Intelligent linkage system and device for oil field gathering and transportation station yard

Abstract

The invention discloses an intelligent linkage system and device for an oil field gathering and transportation station yard, and belongs to the technical field of abnormity processing of the oil field gathering and transportation station yard. The intelligent linkage system comprises an oil field data acquisition module, an edge data fusion module, a gathering and transportation scene simulation and decision selection module and a decision execution and linkage control module; the oil field data acquisition module comprises a multi-modal sensing unit, acquires equipment data in the oil field gathering and transportation process based on a unified timestamp, calibrates equipment sensitivity in the multi-modal sensing unit by combining external environments of different oil field gathering and transportation stations, and transmits the acquired data into the edge data fusion module; and the edge data fusion module. According to the intelligent linkage system and device for the oil field gathering and transportation station yard, the accuracy of abnormal recognition, the scientificity of decision making and the stability of system operation are improved through the intelligent system integrating multi-mode sensing, edge data fusion, scene simulation decision making and linkage control.

Description

Technical Field

[0001] The present invention belongs to the technical field of abnormality processing of oilfield gathering and transportation stations, and in particular relates to an intelligent linkage system and device for oilfield gathering and transportation stations. Background Art

[0002] Oilfield gathering and transportation stations, as key nodes in crude oil extraction and transportation, undertake important tasks such as oil and gas separation, metering, and transportation. Their operational stability directly impacts oilfield production efficiency and safety. However, gathering and transportation stations require a wide range of equipment and complex processes, involving pumps, pipelines, separators, and other equipment. Furthermore, affected by factors such as geological conditions, climate, and equipment aging, they are prone to single or combined abnormalities such as pressure anomalies, leaks, and equipment failures. Traditional operation and management models face numerous challenges. Traditional gathering and transportation station management relies heavily on manual inspections and decentralized monitoring. The data collection method is single and each sensor operates independently. There is a lack of unified time calibration and environmental sensitivity calibration, making it difficult to achieve real-time and accurate capture of the status of the entire process chain, resulting in delayed or misjudgment of abnormality identification. In addition, abnormality handling relies on manual experience, making it difficult to quickly generate scientific adjustment strategies when faced with complex abnormalities. The lack of closed-loop linkage between decision-making and equipment control can easily expand the impact of faults due to improper adjustments, resulting in low practicality and functionality. Summary of the Invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes an intelligent linkage system and device for oilfield gathering and transportation stations, which solves the above technical problems by improving detection and processing methods.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions: An intelligent linkage system for oilfield gathering and transportation stations, including an oilfield data acquisition module, an edge data fusion module, a gathering and transportation scenario simulation and decision selection module, and a decision execution and linkage control module; The oilfield data acquisition module includes a multimodal sensing unit that collects equipment data during the oilfield gathering and transportation process based on a unified timestamp. It also calibrates the sensitivity of the equipment in the multimodal sensing unit based on the external environment of different oilfield gathering and transportation stations, and transmits the collected data to the edge data fusion module. The edge data fusion module normalizes the received collected data, outputs the collected data in a unified format of time series structure to obtain health vectors, sets edge judgment models for different types of collected data in the multimodal sensing unit, performs single anomaly judgment and composite anomaly recognition on the collected data, and transmits the recognition results to subsequent modules; The gathering and transportation scenario simulation and decision-making selection module generates a station simulation model using 3D point cloud data based on the environmental and equipment data of different oilfield gathering and transportation stations. A set of simulation equations is embedded in the station simulation model. The module also calibrates the status of different equipment based on historical data and assigns corresponding compensation values ​​to the station simulation model, taking into account the service life and failure frequency of the equipment. An abnormal health vector is input into the station simulation model to generate an output decision. The output decision is then simulated, and the optimal adjustment strategy is selected and output to subsequent modules. The decision-making execution and linkage control module converts the received optimal adjustment strategy into structured control instructions and binds the specific equipment action logic of different oilfield gathering and transportation sites to execute the optimal adjustment strategy. At the same time, it collects the adjusted equipment data through the multimodal sensing unit and performs abnormality verification to achieve closed-loop adjustment control.

[0005] Furthermore, the oilfield data acquisition module includes a multimodal sensing unit, which collects equipment data during the oilfield gathering and transportation process based on a unified timestamp. At the same time, the sensitivity of the equipment in the multimodal sensing unit is calibrated in combination with the external environment of different oilfield gathering and transportation stations, and the collected data is transmitted to the edge data fusion module. The specific steps are as follows: By deploying multimodal sensing units in different oilfield gathering and transportation stations to collect equipment data during the oilfield gathering and transportation process, the multimodal sensing units integrate temperature sensors, pressure sensors, flow sensors, liquid level sensors, vibration sensors, infrared thermal imaging acquisition probes, visible light camera probes, and gas detection probes; The data collected by the multimodal sensor unit is clock-shifted Compensate for errors and add a time stamp to each collected data ,in Represents the clock offset compensation value, They represent the master clock sending time, slave clock receiving time, slave clock reply time, and master clock receiving time respectively. Represents the timestamp time set for the data, Represents the time when the data was collected; Combined with the external environment data of different oilfield gathering and transportation stations, The sensitivity of the sensors in the multimodal sensing unit is adjusted in a targeted manner, wherein Represents the sensor sensitivity adjustment value, Represents the current sensor sensitivity reference value, Represent the environmental attenuation coefficient and interference intensity respectively.

