylinder pipeline units.

[0064] The control terminal is connected to several dual-frequency integrated booster air-lift compressors and is configured to execute the dual-frequency integrated booster air-lift compressor operation control method described in any of the above descriptions.

[0065] The beneficial effects of this invention are as follows: It proposes an operation control method and system for a dual-frequency integrated booster air lift compressor. By acquiring the gas well correlation characteristics and pipeline connection relationships of several gas wells in the target area, and using the gas well correlation characteristics, it predicts the gas lift demand pressure change sequence and booster demand pressure change sequence of each gas well during the target operating period. Then, combined with the first network information between gas wells in the pipeline connection relationship and the second network information between the dual-frequency integrated booster air lift compressor and the gas well, it generates an operation control instruction set and drives and controls the gas lift variable frequency cylinder pipeline unit and the booster variable frequency cylinder pipeline unit of each dual-frequency integrated booster air lift compressor, providing gas lift pressure output and booster pressure output. Therefore, this invention integrates gas well correlation characteristics, production fluctuation coefficient, and fracture interweaving influence factors to quantify the compressor loss coefficient. Simultaneously, it establishes well rig adaptation rules by combining pipeline pressure chain fluctuation thresholds. This guides the connection drive between the gas lift variable frequency cylinder pipeline unit and the booster variable frequency cylinder pipeline unit in the dual-frequency integrated booster gas lift compressor and the gas well. It can respond in real time to dynamic changes in gas well operating conditions and pipeline status, quickly offsetting the impact of external disturbances on pressure output. This significantly improves the stability of compressor operation and the accuracy of pressure control, ensuring stable output of gas well production capacity and enhancing the accuracy and stability of well rig collaborative control. Attached Figure Description

[0066] Figure 1 This is a flowchart illustrating the operation control method of the dual-frequency integrated booster air lift compressor according to an embodiment of the present invention. Detailed Implementation

[0067] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0068] This invention provides a method for controlling the operation of a dual-frequency integrated booster air-lift compressor, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the operation control method of the dual-frequency integrated booster air lift compressor according to an embodiment of the present invention.

[0069] In this embodiment, a method for controlling the operation of a dual-frequency integrated booster air-lift compressor includes:

[0070] S100: Obtain the operating condition association information of several gas wells within the target area; wherein, the operating condition association information includes gas well association characteristics and pipeline connection relationships.

[0071] Specifically, step S100 includes the following execution process:

[0072] Formation parameters, historical production data, fluid accumulation change records, and historical response data of several gas wells within the target area are collected to form a basic gas well dataset. Based on the basic gas well dataset, gas well correlation features are extracted. These features include the inter-well fracture connectivity coefficient, production correlation coefficient, pressure fluctuation synchronization rate, and fluid accumulation co-change index. Data on the manifold layout, pipeline diameter, pressure transmission coefficient, and valve connection status of the pipeline network within the target area are collected to construct a pipeline network connection relationship consisting of a first group of network information between gas wells and a second group of network information between the dual-frequency integrated booster gas lift compressor and the gas wells.

[0073] In this embodiment of the invention, multi-dimensional data acquisition is first conducted around the core of gas well production capacity and pipeline coupling. Specifically, formation parameter monitoring sensors, production capacity metering devices, liquid accumulation detection modules, and pressure response acquisition units are deployed on the gas well side, covering the bottom of the gas well, the wellhead, and the near-wellbore formation area: the formation parameter sensors collect data such as reservoir pressure, porosity, and fracture distribution in real time; the production capacity metering device records daily gas production and liquid production at 30-minute intervals; the liquid accumulation detection module obtains the liquid accumulation height in the wellbore through an acoustic level gauge and converts it into liquid accumulation data; the pressure response acquisition unit synchronously records the wellhead pressure change curve after gas lift / boost pressure adjustment.

