A district heating network dynamic heat integration equivalent modeling method and device

Abstract

The application provides a regional heat supply network dynamic heat integration equivalent modeling method and device, effectively solves the problem of how to comprehensively consider local high-precision dynamic heat modeling and overall rapid equivalent modeling to realize regional heat supply network dynamic heat integration equivalent modeling. The method comprises the following steps: dividing the abstracted directed graph of the heat supply network in the target region based on a division algorithm to obtain a plurality of preliminary cluster segment equivalent models containing unknown parameters; identifying the unknown parameters to obtain a preliminary cluster segment equivalent model not containing unknown parameters, and optimizing the preliminary cluster segment equivalent model not containing unknown parameters into a cluster segment equivalent model; constructing a compensation network, and fusing the compensation network and the cluster segment equivalent model to obtain a hybrid semi-mechanism cluster segment equivalent model; cascading a plurality of hybrid semi-mechanism cluster segment equivalent models based on hybrid state estimation values calculated by the hybrid semi-mechanism cluster segment equivalent model to obtain a regional heat network dynamic heat integration equivalent model.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of heat supply systems, in particular to a dynamic heat integration equivalent modeling method and device for a district heating network. BACKGROUND

[0002] A district heating network is an important part of a modern urban integrated energy network and has been widely used in scenarios such as residential life and industrial manufacturing in northern China. In order to fully share heat transmission infrastructure, a district heating network is usually established in related areas. In order to ensure the safe, energy-saving and low-carbon operation of the heating network, it is necessary to quickly and accurately model the dynamic heat of the heating network.

[0003] At present, many studies have improved the penetration rate of new energy and energy utilization rate by modeling the flexibility of the heating system. In these modeling studies, some of them use the finite element method represented by solving partial differential equations to model the internal dynamic heat of the heating pipe network in detail, but this brings a huge amount of calculation to the system operation, because it needs to build all the micro-element heat of all the pipes of the heat network according to the boundary conditions of the data to obtain the heat state of the nodes required. In fact, in state estimation, most problems only need to obtain the estimated value of an internal node to express the measurement data of the actual sensor, and in view of the consideration of calculation speed, in the problem of building the heat network model, another part of the scheme uses a lumped parameter equation representing the whole to model the equivalent without considering the internal dynamics of the pipe, which brings the problem of insufficient measurement accuracy of the multi-level connected integrated equivalent model when the network topology is too complex and the number of internal sensors is insufficient. Therefore, how to comprehensively consider the local high-precision dynamic heat modeling and the overall fast equivalent modeling to realize the dynamic heat integration equivalent modeling of the district heating network is a technical problem to be solved. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a dynamic heat integration equivalent modeling method and device for a district heating network, which effectively solves the problem of how to comprehensively consider the local high-precision dynamic heat modeling and the overall fast equivalent modeling to realize the dynamic heat integration equivalent modeling of the district heating network.

[0005] In a first aspect, an embodiment of the present application provides a dynamic heat integration equivalent modeling method for a district heating network, which comprises:

[0006] The preliminary cluster segment equivalent model containing unknown parameters is obtained by dividing the directed graph abstracted from the target area of the heat supply network based on a division algorithm; the edges of the directed graph are divided into multiple intermediate nodes; the nodes of the directed graph are abstracted shunt nodes and pipeline nodes, and the edges of the directed graph are distances between the shunt nodes and the pipeline nodes;

[0007] The unknown parameters in the preliminary cluster segment equivalent model are identified based on the characteristics of the heat supply network, to obtain a preliminary cluster segment equivalent model not containing unknown parameters, and the preliminary cluster segment equivalent model not containing unknown parameters is optimized into a cluster segment equivalent model; the cluster segment equivalent model is used to output predicted temperature data of the intermediate nodes; the parameters of the cluster segment equivalent model include identification data time delay;

[0008] The predicted temperature data output by the cluster segment equivalent model and the actual temperature data collected are selected as feature vectors according to the identification data time delay parameter, a compensation network used to compensate the cluster segment equivalent model is constructed, and a hybrid semi-mechanism cluster segment equivalent model is obtained by fusing the compensation network and the cluster segment equivalent model;

[0009] Based on the hybrid state estimation value of the key nodes meeting the preset condition in the intermediate nodes calculated in the hybrid semi-mechanism cluster segment equivalent model, a plurality of hybrid semi-mechanism cluster segment equivalent models are cascaded based on the hybrid state estimation value of the key nodes, to obtain a regional heat network dynamic thermal integration equivalent model, and the dynamic thermal integration equivalent model is used to control the heat transfer of the heat supply network in the region.

[0010] In combination with the first aspect, the first possible implementation manner of the first aspect is provided, in which the directed graph abstracted from the heat supply network in the region is divided based on a division algorithm, to obtain a plurality of preliminary cluster segment equivalent models containing unknown parameters, including:

[0011] A node division rule is designed based on the connection relationship between the nodes in the heat supply network, and the node division rule is input into the division algorithm;

[0012] The division algorithm performs segment division on the abstracted directed graph based on the node division rule, to obtain a preliminary cluster segment equivalent model.

[0013] In combination with the first aspect, the second possible implementation manner of the first aspect is provided, in which the division algorithm performs division on the abstracted directed graph based on the node division rule, to obtain a preliminary cluster segment equivalent model, including:

[0014] The pipeline input temperature and the environment temperature of the intermediate nodes obtained by performing segment division between the nodes of the directed graph are acquired;

[0015] The preliminary cluster segmentation equivalent model processes the pipeline input temperature and the ambient temperature of the intermediate node to obtain predicted temperature data and a predicted temperature change amount of the next moment of the intermediate node.

[0016] With reference to the first aspect, in a third possible implementation manner of the first aspect, the preliminary cluster segmentation equivalent model is based on feature recognition of the heat supply network to obtain unknown parameters in the preliminary cluster segmentation equivalent model, and the preliminary cluster segmentation equivalent model without the unknown parameters is obtained, and the preliminary cluster segmentation equivalent model without the unknown parameters is obtained by:

[0017] The number of the actual temperature data of the heat supply network and the number of the intermediate nodes, the penalty value of the intermediate node when the preset penalty condition is met, and the deviation between the predicted temperature data and the actual temperature data of the end pipeline node output by the preliminary cluster segmentation equivalent model are input into the model parameter recognition network;

[0018] The model parameter recognition network processes the number of the actual temperature data of the heat supply network, the number of the intermediate nodes, the penalty value of the intermediate node when the preset penalty condition is met, and the deviation between the predicted temperature data and the actual temperature data of the end pipeline node output by the preliminary cluster segmentation equivalent model to obtain a parameter value corresponding to the unknown parameter in the preliminary cluster segmentation equivalent model, and eliminate the unknown parameter to obtain the preliminary cluster segmentation equivalent model without the unknown parameter.