[0006] Furthermore, the edge data fusion module normalizes the received collected data and outputs the collected data into a time series structure in a unified format to obtain a health vector, including the following steps: By receiving various equipment data collected by the multimodal sensor unit in the oil field data acquisition module ,in Represents the sensor type, integrates the collected data into a unified dataset, and normalizes the data in the dataset through Z-score standardization: ; in, Representative The data obtained by the sensor after normalization processing, Representative Sliding mean of historical data of similar sensors, Representative The standard deviation of the sensor class is used to align the normalized data in time series through dynamic time warping. Establish a data statistics database and compile data in the same time series into the same data set to generate health vectors : ; in, Represents the timing, Representative Sensors in Normalized data in time series, Represent the collected image feature vector and gas concentration respectively.

[0007] Furthermore, the edge judgment model is set for different types of collected data in the multimodal sensing unit, single anomaly judgment and compound anomaly recognition are performed on the collected data, and the recognition results are transmitted to the subsequent module, including the following steps: For the data collected by the multimodal sensing unit, the data types are divided into image data, time series data, and numerical data, and single anomaly judgment and compound anomaly judgment are performed respectively: In the single anomaly determination process, a convolutional neural network model is built for image data to identify abnormal targets in the image. For time series data, anomalies are identified by building a long short-term memory network model. For numerical data, anomalies are identified based on preset thresholds. Based on the single anomaly determination results, the types of each single anomaly in the same time series are integrated, and the anomaly in the current same time series is confirmed in combination with the composite anomaly determination rules. The specific steps are as follows: At the same time, collect all single abnormality judgment results and integrate the collected judgment results into a judgment vector ,in Represents the judgment results of different data types, Represents the timing Next The data judgment result collection vector is Substitute into the output rule to perform compound anomaly judgment, and output the compound anomaly judgment result ,in , This is the preset compound anomaly determination rule.

[0008] Furthermore, the gathering and transportation scenario simulation and decision selection module generates a station simulation model through three-dimensional point cloud data based on the environment and equipment data of different oilfield gathering and transportation stations, and embeds a set of simulation equations in the station simulation model. At the same time, combined with the service life and failure frequency of the equipment, the status of different equipment is calibrated according to historical data and corresponding compensation values ​​are assigned in the station simulation model. The abnormal health vector is input into the station simulation model to generate an output decision, simulate the output decision, screen the optimal adjustment strategy, and output it to the subsequent module, including the following steps: Statistics are collected on the service life and failure frequency of different equipment in the current oilfield gathering and transportation station. The equipment status under different service life and failure frequency are divided according to historical data. The service life and failure frequency status of the operating equipment in the current gathering and transportation station are determined respectively. The determination results are selected to obtain the equipment status; 3D point cloud data of the current oilfield gathering and transportation station is acquired through 3D laser scanning to construct a 3D simulation model of the station. Simultaneously, a set of simulation equations describing the station's operation is established based on the physical principles and process flow of the gathering and transportation station. Based on the equipment status of different devices, corresponding parameter compensation values ​​are assigned to the equipment in the station simulation model. Abnormal health vectors are input to generate output decisions, and simulation evaluation and screening are performed to obtain the optimal decision.

[0009] Furthermore, the service life and failure frequency of different equipment in the current oilfield gathering and transportation station are counted, and the equipment status under different service life and failure frequency are divided according to historical data. The service life and failure frequency status of the operating equipment in the current gathering and transportation station are determined respectively, and the determination results are selected to obtain the equipment status. The specific steps are as follows: Collect historical data on the commissioning time and failure records of different equipment in the current oilfield gathering and transportation station, and calculate the service life of different equipment ,in Represents the current time and the time the equipment is put into use, and the unit time is calculated at the same time Frequency of equipment failures within ,in Represents the device in unit time Number of failures within The service life and fault frequency of the same equipment are combined to calculate the equipment age status, including good, normal, and fair. At the same time, based on the high and low thresholds of the equipment fault frequency per unit time, the equipment fault frequency status is determined for each device separately. The equipment age status and equipment fault frequency status are selected to obtain the current equipment status. The specific steps are as follows: For each device, according to its age Make a judgment, when ≤ The equipment is in good condition when < ≤ When the equipment age status is normal, > When the equipment age status is general, 、 Represents the lower and upper age thresholds of the current device; For each device, according to its failure frequency Make a judgment, when ≤ When the equipment fault frequency status is good, < ≤ When the equipment fault frequency status is normal, > When the equipment fault frequency status is normal, 、 Represents the low and high thresholds for the fault frequency of the current device. The equipment age status and equipment failure frequency status are selected to obtain the current equipment status.