[0074] For gas well correlation feature extraction: Spatial clustering algorithms are used to analyze microseismic monitoring data to calculate the fracture connectivity coefficient between gas wells (values ​​range from 0 to 1, with higher values ​​indicating stronger connectivity). Then, based on Pearson correlation analysis, correlation coefficients for daily gas production and liquid accumulation of different gas wells are calculated, yielding the production correlation coefficient and the liquid accumulation synergistic change index. Finally, using time-series aligned pressure data, the synchronization degree of pressure fluctuations between gas wells is statistically analyzed to generate a pressure fluctuation synchronization rate. It should be noted that these features quantify the correlation between gas wells from two dimensions: formation connectivity and production linkage, providing a lateral correlation basis for subsequent pressure prediction.

[0075] For pipeline-side data collection: Topological data such as manifold layout, pipeline diameter, and valve location are acquired through a pipeline GIS system. Pressure transmission data for different pipe sections is collected at 15-minute intervals using pipeline pressure sensors, and the pressure transmission coefficient is calculated using fluid dynamics simulation. Simultaneously, valve status monitoring modules record valve opening and closing status to determine the existence of pathways between gas wells and compressors, and between gas wells themselves. Based on this data, two types of network information are constructed: The first network information is represented by a manifold coupling relationship matrix, where the rows and columns are gas well numbers, and the elements include the pressure transmission efficiency of the corresponding two gas wells and the pipeline load superposition coefficient; the second network information is represented by a connectability matrix, where the rows are gas well numbers, the columns are compressor numbers, and the elements include a pathway presence indicator (0 = no pathway, 1 = pathway present), the maximum pipeline pressure, and the maximum flow rate.

[0076] After collecting and constructing the basic dataset of gas wells, gas well correlation characteristics, and pipeline connection relationships, the three types of data are aggregated to form unified operational condition correlation information. This information set contains a complete operational condition description of the gas well's own characteristics, inter-well correlations, and pipeline constraints, providing a foundation for subsequent pressure prediction and well rig matching, and enabling control methods to make decisions based on global operational condition information.

[0077] S200: Based on the gas well correlation characteristics, predict the gas lift demand pressure change sequence and pressurization demand pressure change sequence for each gas well during the target operating period.

[0078] Specifically, step S200 includes the following execution process:

[0079] S210: Normalize the gas well associated features to generate a standardized feature vector.

[0080] In this embodiment of the invention, considering that the physical dimensions of the gas well-related features are different, directly using them for model training will lead to an imbalance in feature weights. Therefore, before training, it is necessary to perform standardized normalization processing on each feature to eliminate the influence of the difference in dimensions on model training and generate standardized feature vectors.

[0081] S220: Based on the standardized feature vector, the short-term fluctuation range of gas well production and the influence factors of the interweaving of artificial and natural fractures are incorporated to construct a dual-pressure time series prediction model based on LSTM.

[0082] Specifically, step S220 includes the following execution process:

[0083] Based on historical gas well production data, a production fluctuation coefficient per unit time is calculated to quantify the impact weight of short-term production fluctuations on pressure demand. Formation fracture propagation status is captured using microseismic monitoring data, generating a fracture interweaving influence factor. This factor characterizes the dynamic effect of artificial and natural fracture connectivity on gas well production capacity and pressure demand. The production fluctuation coefficient and fracture interweaving influence factor are used as additional input features and fused with the standardized feature vector to construct the input layer of an LSTM-based dual-pressure time-series prediction model. The number of hidden layer nodes, iteration count, and learning rate of the LSTM-based dual-pressure time-series prediction model are preset, with the actual gas well pressure change sequence as the output label. An Adam optimizer is preset for training the model to obtain the LSTM-based dual-pressure time-series prediction model.

[0084] To determine the production fluctuation coefficient, based on historical gas well production data, a sliding window method (e.g., a window length of 7 days) is used to calculate the production fluctuation coefficient per unit time. The expression is as follows:

[0085] ;

[0086] In the formula, max(Q) represents the maximum daily gas production within the window, and min(Q) represents the minimum daily gas production within the window. δ represents the average daily gas production within the window, and δ is the production fluctuation coefficient.

[0087] To calculate the impact factor of fracture interweaving, the formation fracture propagation state is captured by a microseismic monitoring system, and parameters such as fracture length, width, and number of connected nodes are extracted. A weighted summation method is then used to generate the impact factor of fracture interweaving. For example, the impact of fracture interweaving on gas well productivity can be represented by the sum of the products of the first preset weight and the intersection density (number of fractures per unit area) of artificial and natural fractures, the second preset weight and the fracture connectivity rate (ratio of connected nodes to total nodes), and the third preset weight and the dynamic fracture propagation rate (length of propagation per day).

