Natural gas comprehensive operation and management platform based on the Internet of Things

Abstract

The present invention discloses a natural gas comprehensive operation and control platform based on the Internet of Things, which relates to the field of natural gas management technology, and includes: a cloud server; a data acquisition unit, which is used to collect the operating parameters of each node of the natural gas pipeline network and transmit them to the cloud server; a simulation modeling unit, which constructs a virtual model of the natural gas pipeline network according to the operating parameters and performs simulation analysis; a solution generation unit, which uses an optimization algorithm to calculate a control instruction set based on the simulation results and combines them into a natural gas operation and control solution; a pipeline network control unit, which is used to receive the natural gas operation and control solution, adjust the valve opening, and detect the physical quantity deviation value during the adjustment process, and feed the physical quantity deviation value back to the cloud server to update the natural gas operation and control solution. The present invention improves the acquisition accuracy and comprehensiveness of pipeline network operation data, realizes real-time monitoring of gas components, and improves the operation efficiency, safety and reliability of the natural gas pipeline network.

Description

Technical Field

[0001] The present invention relates to the field of natural gas management technology, and in particular to a natural gas comprehensive operation and control platform based on the Internet of Things. Background Art

[0002] As a clean and efficient energy carrier, natural gas plays an increasingly important role in the transformation of the global energy structure. With the continuous growth of natural gas demand and the continuous expansion of the supply network, the operation and management of natural gas pipeline networks face unprecedented complexity and challenges. Traditional pipeline network monitoring and scheduling methods mainly rely on discrete measurement points and empirical manual decisions, which are often insufficient when dealing with large-scale and highly dynamic pipeline systems. In recent years, the rapid development of Internet of Things technology has opened up new ways for the intelligent management of natural gas pipeline networks. By deploying a large-scale intelligent sensor network at each key node of the pipeline network, all-round and real-time monitoring of pipeline network operating parameters is achieved, laying a solid data foundation for the precise control and optimized operation of the pipeline network. However, how to effectively process and utilize these massive and heterogeneous data streams, build a high-precision pipeline network digital twin model, and realize data-driven intelligent decision-making is still a major technical problem facing the current field of natural gas pipeline network operation and management.

[0003] The current natural gas pipeline network operation and management technology still has many shortcomings in terms of the real-time and comprehensiveness of data collection, the accuracy of simulation models, the degree of intelligence of decision-making, and the coordination of systems. First, the existing data acquisition technology often cannot meet the needs of high-precision pipeline network simulation and real-time optimization in terms of sampling frequency and accuracy. Secondly, the real-time monitoring and analysis capabilities of gas component changes are generally insufficient, which directly affects the accurate assessment of pipeline network operation efficiency and safety. Furthermore, most pipeline network management systems are still limited to basic data visualization and threshold alarm functions, and lack active optimization capabilities based on high-precision simulation and intelligent algorithms. Finally, there are obvious shortcomings in the coordination mechanism between cloud decision-making and local execution, making it difficult to achieve coordination and rapid response across the entire network. These technical bottlenecks have seriously restricted the further improvement of the efficiency and safety of natural gas pipeline network operations. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the present invention provides a natural gas comprehensive operation and management platform based on the Internet of Things, which can solve the problems mentioned in the background technology.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a natural gas integrated operation and control platform based on the Internet of Things, comprising: a cloud server; and a data acquisition unit, used to collect the operating parameters of each node of the natural gas pipeline network, and transmit the operating parameters to the cloud server; the operating parameters include natural gas pipeline network topology information and gas component data; a simulation modeling unit, used to run a virtual simulation system on the cloud server, build a virtual model of the natural gas pipeline network according to the operating parameters, and perform simulation analysis to obtain simulation results; a solution generation unit, which uses an optimization algorithm to calculate a control instruction set based on the simulation results in the simulation modeling unit, and combines the control instruction set into a natural gas operation and control solution; a pipeline network control unit, used to receive the natural gas operation and control solution issued by the cloud server, adjust the valve opening, and detect the physical quantity deviation value during the adjustment process, and feed the physical quantity deviation value back to the cloud server to update the natural gas operation and control solution.

[0007] As a preferred solution of the IoT-based natural gas integrated operation and control platform described in the present invention, wherein: the data acquisition unit includes a data perception module, a data preprocessing module and a data transmission module; the data perception module uses the IoT devices deployed at each node of the natural gas pipeline network to collect the natural gas pipeline network topology information and gas component data in real time; the data preprocessing module is used to clean and format the real-time data and the gas component data; the data transmission module is used to encrypt and package the real-time data and the gas component data, and transmit them to the cloud server.

[0008] As a preferred solution of the Internet of Things-based natural gas integrated operation and control platform described in the present invention, the natural gas pipeline network topology information includes the connection relationship of pipe sections, pipe diameter edge households, valves, and compressor station location information; the gas component data includes the types and initial concentration distribution of various gas components;

[0009] The simulation modeling unit includes a model construction module, a parameter configuration module and a simulation calculation module; wherein the model construction module adopts a physical feature-driven adaptive grid generation algorithm to dynamically construct an unstructured grid according to the operating parameters; the adaptive grid generation algorithm includes the following steps:

[0010] generating an initial unstructured grid based on the natural gas pipeline network topological structure information;

[0011] Using the gas composition data, calculate the physical characteristic index of each grid cell E c , expressed as:

[0012]

[0013] in, p , v , T are pressure, velocity and temperature respectively, c j For the j The concentration of the gas component, m is the number of gas components, Respectively indicate pressure p ,speed v and temperature T In the grid cell c The gradient norm inside: Indicates pressure p The gradient vector of Represented in grid cells c The magnitude of the internal pressure gradient vector; Indicates speed v The gradient tensor of Represented in grid cells c Norm of the internal velocity gradient tensor; Indicates temperature T The gradient vector of Represented in grid cells c The magnitude of the internal temperature gradient vector; p ref , v ref , T ref , c j,ref is the reference value of the corresponding physical quantity, h c For grid cells c feature size.

[0014] Physical characteristic indicators Exceeding the first preset threshold The mesh units are refined, and the refinement methods include: defining the refinement level L, with an initial value of 0; if the physical characteristic index E c > First preset threshold E threshold ,but:

[0015]

[0016] in, Indicates a certain level of refinement; Indicates the maximum level of refinement allowed.