[0010] Furthermore, the three-dimensional point cloud data of the current oilfield gathering and transportation station is obtained by three-dimensional laser scanning to construct a three-dimensional simulation model of the station. At the same time, according to the physical principles and process flow of the gathering and transportation station, a simulation equation group describing the operation of the station is established. According to the equipment status of different equipment, corresponding parameter compensation values ​​are assigned to the equipment in the station simulation model. The abnormal health vector is input to generate an output decision, and the simulation evaluation and screening are performed to obtain the optimal decision, which includes the following steps: The 3D point cloud data of the current oilfield gathering and transportation station is acquired through 3D laser scanning. The 3D point cloud data is filtered to extract the station's geometric information and topological structure to construct a 3D simulation model of the station. Based on the physical principles and process flow of the oilfield gathering and transportation station, a set of simulation equations describing the station's operation is established and embedded into the station simulation model. Assign different compensation coefficients to the equipment according to different equipment status , calculate and obtain the set value after the current device parameter compensation ,in Represents the set value of the current device after compensation based on the device status parameters. Represents the original parameters of the device; The abnormal health vector obtained by the edge data fusion module is input into the station simulation model. The operation status of the station is updated in real time by solving the simulation equation group. The preset adjustment rule library of equipment adjustment strategies under different historical abnormal parameters is collected. Combined with the operation abnormal parameters in the current station simulation model, the cosine similarity is calculated to match the rules in the adjustment rule library. K rounds of rule matching are performed to generate response strategies. Combined with the adjustment rules with different effects in the adjustment rule library, an adjustment strategy is selected under each adjustment rule through M simple non-repetitive random sampling. M adjustment response paths are generated in combination. Each adjustment response path is simulated in the station simulation model. The adjustment response path with the shortest response time is selected as the optimal adjustment strategy and output to the subsequent modules.

[0011] Furthermore, the decision execution and linkage control module converts the received optimal adjustment strategy into structured control instructions, binds the specific equipment action logic of different oilfield gathering and transportation sites to execute the optimal adjustment strategy, and collects the adjusted equipment data through the multimodal sensing unit and performs abnormality verification to achieve closed-loop adjustment control, including the following steps: Based on the layout and equipment configuration information of different oilfield gathering and transportation sites, a mapping relationship between control instructions and specific equipment is established, and the corresponding equipment action logic is bound to each control instruction. The received optimal adjustment strategy is converted into structured control instructions to control the equipment. The structured control instructions are sent to the equipment control system of the corresponding oilfield gathering and transportation site through the industrial protocol adapter module for instruction execution; The multimodal sensing unit in the oilfield data acquisition module collects data from the oilfield gathering and transportation station after the instruction is executed, and anomalies are identified in the edge data fusion module. If the anomaly still exists, the gathering and transportation scenario simulation and decision selection module generates the optimal adjustment strategy again to adjust the anomaly. The above steps are repeated until the anomaly disappears or the maximum number of cycles is reached, and the anomaly report is transmitted to the on-duty personnel.

[0012] The intelligent linkage device for oilfield gathering and transportation stations is applied to the intelligent linkage system of oilfield gathering and transportation stations, and includes a memory, a processor, and a program stored in the memory and runnable on the processor. When the processor executes the program, the steps of the intelligent linkage system of the oilfield gathering and transportation stations as described in the present invention are implemented.

[0013] Compared with the prior art, the present invention has the following beneficial effects: 1. In the present invention, a multimodal sensing unit is set up to integrate multiple sensors. Data is collected based on a unified timestamp and sensitivity is calibrated in combination with the external environment. This enables real-time collection of the operating status of the entire process chain of the oilfield gathering and transportation station. The edge data fusion module performs data normalization and anomaly determination, accurately identifying single and complex anomalies, providing accurate and comprehensive basic data for subsequent decision-making of the system, and improving the accuracy and timeliness of anomaly identification. 2. In the present invention, by setting up a gathering and transportation scenario simulation and decision-making selection module, a station simulation model is generated using three-dimensional point cloud data. A set of simulation equations is embedded and compensation values ​​are assigned based on the equipment's service life and fault frequency. Abnormal health vectors are input to generate and screen the optimal adjustment strategy, making the output decision more suitable for the actual conditions of different oilfield gathering and transportation stations, thereby enhancing practicality. 3. In the present invention, the decision-making execution and linkage control module converts the optimal adjustment strategy into structured control instructions and binds the equipment action logic. At the same time, the adjusted data is collected through the multimodal sensing unit for abnormality verification to realize closed-loop adjustment control. When the abnormality is not eliminated, the adjustment is repeated until the abnormality disappears or manual intervention is notified, thereby ensuring the stable operation of the system while reducing the losses caused by the failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 The figure is a block diagram of an intelligent linkage system for oilfield gathering and transportation stations according to the present invention. DETAILED DESCRIPTION

[0015] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0016] Example 1: like Figure 1 As shown, an intelligent linkage system for oilfield gathering and transportation stations includes an oilfield data acquisition module, an edge data fusion module, a gathering and transportation scenario simulation and decision selection module, and a decision execution and linkage control module; The oilfield data acquisition module includes a multimodal sensing unit that collects data from equipment during the oilfield gathering and transportation process based on a unified timestamp. It also calibrates the sensitivity of the equipment in the multimodal sensing unit based on the external environment of different oilfield gathering and transportation stations, and transmits the collected data to the edge data fusion module. The specific steps are as follows: By deploying multimodal sensing units in different oilfield gathering and transportation stations to collect equipment data during the oilfield gathering and transportation process, the multimodal sensing units integrate temperature sensors, pressure sensors, flow sensors, liquid level sensors, vibration sensors, infrared thermal imaging acquisition probes, visible light camera probes, and gas detection probes; The data collected by the multimodal sensor unit is clock-shifted Compensate for errors and add a time stamp to each collected data ,in Represents the clock offset compensation value, They represent the master clock sending time, slave clock receiving time, slave clock reply time, and master clock receiving time respectively. Represents the timestamp time set for the data, Represents the time when the data was collected; It should be noted that the multimodal sensing units need to be deployed at key equipment locations such as pump groups, burners, gas gathering pipelines, water injection nodes, and pressure regulating equipment in different oilfield gathering and transportation stations to achieve real-time collection of the operating status of the entire process chain.

