A method and system for coordinated management of oil and gas pipeline transportation for a joint station

Abstract

This invention discloses a method and system for coordinated management of oil and gas pipeline transportation at a joint station, relating to the field of oil and gas field gathering and transportation technology. The system consists of several functional modules, including: a status identification module, which collects multi-dimensional data from joint station equipment via edge computing nodes, identifies real-time equipment efficiency curves online, and generates real-time equipment status sequences; a pipeline network coupling construction module, which constructs a nonlinear hydrothermal coupling mechanism model of the pipeline network based on the real-time equipment status sequences through a cloud-based digital twin platform, and performs online self-correction to obtain a global pipeline network simulation model of real-time field conditions; and a two-layer hierarchical optimization algorithm, which, based on the global pipeline network simulation model and combined with historical inflow data, outputs the optimal pressure and temperature setpoints for each joint station in the future period; wherein the two-layer hierarchical optimization algorithm includes an upper-layer global energy consumption minimization optimization layer and a lower-layer local predictive control tracking layer.

Description

Technical Field

[0001] This invention relates to the field of oil and gas field gathering and transportation technology, specifically to a method and system for coordinated management of oil and gas pipeline transportation at a joint station. Background Technology

[0002] As oil and gas field development enters the middle and late stages, the operating efficiency of the joint station, as the core hub for oil and gas gathering, transportation and processing, directly affects the production cost and energy consumption level of the entire oil field. Domestically and internationally, two main technical approaches have been developed for the scheduling and management of joint stations and pipeline networks. The first is the centralized monitoring mode based on SCADA, which deploys sensors at key nodes within the station to collect real-time data such as temperature, pressure, and flow rate to the central control room, where operators can manually intervene and adjust based on experience or preset single-point thresholds. The second is the scheduling optimization mode based on offline simulation software, which uses hydraulic and thermal simulation software to establish an offline model of the pipeline network based on historical data and design parameters to assist in the formulation of annual or quarterly transportation plans. Existing technologies are mostly limited to independent operation and control of single stations, lacking global dynamic control over the coupling effects between stations along the entire pipeline. When the output changes due to fluctuations in the influent volume or adjustments to the treatment process at the upstream combined station, the downstream station is often in a state of passive, lagging adjustment. Information asymmetry and time delays can easily lead to the superposition and amplification of pressure fluctuations throughout the entire line, which in severe cases can even cause production safety accidents such as pipeline surge and separator overflow, while also increasing unnecessary pump and heat consumption. As the combined station's operating years increase, the output pumps, heaters, and three-phase separators inevitably age, causing their actual operating characteristics to drift. However, existing offline simulation models usually use fixed parameters at the time of manufacture, failing to incorporate the characteristic changes caused by the aging of these devices into the scheduling model. This results in the so-called optimal operating scheme calculated based on theoretical models being seriously inconsistent with actual operating conditions. Not only does it fail to achieve energy saving and consumption reduction, but it may also cause equipment to deviate from the high-efficiency zone due to parameter mismatch, resulting in hidden energy waste. Summary of the Invention

[0003] To achieve the above objectives, the present invention provides the following technical solution: An oil and gas pipeline transportation coordination management system for a joint station, comprising: The status identification module collects multi-dimensional data from the joint station equipment through edge computing nodes on the end side, identifies the real-time efficiency curve of the equipment online, and generates a real-time status sequence of the equipment. The pipeline coupling construction module, through a cloud-based digital twin platform, constructs a nonlinear hydrothermal coupling mechanism model of the pipeline network based on the real-time state sequence of equipment, and performs online self-correction to obtain a global pipeline network simulation model of real-time field conditions. Based on a two-layer hierarchical optimization algorithm, and in conjunction with the global pipeline network simulation model and historical inflow data, it outputs the optimal pressure and temperature setpoints for each joint station in the future period. The two-layer hierarchical optimization algorithm includes an upper-layer global energy consumption minimization optimization layer and a lower-layer local predictive control tracking layer. The collaborative predictive scheduling module, based on the optimal pressure and temperature setpoints, performs predictive collaborative regulation through lower-level distributed control, issues regulation commands to downstream stations in advance, and outputs collaborative control results and energy consumption assessments.

[0004] Furthermore, the process of multi-dimensional data collection is as follows: Sensors are deployed at preset monitoring points of the joint station equipment. Edge computing nodes establish real-time communication connections with each sensor through an industrial bus and trigger data acquisition according to a preset acquisition frequency.

