Method, system, device and medium for municipal heating network working condition twin modeling

Abstract

The application provides a municipal heat supply pipe network working condition twin modeling method, system, device and medium, constructs a pipe network twin model; determines the boundary constraint quantity of the position of each monitoring node under the variable working condition condition according to the correlation coefficient matrix of the working condition response characteristics between the monitoring nodes and the pipe network structure parameters of each monitoring node; extracts the coupling response characteristics of temperature-pressure-flow of each monitoring node under the variable working condition condition in the pipe network twin model, and then determines the coupling response loss of the twin modeling simulation under the variable working condition condition; constructs an error cost function of the pipe network twin simulation according to all the boundary constraint quantities and the coupling response loss, optimizes the model parameters of the pipe network twin model in combination with the error cost function, obtains the optimal model parameters suitable for the variable working condition condition, and updates the simulation control parameters of the pipe network twin model based on the optimal model parameters. With the scheme of the application, the cost optimization of the simulation parameters in the twin modeling of the municipal heat supply pipe network under the variable working condition condition can be realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of twin modeling, more specifically, the present application relates to a municipal heat supply pipe network working condition twin modeling method, system, device and medium. BACKGROUND

[0002] With the continuous improvement of the intelligent level of urban infrastructure, as a key system to ensure the stable supply of urban energy, municipal heat supply pipe networks gradually develop towards digitization and intelligentization. Twin modeling technology, by constructing a digital model reflecting the running state of a physical system, realizes real-time perception and prediction simulation of the running state of the pipe network, and has important significance in improving the running efficiency of the pipe network, optimizing the dispatching strategy and preventing fault risks, and has become an important technical path for intelligent management and control of heat supply systems.

[0003] The existing municipal heat supply pipe network twin modeling method has the problem that the model simulation response cannot effectively match the actual running state when dealing with variable working conditions. The main reason is that the modeling parameters are difficult to accurately control under variable working conditions, and cannot dynamically reflect the coupling response relationship between temperature, pressure, flow and other physical quantities in the heat supply system. Especially when the pipe network appears heat exchange station regulation, hydraulic imbalance or heat load fluctuation, traditional modeling methods usually rely on static boundary setting or empirical parameter correction, resulting in significant simulation error, which is difficult to use for control strategy decision or abnormal diagnosis analysis. Therefore, how to realize the cost optimization of simulation parameters in the twin modeling of municipal heat supply pipe networks under variable working conditions has become a difficult problem in the industry. SUMMARY

[0004] The present application provides a municipal heat supply pipe network working condition twin modeling method, system, device and medium, which can realize the cost optimization of simulation parameters in the twin modeling of municipal heat supply pipe networks under variable working conditions.

[0005] In a first aspect, the present application provides a municipal heat supply pipe network working condition twin modeling method, comprising the following steps:

[0006] Setting a monitoring node at a key node in the municipal heat supply pipe network, and constructing a temperature-pressure-flow multi-physical field coupled pipe network twin model based on the topological structure parameters and working condition parameters of the monitoring node of the municipal heat supply pipe network;

[0007] When the municipal heat supply pipe network is in variable working condition, the correlation coefficient matrix of the working condition response characteristics between the monitoring nodes is determined, and then the boundary constraint quantity of the position of each monitoring node under the variable working condition is determined through the correlation coefficient matrix and the pipe network structure parameters of each monitoring node;

[0008] applying boundary loads of the variable working condition to the pipe network twin model, extracting temperature-pressure-flow coupling response characteristics of each monitoring node in the pipe network twin model under the variable working condition, and then determining a coupling response loss of the twin modeling simulation under the variable working condition through all the coupling response characteristics;

[0009] constructing an error cost function of the pipe network twin simulation according to all the boundary constraint quantities and the coupling response loss, performing parameter optimization on model characteristic parameters of the pipe network twin model in the variable working condition twin simulation in combination with the error cost function, obtaining optimal model parameters applicable to the variable working condition, and then updating simulation control parameters of the pipe network twin model based on the optimal model parameters.

[0010] Preferably, constructing the temperature-pressure-flow multi-physical field coupling pipe network twin model based on the topological structure parameters and the working condition parameters of the municipal heating pipe network specifically includes:

[0011] constructing a pipe network three-dimensional geometric model according to the topological structure parameters of the municipal heating pipe network;

[0012] extracting the temperature, pressure and flow at each monitoring node as initial boundary values of the multi-physical field coupling simulation from the working condition parameters;

[0013] spatially discretizing the pipe network three-dimensional geometric model by the finite volume method, and then constructing the temperature-pressure-flow coupling pipe network twin model in combination with a heat conduction equation, a fluid mechanics equation and an energy conservation equation.

[0014] Preferably, determining the correlation coefficient matrix of the working condition response characteristics between the monitoring nodes specifically includes:

[0015] for each monitoring node, extracting a temperature response feature, a pressure response feature and a flow response feature from a temperature response curve, a pressure response curve and a flow response curve of the monitoring node respectively;

[0016] determining a characteristic response vector of the monitoring node according to the temperature response feature, the pressure response feature and the flow response feature, and then obtaining the characteristic response vector of each monitoring node;

[0017] determining a correlation coefficient of the characteristic response vectors between each two monitoring nodes;

[0018] determining the correlation coefficient matrix of the working condition response characteristics between the monitoring nodes through all the correlation coefficients.

[0019] Preferably, determining the boundary constraint quantities of the monitoring node positions under the variable working condition through the correlation coefficient matrix and the pipe network structure parameters of each monitoring node specifically includes:

[0020] Determine the pipe heat conduction coefficient and flow resistance coefficient of each monitoring node according to the pipe material attribute and pipe diameter size in the pipe network structure parameter;

[0021] Construct the thermal-hydraulic balance constraint equation group between the monitoring nodes by combining the pipe heat conduction coefficient and flow resistance coefficient of each monitoring node with the correlation coefficient matrix;

[0022] Solve the thermal-hydraulic balance constraint equation group by the least square method to obtain the boundary constraint quantity of each monitoring node position under the variable working condition.