[0017] According to the refinement level L , divide the grid cells into subunits, of which d is the spatial dimension; locally reconstruct the refined grid; repeatedly calculate the physical characteristic index E c , to locally reconstruct the refined grid until one of the following conditions is met: the physical characteristic index of all grid cells E c Less than target threshold E target ; Reached the maximum number of iterations N max 。

[0018] During the grid generation and calculation process, the gas components in each grid cell are continuously monitored based on the gas component data. j If the concentration change rate of , then the local grid reconstruction of the unit is triggered; among them, For gas components j The concentration change rate, For gas components j If the local grid reconstruction is triggered, the physical characteristic index is recalculated for the corresponding area. E c , to locally reconstruct the refined mesh and update the mesh structure.

[0019] The parameter configuration module adopts a data assimilation method constrained by a physical model, combined with real-time data and historical data collected by IoT devices, to dynamically update boundary conditions and calculation parameters; the data assimilation method includes: constructing a physical constraint model based on conservation of mass, momentum and energy; using an ensemble Kalman filter algorithm to fuse observed data and physical model predictions; and dynamically adjusting the time-varying boundary conditions of pressure, flow, temperature and gas components based on the assimilation results.

[0020] If the deviation between the assimilation result and the physical constraint exceeds the second preset threshold ε , then adjust the weight parameters in the data assimilation process and re-execute the data assimilation iteration:

[0021]

[0022] in, It represents the results obtained by data assimilation method; Indicates the theoretical value calculated based on the physical model.

[0023] As a preferred solution of the Internet of Things-based natural gas integrated operation and control platform described in the present invention, the simulation calculation module is used to perform fluid mechanics calculations and output simulation results; the simulation calculation module uses an improved characteristic line finite volume method to solve the Navier-Stokes equations considering multi-component transmission, specifically: tracking the motion of fluid particles along the characteristic line to capture wave propagation characteristics; using a high-order TVD format for spatial discretization under the characteristic line framework; introducing a component-based real gas state equation and a transport coefficient model to describe the thermodynamic and transport characteristics of a gas mixture; using an adaptive time step control algorithm based on a characteristic time scale:

[0024]

[0025] in, CFL is the Courant number; is the flow rate; is the speed of sound; is the kinematic viscosity; is the thermal diffusion coefficient.

[0026] If local numerical instability indicators are detected I unstable Exceeding the threshold I threshold , the system is considered to be in an unstable state and automatically switches to the implicit format:

[0027]

[0028] in, Indicates the pressure change; Indicates the change in speed; Indicates the temperature change; Indicates j The change in the concentration of the gas component; It indicates the maximum value among all gas components.

[0029] As a preferred solution of the Internet of Things-based natural gas integrated operation and control platform described in the present invention, wherein: the solution generation unit includes an instruction calculation module, a solution combination module and an optimization analysis module; the instruction calculation module constructs a multi-objective optimization model based on the simulation results, and calculates the pressure control instruction, flow control instruction and temperature control instruction according to the physical characteristics of the unstructured grid, specifically: the corresponding change trends of the pressure gradient, velocity gradient, temperature gradient and gas component concentration gradient in the grid unit are calculated respectively; the balance equation group is established for the pressure difference, flow distribution and temperature distribution between the grid units respectively; according to the simultaneous solution results of the change trend and the balance equation group, the pressure control reference value, the flow control reference value and the temperature control reference value are obtained; an objective function including energy consumption minimization and gas supply stability maximization is constructed, and the optimization calculation is performed with the control reference value as the initial value; wherein the objective function is composed of an energy consumption sub-objective and a gas supply stability sub-objective; the energy consumption sub-objective includes the weighted sum of the compressor energy consumption, the pressure regulating equipment energy consumption and the heating equipment energy consumption; the gas supply stability sub-objective includes the weighted sum of the flow fluctuation amplitude, the pressure fluctuation amplitude and the temperature fluctuation amplitude of each grid unit. The instruction calculation module minimizes the energy consumption sub-objective and maximizes the gas supply stability sub-objective through optimization calculation, and generates the optimization result as the control instruction set.

[0030] As a preferred solution of the Internet of Things-based natural gas integrated operation and control platform described in the present invention, wherein: the solution combination module combines the control instruction set into a natural gas operation and control solution, and the solution combination includes the time sequence arrangement and spatial organization of the control instructions; the solution combination module constructs a control association matrix to determine the execution association relationship between the pressure control instructions, the flow control instructions and the temperature control instructions; the solution combination module combines the control instructions with high correlation into a control instruction group according to the control association matrix, and arranges them according to the execution sequence to form the natural gas operation and control solution; wherein the execution association relationship includes the spatial distance of the control instructions, The optimization analysis module conducts a feasibility assessment on the natural gas operation and control plan, and constructs an evaluation index system including safety constraints, economic constraints and stability constraints; wherein the safety constraints include pipeline pressure limits and equipment operating parameter limits, the economic constraints include energy consumption indicators and gas transmission costs, and the stability constraints include pressure fluctuation amplitude, flow rate change rate and temperature change rate; when each indicator in the evaluation index system does not exceed their respective change limits, the natural gas operation and control plan is determined to be feasible; if any indicator exceeds its change limit, the command calculation module is returned to recalculate the control instruction set.

[0031] As a preferred solution of the Internet of Things-based natural gas integrated operation and control platform described in the present invention, the pipeline network control unit includes a local control module, an instruction execution module, a deviation detection module, and a feedback processing module; the local control module is used to receive and parse the natural gas operation and control plan, the instruction execution module is used to convert the natural gas operation and control plan into a valve opening adjustment instruction, the deviation detection module is used to collect the physical quantity deviation value in the valve adjustment process, and the feedback processing module is used to package the physical quantity deviation value and feed it back to the cloud server.

[0032] To further solve the above technical problems, the present invention provides the following technical solutions: a natural gas comprehensive operation and control method based on the Internet of Things, comprising: collecting operating parameters of each node of the natural gas pipeline network, and transmitting the operating parameters to a cloud server; running a virtual simulation system on the cloud server, constructing a virtual model of the natural gas pipeline network according to the operating parameters, and performing simulation analysis to obtain simulation results; based on the simulation results, using an optimization algorithm to calculate a control instruction set, and combining the control instruction set into a natural gas operation and control plan; the cloud server sends the natural gas operation and control plan to the local control unit of the natural gas pipeline network node, adjusts the valve opening, and detects the physical quantity deviation value during the adjustment process, and feeds back the physical quantity deviation value to the cloud server to update the natural gas operation and control plan.