[0019] With reference to the first aspect, in a fourth possible implementation manner of the first aspect, the preliminary cluster segmentation equivalent model without the unknown parameter is optimized into a cluster segmentation equivalent model, and the optimization comprises:

[0020] The parameter value output by the model parameter recognition network is fixed in the preliminary cluster segmentation equivalent model, and the unknown parameter in the preliminary cluster segmentation equivalent model is replaced by the parameter value to optimize the preliminary cluster segmentation equivalent model into the cluster segmentation equivalent model.

[0021] The cluster segmentation equivalent model is verified by using a verification data set, and the cluster segmentation equivalent model is re-optimized according to a verification result.

[0022] With reference to the first aspect, in a fifth possible implementation manner of the first aspect, the compensation network is constructed to compensate for the cluster segmentation equivalent model, and the hybrid semi-mechanism cluster segmentation equivalent model is obtained by fusing the compensation network and the cluster segmentation equivalent model, and the hybrid semi-mechanism cluster segmentation equivalent model comprises:

[0023] The compensation network is operated and migrated based on a scale factor to obtain a migrated scale compensation network.

[0024] The proportional compensation network after migration processing and the predicted temperature data are fused to obtain a hybrid semi-mechanism cluster segmented equivalent model.

[0025] In conjunction with the first aspect, this application provides a sixth possible implementation of the first aspect, wherein the step of calculating the mixed state estimate of key nodes that meet preset conditions in the intermediate nodes based on the mixed semi-mechanism cluster segmented equivalent model, and cascading multiple mixed semi-mechanism cluster segmented equivalent models based on the mixed state estimate of the key nodes to obtain a regional heating network dynamic thermal integrated equivalent model, includes:

[0026] The dynamic heat transfer characteristics of the key nodes, the connection relationships of the key nodes, and the estimated mixed state values ​​of the key nodes calculated by the hybrid semi-mechanism cluster segmented equivalent model are invoked.

[0027] Based on the estimated mixed state values ​​of the key nodes, the dynamic heat transfer characteristics, and the connection relationships of the key nodes, a dynamic thermal integration equivalent model of the district heating network is constructed in the form of an equivalent model.

[0028] Secondly, embodiments of this application provide a dynamic thermal integrated equivalent modeling device for district heating networks, the device comprising:

[0029] The partitioning module is used to partition the directed graph obtained by abstracting the heating network in the target area based on the partitioning algorithm, and obtain multiple preliminary cluster segmentation iso-value models containing unknown parameters; the edges of the directed graph are partitioned to obtain multiple intermediate nodes; the nodes of the directed graph are the abstracted branch nodes and pipe nodes, and the edges of the directed graph are the distances between the branch nodes and pipe nodes.

[0030] An identification module is used to identify unknown parameters in the preliminary cluster segmented equivalent model based on the characteristics of the heating network, to obtain a preliminary cluster segmented equivalent model without unknown parameters, and to optimize the preliminary cluster segmented equivalent model without unknown parameters into a cluster segmented equivalent model; the cluster segmented equivalent model is used to output the predicted temperature data of intermediate nodes; the parameters of the cluster segmented equivalent model include the identification data delay;

[0031] The fusion module is used to select the predicted temperature data output by the cluster segmented equivalent model and the collected actual temperature data as feature vectors according to the identified data delay parameters, construct a compensation network to compensate the cluster segmented equivalent model, and fuse the compensation network and the cluster segmented equivalent model to obtain a hybrid semi-mechanism cluster segmented equivalent model.

[0032] The cascade module is used to calculate the mixed state estimate of the key nodes in the intermediate nodes from the mixed semi-mechanism cluster segmented equivalent model, and to cascade multiple mixed semi-mechanism cluster segmented equivalent models based on the mixed state estimate of the key nodes to obtain a regional heating network dynamic thermal integration equivalent model, so as to control the heat transfer of the heating network in the region.

[0033] Thirdly, embodiments of this application provide an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of any one of the methods for dynamic thermal integration equivalent modeling of a district heating network.

[0034] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the dynamic thermal integration equivalent modeling method for a district heating network as described in any one of claims 1 to 7.

[0035] This application provides a dynamic thermal integration equivalent modeling method for a regional heating network. The method includes: partitioning a directed graph abstracted from the heating network within a target area using a partitioning algorithm to obtain multiple preliminary cluster segmented equivalent models containing unknown parameters; dividing the edges of the directed graph to obtain multiple intermediate nodes; the nodes of the directed graph are abstracted branch nodes and pipe nodes, and the edges of the directed graph are the distances between branch nodes and pipe nodes; identifying the unknown parameters in the preliminary cluster segmented equivalent models based on the characteristics of the heating network to obtain preliminary cluster segmented equivalent models without unknown parameters, and optimizing the preliminary cluster segmented equivalent models without unknown parameters into cluster segmented equivalent models; the cluster segmented equivalent models are used to output predicted temperature data for intermediate nodes; the parameters of the cluster segmented equivalent models include identified data delay; selecting the predicted temperature data output by the cluster segmented equivalent models and the collected actual temperature data as feature vectors based on the identified data delay parameters to construct a feature vector to compensate for the cluster segmented equivalent models. A compensation network is constructed, and the compensation network and the cluster segmented equivalent model are integrated to obtain a hybrid semi-mechanism cluster segmented equivalent model. Based on the hybrid semi-mechanism cluster segmented equivalent model, the hybrid state estimates of key nodes that meet preset conditions in the intermediate nodes are calculated. Multiple hybrid semi-mechanism cluster segmented equivalent models are cascaded based on the hybrid state estimates of key nodes to obtain a dynamic thermal integrated equivalent model of the regional heating network. The dynamic thermal integrated equivalent model is used to control the heat transfer of the heating network in the region, realizing dynamic thermal equivalent modeling of the regional heating network. It can provide system design, optimization and management efficiency, increase the flexibility and scalability of the regional heating network, and improve the fault tolerance and reliability of the heating network. It can also be used to approximate the actual characteristics of the actual regional heating system with arbitrary precision, reducing the modeling difficulty. It can also be combined with neural network models of arbitrary complexity, thus comprehensively considering the local high-precision dynamic thermal modeling and the overall fast equivalent modeling to achieve the effect of dynamic thermal integrated equivalent modeling of the regional heating network. Attached Figure Description

[0036] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 A flowchart of the first method for dynamic thermal integration equivalent modeling of a district heating network provided in an embodiment of this application is shown;

[0038] Figure 2A schematic diagram of a directed graph of a district heating network provided in an embodiment of this application is shown;

[0039] Figure 3 This diagram shows the result of partitioning the directed graph node clusters of the regional heating network provided in an embodiment of this application.