[0023] Preferably, the temperature-pressure-flow coupling response characteristics of each monitoring node in the pipe network twin model under the variable working condition specifically include:

[0024] Select one monitoring node as a selected monitoring node, and collect the simulation data of the temperature field, pressure field and flow field at the selected monitoring node;

[0025] Extract the temperature fluctuation characteristics, pressure gradient characteristics and flow pulsation characteristics from the simulation data, and then integrate to obtain the temperature-pressure-flow coupling response characteristics of the selected monitoring node under the variable working condition;

[0026] Repeat the above steps to obtain the temperature-pressure-flow coupling response characteristics of the remaining monitoring nodes under the variable working condition.

[0027] Preferably, the coupling response loss of the twin modeling simulation under the variable working condition is determined by all the coupling response characteristics, and specifically includes:

[0028] Obtain the measured response characteristics of each monitoring node under the variable working condition;

[0029] Perform error analysis on the temperature-pressure-flow coupling response characteristics of each monitoring node under the variable working condition and the measured response characteristics of the corresponding monitoring node to obtain the coupling simulation error of each monitoring node;

[0030] Integrate the coupling simulation errors of all monitoring nodes to obtain the coupling response loss of the twin modeling simulation under the variable working condition.

[0031] Preferably, the error cost function of the pipe network twin simulation is constructed according to all the boundary constraint quantities and the coupling response loss, and specifically includes:

[0032] Compare the boundary constraint quantity of each monitoring node position with the corresponding measured boundary quantity to obtain the boundary constraint error term;

[0033] Take the coupling response loss as a simulation error term of multi-physical field coupling;

[0034] The error cost function of the pipe network twin simulation is obtained by integrating the boundary constraint error term and the simulation error term through a linear weighting formula.

[0035] In a second aspect, the present application provides a municipal heat supply pipe network working condition twin modeling system, comprising:

[0036] A modeling module is configured to set monitoring nodes at key nodes in the municipal heat supply pipe network, and construct a temperature-pressure-flow multi-physical field coupled pipe network twin model based on topological structure parameters and working condition parameters of the monitoring nodes.

[0037] A processing module is configured to determine a correlation coefficient matrix of working condition response characteristics between the monitoring nodes when the municipal heat supply pipe network is in a variable working condition, and then determine boundary constraint quantities at positions of the monitoring nodes under the variable working condition through the correlation coefficient matrix and pipe network structure parameters of the monitoring nodes.

[0038] The processing module is further configured to apply boundary loads of the variable working condition to the pipe network twin model, extract temperature-pressure-flow coupled response characteristics of the monitoring nodes under the variable working condition in the pipe network twin model, and then determine a coupled response loss of the twin modeling simulation under the variable working condition through all the coupled response characteristics.

[0039] A parameter updating module is configured to construct an error cost function of the pipe network twin simulation according to all the boundary constraint quantities and the coupled response loss, perform parameter optimization on model characteristic parameters of the pipe network twin model in the variable working condition twin simulation in combination with the error cost function, obtain optimal model parameters applicable to the variable working condition, and then update simulation control parameters of the pipe network twin model based on the optimal model parameters.

[0040] In a third aspect, the present application provides a computer device, comprising a memory and a processor, the memory stores a code, and the processor is configured to acquire the code and perform the municipal heat supply pipe network working condition twin modeling method.

[0041] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the municipal heat supply pipe network working condition twin modeling method.

[0042] The technical scheme provided by the embodiments of the present application has the following beneficial effects:

[0043] In the embodiments of the present application, a monitoring node is arranged at a key node in a municipal heat supply pipe network, a temperature-pressure-flow multi-physical field coupled pipe network twin model is constructed based on topological structure parameters and working condition parameters of the monitoring node of the municipal heat supply pipe network; when the municipal heat supply pipe network is in a variable working condition operation, a correlation coefficient matrix of working condition response characteristics between the monitoring nodes is determined, and then the boundary constraint quantity of the position of each monitoring node under the variable working condition is determined through the correlation coefficient matrix and the pipe network structure parameters of each monitoring node; the boundary load of the variable working condition is applied in the pipe network twin model, the coupling response characteristics of temperature-pressure-flow of each monitoring node in the pipe network twin model under the variable working condition are extracted, and then the coupling response loss of the twin modeling simulation under the variable working condition is determined through all the coupling response characteristics; an error cost function of the pipe network twin simulation is constructed according to all the boundary constraint quantities and the coupling response loss, the model characteristic parameters of the pipe network twin model in the variable working condition twin simulation are optimized in combination with the error cost function, the optimal model parameters suitable for the variable working condition are obtained, and then the simulation control parameters of the pipe network twin model are updated based on the optimal model parameters.

[0044] Therefore, this application constructs an error cost function for pipeline twin simulation based on all boundary constraints and the coupling response loss. Combining this error cost function, it optimizes the model characteristic parameters of the pipeline twin model in variable operating condition twin simulation to obtain the optimal model parameters suitable for variable operating conditions. First, by integrating the pipeline topology and monitoring node operating parameters, a multiphysics twin model capable of simultaneously describing the coupling relationship between temperature, pressure, and flow is constructed. This not only ensures the accuracy of the model structure but also enhances its responsiveness to dynamic operating states. Second, by constructing a correlation coefficient matrix based on response curves, the coupling strength between monitoring nodes under multiphysics responses of temperature, pressure, and flow is quantified. Combined with the pipeline structure parameters corresponding to the nodes, the dynamic derivation of boundary constraints under variable operating conditions is realized. This application's method breaks through the traditional reliance on static boundary settings. By overcoming certain limitations, this approach adaptively reflects the transmission and influence mechanism of operating condition disturbances on the local node state, thus providing more physically consistent and timely boundary conditions for subsequent simulation loading, improving the response accuracy and structural matching capability of the twin model under unsteady-state operation. Furthermore, by introducing dynamic boundary loads and extracting coupled response features into the twin model, the nonlinear correlation of physical variables in the thermal system can be comprehensively reflected, effectively supporting the quantitative assessment of coupled response losses. Finally, by constructing an error cost function centered on boundary constraints and coupled response losses, simulation deviations are systematically measured, and parameter optimization is performed based on this, solving the problem of the lack of adaptability in traditional parameter setting methods. Ultimately, the simulation control quantities are updated through optimal model parameters, achieving high-fidelity reproduction of the real behavior of the heating system under varying operating conditions, providing more accurate data support for actual control strategies. In summary, this application's solution can achieve cost optimization of simulation parameters in twin modeling of municipal heating networks under varying operating conditions, thereby improving the modeling accuracy of the network twin model under varying operating conditions. Attached Figure Description

[0045] Figure 1 This is an exemplary flowchart of a twin modeling method for municipal heating network operating conditions, as shown in some embodiments of this application.