[0033] A computer device includes a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the above-mentioned integrated natural gas operation and control platform based on the Internet of Things when executing the computer program.

[0034] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the above-mentioned natural gas integrated operation and control platform based on the Internet of Things are implemented.

[0035] Beneficial effects of the present invention: The present invention realizes intelligent management and control of the entire process from data collection, simulation modeling to solution generation and execution. First, the collection accuracy and comprehensiveness of pipeline network operation data are significantly improved, and real-time monitoring of gas components is realized; secondly, by constructing a high-precision virtual simulation model, the prediction accuracy of the pipeline network operation status is greatly improved; thirdly, based on the optimization algorithm, the automatic generation and dynamic optimization of the pipeline network operation plan are realized; finally, by establishing a collaborative mechanism between cloud-based decision-making and local execution, the flexibility and response speed of pipeline network control are improved. The present invention improves the operational efficiency, safety and reliability of the natural gas pipeline network, and provides strong support for the sustainable development of the natural gas industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0037] Figure 1 This is an overall schematic diagram of the natural gas comprehensive operation and control platform based on the Internet of Things proposed by the present invention;

[0038] Figure 2 This is a schematic diagram of the structure of the natural gas comprehensive operation and control platform based on the Internet of Things proposed by the present invention;

[0039] Figure 3 This is an interactive sequence diagram of the natural gas comprehensive operation and control platform based on the Internet of Things proposed by the present invention;

[0040] Figure 4 This is a schematic diagram of the interactive process of the natural gas comprehensive operation and control platform based on the Internet of Things proposed by the present invention;

[0041] Figure 5 This is a schematic diagram of the overall process of the natural gas comprehensive operation and control method based on the Internet of Things proposed by the present invention;

[0042] Figure 6 This is a diagram of computer equipment in the natural gas comprehensive operation and control platform based on the Internet of Things proposed by the present invention. DETAILED DESCRIPTION

[0043] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0044] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0045] Example 1, reference Figure 1~Figure 4 , which is an embodiment of the present invention, provides a natural gas comprehensive operation and management platform based on the Internet of Things.

[0046] Figure 1The overall schematic diagram of the natural gas integrated operation and control platform based on the Internet of Things is shown, including a cloud server, a data acquisition unit, a simulation modeling unit, a solution generation unit, and a pipeline network control unit.

[0047] The cloud server is the core computing platform and data processing center of the present invention. On the one hand, it receives the operating parameters (natural gas pipeline network topology information and gas component data) from the data acquisition unit to provide basic data support for the operation of the present invention; on the other hand, it carries the operation of the simulation modeling unit and the solution generation unit, wherein the simulation modeling unit constructs a virtual model of the natural gas pipeline network based on the received operating parameters and performs simulation analysis, and the solution generation unit generates a natural gas operation and control plan based on the simulation results obtained by the simulation analysis; at the same time, the cloud server is also responsible for sending the generated natural gas operation and control plan to the pipeline control unit for execution, and receiving the physical quantity deviation value feedback from the pipeline control unit, thereby forming a complete data closed loop and realizing the continuous optimization and control of the natural gas pipeline network. Through this centralized data processing and distributed execution feedback mechanism, the present invention enables the cloud server to play a key role in data aggregation, analysis and decision-making, and instruction distribution in the entire natural gas comprehensive operation and control platform, and is an important infrastructure to ensure the efficient and safe operation of the natural gas pipeline network.

[0048] Furthermore, Figure 2 The figure is a schematic diagram of the specific structure of the natural gas integrated operation and control platform based on the Internet of Things. The data acquisition unit collects the operating parameters of each node of the natural gas pipeline network and transmits the operating parameters to the cloud server. The operating parameters include the natural gas pipeline network topology information and gas composition data.

[0049] Specifically, the data acquisition unit includes a data sensing module, a data preprocessing module and a data transmission module. The data sensing module collects the natural gas pipeline network topology information and gas component data of each node of the natural gas pipeline network, the data preprocessing module cleans and formats the natural gas pipeline network topology information and gas component data, and the data transmission module encrypts and packages the natural gas pipeline network topology information and gas component data and transmits them to the cloud server.

[0050] It should be noted that the data acquisition unit, as the front end of the present invention, is responsible for collecting natural gas pipeline network topology information and gas component data from various key nodes of the natural gas pipeline network. It consists of three core modules: a data perception module, a data transmission module, and a data preprocessing module. The data perception module uses the Internet of Things devices (including intelligent terminals for collection and control) deployed at each node of the natural gas pipeline network to collect natural gas pipeline network topology information and gas component data in real time. These intelligent terminals constitute a comprehensive intelligent sensor network to ensure the accuracy and real-time performance of data collection. The collected operating parameters are then passed to the data transmission module, which uses a highly secure encryption algorithm to package the data and transmits the collected data to the cloud server through a high-speed and reliable communication network (5G or a dedicated optical fiber network can be used). Before the data arrives at the cloud server, the data preprocessing module will perform preliminary cleaning and formatting on the collected data to ensure its quality and consistency. This preprocessing step can effectively reduce the computing burden of the cloud server and improve the operating efficiency of the present invention. Through this layered design and the application of Internet of Things technology, the data acquisition unit can not only ensure the comprehensiveness and real-time performance of data collection, but also ensure the security and reliability of data transmission. The widespread deployment of IoT devices enables the system to obtain more detailed and timely data, providing a high-quality data foundation for subsequent simulation analysis and decision optimization, thereby realizing the intelligent and refined management of the natural gas pipeline network.

[0051] Figure 3 This is an interactive timing diagram of the natural gas integrated operation and control platform based on the Internet of Things proposed in the present invention. It can be seen that the interaction timing between the various units in the present invention can be simplified as follows: Figure 4 The interactive process diagram is shown in FIG. 1 . In the figure, the simulation modeling unit runs a virtual simulation system on a cloud server, builds a virtual model of the natural gas pipeline network according to the operating parameters, and performs simulation analysis to obtain simulation results.

[0052] Furthermore, the simulation modeling unit includes a model building module, a parameter configuration module and a simulation calculation module.

[0053] The model building module uses a physical feature-driven adaptive mesh generation algorithm to dynamically build an unstructured mesh based on operating parameters. The adaptive mesh generation algorithm includes the following steps:

[0054] 1. Generate the initial unstructured grid based on the natural gas pipeline network topology information.