[0005] Furthermore, the process of generating the real-time state sequence of the device is as follows: The edge computing node calculates the actual head based on the collected pressure difference between the inlet and outlet of the external pump, the medium flow rate, and the motor input power. It also calculates the instantaneous efficiency of the pump under the current operating conditions by combining the medium flow rate and the motor input power. During continuous operation, multiple sets of data points with different flow rates and instantaneous efficiencies are collected. The least squares method is used to perform polynomial fitting on the data points to obtain the real-time efficiency curve of the pump under the current aging state. The fitted real-time efficiency curve, along with the corresponding flow rate, head, and data points, are stored in the equipment real-time status sequence in the order of timestamps.

[0006] Furthermore, the process of constructing a nonlinear hydrothermal coupling mechanism model for the pipe network is as follows: The topology of the combined station and oil pipeline network, as well as the real-time status sequence of the equipment, are imported from the cloud platform's engineering design library as the initial input to the model. The oil pipeline network is abstracted into a network of nodes and pipe segments, with each node being a combined station or confluence point and each pipe segment being an oil pipeline section. For each pipe segment, a nonlinear relationship between pipe segment pressure drop and flow rate is established based on pipe parameters and pipe friction characteristics. For each node, a node flow balance equation is established based on the flow rate. All pipe segment pressure drop equations and node flow balance equations are integrated to form an overall pipeline network hydraulic model. For each pipe segment, a temperature decay model of the medium within the pipe segment is established based on the pipe parameters. For each combined station, the relationship between the furnace outlet temperature and fuel consumption is established based on the furnace efficiency curve and the medium flow rate. All pipe segment temperature decay models and furnace thermal models are integrated to form an overall network thermal model. The hydraulic sub-model and the thermal sub-model are coupled to construct a nonlinear hydrothermal coupling mechanism model.

[0007] Furthermore, the process of obtaining a global pipeline network simulation model of real-time field conditions is as follows: The cloud platform receives real-time device status sequences and pipeline operation monitoring data uploaded from the end side, refits the efficiency curves based on the new device real-time status sequences, and updates the model input.

[0008] Furthermore, the process of outputting the optimal pressure and temperature setpoints for each joint station in the future time period is as follows: By acquiring historical inflow data and combining it with seasonal variations and wellhead production system adjustment patterns, a time series prediction algorithm is used to generate predicted inflow values. The latest parameters of the global pipeline network simulation model are retrieved, and the predicted inflow is used as the model boundary condition to complete the initialization of the simulation environment. With minimizing the total energy consumption of the joint off-site pumps and heating furnaces as the core optimization objective, a constrained optimization problem is constructed and solved. The lower-level local predictive control tracking layer receives the optimal setpoint sequence output from the upper layer, performs fine-tuning based on the actual working conditions of a single station, and generates directly executable control commands. The cloud platform performs the upper-level global optimization calculation once at fixed intervals and updates the optimal setpoint sequence. Each joint station's local control system performs lower-level tracking optimization once per second, dynamically adjusting control commands based on the latest set values. When the global pipeline network simulation model completes self-correction due to equipment status updates or when the predicted and actual liquid flow rates deviate from the threshold, the upper-level optimization layer is immediately triggered to recalculate. The cloud platform then distributes the integrated optimal pressure and temperature set values ​​for each joint station for the future period to the local control system of each joint station in the form of standardized commands.

[0009] Furthermore, the process of the lower-level local predictive control tracking layer is as follows: By collecting real-time operating data from the edge computing nodes of each joint station, the deviations of the current pressure and temperature of a single station from the upper-level setpoints are compared to identify fluctuations in the influent volume and local disturbances caused by instantaneous changes in the equipment's operating conditions. Using the upper-level optimal setpoint as the tracking target, a single-station predictive control model is constructed to predict the trend of operating condition changes in the short term. The adapted single-station pressure and temperature setpoints are decomposed into variable frequency speed commands for the external pump and fuel flow regulation commands for the heating furnace, forming a sequence of control commands for the future period.

[0010] Furthermore, the process of outputting the coordinated control results and energy consumption assessment is as follows: After the coordinated adjustment is completed, the lower-level distributed control integrates the data of the entire process to generate coordinated control results and energy consumption assessment reports. The coordinated control results clarify the actual pressure and temperature operating values ​​of each joint station in the future period, compare the deviation of the optimal setpoint, and statistically analyze the pressure fluctuation range and temperature stabilization time of the entire line to evaluate the effectiveness of the coordinated adjustment and form a safe operation assessment conclusion. The energy consumption assessment combines the real-time efficiency curves of the equipment at each station to calculate the actual energy consumption of each external pump and heating furnace during the adjustment process, and summarizes the total energy consumption of the entire line to compare the energy consumption data before and after adjustment and under the traditional mode.