[0040] Figure 4 This paper presents a schematic diagram illustrating the results of the mixed state estimation provided in an embodiment of this application.

[0041] Figure 5 This illustration shows a schematic diagram of the structure of the first type of dynamic thermal integration equivalent modeling device for district heating networks provided in an embodiment of this application;

[0042] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0044] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0045] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0046] In current state estimation of district heating networks, most problems only require the estimated value of a single internal node to represent the actual sensor measurement data. However, due to computational speed considerations, some schemes for constructing heating network models employ lumped parametric equations representing the entire network, neglecting the dynamics within the pipes. This leads to problems such as insufficient measurement accuracy in multi-level integrated equivalent models and approximations when the network topology is too complex and the number of internal sensors is insufficient. Therefore, how to comprehensively consider high-precision local dynamic thermal modeling and rapid overall equivalent modeling to achieve integrated equivalent modeling of dynamic thermal systems in district heating networks is a pressing technical problem that needs to be solved.

[0047] Based on this, the present application provides a method and apparatus for dynamic thermal integration equivalent modeling of a district heating network, which will be described below through embodiments.

[0048] Example 1

[0049] To facilitate understanding of this embodiment, a detailed description of the dynamic thermal integration equivalent modeling method for district heating networks disclosed in this application embodiment will be provided first. For example... Figure 1 The flowchart shown illustrates a method for dynamic thermal integration equivalent modeling of a district heating network. This application provides a method for dynamic thermal integration equivalent modeling of a district heating network, the method comprising:

[0050] S101. Based on the partitioning algorithm, the directed graph obtained by abstracting the heating network in the target area is partitioned to obtain multiple preliminary cluster segmentation isovalue models containing unknown parameters; the edges of the directed graph are partitioned to obtain multiple intermediate nodes; the nodes of the directed graph are the abstracted branch nodes and pipe nodes, and the edges of the directed graph are the distances between the branch nodes and pipe nodes.

[0051] S102. Based on the characteristics of the heating network, identify the unknown parameters in the preliminary cluster segmented equivalent model to obtain a preliminary cluster segmented equivalent model without unknown parameters, and optimize the preliminary cluster segmented equivalent model without unknown parameters into a cluster segmented equivalent model; the cluster segmented equivalent model is used to output the predicted temperature data of intermediate nodes; the parameters of the cluster segmented equivalent model include the identified data delay;

[0052] S103. Based on the identified data delay parameter, select the predicted temperature data output by the cluster segmented equivalent model and the collected actual temperature data as feature vectors, construct a compensation network to compensate the cluster segmented equivalent model, and fuse the compensation network and the cluster segmented equivalent model to obtain a hybrid semi-mechanism cluster segmented equivalent model.

[0053] S104. Based on the hybrid semi-mechanism cluster segmented equivalent model, calculate the hybrid state estimate of the key nodes in the intermediate nodes that meet the preset conditions, and cascade multiple hybrid semi-mechanism cluster segmented equivalent models based on the hybrid state estimate of the key nodes to obtain a regional heating network dynamic thermal integration equivalent model. The dynamic thermal integration equivalent model is used to control the heat transfer of the heating network within the region.

[0054] In step S101, the entire process of dynamic thermal isometric modeling of the regional heating network is executed using intelligent devices such as computers with data analysis and processing capabilities. The partitioning algorithm is pre-installed on the computer or within the computer and can be called when the directed graph needs to be partitioned. Based on the partitioning algorithm, multiple preliminary cluster segmented isometric models containing unknown parameters are obtained. The directed graph is obtained by abstracting the heating network within the target area. The edges of the directed graph are partitioned to obtain multiple intermediate nodes. The directed graph is a form of graph theory, using a unified thermal network graph theory form to remove the multiple attributes of edges in the traditional thermal network graph theory expression. The nodes of the directed graph are abstracted branch nodes and pipe nodes. The branch nodes are the locations of various sensors arranged at the junctions of the heating pipes, and the pipe nodes are... The directed graph is constructed on the edges of non-edge station nodes and non-pipeline intersection branch nodes. Each pipeline node is connected to a station node or branch node providing temperature input data at its front end and to a station node or branch node providing temperature output data at its rear end. The edges of the directed graph represent the distances between branch nodes and pipeline nodes. The weights of the edges are obtained based on the distances between station nodes, branch nodes, and pipeline nodes. In this paper, terminal nodes include, for example, heating boilers, combined heat and power plants, thermal storage stations, and secondary heat exchange stations. The distance between a station node and a branch node and the nearest connected pipeline node is 0. The distance from a pipeline node to the next node is the complete edge distance, which is the distance taken along the edges before, after, and following the pipeline node to avoid duplicate values. The directed graph uses an adjacency matrix. The formal representation of . The abstracted directed graph is as follows: ,in, A set representing nodes. This represents the set of edges in a directed graph, where each edge is the distance between a branch node and the pipe node to which the flow originates. Represents the node connection relationship, where Expressed using formula (1):

[0055] (1)

[0056] in, For the first The node and the first The distance between nodes, As a directed graph, it is stipulated that the edge weight between the station node and the pipeline node to which the flow direction of the branch node is located is 0 in the diagonal matrix. The directed graph is expressed in the form of an adjacency matrix, which can be uniformly calculated and processed on a computer. It provides a reference scheme for the connection relationship and key node selection of the integrated equivalent model of the heating network. The key node is the intermediate node where the intersection point is located among the intermediate nodes obtained by dividing the two edges with only one intersection point.

[0057] In this context, the pipe node also converts equipment such as expansion joints and three-way valves into equivalent pipe lengths, expressed by formulas (2)-(4):

[0058] (2)

[0059] (3)

[0060] (4)

[0061] in, S j Indicates the local resistivity; d Indicates the diameter of the heating pipe; the coefficient of friction of the heating pipe. Lambda It depends on the flow state of the hot water in the heating pipe and the roughness of the pipe wall; Re Represents the Reynolds number, a dimensionless number that characterizes the state of fluid flow; Epsilon Indicates the relative roughness of the heating pipe wall; It is the viscosity coefficient of the medium. Expansion joints, three-way valves, and other equipment are equivalently transformed into pipe lengths, which is the increase in the length of the edges of the directed graph. By using the above unified expression, any heating network equipment can be equivalently transformed into a pipe and represented as a pipe model node, which can effectively express its thermal and hydraulic transmission characteristics as a connection node.