[0088] Subsequently, the standardized feature vectors are fused with the production fluctuation coefficient and the crack interweaving influence factor to form the model input layer features (dimension N×M, where N is the number of samples and M is the number of features); the model hidden layer is set with 3 layers of LSTM units, with 64 nodes in the first layer, 32 nodes in the second layer, and 16 nodes in the third layer, and the activation function is ReLU; the output layer has 2 neurons, corresponding to the air lift demand pressure and the boost pressure respectively, to obtain the basic configuration of the LSTM-based dual-pressure time series prediction model.

[0089] S230: Input the standardized feature vector, historical gas well pressure data, and formation fracture dynamic monitoring data into the dual-pressure time series prediction model for training to obtain the trained pressure demand prediction model.

[0090] Then, during model training, the historical pressure data in the gas well baseline dataset is divided into training and validation sets in a 7:3 ratio. The actual pressure change sequence for the target operating period (e.g., the next 24 hours, with a time granularity of 1 hour) is used as the output label. Iterative training is performed using the Adam optimizer with a learning rate of 0.001 and 100 iterations. Mean squared error (MSE) is used as the loss function during training, with the formula:

[0091] ;

[0092] Where T represents the number of time points in the prediction period. The actual pressure value at time t. Let be the predicted pressure value at time t. When the MSE of the validation set is lower than 0.01 MPa², training is stopped, and the trained dual-pressure time series prediction model is obtained.

[0093] S240: The trained model outputs the gas lift demand pressure change sequence and booster demand pressure change sequence for each gas well during the target operating period.

[0094] Finally, the standardized feature vector of the target gas well, the real-time production fluctuation coefficient, and the latest fracture interweaving influencing factors are input into the trained model to output the gas lift demand pressure sequence and pressurization demand pressure sequence for the next 24 hours.

[0095] S300: Based on the gas lift demand pressure change sequence and the booster demand pressure change sequence, combined with the first network information between gas wells in the pipeline connection relationship and the second network information between the dual-frequency integrated booster gas lift compressor and the gas well, generate a set of operation control instructions for each dual-frequency integrated booster gas lift compressor.

[0096] Specifically, step S300 includes the following execution process:

[0097] S310: Obtain historical operating data for each dual-frequency integrated booster air lift compressor; wherein, the historical operating data includes speed adjustment frequency, fluctuation amplitude, fault records and cumulative running time.

[0098] First, collect historical operating data for each dual-frequency inverter compressor, including speed adjustment frequency (times / hour), speed fluctuation amplitude (r / min), fault records (fault type, occurrence time, duration), and cumulative operating time (hours).

[0099] S320: Based on the historical operating data, calculate the compressor loss coefficient, expressed as:

[0100] ;

[0101] In the formula, L is the loss coefficient. For cumulative runtime, For the total design duration, Fault frequency Total number of operating days This represents the largest fluctuation in history. This is the rated maximum fluctuation range.

[0102] Then, the loss coefficient is calculated by weighted summation. The ratio of cumulative running time to total design time is used as the time percentage, the ratio of failure frequency to total running days is used as the daily average failure probability, and the ratio of historical maximum fluctuation amplitude to rated maximum fluctuation amplitude is used as the fluctuation amplitude percentage. These factors comprehensively reflect the operating loss status of the compressor. The lower the value, the more severe the compressor loss and the weaker its ability to withstand high-frequency fluctuating loads.

[0103] S330: Based on the first network information, calculate the pipeline pressure chain fluctuation threshold when multiple wells are connected to the same compressor, and establish well rig adaptation rules by combining the connectivity identifier of the second network information.