[0017] Combined with the external environment data of different oilfield gathering and transportation stations, The sensitivity of the sensors in the multimodal sensing unit is adjusted in a targeted manner, wherein Represents the sensor sensitivity adjustment value, Represents the current sensor sensitivity reference value, Represent the environmental attenuation coefficient and interference intensity respectively.

[0018] It should be noted that Represents the current sensor sensitivity reference value, that is, the sensor's calibration value in a standard laboratory environment, usually the sensor's factory setting value. To obtain the environmental attenuation coefficient, it is necessary to test the sensor in different simulation chambers for different sensors and fit the environmental attenuation curve. Represents the intensity of environmental interference. This is estimated by building a mathematical model based on meteorological data and geographic information. Using weather forecast parameters such as wind speed, wind direction, humidity, and temperature, combined with topographic information about the current oilfield gathering and transportation station, such as proximity to deserts and mountains that may affect the distribution of dust, rain, and snow, the environmental interference prediction intensity model is trained based on historical data and machine learning algorithms to estimate the current environmental interference intensity. Example 2: The edge data fusion module normalizes the received collected data and outputs the collected data in a unified format of time series structure to obtain health vectors. It sets edge judgment models for different types of collected data in the multimodal sensing unit, performs single anomaly judgment and composite anomaly recognition on the collected data, and transmits the recognition results to subsequent modules. The module includes the following steps: By receiving various equipment data collected by the multimodal sensor unit in the oil field data acquisition module ,in Represents the sensor type, integrates the collected data into a unified dataset, and normalizes the data in the dataset through Z-score standardization: ; in, Representative The data obtained by the sensor after normalization processing, Representative Sliding mean of historical data of similar sensors, Representative The standard deviation of the sensor class is used to align the normalized data in time series through dynamic time warping. Establish a data statistics database and compile data in the same time series into the same data set to generate health vectors : ; in, Represents the timing, Representative Sensors in Normalized data in time series, Represent the collected image feature vector and gas concentration respectively.

[0019] It should be noted that the health vector is a structured feature vector formed by fusing multi-source data, which is used to represent the health status of the object. The image feature vector is the visual feature extracted by the convolutional neural network from the data collected by the image acquisition probe. During time series alignment, the dynamic time warping algorithm DTW is used to match the time series to determine the health vector under the same time series. For the data collected by the multimodal sensing unit, the data types are divided into image data, time series data, and numerical data, and single anomaly judgment and compound anomaly judgment are performed respectively: In the single anomaly determination process, a convolutional neural network model is built for image data to identify abnormal targets in the image. For time series data, anomalies are identified by building a long short-term memory network model. For numerical data, anomalies are identified based on preset thresholds. It should be noted that in the process of image data recognition, it is necessary to collect image datasets containing normal and abnormal targets in advance, preprocess the images and adjust the image size, select ResNet as the CNN architecture, build the model and determine the parameters and structure of the input layer, convolution layer, pooling layer, fully connected layer, etc., divide the preprocessed image dataset into training set and validation set, use the cross entropy loss function as the loss function, use stochastic gradient descent SGD as the optimizer, use the training set to train the model, calculate the loss between the predicted results and the true labels through forward propagation, update the model parameters through back propagation, use the validation set to evaluate the performance of the model to calculate the accuracy, recall rate, and F1 value, adjust the model parameters according to the evaluation results, and finally obtain the judgment model; When building a long-short-term memory network model for time series data, time series data, such as temperature, pressure, and other time-varying data, is collected and divided into input sequences and corresponding target sequences for model training. For numerical data, the upper and lower thresholds of normal data are determined using the 3 sigma principle based on production process indicators and safety specifications, combined with business knowledge and historical data statistics, to identify anomalies.

[0020] Based on the single anomaly determination results, the types of each single anomaly in the same time series are integrated, and the anomaly in the current same time series is confirmed in combination with the composite anomaly determination rules. The specific steps are as follows: At the same time, collect all single abnormality judgment results and integrate the collected judgment results into a judgment vector ,in Represents the judgment results of different data types, Represents the timing Next The data judgment result collection vector is Substitute into the output rule to perform compound anomaly judgment, and output the compound anomaly judgment result ,in , This is the preset compound anomaly determination rule.

[0021] It should be noted that the compound exception judgment rule needs to be expressed as a logical expression. For example, if the rule is "when exception type 1 and exception type 2 appear at the same time, it is judged as compound exception type A", the rule can be expressed as , Represents the logical AND operator. A compound anomaly judgment rule can be a combination of multiple logical operators. It is necessary to determine the compound anomaly judgment rules for different devices based on different device types and the types of historical anomaly data to determine whether the device in the current time sequence has an anomaly and what type of anomaly has occurred.

