CN-121997508-A - Heat supply network model optimization method based on heat supply pipeline network topology transformation

CN121997508ACN 121997508 ACN121997508 ACN 121997508ACN-121997508-A

Abstract

The invention relates to the technical field of intelligent modeling of heating pipe networks, and discloses a heating network model optimization method based on heating pipeline network topology transformation. The method comprises the steps of receiving an original operation signal from a monitoring platform, obtaining a heat supply basic data set after reliability screening, describing an actual connection state of a heat supply pipe network by using a topological graph, constructing a basic topological graph, identifying a pipe network framework structure with a master-slave level characteristic, building a heat supply pipe network hydraulic operation simulation model based on the basic topological graph, continuously comparing a model predicted value with an actual measured value in operation, triggering a pipe network structure re-identification instruction when deviation continuously exceeds a threshold value, executing the instruction, dynamically updating the basic topological graph, re-dividing a core and a standby channel, and correcting the hydraulic simulation model by using the updated pipe network framework structure. The invention can automatically identify and adapt to the change of the actual structure of the pipe network, realizes the dynamic self-correction of the model, and improves the accuracy and reliability of the model in long-term operation.

Inventors

LIU XUEMEI
ZHANG HANQING
ZHANG LIJUAN
LI SHICHAO
WANG FENGJUAN
ZHENG YUBAO
CAO SHIQIANG

Assignees

山东诺环建工有限公司

Dates

Publication Date: 20260508
Application Date: 20260120

Claims (10)