[0104] Specifically, step S330 includes the following execution process:

[0105] The pressure transmission efficiency and manifold load superposition coefficient of the target compressor to be connected to the gas well are extracted from the coupling relationship matrix between gas wells in the first group of network information. The fluctuation amplitude of the pressure change sequence of the boosting demand of each connected gas well is obtained. Based on the pressure transmission efficiency, manifold load superposition coefficient and fluctuation amplitude, the pipeline pressure chain fluctuation threshold is calculated. The set of compressors with a path to the target gas well is screened from the connectivity matrix of the second group of network information. The adaptability of each compressor in the set is calculated. Based on the adaptability of each compressor in the set, a well machine adaptation rule is established. The well machine adaptation rule is configured as follows: the compressor with the highest adaptability is selected as the access device of the target gas well. If there are multiple compressors with the same adaptability, a second screening is performed according to the principle of minimizing the pipeline pressure transmission loss calculated by the pressure transmission efficiency and pipeline length.

[0106] For calculating the pipeline pressure cascading fluctuation threshold, the pressure transmission efficiency of the gas wells to which the target compressor can be connected is extracted from the manifold coupling relationship matrix of the first group of network information. (i is the gas well number) and the manifold load superposition coefficient k; obtain the pressure fluctuation amplitude of each gas well from the pressure change sequence of boosting demand. The pressure cascading fluctuation threshold T of the pipeline network is calculated using the following formula, which characterizes the maximum pressure fluctuation that the pipeline network can withstand when multiple wells are connected. The expression is:

[0107] ;

[0108] In the formula, is the pressure conduction efficiency of the i-th gas well, is the gathering line load superposition coefficient, is the fluctuation amplitude of the i-th gas well, and T is the threshold of the network pressure chain reaction fluctuation; it should be noted that when multiple wells are connected simultaneously, the actual chain reaction fluctuation value T' should satisfy T' ≤ T, otherwise it will cause the network pressure oscillation.

[0109] For the calculation of the adaptability of each compressor in the set, from the connectivity matrix of the second network information, select the compressors that have a path (marked as 1) to the target gas well to form a compressor set S; calculate the adaptability F of each compressor in the set S, and the expression is:

[0110] ;

[0111] In the formula, F is the adaptability, is the matching score of the loss coefficient and the fluctuation amplitude, is the pressure-bearing adaptability score of the path pipeline.

[0112] Exemplarily, for the scores of and , the following logic is adopted to determine:

[0113] When the compressor loss coefficient L ≤ 0.6 and the gas well pressure fluctuation amplitude ≤ 10%, = 1.0; when 0.6 < L ≤ 0.8 and the gas well pressure fluctuation amplitude ≤ 20%, = 0.8; when L > 0.8 and the gas well pressure fluctuation amplitude ≤ 30%, = 0.6, in other cases = 0.3; when the maximum pressure-bearing value of the pipeline ≥ the maximum pressure demand of the gas well, = 1.0, otherwise = 0.

[0114] After that, based on the adaptability F, establish the well-compressor adaptability rule: preferentially select the compressor with the highest adaptability as the access device for the target gas well; if there are multiple compressors with the same adaptability (the difference ≤ 0.05), then calculate the network pressure conduction loss of each compressor (loss = pressure conduction efficiency × pipeline length), and select the compressor with the minimum loss as the final access device.

[0115] S340: According to the well-compressor adaptability rule, allocate the pressure change sequence of each gas well to the corresponding dual-frequency integrated pressurized gas lift integrated compressor to generate an operation control instruction set including the target speed and pressure output value.

[0116] Specifically, step S340 includes the following execution process:

[0117] All gas wells are sorted according to their production capacity priority to form a gas well allocation priority sequence. Based on the priority sequence, the gas lift demand pressure change sequence and the boost pressure demand pressure change sequence of each gas well are sequentially allocated to the gas lift variable frequency compression pipeline unit or boost pressure variable frequency compression pipeline unit of the dual variable frequency integrated boost pressure gas lift compressor with the highest compatibility. The pressure change sequences of multiple gas wells connected to the same compressor at the same time are time-axis aligned and load superimposed. The target speed of each pipeline unit is calculated based on the superimposed pressure. It is verified whether the superimposed pipeline pressure chain fluctuation prediction value exceeds the threshold T. If so, the gas well with the lowest priority is reassigned to the gas lift variable frequency compression pipeline unit or boost pressure variable frequency compression pipeline unit of the second best compatible compressor. The target speed, the superimposed pressure output value and the pipeline unit type are integrated to generate a standardized operation control instruction set.