[0062] In the specific implementation of step S101, one embodiment is as follows: Based on a partitioning algorithm, the directed graph abstracted from the heating network within the region is partitioned to obtain multiple preliminary cluster segmentation isometric models containing unknown parameters, including:

[0063] S1011. Design node partitioning rules based on the connection relationship between nodes in the heating network, and input the node partitioning rules into the partitioning algorithm;

[0064] S1012. The partitioning algorithm divides the abstracted directed graph into segments based on the node partitioning rules to obtain a preliminary cluster segmentation equivalent model.

[0065] In steps S1011-S1012, the partitioning algorithm pre-stored in the computer or computer can be the Tarjan algorithm based on depth-first search. The Tarjan algorithm was originally used to search for strongly connected components in a directed graph in a tree structure. By modifying the component partitioning conditions of the Tarjan algorithm, it can be applied to any heating network structure to perform graph-based search and partitioning, thereby obtaining multiple node clusters after downscaling and deconstructing the complex heating network. These clusters provide support for the local equivalent modeling scheme and provide the node locations for connection of each cluster, providing a reference for the dynamic thermal integration equivalent modeling scheme of the regional heating network.

[0066] Based on the field graph structure of the heating network, node partitioning rules for the graph theory expression of the heating network are designed to obtain multiple node cluster components. According to the established directed graph adjacency matrix, the following partitioning conditions apply: (1) The head and tail of the cluster must be terminal nodes, that is, the head and tail should be heat source nodes and heat exchange station nodes; (2) When one end of the search has been used, the cluster is partitioned end-to-end from the nearest branch node; (3) When the distance between the two endpoints is short, a separate cluster should be partitioned; (4) When the branch node is at the end of the pipeline, the branch node and the terminal node are partitioned as a whole.

[0067] The above division conditions correspond to the following designs: (1) The proposed segmented equivalent model only uses terminal nodes for equivalent modeling; (2) A highly controllable integrated heat network model without repeated paths is established. This model can be implemented by using branch nodes to connect clusters, rather than relying on approximation methods to model repeated paths; (3) When the distance between two endpoints is short, it indicates that the terminal measurement point data can effectively approximate the branch nodes, improving the quality of the estimated values ​​of the branch nodes; (4) A suitable processing scheme is provided for the cluster division at the end of the pipeline.

[0068] In a specific implementation of step S1012, one embodiment is as follows: the partitioning algorithm partitions the abstracted directed graph based on the node partitioning rules to obtain a preliminary cluster segmentation equivalence model, including:

[0069] S10121. Obtain the pipe input temperature and ambient temperature of the intermediate node obtained by segmenting the nodes of the directed graph.

[0070] S10122. The preliminary cluster segmented equivalent model processes the pipeline input temperature and ambient temperature of the intermediate node to obtain the predicted temperature data of the intermediate node and the predicted temperature change at the next moment.

[0071] In steps S10121-S10122, the preliminary cluster segmentation equivalent model is expressed by formula (5):

[0072] (5)

[0073] in, X SS ( k ) represents each node of the pipeline. k The state vector at time t, in this application, refers to temperature, assuming it exists in the node cluster. N-1 When there are intermediate nodes, X SS ( k ) = [ x SS1 x SS2 … x SSN ] T This represents the predicted temperature data for each segment of the pipe after segmentation. U ( k )=[ u 1( k ) T amb ( k )] T This represents the temperature data of the divided pipelines corresponding to the initial cluster segmentation equivalent model, input from the pipeline input temperature of the intermediate nodes. u 1( k ) and ambient temperature T amb ( k The pipeline input temperature is estimated based on temperature data measured by sensors or other means at the terminal nodes. Y d ( k () represents the output predicted temperature data. Let A, B, and C represent the predicted temperature change at the next moment, and let A, B, and C be the system matrices respectively. 、 The input matrix and the state transition matrix are represented by formulas (6)-(8) respectively:

[0074] (6)

[0075] (7)

[0076] (8)

[0077] in a , b These represent the parameters of the system matrix A and the input matrix B in the piecewise model.

[0078] The heat exchange stations, heat sources, expansion joints, three-way valves, and other heating network equipment within the terminal nodes are equivalently represented as follows:Figure 2 The diagram shows how the complex thermal network topology, after undergoing unified processing, is represented by a graph theory expression and converted into an adjacency matrix that can be processed by a computer, as shown below. e ij ) n×n :

[0079]

[0080] in, Indicates intermediate nodes i With intermediate nodes j The length relationship between nodes was determined, and then the Tarjan graph clustering algorithm, with improved component partitioning rules for district heating networks, was used to perform depth-based node clustering on the directed graph representing the district heating network. The Tarjan algorithm is an original linear-time algorithm for solving strongly connected components of a directed graph; it is based on a depth-first search algorithm, where each strongly connected component is a subtree in the search tree. In the application to district heating networks, this method adaptively modifies the Tarjan algorithm to handle the special graph theory properties of district heating networks. First, the single-heat-source heating network is expressed as an adjacency matrix. Then, by applying a modified Tarjan algorithm, this adjacency matrix is ​​divided into multiple node clusters. Each cluster contains one or more key nodes for interconnection between clusters, and these key nodes share the same equivalent characteristics of pipe heat transfer. In this way, the complex equivalent modeling problem of heat networks can be simplified into multiple smaller sub-modeling problems, each involving only one node cluster. Figure 2 The adjacency matrix of the single heat source heating network shown is divided as follows: Figure 3 The diagram shows a total of 20 node clusters. Here, HS represents heat source nodes, S represents the equivalent nodes of the pipeline model visualization proposed in this method, SM represents key nodes used to connect the various node clusters, HE represents heat exchange station nodes containing measurement data, A represents abbreviated points containing multiple partitioned node clusters, Cluster represents the node cluster results partitioned based on the adjacency matrix and component construction rules constructed according to the field topology, and the dashed lines represent the physical actual distribution on the regional heating network structure map corresponding to the mixed state estimation results of key nodes provided by this method.