[0055] 2. Using gas composition data, calculate the physical characteristic indicators of each grid cell E c , expressed as:

[0056]

[0057] in, p , v , T are pressure, velocity and temperature respectively, c j For the j The concentration of the gas component, m is the number of gas components, Respectively indicate pressure p ,speed v and temperature T In the grid cell c The gradient norm inside: Indicates pressure p The gradient vector of Represented in grid cells c The magnitude (magnitude) of the internal pressure gradient vector; Indicates speed v The gradient tensor of Represented in grid cells c The norm of the internal velocity gradient tensor (can be the Frobenius norm); Indicates temperature T The gradient vector of Represented in grid cells c The magnitude (magnitude) of the internal temperature gradient vector; p ref , v ref , T ref , c j,ref is the reference value of the corresponding physical quantity, h c For unit c feature size.

[0058] It should be noted that the calculation of these gradients reflects the rate of change of the corresponding physical quantity (pressure, velocity, temperature) in space. A larger gradient value indicates that the physical quantity changes dramatically within the grid cell, and a finer grid may be required to accurately capture this change. E c In the calculation of , these gradients are used to identify areas that require higher resolution, thereby guiding the adaptive mesh refinement process.

[0059] It should be noted that in the natural gas pipeline network, the pressure reference value p refIt is usually selected as the nominal working pressure of the system. For long-distance pipelines, 4.0MPa (medium-pressure pipeline network) or 10.0MPa (high-pressure pipeline network) can be selected as the reference value. The selection of this reference value is based on the design pressure level of the pipeline network, making the normalized calculation of the pressure gradient more physically meaningful. In practical applications, it can also be determined based on the statistical average of historical operating data, usually taking 75%~85% of the operating pressure. Velocity reference value in natural gas pipelines v ref Usually selected as the pipeline design flow rate, this value needs to consider the safe transportation of gas and the economy of the pipeline. According to engineering experience, the reference flow rate of natural gas pipelines is generally 15~20m / s. The determination of this reference value needs to balance the pipeline transportation capacity and pressure loss. Too high a flow rate will lead to excessive pressure loss and pipeline wear. Temperature reference value T ref The standard operating temperature of the natural gas pipeline network is usually 293.15K (20°C). The selection of this reference value takes into account the normal operating temperature range of natural gas in the pipeline and the temperature limit to avoid hydrate formation. In cold areas, this reference value can be appropriately adjusted according to local climatic conditions. Reference value of gas component concentration c j,ref :For the j For a gas component, its concentration reference value is usually taken as the standard concentration value of the component in natural gas. For example, for methane (the main component), it can be taken as 0.900.95; for ethane, it can be taken as 0.020.05; for other trace components, it is determined according to the characteristics of the gas source. The selection of these reference values ​​needs to consider the natural gas quality standard and the actual gas supply requirements.

[0060] 3. Physical characteristic indicators E c Exceeding the first preset threshold E threshold The mesh cells are refined as follows:

[0061] First, define the refinement level L, with an initial value of 0;

[0062] Then, if the physical characteristic index E c > First preset threshold E threshold ,but:

[0063]

[0064] in, Indicates a certain level of refinement; Represents the maximum refinement level allowed. It should be noted that the first preset threshold is the judgment criterion for triggering grid refinement, and its physical meaning is to identify areas where flow changes drastically. The determination of the first preset threshold needs to take into account typical flow characteristics in the natural gas pipeline network, such as high-speed jets at the outlet of the compressor station, complex flows at pipeline intersections, etc. In practical applications, the threshold can be determined by analyzing the pressure fluctuations and flow rate change characteristics in historical operating data. According to the adaptive grid algorithm of the present invention, grid refinement will be triggered when the physical characteristic index exceeds the first preset value, and the value range can be 0.15~0.18. For example, in the downstream area of ​​the compressor station, if the first preset threshold is taken E threshold The value is 0.16, which can effectively identify the high gradient areas that need to be refined and ensure accurate simulation of complex flows.

[0065] Finally, according to the refinement level L , divide the grid cells into subunits, of which d is the spatial dimension.

[0066] 4. Perform local reconstruction on the refined mesh to maintain mesh quality and achieve smooth transition of the mesh.

[0067] 5. Repeat steps 2 to 4 until one of the following conditions is met:

[0068] a) Physical characteristic indicators of all grid cells E c Less than target threshold E target ;

[0069] b) Reach the maximum number of iterations N max 。

[0070] It should be noted that the target threshold is a key indicator for evaluating grid quality and is used to determine the termination condition for adaptive grid generation. In natural gas pipeline network simulation, this threshold directly affects the calculation accuracy and resource consumption. The target threshold needs to be determined comprehensively based on the characteristics of the pipeline network (such as pipe diameter, length) and operating parameters (such as pressure level, flow change). Exemplarily, based on the physical feature driving mechanism of the present invention, it is recommended to take a value of 0.020.03 in the high-pressure pipeline network (above 10.0MPa), a value of 0.030.04 in the medium-pressure pipeline network (about 4.0MPa), and a value of 0.04~0.05 in the low-pressure pipeline network. This hierarchical setting can avoid excessive consumption of computing resources while ensuring the calculation accuracy. For example, for a section of a high-pressure pipeline with a length of 100km, when the target threshold is 0.025, it can accurately capture the pressure fluctuations and component transmission characteristics while maintaining a reasonable amount of calculation.

[0071] In practical applications, the adaptive mesh generation algorithm can effectively handle complex flow phenomena in natural gas pipeline networks. For example, near compressor stations, pipeline intersections, or areas where gas composition changes rapidly, the algorithm automatically increases the mesh density to accurately capture the flow details in these areas. At the same time, in long straight pipe sections where the flow is relatively stable, the algorithm will maintain a coarser mesh to save computing resources.

[0072] 6. During the grid generation and calculation process, based on the gas composition data, continuously monitor the gas components in each grid cell j If the concentration change rate meets the following conditions, the local grid reconstruction of the unit is triggered:

[0073]

[0074] in, For gas components j The concentration change rate, For gas components j It should be noted that this mechanism is particularly useful when dealing with natural gas source switching or blending operations, and can adjust the grid in time to adapt to new flow and component distribution characteristics.