[0118] In this embodiment of the invention, when generating the operation control instruction set, all gas wells are sorted according to their production capacity priority (e.g., high-yield wells > low-yield liquid accumulation wells > conventional wells) to form a gas well allocation priority sequence. Based on this sequence, the gas lift / boost pressure change sequence of each gas well is sequentially allocated to the compressor module with the highest compatibility (i.e., the gas lift sequence is allocated to the gas lift variable frequency compression pipeline unit, and the boosting sequence is allocated to the boosting variable frequency compression pipeline unit). The pressure change sequences of multiple gas wells connected to the same compressor within the same time period are aligned on the time axis, and the pressure requirements are superimposed according to the time granularity to obtain the total pressure requirement of the module. The target rotational speed of the module is calculated using the following formula:

[0119] ;

[0120] In the formula, For the target speed, This is the compressor's rated speed. The pressure after superposition, This is the compressor's rated pressure output value.

[0121] Following this, the superimposed pipeline pressure cascading fluctuation prediction value T′ is verified: if T′≤T, control commands are directly generated; if T′>T, the lowest priority gas well is reassigned to the corresponding module of the second-best matched compressor, and verification is repeated until the threshold requirement is met. Finally, the compressor ID, module type, target speed, pressure output value, and gas well ID are integrated into a standardized set of operation control commands.

[0122] S400: According to the set of operation control instructions, drive and control the air lift variable frequency cylinder pipeline unit and the booster variable frequency cylinder pipeline unit of each dual-frequency integrated booster air lift compressor respectively, and provide air lift pressure output and booster pressure output.

[0123] Specifically, step S400 includes the following execution process:

[0124] The operation control command set is distributed to the dual-frequency integrated booster air-lift compressor according to the pipeline unit type. The target pressure value is converted into the speed control signal of the frequency converter, driving the compressor cylinders of the air-lift frequency-converting compression pipeline unit and the booster frequency-converting compression pipeline unit to run at the target speed. The actual gas lift pressure and actual booster pressure at the gas wellhead are collected in real time. The deviation between the command target value and the actual value is calculated to determine whether the gas lift pressure deviation or booster pressure deviation meets the error requirements. If so, the frequency converter speed signal is dynamically corrected in combination with the pressure transmission efficiency and fracture interweaving influence factor until the deviation falls back to the error requirement range.

[0125] In this embodiment of the invention, the control instruction set is first distributed to the controller of the corresponding compressor. After the controller parses the instruction, it converts the target speed into a pulse width modulation (PWM) signal of the frequency converter, drives the variable frequency motor of the air lift / boost module to run at the target speed, and then controls the compressor cylinder to output the corresponding pressure.

[0126] In the pressure monitoring stage, a high-frequency acquisition strategy can be adopted, using a wellhead pressure sensor to collect the actual gas lift pressure at a frequency of 10 seconds per acquisition. and actual boost pressure Calculate and execute target values. , The deviation is expressed as:

[0127] ;

[0128] ;

[0129] Then, by setting the error requirement as If the deviation meets the requirements, the current speed will be maintained; if the deviation exceeds the requirements, the dynamic correction process will be initiated.

[0130] After this, the cause of the deviation is determined. The determination method is as follows: based on the actual pressure fluctuation frequency of the gas well and the predicted content fluctuation frequency, it is determined whether it is caused by the fluctuation of gas well production (for example, considering the difference in fluctuation frequency or the synchronicity of fluctuation). Based on the actual pressure fluctuation of the gas well and the pressure fluctuation of adjacent gas wells, it is determined whether it is caused by pipeline network cascading fluctuations. When the deviation is caused by the fluctuation of gas well production, the first formula is used to correct the inverter speed signal. When the deviation is caused by the pipeline network cascading fluctuations, the second formula is used to correct the inverter speed signal.

[0131] For example, the expression of the first formula is:

[0132] ;

[0133] For example, the expression for the second formula is:

[0134] ;

[0135] In the formula, For the corrected rotational speed, The current rotational speed, This is the pressure deviation value. The influencing factor of crack interweaving, For pressure transmission efficiency.