[0046] Figure 2 This is a flowchart illustrating the process of determining the correlation coefficient matrix according to some embodiments of this application;

[0047] Figure 3 This is a schematic flowchart illustrating the determination of coupling response loss according to some embodiments of this application;

[0048] Figure 4 This is a schematic diagram of the structure of a municipal heating network operating condition twin modeling system according to some embodiments of this application;

[0049] Figure 5is a structural schematic diagram of a computer device for implementing a municipal heat supply pipeline working condition twin modeling method according to some embodiments of the present application. DETAILED DESCRIPTION

[0050] In order to better understand the technical solutions of the present application, the technical solutions of the present application will be described in detail below in combination with the drawings of the specification and specific embodiments.

[0051] Reference Figure 1 The figure is an exemplary flowchart of a municipal heat supply pipeline working condition twin modeling method according to some embodiments of the present application, which mainly includes the following steps:

[0052] In step 101, monitoring nodes are set at key nodes in the municipal heat supply pipeline, and a temperature-pressure-flow multi-physical field coupled pipeline twin model is constructed based on the topological structure parameters of the municipal heat supply pipeline and the working condition parameters of the monitoring nodes.

[0053] It should be noted that the key nodes in the present application refer to pipeline function nodes in the municipal heat supply pipeline that have a significant impact on the heat transmission and distribution process, specifically including heat exchange station nodes, main pipe branch nodes and hydraulic control valve nodes.

[0054] In some embodiments, the temperature-pressure-flow multi-physical field coupled pipeline twin model can be constructed based on the topological structure parameters of the municipal heat supply pipeline and the working condition parameters of the monitoring nodes in the following manner:

[0055] A pipeline three-dimensional geometric model is constructed according to the topological structure parameters of the municipal heat supply pipeline;

[0056] The temperature, pressure and flow at each monitoring node are extracted from the working condition parameters as initial boundary values for multi-physical field coupled simulation;

[0057] The pipeline three-dimensional geometric model is spatially discretized by the finite volume method, and then a temperature-pressure-flow coupled pipeline twin model is constructed in combination with the heat conduction equation, the fluid mechanics equation and the energy conservation equation.

[0058] It should be noted that the initial boundary values in the present application refer to the starting parameters and boundary conditions used to constrain the physical state of the model at the beginning of numerical simulation, including the temperature, pressure and flow of each node at the initial time; the pipeline twin model in the present application refers to a multi-physical field simulation model that can synchronously reflect the temperature, pressure and flow variation characteristics based on the heat supply pipeline structure and operation data.

[0059] In specific implementation, the construction of a three-dimensional geometric model of the municipal heating network based on its topological parameters can be achieved in the following way: Based on the topological diagram of the municipal heating network, a complete three-dimensional geometric model can be constructed using computer-aided design (CAD) software, according to the pipe segment connection relationships, pipe diameters, and node locations. Extracting the temperature, pressure, and flow rate at each monitoring node from the operating parameters as the initial boundary values ​​for multiphysics coupling simulation can be achieved in the following way: Temperature, pressure, and flow rate data from each monitoring node are collected, and then the collected temperature, pressure, and flow rate data are input into the simulation model as initial operating conditions and boundary conditions, where temperature serves as the thermal boundary condition, pressure as the hydraulic boundary condition, and flow rate as the mass constraint condition. The three-dimensional geometric model of the network is spatially discretized using the finite volume method, and then a temperature-pressure-flow rate coupled network twin is constructed by combining the heat conduction equation, fluid dynamics equation, and energy conservation equation. The twin model can be implemented in the following way: the three-dimensional geometric model of the pipeline network can be discretized using the finite volume method, and the continuous fluid region can be divided into multiple control volumes. The heat conduction equation, mass conservation equation, and momentum conservation equation can be established by the control volume components. The heat conduction equation can be established based on Fourier's law, and the mass conservation equation can be established based on the continuity equation. The momentum conservation equation can adopt the Navier-Stokes equation. Finally, the above physical control equation set is input into the twin simulation platform, and the coupled solution process is set. The dynamic response relationship of temperature-pressure-flow between different monitoring nodes is solved by time stepping, and the constructed simulation model is used as the twin model of the pipeline network.

[0060] In step 102, when the municipal heating network is operating under variable conditions, the correlation coefficient matrix of the operating condition response characteristics between each monitoring node is determined, and then the boundary constraint quantity of the location of each monitoring node under variable operating conditions is determined by the correlation coefficient matrix and the network structure parameters of each monitoring node.

[0061] It should be noted that the variable operating condition in this application refers to the non-steady-state operating state in which the temperature, pressure and flow parameters of the heating network change over time during the heat load switching or adjustment process.

[0062] In some embodiments, reference Figure 2 As shown in the figure, this is a flowchart illustrating the process of determining the correlation coefficient matrix in some embodiments of this application. In this embodiment, the determination of the correlation coefficient matrix of the operating condition response characteristics between each monitoring node can be achieved by the following steps:

[0063] In step 1021, for each monitoring node, temperature response features, pressure response features, and flow response features are extracted from the temperature response curve, pressure response curve, and flow response curve of the monitoring node, respectively.