[0011] A method for coordinated management of oil and gas pipeline transportation at a joint station includes the following steps: Step 1: Collect multi-dimensional data from the joint station equipment through edge computing nodes on the end side, identify the real-time efficiency curve of the equipment online, and generate the real-time status sequence of the equipment. Step 2: Using a cloud-based digital twin platform, a nonlinear hydrothermal coupling mechanism model of the pipeline network is constructed based on the real-time status sequence of the equipment, and online self-correction is performed to obtain a global pipeline network simulation model of the real-time field conditions. Based on a two-layer hierarchical optimization algorithm, and according to the global pipeline network simulation model and combined with historical inflow data, the optimal pressure and temperature setpoints for each joint station in the future are output. The two-layer hierarchical optimization algorithm includes an upper global energy consumption minimization optimization layer and a lower local predictive control tracking layer. Step 3: Based on the optimal pressure and temperature setpoints, predictive coordinated regulation is carried out through lower-level distributed control, and regulation commands are issued to downstream stations in advance, outputting coordinated control results and energy consumption assessments.

[0012] The present invention provides a method and system for coordinated management of oil and gas pipeline transportation at a joint station, which has the following beneficial effects: (1) By constructing a digital twin at the station group level, the present invention can dynamically control the coupling effect between stations globally. When the upstream liquid volume fluctuates, the system can issue a pre-adjustment command to the downstream station in advance, transforming passive response into active coordination, effectively suppressing the superposition and amplification of pressure fluctuations, and avoiding safety risks such as pipeline surge and separator overflow. By identifying the real-time efficiency curve of the equipment online through the edge nodes on the end side and integrating it into the cloud twin model, the drawback of the traditional model relying on fixed design parameters is changed. It reflects the characteristic drift caused by equipment aging in real time, so that the scheduling decision is always based on the actual operating status of the equipment, ensuring that each pump and each boiler operates in the high-efficiency zone.

[0013] (2) This invention utilizes liquid volume prediction and liquid flow transmission simulation to achieve control that is predicted first and then adjusted. Through a two-layer hierarchical optimization algorithm, it not only improves the adjustment speed and accuracy, but also continuously optimizes the scheduling strategy based on real-time data, realizing the transition from coarse adjustment to fine control, and significantly reducing the overall energy consumption of oil and gas gathering and transportation.

[0014] (3) Through self-learning and self-correction capabilities, the twin model automatically updates the efficiency curve and model parameters when the equipment ages, is replaced, or the operating conditions change. This not only reduces the workload and operation and maintenance costs of the model maintenance, but also when the equipment experiences aging phenomena such as wear, scaling, and corrosion due to long-term operation, or when the external pump impeller and heating furnace tube are replaced due to maintenance, the edge computing node on the end side will collect the operating data under the new operating conditions in real time, automatically identify and generate new equipment efficiency curves. The cloud-based digital twin platform will then correct the key parameters of the pipeline water-thermal coupling model online based on the updated equipment state sequence. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the system of the present invention; Figure 2 This is a schematic diagram of the overall method of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1 Please see Figure 1 Embodiment 1 of this application provides an oil and gas pipeline transportation coordination and management system for a joint station, the system comprising: The status identification module collects multi-dimensional data from the joint station equipment through edge computing nodes on the end side, identifies the real-time efficiency curve of the equipment online, and generates a real-time status sequence of the equipment. Monitoring points and sensors are deployed on the three-phase separator, external pump, and heating furnace equipment of the combined station, with sensor arrays deployed at the pre-set monitoring points: The three-phase separator is equipped with high-precision electromagnetic flowmeters, differential pressure densitometers, near-infrared moisture analyzers, and laser particle size analyzers installed at the inlet main pipe, oil phase outlet, water phase outlet, and gas phase outlet, respectively. At the same time, level transmitters and pressure transmitters are installed on the separator cylinder to monitor the inlet liquid flow, flow rate of each phase, medium density, moisture content, oil content, liquid level, and internal pressure.

[0018] The external pump set is equipped with pressure transmitters and temperature transmitters at the inlet and outlet of each external pump, respectively. Electromagnetic flow meters and vibration acceleration sensors are installed in the pump outlet pipeline. Current transformers, voltage transmitters, and power factor meters are installed in the power distribution cabinet of the drive motor. Temperature sensors and vibration sensors are also installed on the motor bearing housing to monitor the pump inlet and outlet pressure difference, medium temperature, flow rate, pump body vibration, motor current, voltage, power factor, and bearing conditions.

[0019] The heating furnace uses vortex flow meters and pressure transmitters installed in the fuel gas pipeline, platinum resistance temperature sensors and electromagnetic flow meters installed in the medium inlet and outlet pipelines, and a flue gas analyzer installed at the furnace exhaust port to detect O2, CO, and NO. x The concentration is monitored, and temperature sensors are installed on the furnace body insulation layer to monitor fuel consumption, medium inlet and outlet temperatures, flow rate, flue gas composition, and furnace heat dissipation.