[0081] In step S102, unknown parameters in the preliminary cluster segmented equivalent model are identified based on the characteristics of the heating network. Since the most important characteristic of the heating network is temperature, the unknown parameters in the preliminary cluster segmented equivalent model are identified based on temperature. The identified unknown parameters are then used to replace the unknown parameters in the preliminary cluster segmented equivalent model, resulting in a preliminary cluster segmented equivalent model without unknown parameters. This preliminary cluster segmented equivalent model without unknown parameters is then optimized into a cluster segmented equivalent model. The cluster segmented equivalent model is used to output the predicted temperature data of intermediate nodes, which is not the actual temperature of the heating network. The cluster segmented equivalent model has multiple parameters, from which the parameter of data identification delay is selected for use.

[0082] In a specific implementation of step S102, one embodiment is as follows: the identification of unknown parameters in the preliminary cluster segmentation equivalent model based on the features of the heating network to obtain a preliminary cluster segmentation equivalent model that does not contain unknown parameters includes:

[0083] S10211. Input the number of actual temperature data of the heating network obtained by statistics, the number of intermediate nodes, the calculated penalty value of the intermediate node when the preset penalty condition is met, and the deviation between the predicted temperature data of the end pipe node output by the preliminary cluster segmentation equivalent model and the actual temperature data into the model parameter identification network.

[0084] S10212, The model parameter identification network processes the number of actual temperature data of the heating network, the number of intermediate nodes, the penalty value of intermediate nodes when they meet the preset penalty conditions, and the deviation between the predicted temperature data of the terminal pipe nodes output by the preliminary cluster segmented equivalent model and the actual temperature data, to obtain the parameter values ​​corresponding to the unknown parameters in the preliminary cluster segmented equivalent model, and eliminates the unknown parameters to obtain a preliminary cluster segmented equivalent model that does not contain unknown parameters.

[0085] In steps S1021-S1022, the model parameter identification network pre-stored in the computer or computer system is represented by an objective function, which is expressed by formula (9):

[0086] (9)

[0087] Where obj is the parameter value corresponding to the unknown parameter. N The value represents the number of predicted temperature data points from the preliminary cluster segmented isometry model; error represents the deviation between the predicted temperature data of the terminal pipe nodes output by the preliminary cluster segmented isometry model and the actual temperature data; Xest represents the number of intermediate nodes; and penalty represents the number of intermediate nodes.i For the penalty value when the path exceeds the boundary conditions and the mismatched mechanism parameters are identified, the actual temperature data is obtained by the district heating network using temperature sensors or other methods, wherein:

[0088] (10)

[0089] (11)

[0090] (12)

[0091] in, T Indicates the sampling time step. State k This represents the end pipe node output by the preliminary cluster segmentation equivalent model. k The identification results of the predicted temperature data at any given time. State k est Indicates intermediate nodes k The result of identifying the actual temperature at any given time. H Indicates intermediate nodes i Boundary conditions, The system matrix A represents the model parameter identification network identification system matrix A. i OK i The value of the column, α i Indicates intermediate nodes i The convective heat transfer coefficient of the pipe section C w Indicates specific heat capacity. Indicates the flow velocity in the pipe section. L i This indicates the perimeter of the pipe section. d i This indicates the length of the pipe section. S The number of intermediate nodes representing the mechanism constraints of the construction can be understood as: (1) Error The term represents the difference between the predicted temperature data and the actual temperature data at the end of the preliminary cluster segmented equivalent model constructed by the model parameter identification network, which is used to ensure that the output of the equivalent model approximates the true value; (2) Penalty The term represents the temperature data of intermediate nodes with internal mechanism constraints identified by the model parameter identification network. This temperature data should be within the data boundary, and the identification parameters should satisfy the mechanism constraints as much as possible.

[0092] For the optimization problem of a single unknown parameter proposed by the model parameter identification network, the simulated annealing algorithm is used to solve for the optimal value of the unknown parameter, realizing parameter identification of the cluster segmented isomorphic model from the perspective of global search.

[0093] In the specific implementation of step S102, another embodiment exists: optimizing the preliminary cluster segmentation isometry model that does not contain unknown parameters into a cluster segmentation isometry model includes:

[0094] S10221. Fix the parameter values ​​output by the model parameter identification network in the preliminary cluster segmentation equivalent model, and replace the unknown parameters in the preliminary cluster segmentation equivalent model with the parameter values, so as to optimize the preliminary cluster segmentation equivalent model into a cluster segmentation equivalent model.

[0095] S10222. Validate the cluster segmented equivalence model using the validation dataset, and further optimize the cluster segmented equivalence model based on the validation results.

[0096] In steps S10221-S10222, the cluster segmentation equivalent model obtained by optimization based on the preliminary cluster segmentation equivalent model is expressed by formula (13):

[0097] (13)

[0098] in, P =- u w / d - αL / Fc w Rho w , u ( k )= [ T in w( k ) T amb ( k )], u w Represents the instantaneous flow velocity in the pipe, with units of m / s. T amb( t ( ) represents the ambient temperature, in °C. α It refers to the convective heat transfer coefficient of the environment, with units of J / (m²·℃·s). L It is the circumference of the pipe, in meters (m). d This represents the total length of the pipeline, in meters (m). F It is the cross-sectional area of ​​the pipe, measured in meters (m). 2 , c w It is the specific heat capacity of water, measured in J / L. C, Rho w This is the density of water, expressed in kg / m³. At this point, the temperature... xss ( k Modify the state transition matrix based on the matrix. C The structure allows for the prediction of temperature data. y ( k The predicted temperature data for key nodes is transformed into actual temperature data. The cluster segmented equivalent model is then validated using a pre-stored validation dataset, which consists of historically collected actual temperature data from the regional heating network. If the deviation between the output predicted temperature data and the actual temperature data is within a preset range, the validation result is successful; otherwise, it is considered a failure. If the validation result is a failure, the cluster segmented equivalent model is further optimized to ensure its accuracy.

[0099] In step S103, the cluster segmented equivalent model is established for each intermediate node. However, in actual use, all models will generate time delays during operation. The cluster segmented equivalent model generates multiple parameters when identifying the input data, one of which is the identification data delay parameter, which also generates nonlinear errors. Therefore, the predicted temperature data output by the cluster segmented equivalent model and the collected actual temperature data are selected as feature vectors for the identification data delay parameter. A compensation network is constructed to compensate for the cluster segmented equivalent model. The compensation network and the cluster segmented equivalent model are then fused to obtain a hybrid semi-mechanism cluster segmented equivalent model. At this time, the predicted temperature data output by the hybrid semi-mechanism cluster segmented equivalent model is closer to the actual temperature data, which greatly improves the accuracy of the output predicted temperature data.