[0075] It should be noted that the gas composition j The concentration change rate threshold It is used to monitor the dynamic changes of gas components and is an important parameter for triggering local grid reconstruction. In the operation of natural gas pipeline networks, especially when different gas sources are blended or switched, this threshold directly affects the ability to capture component changes. The setting of the threshold needs to consider the importance and allowable fluctuation range of different gas components. For major components (such as methane, molar fraction>90%), the value can be 0.008 / s; for important minor components (such as ethane, molar fraction 2%~5%), the value can be 0.002 / s; for trace components, the value can be 0.001 / s. This differentiated setting can accurately reflect the transmission characteristics of different components and provide a reliable basis for pipeline network scheduling optimization.

[0076] 7. If local grid reconstruction is triggered, re-execute steps 2 to 4 for the corresponding area to update the grid structure.

[0077] Through the above steps, the adaptive grid generation algorithm can effectively handle complex flow phenomena in the natural gas pipeline network according to the operating parameters, while ensuring the calculation accuracy and optimizing the use of computing resources. The algorithm dynamically adjusts the grid density according to the physical characteristic indicators, increases the grid accuracy in areas where the flow changes drastically or the component distribution is complex, and maintains a coarser grid in areas where the flow is relatively stable. At the same time, by continuously monitoring the rate of change of gas components, the algorithm can respond to dynamic changes such as natural gas source switching or blending operations in a timely manner, ensuring that the grid structure always adapts to the current flow state and component distribution.

[0078] The parameter configuration module uses the data assimilation method of physical model constraints, combined with the real-time data and historical data collected by IoT devices, to dynamically update boundary conditions and calculation parameters. Data assimilation methods include:

[0079] Construct physical constraint models based on conservation of mass, momentum, and energy;

[0080] Using the ensemble Kalman filter algorithm to fuse observation data and physical model predictions;

[0081] Based on the assimilation results, dynamically adjust the time-varying boundary conditions of pressure, flow, temperature and gas composition;

[0082] In actual operation, the data assimilation method can effectively integrate multi-source data from SCADA systems, gas chromatographs, flow meters, etc., to achieve accurate estimation of the status of the pipeline network. For example, when dealing with pressure fluctuations in the pipeline network, the data assimilation method can combine physical models and real-time pressure sensor data to accurately predict the propagation and attenuation of fluctuations, providing a basis for the optimal control of pressure regulating equipment.

[0083] If the deviation between the assimilation result and the physical constraint exceeds the second preset threshold ε , then adjust the weight parameters in the data assimilation process and re-execute the data assimilation iteration:

[0084]

[0085] in, It represents the results obtained by data assimilation method; It represents the theoretical value calculated based on the physical model, reflecting the result predicted based on physical laws and known conditions. This mechanism helps to timely detect abnormal conditions in the operation of the pipeline network, such as leakage, equipment failure or data collection abnormality. It should be noted that the second preset threshold εIt is an important indicator for evaluating the reliability of data assimilation results, and is used to determine whether the deviation between the assimilation results and the physical model is within an acceptable range. Determining the second preset threshold requires balancing the uncertainty of the measurement data and the predictive ability of the physical model. In the operation of the natural gas pipeline network, different physical quantities have different measurement accuracy and allowable error ranges. According to the physical model constrained data assimilation method of the present invention, the value range can be 0.07~0.08. For example, when the second preset threshold is 0.075, it can not only ensure the reliability of the assimilation results, but also tolerate reasonable measurement errors and deviations caused by model simplification.

[0086] The simulation calculation module performs fluid mechanics calculations and outputs simulation results. Specifically, the simulation calculation module uses an improved characteristic line finite volume method to solve the Navier-Stokes equations considering multi-component transmission, specifically:

[0087] 1. Track the motion of fluid particles along characteristic lines and capture wave propagation characteristics;

[0088] 2. In the feature line framework, a high-order TVD format is used for spatial discretization;

[0089] 3. Introduce the component-based real gas state equation and transport coefficient model to describe the thermodynamic and transport characteristics of gas mixtures;

[0090] 4. Use an adaptive time step control algorithm based on characteristic time scale:

[0091]

[0092] in, CFL is the Courant number; is the flow rate; is the speed of sound; is the kinematic viscosity; is the thermal diffusion coefficient.

[0093] This calculation method is particularly suitable for dealing with fast transient processes in natural gas pipeline networks, such as pressure fluctuations caused by rapid valve switching, compressor start-up and shutdown, etc. At the same time, the multi-component transmission model can accurately simulate the mixing process of natural gas from different sources, providing a reliable basis for pipeline network scheduling optimization.

[0094] If local numerical instability indicators are detected I unstable Exceeding the threshold I threshold， The system is considered to be in an unstable state and automatically switches to an implicit format (such as the Crank-Nicolson format) to improve numerical stability:

[0095]

[0096] in, Indicates the pressure change; Indicates the change in speed; Indicates the temperature change; Indicates j The change in the concentration of the gas component; represents the maximum value among all gas components; the function of this formula is to comprehensively consider the changes in pressure, velocity, temperature and concentration of each gas component, and evaluate the instability of the system through their relative changes. Selecting the maximum value among these changes as the instability indicator can capture the most significant unstable factors in the system. When this indicator exceeds the preset threshold, it indicates that the system may require special processing or additional computing resources to maintain numerical stability.

[0097] It should be noted that the threshold I threshold It is a key parameter for judging the stability of numerical calculations and is used to automatically switch the numerical format during the calculation process. The setting of this threshold needs to take into account typical transient processes in the natural gas pipeline network, such as pressure fluctuations caused by rapid valve adjustment, compressor start and stop operations, etc. According to the characteristic line finite volume method of the present invention, the value range can be 0.25~0.28. Larger I threshold A large value (such as 0.27) is suitable for trunk networks with relatively gentle changes in operating parameters, while a smaller value (such as 0.25) is suitable for branch networks with large parameter fluctuations. This setting can reduce unnecessary format switching and improve calculation efficiency while ensuring calculation stability.

[0098] The simulation results output by the simulation calculation module include the following:

[0099] Pipeline network flow field parameters: pressure distribution, flow velocity distribution, temperature distribution;

[0100] Gas composition: concentration distribution of each component;

[0101] Pipeline network performance indicators: gas transmission volume, pressure loss, energy consumption;

[0102] Time series data: changes in the above parameters over time;

[0103] Key node information: operating status of key equipment such as compressor stations, pressure regulating stations, valves, etc.

[0104] Warning of abnormal situations: potential leakage points, hydrate formation risk areas, overpressure or underpressure areas.