[0020] Real-time data acquisition and synchronization edge computing nodes establish low-latency, highly reliable real-time communication links with each sensor via industrial communication protocols such as Industrial Ethernet, Modbus, or Profinet. They trigger data acquisition commands according to a preset acquisition frequency to synchronously acquire the analog or digital signals output by each sensor. For the three-phase separator, data on incoming liquid flow, oil-water-gas phase flow, medium density, water content, oil content, liquid level, and internal pressure are collected simultaneously. For each external pump, data on inlet and outlet pressure, medium temperature, flow rate, pump body vibration, motor current, voltage, power factor, bearing temperature, and vibration are collected simultaneously. For the heating furnace, data on fuel flow rate, medium inlet and outlet temperature, flow rate, flue gas composition, and furnace body temperature are collected simultaneously.

[0021] Data preprocessing and quality control: Edge computing nodes perform real-time preprocessing on the collected raw data to ensure data quality. Outlier removal is achieved using the 3σ principle and box plot method to automatically identify and remove abnormal data points caused by sensor malfunctions, electromagnetic interference, or process fluctuations. Missing data due to communication interruptions or sampling losses is appropriately filled using linear interpolation or sliding window averaging. Sensor data with different dimensions and ranges are normalized and converted into standardized data in a unified format. All collected data is timestamped with high precision to ensure strict alignment of data from different devices and sensors in the time dimension, forming a structured equipment operation dataset.

[0022] The preprocessed structured data is first temporarily stored in the local cache of the edge node. Key safety parameters, such as separator liquid level, pump outlet pressure, and furnace outlet temperature, are transmitted with high priority. Equipment operating parameters, such as motor current, vibration, and fuel flow, are transmitted periodically to balance real-time performance and bandwidth. Historical trend data is transmitted in batches with compression to reduce cloud load. The processed equipment operating dataset is then transmitted to the cloud digital twin platform via industrial private network or 5G network through the edge node.

[0023] The pipeline coupling construction module, through a cloud-based digital twin platform, constructs a nonlinear hydrothermal coupling mechanism model of the pipeline network based on the real-time state sequence of equipment, and performs online self-correction to obtain a global pipeline network simulation model of real-time field conditions. Based on a two-layer hierarchical optimization algorithm, and in conjunction with the global pipeline network simulation model and historical inflow data, it outputs the optimal pressure and temperature setpoints for each joint station in the future period. The two-layer hierarchical optimization algorithm includes an upper-layer global energy consumption minimization optimization layer and a lower-layer local predictive control tracking layer. The process of constructing a nonlinear hydrothermal coupling mechanism model for pipe networks is as follows: The cloud platform for initializing pipeline topology and parameters first imports the topology of the joint stations and oil pipelines from the engineering design library, including basic parameters such as the location of each joint station, the connection relationship of the pipeline segments, the pipeline length, the inner diameter, the design pressure, and the insulation layer thickness. At the same time, it extracts the real-time efficiency curves and operating characteristics of the external pumps, heating furnaces and three-phase separators of each station from the real-time status sequence of the equipment as the initial input of the model.

[0024] The hydraulic sub-model is constructed based on the pipeline network topology and the real-time status of the equipment. The pipeline network is abstracted into a network of nodes and pipe segments. Each node represents a combined station or confluence point, and each pipe segment represents a section of oil pipeline. For each pipe segment, based on parameters such as pipeline length, inner diameter, medium density, and flow velocity, combined with pipeline friction characteristics, and corrected by real-time operating data, a nonlinear relationship between pressure drop and flow rate is established. For each node, a flow balance equation is established based on the inflow, outflow and pipe segment flow rate to ensure that the total flow rate into the node is equal to the total flow rate out of the node. All pipe segment pressure drop equations and node flow balance equations are integrated to form an overall pipe network hydraulic model, which is used to calculate the pressure distribution of each node under any operating condition.

[0025] The thermal sub-model is constructed by combining the furnace efficiency curve and medium inlet and outlet temperatures in the real-time state sequence of the equipment to build a pipeline network thermal sub-model. For each pipe segment, a temperature decay model of the medium within the pipe segment is established based on the medium flow rate, inlet and outlet temperatures, ambient temperature, and pipeline heat transfer coefficient, corrected by the insulation layer state and soil thermal conductivity. For each combined station, the relationship between the furnace outlet temperature and fuel consumption is established based on the furnace efficiency curve and medium flow rate. All pipe segment temperature decay models and furnace thermal models are integrated to form an overall pipeline network thermal model, which is used to calculate the medium temperature distribution at each node under any operating condition.