[0100] The nonlinear error generated by the cluster segmented equivalent model is expressed by formula (14):

[0101] (14)

[0102] The intermediate node receives the thermal or hydraulic input temperature from other intermediate nodes. T in w( k The output temperature of the intermediate node to other intermediate nodes. y real ( k The error between the predicted temperature data and the actual temperature data output by the cluster segmented isometry model. e ( k The autoregressors are used as input and output vectors to train the neural network model, as expressed by formulas (15)-(16):

[0103] U com (k)=[u(k)u(k-2)…u(kn b )y(k-1)y(k-2)…y(kn a)e(k-1)e(k-2)…e(kn a (15)

[0104] (16)

[0105] in, e This is the error term, the input temperature. U com ( k and output temperature Y com ( k This can be extended to a multi-output format, where the identified data delay parameter includes the delay order of the predicted temperature data output by the cluster segmented equivalent model. n a Delay order of input temperature n b Based on computational performance, the longer the time delay of the heating network features and the more data, the better the nonlinear compensation performance, but the slower the computation speed. A compensation network is constructed to compensate the cluster segmented equivalent model, wherein the compensation network is a temporal neural network.

[0106] In a specific implementation of step S103, one embodiment is as follows: The construction of a compensation network to compensate for the cluster segmentation equivalence model, and the fusion of the compensation network and the cluster segmentation equivalence model to obtain a hybrid semi-mechanistic cluster segmentation equivalence model, includes:

[0107] S1031. Perform calculations and transfer processing on the compensation network based on the scaling factor to obtain the proportional compensation network after transfer processing.

[0108] S1032. The proportional compensation network after migration processing and the predicted temperature data are fused to obtain a hybrid semi-mechanism cluster segmented equivalent model.

[0109] In steps S1031-S1032, the predicted temperature data after migration processing is fused with the compensation network calculated proportionally to obtain the compensation term for the predicted temperature data of the intermediate nodes, expressed by formula (17):

[0110] (17)

[0111] in, e cp,trans ( k ) is the compensation value of the compensation network. e cp ( k After compensating the heating equipment within the terminal node, k The compensation value is constantly transmitted to the intermediate node. d forwardThis represents the distance from the input node to the intermediate node, where the input node is any other node in the hydraulic or thermal analysis. d total Let represent the total length of the segmented pipeline. The hybrid semi-mechanism cluster segmented equivalent model obtained by integrating the compensation network and the cluster segmented equivalent model is expressed by formula (18):

[0112] (18)

[0113] Among them, g( k ) is a data-driven compensation term output by a neural network model based on deviation dynamics, g( k )=[ e cp,trans ( k ), e cp ( k By establishing the compensation network and the cluster segmented equivalent model, a hybrid semi-mechanistic segmented equivalent model of the node cluster is established. This obtains the estimated hybrid state of internal nodes based on the boundary node data of the heat exchange station, including the terminal nodes, and the mechanistic constraints under the cluster equivalent model. This provides a means to obtain the estimated hybrid state of key nodes, i.e., predict the temperature data, when there are insufficient internal measurement points in the regional heating network. This provides effective support for the rapid cascaded equivalent modeling of the regional heating network.

[0114] By identifying the internal propagation delay under a fixed flow velocity, aligning the time axis to process the delay relationship between intermediate and output nodes, and using the migration compensation results after scaling the neural network output values, we obtain the mixed state estimates of the estimated nodes in the node cluster. It should be noted that the preliminary state estimation results can be directly derived from the piecewise state variables of the model. x ss ( k The paper proposes that the hybrid semi-mechanistic state estimate needs to be obtained by aligning the piecewise time delays under a fixed flow velocity and then processing the data through the output of a transfer neural network. e cp,trans ( k Performance of compensation and mixed-state estimation Figure 4 As shown.

[0115] In step S104, the mixed state estimate of the key node in the intermediate node that meets the preset conditions is calculated based on the mixed semi-mechanism cluster segmented equivalent model. The mixed state estimate is the predicted temperature data. That is, the key node is the intermediate node where the intersection point is located in the intermediate node obtained by dividing the two edges with only one intersection point. That is, the mixed semi-mechanism cluster segmented equivalent model is established for the key node including a section of pipeline and a branch node. Then, the predicted temperature data of this key node is used as the input of the mixed semi-mechanism cluster segmented equivalent model of the next key node. Multiple mixed semi-mechanism cluster segmented equivalent models are cascaded based on the mixed state estimate of the key node to obtain the regional heating network dynamic thermal integrated equivalent model. The dynamic thermal integrated equivalent model is used to control the heat transfer of the heating network in the region.

[0116] In the specific implementation of step S04, one embodiment is as follows: Based on the hybrid semi-mechanism cluster segmented equivalent model, the estimated hybrid state of key nodes meeting preset conditions in the intermediate nodes is calculated. Multiple hybrid semi-mechanism cluster segmented equivalent models are cascaded based on the estimated hybrid state of the key nodes to obtain a regional heating network dynamic thermal integration equivalent model, including:

[0117] S1041. Call the dynamic heat transfer characteristics of the key node, the connection relationship of the key node, and the estimated value of the mixed state of the key node calculated by the mixed semi-mechanism cluster segmented equivalent model.

[0118] S1042. Based on the estimated mixed state values ​​of the key nodes, dynamic heat transfer characteristics, and connection relationships of the key nodes, a dynamic heat integration equivalent model of the district heating network is constructed in the form of an equivalent model.

[0119] In steps S1041-S1042, a dynamic thermal integration equivalent model of the district heating network is established and expressed by formula (19):

[0120] (19)

[0121] in, M The number of node clusters represented by the Tarjan algorithm, which improves the component partitioning rules, is included in the dynamic thermal integration equivalent model of the district heating network established above. This model includes the dynamic thermal transfer characteristics of the key nodes, the connection relationships of the key nodes, and the estimated mixed state values ​​of the key nodes calculated by the hybrid semi-mechanism cluster segmentation equivalent model. This further ensures the accuracy of the established dynamic thermal integration equivalent model of the district heating network, guarantees its adaptability to the district heating network, and accurately reflects the temperature of thermal or hydraulic transfer in the district heating network.

[0122] Based on different dynamic thermal equivalent modeling methods for heating networks, this method evaluates the terminal output results of the model using the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE), calculated by formulas (20)-(22):

[0123] (20)

[0124] (twenty one)

[0125] (twenty two)

[0126] In the formula, This indicates the output predicted value. To output the actual value, N To predict the number of samples, the final output of the parameter identification model obtained by solving the optimization problem after compensation by different neural network models is shown in Table 1. It can be seen that the effect of this method is better than other methods.