[0064] In step 1022, a characteristic response vector of the monitoring node is determined according to the temperature response characteristic, the pressure response characteristic and the flow response characteristic, and then a characteristic response vector of each monitoring node is obtained;

[0065] In step 1023, a correlation coefficient of the characteristic response vectors between each two monitoring nodes is determined.

[0066] In step 1024, a correlation coefficient matrix of the working condition response characteristics between the monitoring nodes is determined through all the correlation coefficients.

[0067] It should be noted that the correlation coefficient in the present application is an index for measuring the degree of synchronization of the response characteristic changes of two monitoring nodes under variable working conditions; and the correlation coefficient matrix in the present application refers to a symmetric matrix for quantifying the correlation degree of the response characteristics between all monitoring nodes under variable working conditions.

[0068] When specifically implemented, the temperature response characteristic, the pressure response characteristic and the flow response characteristic can be extracted from the temperature response curve, the pressure response curve and the flow response curve respectively by using the following manner, i.e., the fluctuation rate extracted from the temperature response curve can be taken as the temperature response characteristic, the fluctuation amplitude extracted from the pressure response curve can be taken as the pressure response characteristic, and the fluctuation rate extracted from the flow response curve can be taken as the flow response characteristic; the characteristic response vector of the monitoring node can be determined according to the temperature response characteristic, the pressure response characteristic and the flow response characteristic by using the following manner, i.e., the vector composed of the temperature response characteristic, the pressure response characteristic and the flow response characteristic can be taken as the characteristic response vector of the monitoring node; the correlation coefficient of the characteristic response vectors between each two monitoring nodes can be determined by using the following manner, i.e., the Euclidean distance of the characteristic response vectors between each two monitoring nodes can be taken as the correlation coefficient; the correlation coefficient matrix of the working condition response characteristics between the monitoring nodes can be determined through all the correlation coefficients by using the following manner, i.e., the correlation coefficients between all node pairs are summarized, a symmetric correlation matrix is constructed according to the node numbers, and the constructed correlation matrix is taken as the correlation coefficient matrix for describing the coupling correlation degree of the response characteristics between the nodes of the entire heating pipe network under variable working conditions.

[0069] In some embodiments, the boundary constraint quantity of the position of each monitoring node under the variable working condition can be determined by using the following steps through the correlation coefficient matrix and the pipe network structure parameters of each monitoring node:

[0070] The pipe heat conduction coefficient and the flow resistance coefficient of each monitoring node are determined according to the pipe material properties and the pipe diameter size in the pipe network structure parameters;

[0071] The thermal-hydraulic balance constraint equation set between the monitoring nodes is constructed by combining the pipe thermal conductivity coefficient and the flow resistance coefficient of each monitoring node through the correlation coefficient matrix;

[0072] The thermal-hydraulic balance constraint equation set is solved by the least square method to obtain the boundary constraint quantity of the position of each monitoring node under the variable working condition.

[0073] It should be noted that the pipe material properties in the present application specifically include thermal conductivity, specific heat capacity, inner wall roughness, elastic modulus and Poisson's ratio; the pipe thermal conductivity coefficient in the present application refers to the heat conducted through the pipe material per unit time under unit temperature difference and unit length, reflecting the heat conduction capacity; the flow resistance coefficient in the present application refers to the resistance loss degree caused by friction and local structure change when the fluid flows in the pipe, used to characterize the resistance size of the fluid flow in the unit length pipe; the thermal-hydraulic balance constraint equation set in the present application refers to the combined balance condition meeting the heat conduction and fluid flow law, used to constrain the coupling relationship between the heat energy transfer and the flow resistance between the monitoring nodes; the boundary constraint quantity in the present application refers to the constraint parameter used to limit the state variable (including temperature, pressure, flow) at the model boundary in the twin modeling.

[0074] In a specific implementation, the determination of the pipe heat conduction coefficient and the flow resistance coefficient of each monitoring node according to the pipe material attribute and the pipe diameter size in the pipe network structure parameters can be implemented in the following manner: for each monitoring node, the material attribute and the pipe diameter size of the pipe at the monitoring node are obtained, and then the pipe heat conduction coefficient of the monitoring node is calculated by using the steady-state heat conduction formula in heat transfer according to the material attribute and the pipe diameter size of the pipe, thereby obtaining the pipe heat conduction coefficient of each monitoring node. It needs to be further explained that the pipe diameter sizes at different monitoring nodes are usually different, and further, the flow resistance coefficient of each monitoring node is calculated according to the Darcy-Weisbach resistance formula in fluid mechanics in combination with the pipe diameter size and the pipe roughness at the monitoring node. The construction of the thermal-hydraulic balance constraint equation set between the monitoring nodes by using the correlation coefficient matrix in combination with the pipe heat conduction coefficient and the flow resistance coefficient of each monitoring node can be implemented in the following manner: the response correlation between the monitoring nodes is quantified as the coupling strength of the monitoring nodes on the basis of the correlation coefficient matrix, the degree of mutual influence of the thermal force and the hydraulic force between the monitoring nodes is adjusted by the weight, and further, the thermal balance equation and the hydraulic balance equation are constructed in combination with the pipe heat conduction coefficient and the flow resistance coefficient of each monitoring node. The thermal balance equation is based on the principle of energy conservation and describes the relationship between heat transfer and heat loss between the monitoring nodes, and the hydraulic balance equation reflects the dynamic balance of pressure loss and flow distribution between the monitoring nodes according to the mass conservation and energy equation. The thermal balance equation and the hydraulic balance equation are combined to form an equation set in the order of the monitoring nodes, thereby obtaining a coupling mathematical model containing multiple monitoring nodes and multiple variables, i.e., the thermal-hydraulic balance constraint equation set. In this process, the correlation coefficient matrix can adjust the coupling strength between the monitoring nodes to ensure that the equation set can accurately reflect the thermal-hydraulic interaction under actual variable working conditions. The determination of the boundary constraint quantity of each monitoring node position under variable working conditions by solving the thermal-hydraulic balance constraint equation set by using the least square method can be implemented in the following manner: in the MATLAB software, the thermal-hydraulic balance constraint equation set is solved by using the least square method through iterative optimization, and the conditional solution set obtained by the solving is taken as the boundary constraint quantity of each monitoring node position under variable working conditions in the present application. It needs to be further explained that in MATLAB, the least square method takes the residual sum of squares of the thermal-hydraulic balance constraint equation set as the optimization target by constructing an objective function, and the error between the model prediction value and the actual observation value is minimized by continuously adjusting the unknown variables through an iterative algorithm. This process takes numerical optimization as the core, uses the Jacobian matrix to describe the sensitivity of the function to the variable, and ensures the convergence and stability of the solving process. Finally, a set of variable solutions that satisfy the constraint conditions and have the minimum error are obtained, i.e., the boundary constraint quantity of each monitoring node under variable working conditions.