[0026] The hydrothermal coupling and model integration couples the hydraulic and thermal sub-models to construct a nonlinear hydrothermal coupling mechanism model. The physical properties of the medium, such as density and viscosity, change with temperature. Therefore, the calculation of friction coefficient and pressure drop in the hydraulic model depends on the temperature value output by the thermal model. The parameters such as medium flow rate and velocity affect the residence time of the medium in the pipe, which in turn affects the temperature decay calculation in the thermal model. Through iterative solution, the calculation results of the hydraulic and thermal models are made self-consistent, forming a coupled model that can simultaneously describe the pressure and temperature distribution of the pipeline network.

[0027] Online self-correction and dynamic updates: The cloud platform receives real-time equipment status sequences and pipeline operation monitoring data uploaded from the end side, performs online self-correction on the coupled model, compares the node pressure and temperature calculated by the model with the actual monitored values, and automatically adjusts the friction coefficient, heat transfer coefficient, or equipment efficiency curve parameters of the corresponding pipe section if the deviation exceeds a preset threshold. When equipment is maintained, replaced, or aged more rapidly, the efficiency curve is refitted and the model input is updated based on the new real-time equipment status sequence, ensuring that the model always remains consistent with the actual on-site conditions. The model self-correction process is executed every 15 minutes, and is immediately triggered when critical operating conditions fluctuate, such as sudden changes in influent flow, to ensure model accuracy and real-time performance. The completed nonlinear hydrothermal coupling mechanism model can output the pressure, temperature, and flow distribution of all nodes along the entire line, as well as the energy consumption requirements of each device, under any given influent flow and equipment operating parameters, thus obtaining a global pipeline simulation model of real-time on-site conditions.

[0028] The process of outputting the optimal pressure and temperature setpoints for each joint station in the future time period is as follows: The cloud-based digital twin platform for preprocessing data and predicting inflow volume analyzes historical inflow volume data over time, eliminates invalid data under abnormal operating conditions, and combines seasonal changes and wellhead production system adjustment patterns to generate predicted inflow volume values ​​for every 15 minutes within the next 24 hours using a time series prediction algorithm. Simultaneously, it retrieves the latest parameters of the global pipeline network simulation model, uses the predicted inflow volume as the model boundary condition, and completes the initialization of the simulation environment, laying the data foundation for two-level hierarchical optimization calculations.

[0029] The upper-level global energy consumption minimization optimization layer uses the initialized global pipeline network simulation model as the core simulation environment. The core optimization objective is to minimize the total energy consumption of all combined pumps and heaters at all stations along the entire line. A constrained optimization problem is constructed and solved. Decision variables are determined, with the setpoints for the external pressure and heater outlet temperature of each combined station in future time periods as the core optimization variables. An energy consumption objective function is constructed, combining the real-time efficiency curves of each device in the global pipeline network simulation model. The shaft power of each external pump and the fuel consumption of each heater are summarized to form the total energy consumption calculation formula for the entire line. Multi-dimensional constraints are set, including pipeline hydraulic constraints, satisfying node flow balance, pipe section pressure drop limits, and equipment operation constraints, ensuring that pressure, temperature, and flow do not exceed the rated range of the equipment, pipeline pressure does not exceed the design value, and medium temperature is higher than the freezing point. An intelligent optimization algorithm is used to solve the problem, with the global pipeline network simulation model serving as the algorithm's simulation evaluator. Iterative calculations are used to select the optimal solution that satisfies all constraints and has the lowest total energy consumption, generating a sequence of optimal pressure and temperature setpoints for each combined station in future time periods, which serves as the target benchmark for the lower-level control.

[0030] The lower-level local predictive control tracking layer receives the optimal setpoint sequence output from the upper layer, performs fine-tuning based on the actual operating conditions of each station, generates directly executable control commands, and identifies operating condition deviations. By comparing the deviations between the current pressure and temperature of each station and the upper-level setpoints with real-time operating data collected from the edge computing nodes of each joint station, it identifies local disturbances such as fluctuations in influent flow and instantaneous changes in equipment operating conditions. It then optimizes tracking control, using the upper-level optimal setpoint as the tracking target, constructs a single-station predictive control model, predicts the operating condition change trend in the short term, optimizes control increments, and ensures a smooth adjustment process without overshoot. Through command generation and output, the adapted single-station pressure and temperature setpoints are decomposed into external pump frequency conversion speed commands and heater fuel flow adjustment commands, forming a control command sequence for the future period, thus completing the conversion of the optimal setpoints into actual values.