[0105] These simulation results are presented in the form of numerical data, charts, and dynamic visualization, providing reliable data support for subsequent solution generation and decision-making. By accurately simulating the flow and transmission process of natural gas in the pipeline network, the simulation results not only reflect the current state of the pipeline network, but also predict the operation trend in the future, providing an important basis for optimizing the dispatching and safe operation of the pipeline network.

[0106] The solution generation unit calculates the control instruction set based on the simulation results in the simulation modeling unit using an optimization algorithm, and combines the control instruction set into a natural gas operation management and control solution.

[0107] Furthermore, the solution generation unit includes an instruction calculation module, a solution combination module and an optimization analysis module.

[0108] The instruction calculation module builds a multi-objective optimization model based on the simulation results, and calculates the pressure control instructions, flow control instructions and temperature control instructions according to the physical characteristics of the unstructured grid. The physical characteristics include the pressure gradient, velocity gradient, temperature gradient and gas component concentration gradient within the grid unit, as well as the pressure difference, flow distribution and temperature distribution between grid units; the control instruction set includes pressure control instructions for pressure gradient and pressure difference, flow control instructions for velocity gradient and flow distribution, and temperature control instructions for temperature gradient and temperature distribution.

[0109] The process of the instruction calculation module calculating the control instruction set based on physical characteristics includes the following:

[0110] First, the control reference value is calculated: the corresponding change trends of the pressure gradient, velocity gradient, temperature gradient and gas component concentration gradient within the grid unit are calculated respectively; the equilibrium equation group is established for the pressure difference, flow distribution and temperature distribution between the grid units respectively; according to the joint solution results of the change trend and the equilibrium equation group, the pressure control reference value, flow control reference value and temperature control reference value are obtained.

[0111] Specifically, the calculation process of the change trend includes: projecting the pressure gradient onto the main flow direction of the pipeline network to obtain the main direction of pressure change, projecting the velocity gradient onto the cross section to obtain the velocity distribution characteristics, and decomposing the temperature gradient and the gas component concentration gradient in three-dimensional space to obtain the isotropic transfer characteristics; the establishment process of the equilibrium equation group includes: constructing the node pressure balance equation based on the pressure difference, constructing the branch flow conservation equation based on the flow distribution, and constructing the energy transfer equation based on the temperature distribution; the simultaneous solution adopts a step-by-step iterative method to solve each equation in turn to obtain the corresponding control reference value.

[0112] Then, the instruction calculation module constructs an objective function including energy consumption minimization and air supply stability maximization, and performs optimization calculation with the control reference value as the initial value. The objective function consists of energy consumption sub-objectives and air supply stability sub-objectives, where the energy consumption sub-objective includes the weighted sum of compressor energy consumption, pressure regulating equipment energy consumption and heating equipment energy consumption, and the air supply stability sub-objective includes the weighted sum of the flow fluctuation amplitude, pressure fluctuation amplitude and temperature fluctuation amplitude of each grid unit; the instruction calculation module minimizes the energy consumption sub-objective while maximizing the air supply stability sub-objective through optimization calculation, and generates the optimization result as a control instruction set.

[0113] The solution combination module combines pressure control instructions, flow control instructions and temperature control instructions into a natural gas operation management and control solution.

[0114] Specifically, the scheme combination module constructs a control association matrix to determine the execution association relationship between pressure control instructions, flow control instructions, and temperature control instructions. The execution association relationship includes the spatial distance, execution time interval, and mutual influence degree of the control instructions; the scheme combination module combines the control instructions with high correlation into a control instruction group according to the control association matrix, and arranges them in execution sequence to form a natural gas operation control plan.

[0115] The optimization analysis module conducts feasibility assessment on natural gas operation and control solutions, including safety, economy and stability.

[0116] Specifically, the optimization analysis module constructs an evaluation index system that includes safety constraints, economic constraints and stability constraints; among them, safety constraints include pipeline pressure limits and equipment operating parameter limits, economic constraints include energy consumption indicators and gas transmission costs, and stability constraints include pressure fluctuation amplitude, flow rate change rate and temperature change rate; when each indicator in the evaluation index system does not exceed their respective change limits, the natural gas operation and control plan is judged to be feasible; if any indicator exceeds its change limit, it returns to the instruction calculation module to recalculate the control instruction set.

[0117] Preferably, the solution generation unit of the present invention realizes the intelligent generation of the natural gas pipeline network operation and control plan through the coordinated cooperation of the instruction calculation module, the solution combination module and the optimization analysis module. Among them, the instruction calculation module innovatively combines physical feature analysis with target optimization. First, the control reference value is calculated based on the physical characteristics of the unstructured grid to ensure the physical feasibility of the control instruction. Then, the reference value is adjusted through multi-objective optimization of energy consumption and gas supply stability, which improves the operation efficiency while ensuring the control accuracy; the solution combination module effectively solves the problem of coordinated execution between different types of control instructions by constructing a control association matrix, avoiding the problem that control instructions may interfere with each other or conflict in execution in traditional methods; the optimization analysis module establishes a multi-dimensional evaluation system including safety, economy and stability, and sets a feedback adjustment mechanism, which significantly improves the reliability of the operation and control plan. Overall, the solution generation unit of the present invention realizes the transformation of the natural gas pipeline network operation and control from passive response to active optimization through the organic combination of physical constraints and optimization goals. Compared with the single control strategy or simple optimization method in the prior art, it has higher control accuracy and operation efficiency.

[0118] The pipeline network control unit receives the natural gas operation and control plan issued by the cloud server, adjusts the valve opening, detects the physical quantity deviation value during the adjustment process, and feeds the physical quantity deviation value back to the cloud server to update the natural gas operation and control plan.

[0119] Furthermore, the pipe network control unit includes a local control module, an instruction execution module, a deviation detection module, and a feedback processing module.

[0120] The local control module receives and parses the natural gas operation control plan, and decomposes the natural gas operation control plan into corresponding pressure control instructions, flow control instructions and temperature control instructions.

[0121] Specifically, the local control module parses the control instruction group according to the execution sequence, and determines the execution priority of each control instruction according to the control association matrix; the local control module performs execution planning for the pressure control instructions, flow control instructions and temperature control instructions in the control instruction group based on the execution priority.

[0122] The instruction execution module converts the pressure control instruction, flow control instruction and temperature control instruction into the opening adjustment instruction of the corresponding valve according to the type of control instruction and the execution plan.