[0127] Table 1. Performance of dynamic thermal dynamic equivalent modeling of thermal networks compensated by different network models in a 7-day test.

[0128] Example 2

[0129] This application also provides a dynamic thermal integration equivalent modeling device for district heating networks, such as... Figure 5 The diagram shows a block diagram of a dynamic thermal integration equivalent modeling device for a district heating network. This device performs functions corresponding to the steps described above in executing a dynamic thermal integration equivalent modeling method for a district heating network on a terminal device. The device can be understood as a server component including a processor. The device includes:

[0130] The partitioning module 501 is used to partition the directed graph obtained by abstracting the heating network in the target area based on the partitioning algorithm to obtain multiple preliminary cluster segmentation isovalue models containing unknown parameters; the edges of the directed graph are partitioned to obtain multiple intermediate nodes; the nodes of the directed graph are the abstracted branch nodes and pipe nodes, and the edges of the directed graph are the distances between the branch nodes and pipe nodes.

[0131] The identification module 502 is used to identify unknown parameters in the preliminary cluster segmented equivalent model based on the characteristics of the heating network, to obtain a preliminary cluster segmented equivalent model without unknown parameters, and to optimize the preliminary cluster segmented equivalent model without unknown parameters into a cluster segmented equivalent model; the cluster segmented equivalent model is used to output the predicted temperature data of intermediate nodes; the parameters of the cluster segmented equivalent model include the identification data delay;

[0132] The fusion module 503 is used to select the predicted temperature data output by the cluster segmented equivalent model and the collected actual temperature data as feature vectors according to the identified data delay parameter, construct a compensation network to compensate the cluster segmented equivalent model, and fuse the compensation network and the cluster segmented equivalent model to obtain a hybrid semi-mechanism cluster segmented equivalent model.

[0133] The cascade module 504 is used to calculate the mixed state estimate of the key nodes in the intermediate nodes from the mixed semi-mechanism cluster segmented equivalent model, and to cascade multiple mixed semi-mechanism cluster segmented equivalent models based on the mixed state estimate of the key nodes to obtain a regional heating network dynamic thermal integration equivalent model, so as to control the heat transfer of the heating network in the region.

[0134] In one feasible implementation, the modules are divided, including:

[0135] The design module is used to design node partitioning rules based on the connection relationships between nodes in the heating network, and input the node partitioning rules into the partitioning algorithm;

[0136] The abstract module is used by the partitioning algorithm to segment the abstracted directed graph based on the node partitioning rules to obtain a preliminary cluster segmentation equivalent model.

[0137] In one feasible implementation, the module division further includes:

[0138] The acquisition module is used to acquire the pipe input temperature and ambient temperature of the intermediate nodes obtained by segmenting the nodes of the directed graph.

[0139] The prediction module is used to process the pipeline input temperature and ambient temperature of the intermediate node in the preliminary cluster segmentation isometry model to obtain the predicted temperature data of the intermediate node and the predicted temperature change at the next moment.

[0140] In one feasible implementation, the identification module includes:

[0141] The statistics module is used to input the number of actual temperature data and intermediate nodes of the heating network obtained by statistics, the penalty value of the intermediate node when the preset penalty condition is met, and the deviation between the predicted temperature data of the end pipe node output by the preliminary cluster segmentation equivalent model and the actual temperature data into the model parameter identification network.

[0142] The processing module is used to process the number of actual temperature data of the heating network, the number of intermediate nodes, the penalty value of intermediate nodes when they meet the preset penalty conditions, and the deviation between the predicted temperature data of the terminal pipe nodes output by the preliminary cluster segmented equivalent model and the actual temperature data, to obtain the parameter values ​​corresponding to the unknown parameters in the preliminary cluster segmented equivalent model, and to eliminate the unknown parameters to obtain a preliminary cluster segmented equivalent model that does not contain unknown parameters.

[0143] In one feasible implementation, the identification module further includes:

[0144] A fixing module is used to fix the parameter values ​​output by the model parameter identification network in the preliminary cluster segmentation equivalent model, and replace the unknown parameters in the preliminary cluster segmentation equivalent model with the parameter values, so as to optimize the preliminary cluster segmentation equivalent model into a cluster segmentation equivalent model.

[0145] The verification module is used to verify the cluster segmentation isometry model using a verification dataset, and to further optimize the cluster segmentation isometry model based on the verification results.

[0146] In one feasible implementation, the fusion module includes:

[0147] The computation module is used to perform computation and transfer processing on the compensation network based on the scaling factor to obtain the proportional compensation network after transfer processing.

[0148] The migration module is used to fuse the migrated proportional compensation network and the predicted temperature data to obtain a hybrid semi-mechanism cluster segmented equivalent model.

[0149] In one feasible implementation, the cascade module includes:

[0150] The calling module is used to call the dynamic heat transfer characteristics of the key nodes, the connection relationship of the key nodes, and the estimated value of the hybrid state of the key nodes calculated by the hybrid semi-mechanism cluster segmented equivalent model.

[0151] A module is established to construct a dynamic thermal integration equivalent model of the district heating network in the form of an equivalent model based on the mixed state estimates of the key nodes, dynamic heat transfer characteristics, and connection relationships of the key nodes.

[0152] Example 3

[0153] This application provides an electronic device, such as... Figure 6As shown, it includes: a processor 601, a memory 602, and a bus 603. The memory 602 stores machine-readable instructions that can be executed by the processor 601. When the electronic device is running, the processor 601 and the memory 602 communicate through the bus 603. When the machine-readable instructions are executed by the processor 601, the steps of the dynamic thermal integration equivalent modeling method for a district heating network as described in any of the above claims are executed.

[0154] Example 4

[0155] A computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of any one of the methods for dynamic thermal integration equivalent modeling of a district heating network.