[0031] The cloud platform performs upper-level global optimization calculations every 15 minutes to update the optimal setpoint sequence; each joint station's local control system performs lower-level tracking optimizations every second, dynamically adjusting control commands based on the latest setpoints; when the global pipeline network simulation model completes self-correction due to equipment status updates, or when the predicted and actual liquid inflow values ​​deviate from the threshold, the upper-level optimization layer is immediately triggered to recalculate, achieving dynamic collaboration between the two-layer algorithms; the cloud platform then distributes the integrated optimal pressure and temperature setpoints for each joint station in the future time period to each joint station's local control system in the form of standardized commands.

[0032] The collaborative predictive scheduling module, based on the optimal pressure and temperature setpoints, performs predictive collaborative regulation through lower-level distributed control, issues regulation commands to downstream stations in advance, and outputs collaborative control results and energy consumption assessments. The process of outputting coordinated control results and energy consumption assessment is as follows: The lower-level distributed control receives the optimal pressure and temperature setpoint sequence for each joint station in real time from the cloud platform for future time periods. It simultaneously retrieves the fluid transmission prediction data output by the global pipeline network simulation model to clarify the transmission time, pressure and temperature change amplitude, and impact range of upstream fluid flow fluctuations. First, the optimal setpoints are localized and adapted. Combining the real-time efficiency curves of individual station equipment and current operating conditions, such as current pressure, temperature, and flow rate, setpoints that exceed the real-time operating capacity of the equipment are eliminated, and the adjustment range is corrected to ensure the feasibility of the commands. At the same time, the setpoints are segmented and sorted according to timestamps, corresponding to the adjustment targets every 15 minutes in the future, to generate standardized adjustment command templates.

[0033] Predictive coordinated regulation execution and command issuance are based on the predicted results of fluid flow transmission. The upstream fluctuations, such as the increase or decrease in the amount of fluid, are calculated to determine the precise time when they will reach each downstream joint station. Regulation commands are then issued to the distributed control systems of the corresponding downstream stations 5 to 10 minutes in advance.

[0034] During the upstream station's adjustment process, when the upstream station detects fluctuations in the incoming liquid volume or receives an optimization command from the cloud, the lower-level DCS immediately initiates the adjustment program. It adjusts the pump speed through the external pump frequency conversion speed control module and controls the external pressure to the optimal set value. It also adjusts the fuel supply through the heater fuel flow regulation module to stabilize the heater outlet temperature. At the same time, it records the equipment operating parameters during the adjustment process, such as pump speed and fuel flow.

[0035] During the pre-regulation process at the downstream station, after receiving the upstream fluctuation warning and regulation command, the downstream station DCS starts local regulation in advance without waiting for the liquid flow to arrive. It adjusts the operating parameters of its own external pump and heating furnace according to the optimal set value, optimizes the pressure and temperature conditions in the station in advance, and reserves fluctuation buffer space to avoid pressure superposition and temperature imbalance caused by upstream fluctuations being transmitted to the downstream.

[0036] During the cross-station collaborative verification process, the DCS of each station interacts with the adjustment progress data in real time through the industrial private network, and the cloud platform monitors the adjustment status of the entire line synchronously. If the adjustment deviation of a certain station exceeds the preset range, such as the pressure deviation exceeding ±3%, a correction command is immediately issued to ensure that the adjustment actions of each station are coordinated and consistent, and to smooth out pressure and temperature fluctuations across the entire line.

[0037] During the predictive collaborative regulation process, real-time monitoring and feedback are crucial. The lower-level distributed control system collects operating parameters of each station's equipment in real time through end-side sensors, including pressure, temperature, flow rate, energy consumption, and pipeline operating status, including pipe section pressure drop and medium flow velocity. Data acquisition and uploading are completed every second, and the deviation between the actual value after regulation and the optimal set value is compared synchronously. If the deviation is within the allowable range, the current regulation command is continuously executed to maintain stable equipment operation. If a sudden disturbance occurs, such as sensor failure or momentary equipment failure, an emergency regulation mechanism is immediately triggered to temporarily adjust the command parameters to avoid regulation failure. At the same time, the fault information is uploaded to the cloud platform to remind maintenance personnel to handle the situation. After adjustment, the actual adjustment parameters, fluctuation range, and execution duration for each time period are recorded to form an adjustment process ledger. After the coordinated adjustment is completed, the lower-level distributed control integrates the data from the entire process to generate a coordinated control result and energy consumption assessment report. The coordinated control result is obtained by clarifying the actual pressure and temperature operating values ​​of each joint station for future time periods and comparing the deviation from the optimal setpoint. The pressure fluctuation range and temperature stabilization duration of the entire line are statistically analyzed to evaluate the effectiveness of the coordinated adjustment. Safety hazards such as pipeline overpressure and equipment overload that did not occur during the adjustment process are recorded to form a safe operation assessment conclusion.