[0136] Therefore, this embodiment of the invention integrates gas well correlation characteristics, production fluctuation coefficient, and fracture interweaving influence factors to quantify the compressor loss coefficient and establish well rig adaptation rules by combining pipeline pressure chain fluctuation threshold. This guides the connection drive between the gas lift variable frequency cylinder pipeline unit and the booster variable frequency cylinder pipeline unit in the dual-frequency integrated booster gas lift compressor and the gas well. It can respond in real time to the dynamic changes in gas well operating conditions and pipeline status, quickly offset the impact of external disturbances on pressure output, significantly improve the stability of compressor operation and the accuracy of pressure control, ensure the stable output of gas well production capacity, and improve the accuracy and stability of well rig collaborative control.

[0137] In a preferred embodiment, the present invention also proposes an integrated dual-frequency conversion booster air lift compressor operation control system, the system comprising:

[0138] Several dual-frequency integrated booster air-lift compressors are configured to have air-lift variable frequency cylinder pipeline units and booster variable frequency cylinder pipeline units.

[0139] The control terminal is connected to several dual-frequency integrated booster air-lift compressors and is configured to execute the dual-frequency integrated booster air-lift compressor operation control method described in any of the above descriptions.

[0140] Other embodiments or specific implementations of the dual-frequency integrated booster air lift compressor operation control system of the present invention can be referred to the above-described method embodiments, and will not be repeated here.

[0141] It is understood that in the description of this specification, references to terms such as "one embodiment," "another embodiment," "other embodiments," or "first embodiment to Nth embodiment," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0142] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0143] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for controlling the operation of a dual-frequency integrated booster air-lift compressor, characterized in that, The method includes: Obtain operational condition correlation information for several gas wells within a target area; wherein, the operational condition correlation information includes gas well correlation characteristics and pipeline connection relationships; specifically including: Collect formation parameters, historical production data, liquid accumulation change records, and historical response data of several gas wells within the target area to form a basic dataset of gas wells; Based on the basic dataset of several gas wells, gas well correlation features are extracted; wherein, the gas well correlation features include the fracture connectivity coefficient between gas wells, the production capacity correlation coefficient, the pressure fluctuation synchronization rate, and the liquid accumulation volume cooperative change index. Collect data on the manifold layout, pipeline diameter, pressure transmission coefficient, and valve connection status of the pipeline network within the target area, and construct a pipeline network connection relationship consisting of the first group of network information between gas wells and the second group of network information between the dual-frequency integrated booster gas lift compressor and the gas wells. The first group of network information is a manifold coupling relationship matrix between gas wells, and the first matrix element in the manifold coupling relationship matrix includes the pressure transmission efficiency between gas wells and the pipeline load superposition coefficient; the second group of network information is a connectability matrix between the dual-frequency integrated booster gas lift compressor and the gas well, and the second matrix element in the connectability matrix includes the passage existence identifier, the maximum pipeline pressure value, and the upper limit of flow rate. Based on the gas well correlation characteristics, predict the gas lift demand pressure change sequence and pressurization demand pressure change sequence for each gas well during the target operating period; Based on the gas lift demand pressure change sequence and the booster demand pressure change sequence, combined with the first network information between gas wells and the second network information between the dual-frequency integrated booster gas lift compressor and the gas well in the pipeline connection relationship, an operating control instruction set for each dual-frequency integrated booster gas lift compressor is generated. According to the set of operation control instructions, the air lift variable frequency cylinder pipeline unit and the booster variable frequency cylinder pipeline unit of each dual-frequency integrated booster air lift compressor are driven and controlled respectively to provide air lift pressure output and booster pressure output.

2. The operation control method for the dual-frequency integrated booster air-lift compressor as described in claim 1, characterized in that, Based on the aforementioned gas well correlation characteristics, the steps for predicting the gas lift demand pressure change sequence and booster demand pressure change sequence for each gas well during the target operating period specifically include: The gas well-related features are normalized to generate a standardized feature vector; By incorporating short-term fluctuations in gas well production and the interplay of artificial and natural fractures into the standardized feature vector, a dual-pressure time-series prediction model based on LSTM is constructed. The standardized feature vector, historical gas well pressure data, and dynamic formation fracture monitoring data are input into the dual-pressure time-series prediction model for training, thereby obtaining the trained pressure demand prediction model. The trained model outputs the gas lift demand pressure change sequence and the booster demand pressure change sequence for each gas well during the target operating period.