[0022] Example 3: The gathering and transportation scenario simulation and decision-making selection module generates a station simulation model using 3D point cloud data based on the environmental and equipment data of different oilfield gathering and transportation stations. It also embeds a set of simulation equations in the station simulation model. Furthermore, the module combines the service life and failure frequency of the equipment, calibrates the status of different equipment based on historical data, and assigns corresponding compensation values ​​in the station simulation model. It then inputs abnormal health vectors into the station simulation model to generate output decisions. The module then simulates the output decisions, selects the optimal adjustment strategy, and outputs it to subsequent modules. The module includes the following steps: Statistics are collected on the service life and failure frequency of different equipment in the current oilfield gathering and transportation station. The equipment status under different service life and failure frequency are divided according to historical data. The service life and failure frequency status of the running equipment in the current gathering and transportation station are determined respectively. The determination results are selected to obtain the equipment status. The specific steps are as follows: Collect historical data on the commissioning time and failure records of different equipment in the current oilfield gathering and transportation station, and calculate the service life of different equipment ,in Represents the current time and the time the equipment is put into use, and the unit time is calculated at the same time Frequency of equipment failures within ,in Represents the device in unit time Number of failures within The service life and fault frequency of the same equipment are combined to calculate the equipment age status, including good, normal, and fair. At the same time, based on the high and low thresholds of the equipment fault frequency per unit time, the equipment fault frequency status is determined for each device separately. The equipment age status and equipment fault frequency status are selected to obtain the current equipment status. The specific steps are as follows: For each device, according to its age Make a judgment, when ≤ The equipment is in good condition when < ≤ When the equipment age status is normal, > When the equipment age status is general, 、 Represents the lower and upper age thresholds of the current device; For each device, according to its failure frequency Make a judgment, when ≤ When the equipment fault frequency status is good, < ≤ When the equipment fault frequency status is normal, > When the equipment fault frequency status is normal, 、 Represents the low and high thresholds for the fault frequency of the current device. It should be noted that when calculating the failure frequency per unit time, the unit time The typical setting is three months, but it can also be adjusted based on actual usage. The lower and upper age thresholds are calculated using the 3sigma principle for the failure frequencies of the same equipment at different historical ages. The lower and upper failure frequency thresholds are set based on the equipment type, historical data, and industry standards, combined with empirical methods.

[0023] The equipment age status and equipment failure frequency status are selected to obtain the current equipment status.

[0024] It should be noted that by making a selection based on the equipment age status and equipment failure frequency status to obtain the current equipment status, it is possible to avoid inaccurate age status determination due to the special failure frequency of the equipment itself.

[0025] 3D point cloud data of the current oilfield gathering and transportation station is acquired through 3D laser scanning to construct a 3D simulation model of the station. Simultaneously, a set of simulation equations describing the station operation is established based on the physical principles and process flow of the gathering and transportation station. Based on the status of different equipment, corresponding parameter compensation values ​​are assigned to the equipment in the station simulation model. Abnormal health vectors are input to generate output decisions. Simulation evaluation and screening are performed to obtain the optimal decision, including the following steps: The 3D point cloud data of the current oilfield gathering and transportation station is acquired through 3D laser scanning. The 3D point cloud data is filtered to extract the station's geometric information and topological structure to construct a 3D simulation model of the station. Based on the physical principles and process flow of the oilfield gathering and transportation station, a set of simulation equations describing the station's operation is established and embedded into the station simulation model. It should be noted that when performing point cloud filtering, Gaussian filtering is selected to perform weighted averaging on the entire image, so that the value of each pixel is obtained by weighted averaging the value of itself and other pixels in the neighborhood to eliminate noise. The equation group includes oil-water-gas three-phase flow, heat exchange, water balance, pipe network pressure difference and other equation groups. The equation group is solved by numerical calculation method to simulate the operation status of the station. Take the heat conduction equation as an example: ; Among them, T represents temperature, t represents time, x represents spatial coordinate, and β represents thermal diffusion coefficient. The finite difference method is used for numerical solution. The equation is converted into a discrete form that can be solved iteratively by computer through numerical calculation methods. Through point-by-point and time-step calculations, the changes of the station operation status with time and space are simulated.

[0026] Assign different compensation coefficients to the equipment according to different equipment status , calculate and obtain the set value after the current device parameter compensation ,in Represents the set value of the current device after compensation based on the device status parameters. Represents the original parameters of the device; It should be noted that the compensation coefficient needs to be set separately in combination with different devices, and the historical operating data of the equipment in different states needs to be collected. The data is grouped according to the equipment status, and the changes in the equipment parameters in each group of data are analyzed. The change rate of the equipment parameters in different states relative to the normal state, that is, the parameters in the good state, is calculated, and the calculated parameter change rate is used as the compensation coefficient of the current equipment in different equipment states.

[0027] The abnormal health vector obtained by the edge data fusion module is input into the station simulation model. The operation status of the station is updated in real time by solving the simulation equation group. The preset adjustment rule library of equipment adjustment strategies under different historical abnormal parameters is collected. Combined with the operation abnormal parameters in the current station simulation model, the cosine similarity is calculated to match the rules in the adjustment rule library. K rounds of rule matching are performed to generate response strategies. Combined with the adjustment rules with different effects in the adjustment rule library, an adjustment strategy is selected under each adjustment rule through M simple non-repetitive random sampling. M adjustment response paths are generated in combination. Each adjustment response path is simulated in the station simulation model. The adjustment response path with the shortest response time is selected as the optimal adjustment strategy and output to the subsequent modules.