[0038] The energy consumption assessment combines the real-time efficiency curves of equipment at each station to calculate the actual energy consumption of each external pump and heating furnace during the adjustment process, and summarizes the total energy consumption of the entire line. It compares the energy consumption data before and after adjustment with the energy consumption data under the traditional scheduling mode to quantify the energy-saving effect. It analyzes abnormal energy consumption nodes, such as the energy consumption of a certain station being higher than the optimal value. The collaborative control results and energy consumption assessment report are uploaded to the cloud digital twin platform simultaneously for model self-correction and adjustment of upper-level optimization algorithm parameters, and are also displayed through a visual interface.

[0039] Example 2 Please see Figure 2 Based on Example 1, Example 2 of this application also provides a method for coordinated management of oil and gas pipeline transportation at a joint station, including the following specific steps: Step 1: Collect multi-dimensional data from the joint station equipment through edge computing nodes on the end side, identify the real-time efficiency curve of the equipment online, and generate the real-time status sequence of the equipment. Step 2: Using a cloud-based digital twin platform, a nonlinear hydrothermal coupling mechanism model of the pipeline network is constructed based on the real-time status sequence of the equipment, and online self-correction is performed to obtain a global pipeline network simulation model of the real-time field conditions. Based on a two-layer hierarchical optimization algorithm, and according to the global pipeline network simulation model and combined with historical inflow data, the optimal pressure and temperature setpoints for each joint station in the future are output. The two-layer hierarchical optimization algorithm includes an upper global energy consumption minimization optimization layer and a lower local predictive control tracking layer. Step 3: Based on the optimal pressure and temperature setpoints, predictive coordinated regulation is carried out through lower-level distributed control, and regulation commands are issued to downstream stations in advance, outputting coordinated control results and energy consumption assessments.

[0040] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0041] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0042] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A coordinated management system for oil and gas pipeline transportation at a joint station, characterized in that, The system includes: a status identification module, which collects multi-dimensional data from the joint station equipment through edge computing nodes on the end side, identifies the real-time efficiency curve of the equipment online, and generates a real-time status sequence of the equipment; The pipeline coupling construction module, through a cloud-based digital twin platform, constructs a nonlinear hydrothermal coupling mechanism model of the pipeline network based on the real-time state sequence of equipment, and performs online self-correction to obtain a global pipeline network simulation model of real-time field conditions. Based on a two-layer hierarchical optimization algorithm, and in conjunction with the global pipeline network simulation model and historical inflow data, it outputs the optimal pressure and temperature setpoints for each joint station in the future period. The two-layer hierarchical optimization algorithm includes an upper-layer global energy consumption minimization optimization layer and a lower-layer local predictive control tracking layer. The collaborative predictive scheduling module, based on the optimal pressure and temperature setpoints, performs predictive collaborative regulation through lower-level distributed control, issues regulation commands to downstream stations in advance, and outputs collaborative control results and energy consumption assessments.

2. The oil and gas pipeline transportation coordination management system for a joint station according to claim 1, characterized in that, The process of multi-dimensional data collection is as follows: Sensors are deployed at preset monitoring points of the joint station equipment. Edge computing nodes establish real-time communication connections with each sensor through an industrial bus and trigger data acquisition according to a preset acquisition frequency.

3. The oil and gas pipeline transportation coordination management system for a joint station according to claim 2, characterized in that, The process of generating a real-time device status sequence is as follows: The edge computing node calculates the actual head based on the collected pressure difference between the inlet and outlet of the external pump, the medium flow rate, and the motor input power. It also calculates the instantaneous efficiency of the pump under the current operating conditions by combining the medium flow rate and the motor input power. During continuous operation, multiple sets of data points with different flow rates and instantaneous efficiencies are collected. The least squares method is used to perform polynomial fitting on the data points to obtain the real-time efficiency curve of the pump under the current aging state. The fitted real-time efficiency curve, along with the corresponding flow rate, head, and data points, are stored in the equipment real-time status sequence in the order of timestamps.

4. The oil and gas pipeline transportation coordination management system for a joint station according to claim 1, characterized in that, The process of constructing a nonlinear hydrothermal coupling mechanism model for pipe networks is as follows: Import the topology of the joint station and oil pipeline network, as well as the real-time status sequence of the equipment, from the cloud platform engineering design library as the initial input of the model. The oil pipeline network is abstracted into a network of nodes and pipe segments, where each node is a joint station or junction point, and each pipe segment is a section of oil pipeline. For each pipe segment, a nonlinear relationship between pressure drop and flow rate is established based on pipe parameters and pipe friction characteristics. For each node, a node flow balance equation is established based on flow rate. All pipe segment pressure drop equations and node flow balance equations are integrated to form an overall pipe network hydraulic model. For each pipe segment, a temperature decay model of the medium within the pipe segment is established based on the pipe parameters. For each combined station, the relationship between the furnace outlet temperature and fuel consumption is established based on the furnace efficiency curve and the medium flow rate. All pipe segment temperature decay models and furnace thermal models are integrated to form an overall network thermal model. The hydraulic sub-model and the thermal sub-model are coupled to construct a nonlinear hydrothermal coupling mechanism model.