[0123] Specifically, the instruction execution module establishes a mapping relationship between the pressure control instruction and the pressure regulating valve opening, the flow control instruction and the flow control valve opening, and the temperature control instruction and the temperature control valve opening; generates the opening adjustment instruction of each valve according to the mapping relationship, and executes the opening adjustment instruction according to the execution plan.

[0124] The deviation detection module collects physical quantity deviation values ​​during the valve adjustment process. The physical quantity deviation values ​​include pressure deviation values, flow deviation values ​​and temperature deviation values.

[0125] Specifically, the deviation detection module collects the pressure, flow and temperature data before and after executing the opening adjustment instruction, and calculates the pressure deviation value, flow deviation value and temperature deviation value; the deviation detection module also monitors the changing trend of the physical quantity deviation value. When the changing trend of the physical quantity deviation value exceeds the preset range, a warning signal is sent to the feedback processing module.

[0126] The feedback processing module packages the physical quantity deviation value and the warning signal, and feeds back the packaged data to the cloud server.

[0127] Specifically, the feedback processing module associates the physical quantity deviation value with the corresponding control instruction group, and generates a feedback data packet containing the execution time, execution location, control instruction type, deviation value and warning information; the cloud server updates the natural gas operation management and control plan based on the information in the feedback data packet.

[0128] In summary, the present invention realizes intelligent management and control of the entire process from data collection, simulation modeling to solution generation and execution. First, the collection accuracy and comprehensiveness of pipeline network operation data are significantly improved, and real-time monitoring of gas components is realized; secondly, by constructing a high-precision virtual simulation model, the prediction accuracy of the pipeline network operation status is greatly improved; thirdly, based on the optimization algorithm, the automatic generation and dynamic optimization of the pipeline network operation plan are realized; finally, by establishing a collaborative mechanism between cloud-based decision-making and local execution, the flexibility and response speed of pipeline network control are improved. The present invention improves the operational efficiency, safety and reliability of the natural gas pipeline network, and provides strong support for the sustainable development of the natural gas industry.

[0129] Example 2, reference Figure 5 , which is an embodiment of the present invention, provides a natural gas comprehensive operation and management method based on the Internet of Things, including:

[0130] S1: Collect the operating parameters of each node in the natural gas pipeline network and transmit them to the cloud server; the operating parameters include real-time data and gas composition data;

[0131] S2: Run the virtual simulation system on the cloud server, build a virtual model of the natural gas pipeline network according to the operating parameters, and perform simulation analysis to obtain simulation results;

[0132] S3: Based on the simulation results, the control instruction set is calculated using the optimization algorithm, and the control instruction set is combined into a natural gas operation control plan; the control instruction set includes pressure control instructions, flow control instructions and temperature control instructions;

[0133] S4: The cloud server sends the natural gas operation management and control plan to the local control unit of the natural gas pipeline network node to adjust the valve opening, detect the physical quantity deviation value during the adjustment process, and feed back the physical quantity deviation value to the cloud server to update the natural gas operation management and control plan.

[0134] Example 3, reference Figure 6 , is an embodiment of the present invention, which is different from the previous embodiment in that: if the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0135] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0136] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0137] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0138] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. 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 solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The natural gas comprehensive operation and management platform based on the Internet of Things is characterized by: include: Cloud servers; as well as, A data acquisition unit, used to collect the operating parameters of each node of the natural gas pipeline network and transmit the operating parameters to the cloud server; the operating parameters include natural gas pipeline network topology information and gas composition data; A simulation modeling unit, used to run a virtual simulation system on the cloud server, build a virtual model of the natural gas pipeline network according to the operating parameters, and perform simulation analysis to obtain simulation results; A scheme generating unit, which calculates a control instruction set using an optimization algorithm based on the simulation results in the simulation modeling unit, and combines the control instruction set into a natural gas operation control scheme; A pipeline network control unit, used to receive the natural gas operation control plan issued by the cloud server, adjust the valve opening, detect the physical quantity deviation value during the adjustment process, feed back the physical quantity deviation value to the cloud server, and update the natural gas operation control plan; The data acquisition unit includes a data sensing module, a data preprocessing module and a data transmission module; The data sensing module uses the Internet of Things devices deployed at each node of the natural gas pipeline network to collect the natural gas pipeline network topology information and gas component data in real time; The data preprocessing module is used to clean and format the real-time data and the gas component data; The data transmission module is used to encrypt and package the real-time data and the gas composition data, and transmit them to the cloud server; The natural gas pipeline network topology information includes the connection relationship of pipe sections, pipe diameters, valves, and compressor station location information; the gas component data includes the types and initial concentration distribution of various gas components; The simulation modeling unit includes a model construction module, a parameter configuration module and a simulation calculation module; wherein the model construction module adopts a physical feature-driven adaptive grid generation algorithm to dynamically construct an unstructured grid according to the operating parameters; the adaptive grid generation algorithm includes the following steps: generating an initial unstructured grid based on the natural gas pipeline network topological structure information; Using the gas composition data, calculate the physical characteristic index E of each grid unit c , expressed as: Among them, p, v, and T are pressure, velocity, and temperature, respectively, and c j is the concentration of the jth gas component, m is the number of gas components, and They represent the gradient norms of pressure p, velocity v and temperature T in the grid cell c respectively: represents the gradient vector of pressure p, represents the magnitude of the pressure gradient vector in grid cell c; The gradient tensor representing the velocity v, represents the norm of the velocity gradient tensor in the grid cell c; represents the gradient vector of temperature T, represents the magnitude of the temperature gradient vector in the grid cell c; p ref 、v ref 、T ref 、c j,ref is the reference value of the corresponding physical quantity, h c is the characteristic size of the grid cell c; Physical characteristic index E c Exceeding the first preset threshold R threshold The mesh cells are refined by: Define the refinement level L, with an initial value of 0; If the physical characteristic index E c >First preset threshold E threshold ,but: Where L represents the determined refinement level; L max Indicates the maximum level of refinement allowed; According to the refinement level L, the grid cells are divided into (2 L ) d subunits, where d is the spatial dimension; Perform local reconstruction on the refined mesh; Repeated calculation of physical characteristic index E c , to locally reconstruct the refined mesh until one of the following conditions is met: Physical characteristic index E of all grid cells c Less than the target threshold E target ; Reach the maximum number of iterations N max ; During the grid generation and calculation process, based on the gas component data, the concentration change rate of each gas component j in each grid unit is continuously monitored. Then the local grid reconstruction of the unit is triggered; among them, is the concentration change rate of gas component j, δc j,threshold is the concentration change rate threshold of gas component j; if local grid reconstruction is triggered, the physical characteristic index E is recalculated for the corresponding area c , to locally reconstruct the refined grid and update the grid structure; The parameter configuration module adopts the data assimilation method constrained by the physical model, combines the real-time data and historical data collected by the Internet of Things devices, and dynamically updates the boundary conditions and calculation parameters; the data assimilation method includes: Construct physical constraint models based on conservation of mass, momentum, and energy; Using the ensemble Kalman filter algorithm to fuse observation data and physical model predictions; Based on the assimilation results, dynamically adjust the time-varying boundary conditions of pressure, flow, temperature and gas composition; If the deviation between the assimilation result and the physical constraint exceeds the second preset threshold ε, the weight parameters in the data assimilation process are adjusted and the data assimilation iteration is re-executed: Among them, X 同化 Indicates the result obtained by data assimilation method; X 物理模型 Indicates the theoretical value calculated based on the physical model; The simulation calculation module is used to perform fluid mechanics calculations and output simulation results; the simulation calculation module uses an improved characteristic line finite volume method to solve the Navier-Stokes equations considering multi-component transmission, specifically: Track the motion of fluid particles along characteristic lines to capture wave propagation characteristics; In the feature line framework, a high-order TVD format is used for spatial discretization; Introducing the component-based real gas state equation and transport coefficient model to describe the thermodynamic and transport properties of gas mixtures; Use an adaptive time step control algorithm based on the characteristic time scale: Where CFL is the Courant number; v c is the flow rate; c s is the speed of sound; h c is the kinematic viscosity; α c is the thermal diffusion coefficient; If a local numerical instability indicator I is detected unstable Exceeding the threshold I threshold , the system is considered to be in an unstable state and automatically switches to the implicit format: Among them, Δp represents the pressure change; Δv represents the velocity change; ΔT represents the temperature change; Δc j Indicates the change in the concentration of the jth gas component; max j It indicates the maximum value among all gas components.