[0075] It should be noted that the scheme in the present application introduces the pipe heat transfer coefficient and flow resistance coefficient in the pipe network structure parameter, combines the correlation coefficient matrix between the monitoring nodes, and constructs a balance constraint equation set fully reflecting the coupling relationship between heat and water force, thereby overcoming the problems of lack of correlation between nodes and inaccurate boundary conditions in the existing multi-physical field coupling analysis, and further solving the equation set by using the least square method to realize the accurate inversion of the boundary constraint quantity under the variable working condition, effectively improving the physical authenticity of the boundary condition and the response accuracy of the model, avoiding the error accumulation caused by traditional experience estimation or single physical field analysis, and enhancing the adaptability and prediction accuracy of the twin model to complex dynamic working conditions.

[0076] In step 103, the boundary load of the variable working condition is applied in the pipe network twin model, the temperature-pressure-flow coupling response characteristics of each monitoring node in the pipe network twin model under the variable working condition are extracted, and then the coupling response loss of the twin modeling simulation under the variable working condition is determined through all the coupling response characteristics.

[0077] It should be noted that the application of the boundary load of the variable working condition in the pipe network twin model in the present application refers to applying the temperature, pressure and flow boundary constraint quantity of each monitoring node under the variable working condition as an input condition to the boundary position of the simulation model.

[0078] In some embodiments, the extraction of the temperature-pressure-flow coupling response characteristics of each monitoring node in the pipe network twin model under the variable working condition can be realized by the following steps:

[0079] Selecting one monitoring node as a selected monitoring node, collecting the simulation data of the temperature field, pressure field and flow field at the selected monitoring node;

[0080] Extracting the temperature fluctuation characteristics, pressure gradient characteristics and flow pulsation characteristics from the simulation data, and then integrating to obtain the temperature-pressure-flow coupling response characteristics of the selected monitoring node under the variable working condition;

[0081] Repeating the above steps to obtain the temperature-pressure-flow coupling response characteristics of the remaining monitoring nodes under the variable working condition.

[0082] It should be noted that the corresponding monitoring nodes in the pipe network twin model in the present application refer to virtual monitoring nodes in the pipe network twin model whose spatial positions are consistent with the monitoring nodes set in the municipal heating pipe network.

[0083] It should be noted that the coupling response characteristics in the present application are comprehensive indicators for quantifying the temperature, pressure and flow response change characteristics of the monitoring nodes under the action of multiple physical fields.

[0084] In a specific implementation, the analog data of the temperature field, the pressure field and the flow field at the selected monitoring nodes can be collected in the following manner: the simulation output data of the temperature field, the pressure field and the flow field of the monitoring nodes under the current variable working condition are called from the twin modeling simulation, and the simulation output data is three-dimensional time series information varying with time; the temperature fluctuation feature, the pressure gradient feature and the flow pulsation feature are extracted from the analog data, and the coupling response feature of the temperature-pressure-flow of the selected monitoring nodes under the variable working condition is obtained by integration in the following manner: the change rate features of the high-frequency and low-frequency components extracted from the temperature field data are taken as the temperature fluctuation feature, the gradient change feature extracted from the pressure field data is taken as the pressure gradient feature, and the fluctuation frequency of the flow field data is taken as the flow pulsation feature; then, the temperature fluctuation feature, the pressure gradient feature and the flow pulsation feature are normalized and combined to obtain a vector, and the vector is taken as the coupling response feature of the temperature-pressure-flow of the monitoring nodes under the variable working condition.

[0085] In some embodiments, the reference Figure 3 As shown in the figure, the figure is a flowchart for determining the coupling response loss in some embodiments of the present application. In the present embodiment, the coupling response loss of the twin modeling simulation under the variable working condition is determined by all coupling response features in the following steps:

[0086] In step 1031, the measured response features of the monitoring nodes under the variable working condition are obtained.

[0087] In step 1032, the coupling response features of the temperature-pressure-flow of the monitoring nodes under the variable working condition are subjected to error analysis with the measured response features of the corresponding monitoring nodes to obtain the coupling simulation errors of the monitoring nodes.

[0088] In step 1033, the coupling simulation errors of all monitoring nodes are integrated to obtain the coupling response loss of the twin modeling simulation under the variable working condition.

[0089] It should be noted that the coupling simulation error in the present application is an error between the simulation results of the monitoring nodes in the twin simulation model and the actual measurement results; the coupling response loss in the present application is a loss index for measuring the fitting accuracy of the response parameters of the pipe network twin model under the synergistic action of multiple physical fields.

[0090] In a specific implementation, the measured response characteristics of each monitoring node under the variable working condition can be obtained by the following method: collecting time series data of temperature, pressure and flow rate from the multi-physical sensors deployed at the key nodes of the pipe network, and extracting the measured coupling response characteristics with the same structure as the simulation model according to the foregoing method; the coupling simulation error of each monitoring node can be obtained by the following method: for each monitoring node, taking the Euclidean distance between the coupling response characteristics and the measured response characteristics of the monitoring node as the coupling simulation error of the monitoring node, and then obtaining the coupling simulation error of each monitoring node; the coupling response loss of the twin modeling simulation under the variable working condition can be obtained by the following method: the coupling simulation errors of all monitoring nodes are summarized according to the spatial distribution, and the matrix obtained by the summarization is used to describe the coupling response loss of the twin modeling simulation under the variable working condition.