5. The oil and gas pipeline transportation coordination management system for a joint station according to claim 1, characterized in that, The process of obtaining a global pipeline network simulation model with real-time on-site operating conditions is as follows: The cloud platform receives real-time device status sequences and pipeline operation monitoring data uploaded from the end side, refits the efficiency curves based on the new device real-time status sequences, and updates the model input.

6. The oil and gas pipeline transportation coordination management system for a joint station according to claim 5, characterized in that, The process of outputting the optimal pressure and temperature setpoints for each joint station in the future time period is as follows: By acquiring historical inflow data and combining it with seasonal variations and wellhead production system adjustment patterns, a time series prediction algorithm is used to generate predicted inflow values. The latest parameters of the global pipeline network simulation model are retrieved, and the predicted inflow is used as the model boundary condition to complete the initialization of the simulation environment. With minimizing the total energy consumption of the joint off-site pumps and heating furnaces as the core optimization objective, a constrained optimization problem is constructed and solved. The lower-level local predictive control tracking layer receives the optimal setpoint sequence output from the upper layer, adapts it to the actual working conditions of a single station, and generates control commands. The cloud platform executes the upper-level global optimization calculation once at fixed intervals and updates the optimal setpoint sequence. Each joint station's local control system performs lower-level tracking optimization once per second, dynamically adjusting control commands based on the latest setpoints. When the global pipeline network simulation model completes self-correction due to equipment status updates or when the predicted and actual liquid inflow values ​​deviate from the threshold, the upper-level optimization layer is triggered to recalculate. The cloud platform then distributes the integrated optimal pressure and temperature setpoints for each joint station for future periods to the local control systems of each joint station in the form of standardized commands.

7. The oil and gas pipeline transportation coordination management system for a joint station according to claim 6, characterized in that, The process of the lower-level local predictive control tracking layer is as follows: By collecting real-time operating data from the edge computing nodes of each joint station, the deviations of the current pressure and temperature of a single station from the upper-level setpoints are compared to identify fluctuations in the influent volume and local disturbances caused by instantaneous changes in the equipment's operating conditions. Using the upper-level optimal setpoint as the tracking target, a single-station predictive control model is constructed to predict the trend of operating condition changes in the short term. The adapted single-station pressure and temperature setpoints are decomposed into variable frequency speed commands for the external pump and fuel flow regulation commands for the heating furnace, forming a sequence of control commands for the future period.

8. The oil and gas pipeline transportation coordination management system for a joint station according to claim 1, characterized in that, The process of outputting coordinated control results and energy consumption assessment is as follows: After the coordinated adjustment is completed, the lower-level distributed control integrates the data of the entire process to generate coordinated control results and energy consumption assessment reports. The coordinated control results clarify the actual pressure and temperature operating values ​​of each joint station in the future period, compare the deviation of the optimal setpoint, and statistically analyze the pressure fluctuation range and temperature stabilization time of the entire line to evaluate the effectiveness of the coordinated adjustment and form a safe operation assessment conclusion. The energy consumption assessment combines the real-time efficiency curves of the equipment at each station to calculate the actual energy consumption of each external pump and heating furnace during the adjustment process, and summarizes the total energy consumption of the entire line to compare the energy consumption data before and after adjustment and under the traditional mode.

9. A method for coordinated management of oil and gas pipeline transportation at a joint station, characterized in that, Includes the following steps: Step 1: Collect multi-dimensional data from the joint station equipment through edge computing nodes on the end side, identify the real-time efficiency curve of the equipment online, and generate the real-time status sequence of the equipment. Step 2: Using a cloud-based digital twin platform, a nonlinear hydrothermal coupling mechanism model of the pipeline network is constructed based on the real-time status sequence of the equipment, and online self-correction is performed to obtain a global pipeline network simulation model of the real-time field conditions. Based on a two-layer hierarchical optimization algorithm, and according to the global pipeline network simulation model and combined with historical inflow data, the optimal pressure and temperature setpoints for each joint station in the future are output. The two-layer hierarchical optimization algorithm includes an upper global energy consumption minimization optimization layer and a lower local predictive control tracking layer. Step 3: Based on the optimal pressure and temperature setpoints, predictive coordinated regulation is carried out through lower-level distributed control, and regulation commands are issued to downstream stations in advance, outputting coordinated control results and energy consumption assessments.

Images