[0156] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0157] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0158] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0159] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a platform server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0160] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for dynamic thermal integration equivalent modeling of district heating networks, characterized in that, The method includes: The directed graph obtained by abstracting the heating network in the target area based on the partitioning algorithm is divided to obtain multiple preliminary cluster segmentation isovalue models containing unknown parameters; the edges of the directed graph are partitioned to obtain multiple intermediate nodes; the nodes of the directed graph are the abstracted branch nodes and pipe nodes, and the edges of the directed graph are the distances between the branch nodes and pipe nodes. Based on the characteristics of the heating network, the unknown parameters in the preliminary cluster segmented equivalent model are identified to obtain a preliminary cluster segmented equivalent model without unknown parameters. The preliminary cluster segmented equivalent model without unknown parameters is then optimized into a cluster segmented equivalent model. The cluster segmented equivalent model is used to output the predicted temperature data of intermediate nodes. The parameters of the cluster segmented equivalent model include the identified data delay. Based on the identified data delay parameter, the predicted temperature data output by the cluster segmented equivalent model and the collected actual temperature data are selected as feature vectors. A compensation network is constructed to compensate the cluster segmented equivalent model, and the compensation network and the cluster segmented equivalent model are fused to obtain a hybrid semi-mechanism cluster segmented equivalent model. Based on the hybrid semi-mechanism cluster segmented equivalent model, the hybrid state estimate of the key nodes in the intermediate nodes that meet the preset conditions is calculated. Multiple hybrid semi-mechanism cluster segmented equivalent models are cascaded based on the hybrid state estimate of the key nodes to obtain the regional heating network dynamic thermal integration equivalent model. The dynamic thermal integration equivalent model is used to control the heat transfer of the heating network in the region.

2. The method according to claim 1, characterized in that, Based on the partitioning algorithm, the directed graph abstracted from the heating network within the region is partitioned to obtain several preliminary cluster segmentation isometric models containing unknown parameters, including: Node partitioning rules are designed based on the connection relationships between nodes in the heating network, and these rules are then input into the partitioning algorithm. The partitioning algorithm divides the abstracted directed graph into segments based on the node partitioning rules, resulting in a preliminary cluster segmentation equivalent model.

3. The method according to claim 2, characterized in that, The partitioning algorithm partitions the abstracted directed graph based on the node partitioning rules to obtain a preliminary cluster segmentation equivalence model, including: Obtain the pipe input temperature and ambient temperature of the intermediate node obtained by segmenting the nodes of the directed graph. The preliminary cluster segmented equivalent model processes the pipeline input temperature and ambient temperature of the intermediate node to obtain the predicted temperature data of the intermediate node and the predicted temperature change at the next moment.

4. The method according to claim 1, characterized in that, The step of identifying unknown parameters in the preliminary cluster segmentation equivalent model based on the feature identification of the heating network, to obtain a preliminary cluster segmentation equivalent model that does not contain unknown parameters, includes: The number of actual temperature data and intermediate nodes of the heating network obtained by statistics, the penalty value of the intermediate node when the preset penalty condition is met, and the deviation between the predicted temperature data of the terminal pipe node output by the preliminary cluster segmentation equivalent model and the actual temperature data are input into the model parameter identification network. The model parameter identification network processes the number of actual temperature data of the heating network, the number of intermediate nodes, the penalty value of intermediate nodes when they meet preset penalty conditions, and the deviation between the predicted temperature data of the terminal pipe nodes output by the preliminary cluster segmented equivalent model and the actual temperature data, to obtain the parameter values ​​corresponding to the unknown parameters in the preliminary cluster segmented equivalent model, and eliminates the unknown parameters to obtain a preliminary cluster segmented equivalent model that does not contain unknown parameters.

5. The method according to claim 4, characterized in that, The optimization of the preliminary cluster segmentation equivalent model, which does not contain unknown parameters, into a cluster segmentation equivalent model includes: The parameter values ​​output by the model parameter identification network are fixed in the preliminary cluster segmentation equivalent model, and the parameter values ​​are used to replace the unknown parameters in the preliminary cluster segmentation equivalent model, so as to optimize the preliminary cluster segmentation equivalent model into a cluster segmentation equivalent model. The cluster segmentation isometry model is validated using a validation dataset, and then further optimized based on the validation results.

6. The method according to claim 1, characterized in that, The construction of a compensation network to compensate for the cluster segmentation equivalence model, and the fusion of the compensation network and the cluster segmentation equivalence model to obtain a hybrid semi-mechanistic cluster segmentation equivalence model, includes: The compensation network is calculated and transferred based on the scaling factor to obtain the proportional compensation network after transfer processing. The proportional compensation network after migration processing and the predicted temperature data are fused to obtain a hybrid semi-mechanism cluster segmented equivalent model.

7. The method according to claim 1, characterized in that, The mixed state estimates of key nodes meeting preset conditions in the intermediate nodes are calculated based on the mixed semi-mechanism cluster segmented equivalent model. Multiple mixed semi-mechanism cluster segmented equivalent models are cascaded based on the mixed state estimates of the key nodes to obtain a regional heating network dynamic thermal integration equivalent model, including: The dynamic heat transfer characteristics of the key nodes, the connection relationships of the key nodes, and the estimated mixed state values ​​of the key nodes calculated by the hybrid semi-mechanism cluster segmented equivalent model are invoked. Based on the estimated mixed state values ​​of the key nodes, the dynamic heat transfer characteristics, and the connection relationships of the key nodes, a dynamic thermal integration equivalent model of the district heating network is constructed in the form of an equivalent model.

8. A dynamic thermal integration equivalent modeling device for district heating networks, characterized in that, The device includes: The partitioning module is used to partition the directed graph obtained by abstracting the heating network in the target area based on the partitioning algorithm, and obtain multiple preliminary cluster segmentation iso-value models containing unknown parameters; the edges of the directed graph are partitioned to obtain multiple intermediate nodes; the nodes of the directed graph are the abstracted branch nodes and pipe nodes, and the edges of the directed graph are the distances between the branch nodes and pipe nodes. An identification module is used to identify unknown parameters in the preliminary cluster segmented equivalent model based on the characteristics of the heating network, to obtain a preliminary cluster segmented equivalent model without unknown parameters, and to optimize the preliminary cluster segmented equivalent model without unknown parameters into a cluster segmented equivalent model; the cluster segmented equivalent model is used to output the predicted temperature data of intermediate nodes; the parameters of the cluster segmented equivalent model include the identification data delay; The fusion module is used to select the predicted temperature data output by the cluster segmented equivalent model and the collected actual temperature data as feature vectors according to the identified data delay parameters, construct a compensation network to compensate the cluster segmented equivalent model, and fuse the compensation network and the cluster segmented equivalent model to obtain a hybrid semi-mechanism cluster segmented equivalent model. The cascade module is used to calculate the mixed state estimate of the key nodes in the intermediate nodes from the mixed semi-mechanism cluster segmented equivalent model, and to cascade multiple mixed semi-mechanism cluster segmented equivalent models based on the mixed state estimate of the key nodes to obtain a regional heating network dynamic thermal integration equivalent model, so as to control the heat transfer of the heating network in the region.

9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of the dynamic thermal integration equivalent modeling method for a district heating network as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the dynamic thermal integration equivalent modeling method for a district heating network as described in any one of claims 1 to 7.

Images