[0028] It should be noted that when solving the simulation equations to update the station's operating status in real time, the model dynamically simulates the transmission and conversion of matter and energy, as well as the interactions between equipment, to reflect the actual changes in the station under abnormal conditions. K-round rule matching is designed to cope with complex abnormal situations. The value of K is usually set to 5, but can be adjusted according to actual conditions. In the process of establishing the adjustment rule base, it is necessary to collect data on various abnormal events that have occurred in the past from data sources such as the oilfield gathering and transportation station's monitoring system, equipment maintenance records, and fault reports. This data should include parameter information at the time of the abnormality, such as temperature, pressure, flow, and liquid level, equipment status, abnormality type (such as equipment failure, process fluctuation, and external interference), as well as the adjustment strategy adopted and the final treatment results. According to the nature, source, and impact of the abnormality, the collected abnormal events are classified into equipment-level abnormalities such as pump failure and valve blockage, system-level abnormalities such as process interruption and pressure imbalance, and external environmental abnormalities such as sudden temperature changes and power failures. For each type of abnormality, the adjustment strategy adopted in historical events is analyzed. Based on the abnormal parameter characteristics and corresponding adjustment strategies, general adjustment rules are summarized. At the same time, the effectiveness of the adjustment rules under each adjustment strategy is evaluated. Based on the impact on the station's operating efficiency, energy consumption, and safety, the preset rules are retained through quantitative indicators. The quantitative indicators include abnormal recovery time, energy consumption change rate, and equipment damage level. Each quantitative indicator retains two preset rules. Through M simple non-repetitive random sampling, an adjustment strategy is selected under each adjustment rule, and M adjustment strategies are generated in combination, where M is usually set to 7 times.

[0029] The decision-making execution and linkage control module converts the received optimal adjustment strategy into structured control instructions and binds the specific equipment action logic of different oilfield gathering and transportation sites to execute the optimal adjustment strategy. At the same time, it collects the adjusted equipment data through the multimodal sensing unit and performs abnormal verification to achieve closed-loop adjustment control. The module includes the following steps: Based on the layout and equipment configuration information of different oilfield gathering and transportation sites, a mapping relationship between control instructions and specific equipment is established, and the corresponding equipment action logic is bound to each control instruction. The received optimal adjustment strategy is converted into structured control instructions to control the equipment. The structured control instructions are sent to the equipment control system of the corresponding oilfield gathering and transportation site through the industrial protocol adapter module for instruction execution; The multimodal sensing unit in the oilfield data acquisition module collects data from the oilfield gathering and transportation station after the instruction is executed, and anomalies are identified in the edge data fusion module. If the anomaly still exists, the gathering and transportation scenario simulation and decision selection module generates the optimal adjustment strategy again to adjust the anomaly. The above steps are repeated until the anomaly disappears or the maximum number of cycles is reached, and the anomaly report is transmitted to the on-duty personnel.

[0030] It should be noted that the maximum number of cycles is usually set to 3 times. When the abnormality cannot be eliminated after 3 cycles, the abnormality report is transmitted to the on-duty personnel to notify them to intervene manually to avoid further expansion of losses.

[0031] The present invention provides an intelligent linkage device for an oilfield gathering and transportation station, which is applied to the intelligent linkage system of the oilfield gathering and transportation station. The device includes a memory, a processor, and a program stored in the memory and runnable on the processor. When the processor executes the program, the steps of the intelligent linkage system of the oilfield gathering and transportation station of the present invention are implemented.

[0032] The present invention integrates multiple sensors by setting up a multimodal sensing unit, collects data based on a unified timestamp and calibrates the sensitivity in combination with the external environment, thereby realizing real-time collection of the operating status of the entire process chain of the oilfield gathering and transportation station. The edge data fusion module performs data normalization processing and abnormality judgment, can accurately identify single and complex abnormalities, and provide accurate and comprehensive basic data for subsequent decision-making of the system, thereby improving the accuracy and timeliness of abnormality identification. By setting up a gathering and transportation scene simulation and decision selection module, a station simulation model is generated using three-dimensional point cloud data, an embedded simulation equation group is combined with compensation values ​​given in combination with the equipment service life and fault frequency, and an abnormal health vector is input to generate and screen the optimal adjustment strategy, so that the output decision is more in line with the actual situation of different oilfield gathering and transportation stations, thereby enhancing practicality.

[0033] In the embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is merely a logical functional division, and other division methods may be used in actual implementation. The modules described as separate components may or may not be physically separate, and the components displayed as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the method of this embodiment.