3. The operation control method for the dual-frequency integrated booster air-lift compressor as described in claim 2, characterized in that, The steps for constructing a dual-pressure time-series prediction model based on LSTM are as follows: Incorporating short-term fluctuations in gas well production and the interplay of artificial and natural fractures into the standardized feature vector. Based on historical gas well production data, the production fluctuation coefficient per unit time is calculated to quantify the impact weight of short-term production fluctuations on pressure demand. By capturing the formation fracture propagation status through microseismic monitoring data, a fracture interweaving influence factor is generated; wherein, the fracture interweaving influence factor is used to characterize the dynamic effect of the connection between artificial fractures and natural fractures on gas well production capacity and pressure demand. The production fluctuation coefficient and crack interweaving influence factor are used as additional input features and fused with the standardized feature vector to construct the input layer of the LSTM-based dual-pressure time series prediction model. The number of hidden layer nodes, number of iterations and learning rate of the LSTM-based dual-pressure time series prediction model are preset. The actual pressure change sequence of the gas well is used as the output label. The Adam optimizer used to train the model is preset to obtain the LSTM-based dual-pressure time series prediction model.

4. The operation control method for the dual-frequency integrated booster air-lift compressor as described in claim 1, characterized in that, Based on the gas lift demand pressure change sequence and the booster demand pressure change sequence, combined with the first network information between gas wells and the second network information between the dual-frequency integrated booster gas lift compressor and the gas well in the pipeline connection relationship, the steps for generating the operation control instruction set for each dual-frequency integrated booster gas lift compressor are as follows: Acquire historical operating data for each dual-frequency integrated booster air-lift compressor; wherein, the historical operating data includes speed adjustment frequency, fluctuation amplitude, fault records, and cumulative operating time; Based on the historical operating data, the compressor loss coefficient is calculated, and the expression is as follows: ； In the formula, L is the loss coefficient. For cumulative runtime, For the total design duration, Fault frequency Total number of operating days This represents the largest fluctuation in history. This is the rated maximum fluctuation range; Based on the first network information, calculate the pipeline pressure chain fluctuation threshold when multiple wells are connected to the same compressor, and establish well rig adaptation rules by combining the connectivity identifier of the second network information. According to the well rig adaptation rules, the pressure change sequence of each gas well is assigned to the corresponding dual-frequency integrated booster air lift compressor, generating a set of operating control instructions containing target speed and pressure output values.

5. The operation control method for the dual-frequency integrated booster air-lift compressor as described in claim 4, characterized in that, Based on the first network information, the threshold for pipeline pressure cascading fluctuations when multiple wells are connected to the same compressor is calculated. Combined with the connectivity identifier of the second network information, a well rig adaptation rule is established, specifically including: Extract the pressure transmission efficiency and manifold load superposition coefficient of the gas wells that the target compressor can access from the gas well coupling relationship matrix of the first group of network information; Obtain the fluctuation amplitude of the pressure change sequence of each connected gas well's boosting demand. Based on the pressure transmission efficiency, manifold load superposition coefficient, and fluctuation amplitude, calculate the pipeline network pressure cascading fluctuation threshold, expressed as: ； In the formula, Let be the pressure transmission efficiency of the i-th gas well. This is the load superposition factor for the manifold. Let T be the fluctuation amplitude of the i-th gas well, and T be the threshold for pipeline pressure cascading fluctuations. From the connectivity matrix of the second network information, select the set of compressors that have a path to the target gas well, and calculate the fit degree of each compressor in the set. The expression is: ； In the formula, F represents the fitness level. The score represents the matching between the loss coefficient and the fluctuation amplitude. Score for pressure-bearing compatibility of the pipeline; Based on the compatibility of each compressor in the set, a well rig compatibility rule is established; wherein, the well rig compatibility rule is configured as follows: select the compressor with the highest compatibility as the access device for the target gas well; if there are multiple compressors with the same compatibility, a secondary screening is performed based on the principle of minimizing the pipeline pressure transmission loss calculated by pressure transmission efficiency and pipeline length.