[0091] In step 104, an error cost function of the pipe network twin simulation is constructed according to all boundary constraint quantities and the coupling response loss, and the model characteristic parameters of the pipe network twin model in the variable working condition twin simulation are optimized in combination with the error cost function, to obtain optimal model parameters suitable for the variable working condition, and then the simulation control parameters of the pipe network twin model are updated based on the optimal model parameters.

[0092] In some embodiments, the error cost function of the pipe network twin simulation can be constructed according to all boundary constraint quantities and the coupling response loss by the following steps:

[0093] The boundary constraint quantities of each monitoring node position are compared with the corresponding measured boundary quantities, and then the boundary constraint error term is obtained;

[0094] The coupling response loss is taken as the simulation error term of the multi-physical field coupling;

[0095] The boundary constraint error term and the simulation error term are integrated by a linear weighting formula to obtain the error cost function of the pipe network twin simulation.

[0096] It should be noted that the boundary constraint error term in the present application is a characteristic term reflecting the degree of agreement between the physical consistency of the twin model under boundary condition constraint and the measured boundary response; the simulation error term in the present application is a characteristic term reflecting the overall deviation degree between the response results in multi-physical field coupling and the measured coupling response; it should be further noted that the error cost function in the present application refers to a function expression for comprehensively evaluating the response fitting accuracy of the twin model to the actual working condition in the simulation process, which fuses the boundary constraint error term and the multi-physical field coupling response error term by linear weighting, reflecting the overall deviation degree of the model in boundary conditions and internal coupling behavior.

[0097] In specific implementation, the boundary constraint quantity of each monitoring node position is compared with the corresponding measured boundary quantity, and then the boundary constraint error term is obtained. The boundary constraint error term can be realized in the following manner: the boundary constraint quantity of each monitoring node is obtained under variable working condition, and is compared with the corresponding boundary physical quantity collected by the sensor in actual operation, the difference is calculated and squared to be taken as the boundary constraint error term. In the present application, L2 norm expression can be used. It should be further noted that the measured boundary quantity specifically includes actual inlet flow, outlet pressure, wall temperature and boundary heat flux and other boundary physical quantities representing the operating state of the pipe network at the monitoring node. The error cost function of the pipe network twin simulation is obtained by integrating the boundary constraint error term and the simulation error term through a linear weighting formula. The error cost function of the pipe network twin simulation can be realized in the following manner: the boundary constraint error term and the simulation error term can be weighted and fused according to the preset weight coefficients a and 1-a, and the obtained function is taken as the error cost function of the pipe network twin simulation, i.e. error cost function = a*boundary constraint error term + (1-a)*simulation error term, wherein the weight coefficient a is used to adjust the optimization bias of the model fitting accuracy to the boundary constraint and the coupling response accuracy, which can be adjusted according to historical experience data. In addition, it should be further noted that in order to suppress overfitting of model parameters or excessive complexity, a regularization term can also be introduced in the present application, for example, L2 regularization is used to limit the fluctuation amplitude or growth rate of model characteristic parameters, so as to enhance the generalization ability of the model under different variable working conditions.

[0098] In some embodiments, the model characteristic parameters of the pipe network twin model in the variable working condition twin simulation are parameter optimized in combination with the error cost function, and the optimal model parameters applicable to the variable working condition can be realized in the following steps:

[0099] The model characteristic parameters in the pipe network twin model are taken as optimization variables.

[0100] An optimization model for parameter optimization is constructed with the objective of minimizing the error cost function.

[0101] The optimization model is iteratively solved by using a particle swarm algorithm, and then the optimal model parameters applicable to the variable working condition are output.

[0102] It should be noted that the model characteristic parameters in the present application refer to a set of key parameters representing the operating behavior of the pipe network, specifically including the pipe thermal conductivity parameter, the inner wall roughness, and the fluid specific heat capacity; it should also be noted that the optimal model parameters in the present application refer to a set of key parameters of the pipe network twin model that can best fit the actual working conditions in the optimization process to minimize the error cost function.

[0103] In specific implementation, the model characteristic parameters in the pipe network twin model can be implemented as optimization variables in the following manner, i.e., the pipe thermal conductivity parameter, the inner wall roughness, and the fluid specific heat capacity in the model characteristic parameters can be uniformly represented as a variable vector to be optimized; the optimization model for parameter optimization can be implemented in the following manner, i.e., taking the error cost function as the objective function, minimizing the value of the objective function as the goal, and taking the parameter value range of the model characteristic parameters as the optimization constraint condition, to obtain an optimization model structure containing the objective function and variable constraints; the optimization model can be iteratively solved by using the particle swarm algorithm, and then the optimal model parameters applicable to the variable working condition can be implemented in the following manner, i.e., initializing a plurality of particle swarms by using the particle swarm algorithm, each particle corresponding to a set of characteristic parameter values, and searching the parameter space by guiding strategies of individual historical optimal value and group optimal value in each iteration, gradually approaching the minimum error region, and outputting the parameter group corresponding to the minimum error cost function as the final optimal model parameters applicable to the variable working condition after meeting the convergence condition.

[0104] It should be noted that the optimization model in the present application refers to a mathematical description and solving framework constructed for the model characteristic parameters with the error cost function of the pipe network twin model as the objective function, the core of which is to minimize the error between the simulation output and the actual monitoring data by adjusting the parameters, the technical principle is based on the numerical optimization theory, the error cost function is defined as the evaluation index by defining the parameter space and the constraint condition, a nonlinear and multivariate optimization problem is established, the particle swarm algorithm as a swarm intelligence optimization method simulates the information sharing and collaborative evolution among individuals in the group, and finds the global optimal solution by iteratively updating the particle position and velocity, this method relies on the individual historical optimal and group global optimal guiding search, has the advantages of strong parallelism, fast convergence speed, and good adaptability to complex non-convex functions, is suitable for solving the parameter optimization problem of the twin model under complex variable working conditions, and effectively improves the accuracy and stability of the simulation model.