2. The natural gas comprehensive operation and management platform based on the Internet of Things according to claim 1, characterized in that: The solution generation unit includes an instruction calculation module, a solution combination module and an optimization analysis module; The instruction calculation module constructs a multi-objective optimization model based on the simulation results, and calculates the pressure control instruction, the flow control instruction and the temperature control instruction according to the physical characteristics of the unstructured grid, specifically: Calculate the corresponding change trends of the pressure gradient, velocity gradient, temperature gradient and gas component concentration gradient within the grid unit; The equilibrium equations are established for the pressure difference, flow distribution and temperature distribution among the grid cells; According to the change trend and the simultaneous solution results of the equilibrium equation group, the pressure control reference value, flow control reference value and temperature control reference value are obtained; Construct an objective function including minimizing energy consumption and maximizing air supply stability, and perform optimization calculation with the control reference value as the initial value; wherein the objective function is composed of an energy consumption sub-objective and an air supply stability sub-objective; the energy consumption sub-objective includes the weighted sum of compressor energy consumption, pressure regulating equipment energy consumption and heating equipment energy consumption; the air supply stability sub-objective includes the weighted sum of the flow fluctuation amplitude, pressure fluctuation amplitude and temperature fluctuation amplitude of each grid unit; The instruction calculation module minimizes the energy consumption sub-objective and maximizes the gas supply stability sub-objective through optimization calculation, and generates the optimization result as the control instruction set.

3. The natural gas comprehensive operation and management platform based on the Internet of Things as claimed in claim 2, characterized in that: The scheme combination module combines the control instruction set into a natural gas operation control scheme, and the scheme combination includes the time sequence arrangement and spatial organization of the control instructions; The scheme combination module constructs a control association matrix to determine the execution association relationship between the pressure control instruction, the flow control instruction and the temperature control instruction; The scheme combination module combines the control instructions with high correlation into a control instruction group according to the control correlation matrix, and arranges them in execution sequence to form the natural gas operation and control scheme; wherein the execution correlation relationship includes the spatial distance, execution time interval and mutual influence degree of the control instructions; The optimization analysis module conducts a feasibility assessment on the natural gas operation and control plan, and constructs an evaluation index system including safety constraints, economic constraints and stability constraints; wherein the safety constraints include pipeline pressure limits and equipment operation parameter limits, the economic constraints include energy consumption indicators and gas transmission costs, and the stability constraints include pressure fluctuation amplitude, flow rate change rate and temperature change rate; When all indicators in the evaluation indicator system do not exceed their respective change limits, the natural gas operation and control plan is determined to be feasible; if any indicator exceeds its change limit, the instruction calculation module is returned to recalculate the control instruction set.

4. The natural gas comprehensive operation and management platform based on the Internet of Things as claimed in claim 3, characterized in that: The pipe network control unit includes a local control module, an instruction execution module, a deviation detection module, and a feedback processing module; The local control module is used to receive and parse the natural gas operation and control plan, the instruction execution module is used to convert the natural gas operation and control plan into a valve opening adjustment instruction, the deviation detection module is used to collect the physical quantity deviation value during the valve adjustment process, and the feedback processing module is used to package the physical quantity deviation value and feed it back to the cloud server.

5. A natural gas comprehensive operation and control method based on the Internet of Things, based on the natural gas comprehensive operation and control platform based on the Internet of Things according to any one of claims 1 to 4, characterized in that: include, Collecting the operating parameters of each node of the natural gas pipeline network and transmitting the operating parameters to the cloud server; Running a virtual simulation system on the cloud server, constructing a virtual model of the natural gas pipeline network according to the operating parameters, and performing simulation analysis to obtain simulation results; Based on the simulation results, a control instruction set is calculated using an optimization algorithm, and the control instruction set is combined into a natural gas operation control plan; The cloud server sends the natural gas operation management and control plan to the local control unit of the natural gas pipeline network node, adjusts the valve opening, detects the physical quantity deviation value during the adjustment process, and feeds back the physical quantity deviation value to the cloud server to update the natural gas operation management and control plan.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the natural gas comprehensive operation and control platform based on the Internet of Things described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the natural gas integrated operation and control platform based on the Internet of Things described in any one of claims 1 to 4 are implemented.

Images