[0034] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent linkage system for oilfield gathering and transportation stations, characterized by: It includes oilfield data acquisition module, edge data fusion module, gathering and transportation scenario simulation and decision selection module, and decision execution and linkage control module; The oilfield data acquisition module includes a multimodal sensing unit that collects equipment data during the oilfield gathering and transportation process based on a unified timestamp. It also calibrates the sensitivity of the equipment in the multimodal sensing unit based on the external environment of different oilfield gathering and transportation stations, and transmits the collected data to the edge data fusion module. The edge data fusion module normalizes the received collected data, outputs the collected data in a unified format of time series structure to obtain health vectors, sets edge judgment models for different types of collected data in the multimodal sensing unit, performs single anomaly judgment and composite anomaly recognition on the collected data, and transmits the recognition results to subsequent modules; The gathering and transportation scenario simulation and decision-making selection module generates a station simulation model using 3D point cloud data based on the environmental and equipment data of different oilfield gathering and transportation stations. A set of simulation equations is embedded in the station simulation model. The module also calibrates the status of different equipment based on historical data and assigns corresponding compensation values ​​to the station simulation model, taking into account the service life and failure frequency of the equipment. An abnormal health vector is input into the station simulation model to generate an output decision. The output decision is then simulated, and the optimal adjustment strategy is selected and output to subsequent modules. The decision-making execution and linkage control module converts the received optimal adjustment strategy into structured control instructions and binds the specific equipment action logic of different oilfield gathering and transportation sites to execute the optimal adjustment strategy. At the same time, it collects the adjusted equipment data through the multimodal sensing unit and performs abnormality verification to achieve closed-loop adjustment control.

2. The intelligent linkage system for oilfield gathering and transportation stations according to claim 1, characterized in that: The oilfield data acquisition module includes a multimodal sensing unit, which collects equipment data during the oilfield gathering and transportation process based on a unified timestamp. At the same time, the sensitivity of the equipment in the multimodal sensing unit is calibrated in combination with the external environment of different oilfield gathering and transportation stations, and the collected data is transmitted to the edge data fusion module. The specific steps are as follows: By deploying multimodal sensing units in different oilfield gathering and transportation stations to collect equipment data during the oilfield gathering and transportation process, the multimodal sensing units integrate temperature sensors, pressure sensors, flow sensors, liquid level sensors, vibration sensors, infrared thermal imaging acquisition probes, visible light camera probes, and gas detection probes; The data collected by the multimodal sensor unit is clock-shifted Compensate for errors and add a time stamp to each collected data ,in Represents the clock offset compensation value, They represent the master clock sending time, slave clock receiving time, slave clock reply time, and master clock receiving time respectively. Represents the timestamp time set for the data, Represents the time when the data was collected; Combined with the external environment data of different oilfield gathering and transportation stations, The sensitivity of the sensors in the multimodal sensing unit is adjusted in a targeted manner, wherein Represents the sensor sensitivity adjustment value, Represents the current sensor sensitivity reference value, Represent the environmental attenuation coefficient and interference intensity respectively.

3. The intelligent linkage system for oilfield gathering and transportation stations according to claim 2, characterized in that: The edge data fusion module normalizes the received collected data and outputs the collected data into a time series structure in a unified format to obtain a health vector, including the following steps: By receiving various equipment data collected by the multimodal sensor unit in the oil field data acquisition module ,in Represents the sensor type, integrates the collected data into a unified dataset, and normalizes the data in the dataset through Z-score standardization: ； in, Representative The data obtained by the sensor after normalization processing, Representative Sliding mean of historical data of similar sensors, Representative The standard deviation of the sensor class is used to align the normalized data in time series through dynamic time warping. Establish a data statistics database and compile data in the same time series into the same data set to generate health vectors : ； in, Represents the timing, Representative Sensors in Normalized data in time series, Represent the collected image feature vector and gas concentration respectively.

4. The intelligent linkage system for oilfield gathering and transportation stations according to claim 3, characterized in that: The method includes setting edge judgment models for different types of collected data in the multimodal sensing unit, performing single anomaly judgment and composite anomaly recognition on the collected data, and transmitting the recognition results to subsequent modules, including the following steps: For the data collected by the multimodal sensing unit, the data types are divided into image data, time series data, and numerical data, and single anomaly judgment and compound anomaly judgment are performed respectively: In the single anomaly determination process, a convolutional neural network model is built for image data to identify abnormal targets in the image. For time series data, anomalies are identified by building a long short-term memory network model. For numerical data, anomalies are identified based on preset thresholds. Based on the single anomaly determination results, the types of each single anomaly in the same time series are integrated, and the anomaly in the current same time series is confirmed in combination with the composite anomaly determination rules. The specific steps are as follows: At the same time, collect all single abnormality judgment results and integrate the collected judgment results into a judgment vector ,in Represents the judgment results of different data types, Represents the timing Next The data judgment result collection vector is Substitute into the output rule to perform compound anomaly judgment, and output the compound anomaly judgment result ,in , This is the preset compound anomaly determination rule.

5. The intelligent linkage system for oilfield gathering and transportation stations according to claim 2, characterized in that: The gathering and transportation scenario simulation and decision selection module generates a station simulation model using three-dimensional point cloud data based on the environment and equipment data of different oilfield gathering and transportation stations. It embeds a set of simulation equations in the station simulation model. It also calibrates the status of different equipment based on historical data and assigns corresponding compensation values ​​in the station simulation model, taking into account the service life and failure frequency of the equipment. It inputs abnormal health vectors into the station simulation model to generate output decisions, simulates the output decisions, screens the optimal adjustment strategy, and outputs it to subsequent modules. The module includes the following steps: Statistics are collected on the service life and failure frequency of different equipment in the current oilfield gathering and transportation station. The equipment status under different service life and failure frequency are divided according to historical data. The service life and failure frequency status of the operating equipment in the current gathering and transportation station are determined respectively. The determination results are selected to obtain the equipment status; 3D point cloud data of the current oilfield gathering and transportation station is acquired through 3D laser scanning to construct a 3D simulation model of the station. Simultaneously, a set of simulation equations describing the station's operation is established based on the physical principles and process flow of the gathering and transportation station. Based on the equipment status of different devices, corresponding parameter compensation values ​​are assigned to the equipment in the station simulation model. Abnormal health vectors are input to generate output decisions, and simulation evaluation and screening are performed to obtain the optimal decision.