[0105] It should be further noted that the simulation control parameters of the pipe network twin model updated based on the optimal model parameters in the present application refer to applying the optimal model parameters obtained through parameter optimization to the twin model to adjust the key parameters in the model for controlling the temperature, pressure and flow simulation process; in specific implementation, the optimal model parameters can be mapped to the input parameter field of the pipe network twin model, and then the updated model parameters are loaded by using the simulation software platform to reconfigure the boundary conditions and physical properties in the simulation control module, further execute the pipe network multi-physical field coupling simulation, verify whether the temperature, pressure and flow responses output by the model are consistent with the measured data, and if necessary, fine-tune and iterate twice.

[0106] On the other hand, in some embodiments, the present application provides a municipal heating pipe network working condition twin modeling system, which refers to Figure 4 The figure is a structural schematic diagram of a municipal heating pipe network working condition twin modeling system according to some embodiments of the present application, which includes a modeling module 401, a processing module 402 and a parameter updating module 403, which are described as follows:

[0107] The modeling module 401 is mainly used for setting monitoring nodes at key nodes in the municipal heating pipe network in the present application, and constructing a temperature-pressure-flow multi-physical field coupled pipe network twin model based on the topological structure parameters and working condition parameters of the monitoring nodes in the municipal heating pipe network;

[0108] The processing module 402 is used for determining the correlation coefficient matrix of the working condition response characteristics between the monitoring nodes when the municipal heating pipe network is in a variable working condition in the present application, and then determining the boundary constraint quantity of each monitoring node position under the variable working condition through the correlation coefficient matrix and the pipe network structure parameters of each monitoring node;

[0109] The processing module 402 is also used for applying the boundary load of the variable working condition in the pipe network twin model in the present application, extracting the temperature-pressure-flow coupling response characteristics of each monitoring node under the variable working condition in the pipe network twin model, and then determining the coupling response loss of the twin modeling simulation under the variable working condition through all the coupling response characteristics;

[0110] The parameter updating module 403 is mainly used for constructing an error cost function of the pipe network twin simulation according to all the boundary constraint quantities and the coupling response loss in the present application, and performing parameter optimization on the model characteristic parameters of the pipe network twin model in the variable working condition twin simulation combined with the error cost function, obtaining the optimal model parameters suitable for the variable working condition, and then updating the simulation control parameters of the pipe network twin model based on the optimal model parameters.

[0111] In addition, the present application further provides a computer device, comprising a memory and a processor, the memory stores codes, and the processor is configured to acquire the codes and execute the municipal heat supply pipeline working condition twin modeling method.

[0112] In some embodiments, reference is made to Figure 5 The figure is a structural schematic diagram of a computer device for implementing the municipal heat supply pipeline working condition twin modeling method according to some embodiments of the present application. The municipal heat supply pipeline working condition twin modeling method in the above embodiments can be implemented by the computer device shown in the figure, which comprises at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504. Figure 5 The processor 501 can be a general central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0113] The processor 501 can be a general central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0114] The communication bus 502 can be used to transmit information between the above components.

[0115] The memory 503 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, an optical disk storage (including a compact disk, a laser disk, an optical disk, a digital versatile disk, a blue-ray disk, etc.), a magnetic disk or other magnetic storage device, or any other medium capable of carrying or storing desired program codes in the form of instructions or data structures and capable of being accessed by a computer, but not limited to this. The memory 503 can exist independently and be connected to the processor 501 through the communication bus 502. The memory 503 can also be integrated with the processor 501.

[0116] The memory 503 is configured to store program codes for implementing the solutions of the present application, and the processor 501 is configured to execute the program codes stored in the memory 503. The program codes can include one or more software modules. The municipal heating pipe network working condition twin modeling method in the above-described embodiments can be implemented by one or more software modules in the program codes in the processor 501 and the memory 503.

[0117] The communication interface 504 is configured to communicate with other devices or communication networks, such as an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc., using any transceiver-like device.

[0118] In specific implementations, as an example, the computer device can include multiple processors, each of which can be a single-CPU processor or a multi-CPU processor. The processor herein can refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0119] The computer device described above can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0120] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the above-described municipal heating pipe network working condition twin modeling method.

[0121] Although the preferred embodiments of the present application have been described, those skilled in the art who understand the basic inventive concept can make additional changes and modifications to the embodiments. Therefore, the appended claims are intended to include the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0122] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. A method for twin modeling of municipal heating pipeline network operating conditions, characterized in that, Includes the following steps: Monitoring nodes are set up at key nodes in the municipal heating pipeline network. A multi-physics coupled network twin model of temperature, pressure, and flow is constructed based on the topological parameters of the municipal heating pipeline network and the operating parameters of the monitoring nodes. Specifically, the construction of the multi-physics coupled network twin model of temperature, pressure, and flow based on the topological parameters of the municipal heating pipeline network and the operating parameters of the monitoring nodes includes: A three-dimensional geometric model of the municipal heating network is constructed based on its topological parameters. Temperature, pressure, and flow rate at each monitoring node are extracted from the operating parameters as initial boundary values ​​for multiphysics coupling simulation. The three-dimensional geometric model of the pipeline network is spatially discretized using the finite volume method, and then a temperature-pressure-flow coupled twin model of the pipeline network is constructed by combining the heat conduction equation, the fluid dynamics equation, and the energy conservation equation. When the municipal heating network is operating under varying conditions, the correlation coefficient matrix of the operating condition response characteristics among each monitoring node is determined. Then, the boundary constraints of each monitoring node's location under varying operating conditions are determined using the correlation coefficient matrix and the network structure parameters of each monitoring node. Specifically, determining the correlation coefficient matrix of the operating condition response characteristics among each monitoring node includes: For each monitoring node, temperature response features, pressure response features, and flow response features are extracted from the temperature response curve, pressure response curve, and flow response curve of the monitoring node, respectively. Based on the temperature response characteristics, the pressure response characteristics, and the flow response characteristics, the feature response vector of the monitoring node is determined, and then the feature response vector of each monitoring node is obtained. Determine the correlation coefficient between the characteristic response vectors of every two monitoring nodes; The correlation coefficient matrix of the operating condition response characteristics among each monitoring node is determined by using all the correlation coefficients. The boundary load of the variable operating condition is applied in the pipeline twin model, and the temperature-pressure-flow coupling response characteristics of each monitoring node in the pipeline twin model under the variable operating condition are extracted. Then, the coupling response loss of the twin modeling simulation under the variable operating condition is determined by all the coupling response characteristics. Based on all boundary constraints and the coupling response loss, an error cost function for the pipeline twin simulation is constructed. The model characteristic parameters of the pipeline twin model in the variable operating condition twin simulation are optimized using the error cost function to obtain the optimal model parameters applicable to the variable operating condition. Then, the simulation control parameters of the pipeline twin model are updated based on the optimal model parameters.