6. The operation control method for the dual-frequency integrated booster air-lift compressor as described in claim 4, characterized in that, According to the well rig adaptation rules, the pressure change sequence of each gas well is assigned to the corresponding dual-frequency integrated booster gas lift compressor, and an operation control instruction set containing target speed and pressure output values ​​is generated. Specifically, this includes the following steps: All gas wells are sorted according to their production capacity priority to form a gas well allocation priority sequence; Based on the priority sequence, the gas lift demand pressure change sequence and the boosting demand pressure change sequence of each gas well are sequentially assigned to the gas lift variable frequency compression pipeline unit or the boosting variable frequency compression pipeline unit of the dual variable frequency integrated boosting gas lift compressor with the highest compatibility. The pressure change sequences of multiple gas wells connected to the same compressor within the same time period are aligned on the time axis and superimposed with the load. The target speed of each pipeline unit is calculated based on the superimposed pressure. The expression is as follows: ； In the formula, For the target speed, This is the compressor's rated speed. The pressure after superposition, This refers to the compressor's rated pressure output value. Verify whether the superimposed pipeline pressure chain fluctuation prediction value exceeds the threshold T. If so, the gas well with the lowest priority is reassigned to the gas lift variable frequency compression pipeline unit or the booster variable frequency compression pipeline unit of the second-best matching compressor. The target speed, the superimposed pressure output value, and the pipeline unit type are integrated to generate a standardized set of operation control instructions.

7. The operation control method for the dual-frequency integrated booster air-lift compressor as described in claim 1, characterized in that, According to the aforementioned set of operating control instructions, the air lift variable frequency cylinder pipeline unit and the booster variable frequency cylinder pipeline unit of each dual-frequency integrated booster air lift compressor are driven and controlled respectively, providing air lift pressure output and booster pressure output steps, specifically including: The set of operation control commands is distributed to the dual-frequency integrated booster air-lift compressor according to the type of pipeline unit. The target pressure value is converted into the speed control signal of the frequency converter, which drives the compressor cylinder of the air-lift variable frequency compression pipeline unit and the booster variable frequency compression pipeline unit to run at the target speed. Real-time acquisition of actual gas lift pressure and actual boost pressure at the wellhead of the gas well; calculation of the deviation between the commanded target value and the actual value; and determination of whether the gas lift pressure deviation or boost pressure deviation meets the error requirements. If so, the inverter speed signal is dynamically corrected by combining the pressure transmission efficiency and the influence factor of crack interweaving until the deviation falls back to the error requirement range.

8. The operation control method for the dual-frequency integrated booster air-lift compressor as described in claim 7, characterized in that, Combining pressure transmission efficiency and crack interweaving influence factors, the inverter speed signal is dynamically corrected until the deviation falls back to the required error range. This process includes the following steps: Determine the cause of the deviation; the determination method is as follows: determine whether it is caused by gas well production fluctuation based on the actual pressure fluctuation frequency of the gas well and the predicted content fluctuation frequency, and determine whether it is caused by pipeline network cascading fluctuation based on the actual pressure fluctuation of the gas well and the pressure fluctuation of adjacent gas wells. When the deviation is caused by fluctuations in gas well production, the first formula is used to correct the inverter speed signal; when the deviation is caused by fluctuations in pipeline network, the second formula is used to correct the inverter speed signal. The expression for the first formula is: ； The expression for the second formula is: ； In the formula, For the corrected rotational speed, The current rotational speed, This is the pressure deviation value. The influencing factor of crack interweaving, For pressure transmission efficiency.

9. A dual-frequency integrated booster air-lift compressor operation control system, characterized in that, The system includes: Several dual-frequency integrated booster air-lift compressors are configured to have air-lift variable frequency cylinder pipeline units and booster variable frequency cylinder pipeline units. A control terminal is connected to several dual-frequency integrated booster air-lift compressors and is configured to execute the dual-frequency integrated booster air-lift compressor operation control method as described in any one of claims 1-8.

Images