6. The intelligent linkage system for oilfield gathering and transportation stations according to claim 5, characterized in that: The method comprises the following steps: collecting statistics on the service life and failure frequency of different equipment in the current oilfield gathering and transportation station, dividing the equipment status under different service life and failure frequency based on historical data, determining the service life and failure frequency status of the operating equipment in the current gathering and transportation station, and selecting the equipment status based on the determination results. Collect historical data on the commissioning time and failure records of different equipment in the current oilfield gathering and transportation station, and calculate the service life of different equipment ,in Represents the current time and the time the equipment is put into use, and the unit time is calculated at the same time Frequency of equipment failures within ,in Represents the device in unit time Number of failures within The service life and fault frequency of the same equipment are combined to calculate the equipment age status, including good, normal, and fair. At the same time, based on the high and low thresholds of the equipment fault frequency per unit time, the equipment fault frequency status is determined for each device separately. The equipment age status and equipment fault frequency status are selected to obtain the current equipment status. The specific steps are as follows: For each device, according to its age Make a judgment, when ≤ The equipment is in good condition when < ≤ When the equipment age status is normal, > When the equipment age status is general, 、 Represents the lower and upper age thresholds of the current device; For each device, according to its failure frequency Make a judgment, when ≤ When the equipment fault frequency status is good, < ≤ When the equipment fault frequency status is normal, > When the equipment fault frequency status is normal, 、 Represents the low and high thresholds for the fault frequency of the current device. The equipment age status and equipment failure frequency status are selected to obtain the current equipment status.

7. The intelligent linkage system for oilfield gathering and transportation stations according to claim 6, characterized in that: The method acquires 3D point cloud data of the current oilfield gathering and transportation station through 3D laser scanning to construct a 3D simulation model of the station. Simultaneously, a set of simulation equations describing the operation of the station is established based on the physical principles and process flow of the gathering and transportation station. According to the equipment status of different equipment, corresponding parameter compensation values ​​are assigned to the equipment in the station simulation model. An abnormal health vector is input to generate an output decision. The optimal decision is obtained through simulation evaluation and screening, including the following steps: The 3D point cloud data of the current oilfield gathering and transportation station is acquired through 3D laser scanning. The 3D point cloud data is filtered to extract the station's geometric information and topological structure to construct a 3D simulation model of the station. Based on the physical principles and process flow of the oilfield gathering and transportation station, a set of simulation equations describing the station's operation is established and embedded into the station simulation model. Assign different compensation coefficients to the equipment according to different equipment status , calculate and obtain the set value after the current device parameter compensation ,in Represents the set value of the current device after compensation based on the device status parameters. Represents the original parameters of the device; The abnormal health vector obtained by the edge data fusion module is input into the station simulation model. The operation status of the station is updated in real time by solving the simulation equation group. The preset adjustment rule library of equipment adjustment strategies under different historical abnormal parameters is collected. Combined with the operation abnormal parameters in the current station simulation model, the cosine similarity is calculated to match the rules in the adjustment rule library. K rounds of rule matching are performed to generate response strategies. Combined with the adjustment rules with different effects in the adjustment rule library, an adjustment strategy is selected under each adjustment rule through M simple non-repetitive random sampling. M adjustment response paths are generated in combination. Each adjustment response path is simulated in the station simulation model. The adjustment response path with the shortest response time is selected as the optimal adjustment strategy and output to the subsequent modules.

8. The intelligent linkage system for oilfield gathering and transportation stations according to claim 7, characterized in that: The decision execution and linkage control module converts the received optimal adjustment strategy into structured control instructions and binds the specific equipment action logic of different oilfield gathering and transportation sites to execute the optimal adjustment strategy. At the same time, the module collects the adjusted equipment data through the multimodal sensing unit and performs abnormality verification to achieve closed-loop adjustment control. The module includes the following steps: Based on the layout and equipment configuration information of different oilfield gathering and transportation sites, a mapping relationship between control instructions and specific equipment is established, and the corresponding equipment action logic is bound to each control instruction. The received optimal adjustment strategy is converted into structured control instructions to control the equipment. The structured control instructions are sent to the equipment control system of the corresponding oilfield gathering and transportation site through the industrial protocol adapter module for instruction execution; The multimodal sensing unit in the oilfield data acquisition module collects data from the oilfield gathering and transportation station after the instruction is executed, and anomalies are identified in the edge data fusion module. If the anomaly still exists, the gathering and transportation scenario simulation and decision selection module generates the optimal adjustment strategy again to adjust the anomaly. The above steps are repeated until the anomaly disappears or the maximum number of cycles is reached, and the anomaly report is transmitted to the on-duty personnel.

9. An intelligent linkage device for oilfield gathering and transportation stations, characterized in that: The device is applied to the intelligent linkage system of oilfield gathering and transportation stations, and includes a memory and a processor: a memory for non-transitory storage of computer-readable instructions; a processor for executing the computer-readable instructions; When the computer-readable instructions are executed by the processor, the steps in the system according to any one of claims 1 to 8 are executed.

Images