2. The method as described in claim 1, characterized in that, The determination of the boundary constraints for the location of each monitoring node under varying operating conditions using the correlation coefficient matrix and the pipeline structure parameters of each monitoring node specifically includes: The thermal conductivity and flow resistance coefficient of each monitoring node are determined based on the pipe material properties and pipe diameter in the pipeline network structure parameters. The thermo-hydraulic balance constraint equations between the monitoring nodes are constructed by combining the correlation coefficient matrix with the pipeline thermal conductivity coefficient and flow resistance coefficient of each monitoring node. The boundary constraints at each monitoring node location under varying operating conditions are obtained by solving the thermo-hydraulic balance constraint equations using the least squares method.

3. The method as described in claim 1, characterized in that, The extraction of temperature-pressure-flow coupled response characteristics of each monitoring node in the pipeline twin model under the stated variable operating conditions specifically includes: Select a monitoring node as the selected monitoring node, and collect simulated data of temperature field, pressure field and flow field at the selected monitoring node; Temperature fluctuation characteristics, pressure gradient characteristics, and flow pulsation characteristics are extracted from the simulation data, and then integrated to obtain the coupled response characteristics of temperature-pressure-flow of the selected monitoring node under the variable operating conditions. Repeat the above steps to obtain the coupled response characteristics of temperature-pressure-flow under the variable operating conditions of the remaining monitoring nodes.

4. The method as described in claim 1, characterized in that, The coupling response loss determined by all coupling response characteristics under the variable operating conditions in the twin modeling simulation specifically includes: Obtain the measured response characteristics of each monitoring node under the variable operating conditions; Error analysis was performed on the coupled response characteristics of temperature-pressure-flow under the variable operating conditions of each monitoring node and the measured response characteristics of the corresponding monitoring node to obtain the coupled simulation error of each monitoring node. The coupled response loss of the twin modeling simulation under the variable working condition is obtained by integrating the coupled simulation errors of all monitoring nodes.

5. The method as described in claim 1, characterized in that, The error cost function for constructing the pipeline twin simulation based on all boundary constraints and the coupling response loss specifically includes: The boundary constraint quantities at each monitoring node location are compared with their corresponding measured boundary quantities to obtain the boundary constraint error term. The coupling response loss is used as a simulation error term for multiphysics coupling; By integrating the boundary constraint error term and the simulation error term using a linear weighted formula, the error cost function of the pipeline twin simulation is obtained.

6. A twin modeling system for municipal heating pipeline network operating conditions, characterized in that, include: The modeling module is used to set up monitoring nodes at key nodes in the municipal heating pipeline network. Based on the topological parameters of the municipal heating pipeline network and the operating parameters of the monitoring nodes, it constructs a temperature-pressure-flow multiphysics coupled pipeline twin model. Specifically, this construction includes: building a three-dimensional geometric model of the pipeline network based on its topological parameters; extracting the temperature, pressure, and flow rate at each monitoring node from the operating parameters as initial boundary values ​​for the multiphysics coupled simulation; spatially discretizing the three-dimensional geometric model of the pipeline network using the finite volume method; and then constructing the temperature-pressure-flow coupled pipeline twin model by combining the heat conduction equation, fluid dynamics equation, and energy conservation equation. The processing module is used to determine the correlation coefficient matrix of the operating condition response characteristics among monitoring nodes when the municipal heating pipeline network is operating under varying conditions. Then, it determines the boundary constraints of each monitoring node's location under varying operating conditions using the correlation coefficient matrix and the pipeline structure parameters of each monitoring node. Specifically, determining the correlation coefficient matrix of the operating condition response characteristics among monitoring nodes includes: for each monitoring node, extracting temperature response features, pressure response features, and flow response features from the monitoring node's temperature response curve, pressure response curve, and flow response curve, respectively; determining the feature response vector of the monitoring node based on the temperature response features, pressure response features, and flow response features, thereby obtaining the feature response vector of each monitoring node; determining the correlation coefficient between the feature response vectors of every two monitoring nodes; and determining the correlation coefficient matrix of the operating condition response characteristics among all monitoring nodes using all the correlation coefficients. The processing module is also used to apply the boundary load of the variable operating condition to the pipeline twin model, extract the temperature-pressure-flow coupling response characteristics of each monitoring node in the pipeline twin model under the variable operating condition, and then determine the coupling response loss of the twin modeling simulation under the variable operating condition through all the coupling response characteristics. The parameter update module is used to construct an error cost function for the pipeline twin simulation based on all boundary constraints and the coupling response loss. It then uses the error cost function to optimize the model characteristic parameters of the pipeline twin model in the variable operating condition twin simulation to obtain the optimal model parameters applicable to the variable operating condition. Finally, it updates the simulation control parameters of the pipeline twin model based on the optimal model parameters.

7. A computer device comprising a memory and a processor, the memory storing code, characterized in that, The processor is configured to acquire the code and execute the municipal heating network operating condition twin modeling method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the municipal heating network operating condition twin modeling method as described in any one of claims 1 to 5.

Images