1. The heat supply network model optimization method based on heat supply pipeline network topology transformation is characterized by comprising the following steps of: Receiving an original operation signal set from a heat supply system monitoring platform, wherein the original operation signal set comprises time sequence data of a heat source, a heating power station, a pipeline valve and a pressure sensor; Performing reliability screening on the original operation signal set, screening out stable and reliable heat supply operation signals, and removing abnormal signals with data loss or physical contradiction to obtain a heat supply basic data set; Describing the actual connection state of a heat supply pipe network by using a topological graph, wherein a heating station and a key valve are used as graph nodes, and a connecting pipeline is used as a graph edge to construct a basic topological graph of the heat supply pipe network; Identifying a core conveying channel with high influence and a secondary standby branch channel in the basic topological graph, and generating a pipe network framework structure with a master-slave level characteristic; Based on the heat supply basic data set and the pipe network framework structure, establishing a heat supply pipe network hydraulic operation simulation model; Continuously comparing the predicted value of the hydraulic operation simulation model of the heat supply pipe network with the observed value of the heat supply basic data set in the operation process of the heat supply system, and triggering a pipe network structure re-identification instruction when the deviation continuously exceeds a threshold value; executing the pipe network structure re-identification instruction, dynamically updating the basic topological graph, and re-dividing a core conveying channel and a standby branch channel; and correcting the heat supply pipe network hydraulic operation simulation model by using the updated pipe network framework structure to obtain an updated heat supply pipe network hydraulic operation simulation model.
2. The heating network model optimization method based on heating pipeline network topology transformation according to claim 1, wherein the credibility screening comprises: Checking the continuity of each signal in the original running signal set item by item in a preset time window, and marking that an interrupted signal segment exists; Verifying physical logic relation among signals, including verifying rationality of upstream and downstream pressure signals of the same pipe section, rationality of inlet and outlet temperatures of a heating station, and corresponding relation of valve opening and flow; Isolating signals which do not meet the continuity requirement or the physical logic relationship and associated data thereof from the heat supply basic data set to form an abnormal signal set to be checked; And extracting signal combinations with time and space correlation from the to-be-checked abnormal signal set, and providing potential abnormal structural characteristics for subsequent topological transformation.
3. The heating network model optimization method based on the heating pipeline network topology transformation according to claim 2, wherein the constructing the basic topology map of the heating network comprises: establishing an initial logic topology diagram comprising all known heating stations, valves and pipe section connections according to a heating pipe network design drawing and an equipment ledger; Mapping and checking the equipment identification and the position information in the heat supply basic data set one by one with the nodes and edges in the initial logic topological graph, removing the practically abandoned nodes and edges in the drawing, and supplementing the edges which are not recorded in the drawing but have data interaction in practice; and generating a basic topological graph reflecting the real state of the physical connection of the heating network based on the result after verification and supplementation.
4. The method for optimizing a heating network model based on a topology transformation of a heating pipeline network according to claim 1, wherein the generating a pipe network skeleton structure with a master-slave hierarchy characteristic comprises: In the basic topological graph, calculating the accumulated heat load and the average flow carried by each side in a preset history period; According to the accumulated heat load and the average flow, ordering all edges in the basic topological graph in a descending order, and selecting a certain number of edges which are ordered at the front as a candidate set of edges with high influence; analyzing the connection relation of edges in the candidate set of the high-influence edges, and identifying the edge combination which is mutually communicated and has the same conveying direction as a candidate conveying channel; Evaluating the irreplaceability of each candidate conveying channel in the process of conveying and distributing the heating medium, determining the candidate conveying channels with the irreplaceability higher than a specified value as core conveying channels, and classifying the rest candidate conveying channels or non-selected edges as standby branch channels; the core conveying channels and the standby branch channels jointly form the pipe network framework structure, wherein the core conveying channels form a main level, and the standby branch channels form a secondary level.
5. The heating network model optimization method based on the heating pipeline network topology transformation according to claim 4, wherein the building the heating network hydraulic operation simulation model comprises the following steps: Based on the pipe network framework structure, a basic hydraulic equation set for describing flow distribution and pressure distribution in a heating pipe network is established; extracting a plurality of groups of operation data under a history stable working condition from a heat supply basic data set to serve as input and output samples of a basic hydraulic equation set; identifying and calibrating pipe network resistance characteristic coefficients in a basic hydraulic equation set by utilizing the input and output samples; And establishing a basic hydraulic equation set which contains the determined resistance characteristic coefficient after calibration as a heating pipe network hydraulic operation simulation model.
6. The heating network model optimization method based on the heating pipeline network topology transformation according to claim 5, wherein the triggering the pipe network structure re-identification instruction comprises: Acquiring a current observation value of a heat supply basic data set in real time; inputting the key state quantity in the current observation value into a heating pipe network hydraulic operation simulation model to obtain a corresponding model prediction value; calculating point-by-point deviation between the model predicted value and the current observed value on the key state quantity, and carrying out sliding average on the point-by-point deviation in a time window; When the deviation value after the moving average continuously exceeds a preset deviation threshold value and the covered pipe network area exceeds a preset range threshold value, judging that the hydraulic operation simulation model of the heating pipe network is misaligned, and generating a pipe network structure re-identification instruction; the pipe network structure re-identification instruction comprises a pipe network area identifier with deviation overrun, a key state quantity list and a deviation duration.
7. The heating network model optimization method based on heating pipeline network topology transformation of claim 6, wherein dynamically updating the base topology map comprises: Receiving the pipe network structure re-identification instruction, and locking the pipe network area with the deviation overrun contained in the instruction; calling an abnormal signal set to be checked generated in a near term in the pipe network area; analyzing the space-time distribution pattern of the signal combination in the abnormal signal set to be checked, and identifying the signal characteristics possibly indicating the change of the physical connection of the pipe network; modifying or increasing or decreasing the connection relation between the nodes and the edges in the corresponding pipe network area in the basic topological graph based on the signal characteristics to form an update proposal; and verifying the rationality of the updating proposal according to the data of the latest period in the heat supply basic data set, and dynamically updating the basic topological graph after the verification to generate a corrected basic topological graph.
8. The heating network model optimization method based on heating pipeline network topology transformation of claim 7, wherein the repartitioning the core transport path and the backup branch path comprises: re-calculating the current operation index of each side in the graph on the basis of the corrected basic topological graph; According to the recalculated current operation index, sequencing edges, identifying candidate conveying channels and evaluating irreplaceability; and re-determining the core conveying channel and the standby branch channel in the corrected basic topological graph according to the latest evaluation result, and generating an updated pipe network framework structure.
9. The heating network model optimization method based on the heating pipeline network topology transformation according to claim 8, wherein the modifying the heating network hydraulic operation simulation model comprises: Comparing the updated pipe network framework structure with the original pipe network framework structure, and identifying edges and nodes with changes; aiming at the changed edge, in a basic hydraulic equation set of a hydraulic operation simulation model of a heating pipe network, adjusting a corresponding resistance characteristic coefficient or increasing and decreasing a corresponding hydraulic equation; Aiming at the special key nodes which are changed, adding or modifying a boundary condition constraint equation in a heating pipe network hydraulic operation simulation model; and carrying out parameter recalibration on the adjusted heating pipe network hydraulic operation simulation model by utilizing the heating basic data set in the latest period to obtain an updated heating pipe network hydraulic operation simulation model.
10. A heating network model optimization method based on a heating pipeline network topology transformation according to claim 9, characterized in that the method further comprises a verification step of the update procedure: After the updated heating network hydraulic operation simulation model is obtained, new heating system operation observation data are collected in an independent verification time window; Inputting new operation observation data into the updated heating network hydraulic operation simulation model, and calculating the prediction deviation of the model on the new data; if the prediction deviation is lower than a preset verification threshold, confirming that the model update is effective; If the predicted deviation is still higher than the preset verification threshold, triggering a new pipe network structure re-identification instruction, and starting an iterative optimization process until the predicted deviation meets the requirement.

Description

Heat supply network model optimization method based on heat supply pipeline network topology transformation Technical Field The invention relates to the technical field of intelligent modeling of a heating pipe network, in particular to a heating network model optimization method based on heating pipeline network topology transformation. Background Existing heating network simulation models generally rely on design drawings or one-time mapping to construct static pipe network topologies. The model fixes the connection relation between the elements such as the heating power station, the valve and the pipeline, and performs hydraulic and thermal calculation based on the connection relation. After the model is put into operation, even if the actual observed data and the model predicted value have significant deviation, the conventional optimization means is limited to adjusting parameters such as resistance coefficient of the pipeline, heat source output and the like, and the physical connection and the functional hierarchy structure of the network are regarded as the premise of no change. This static model approach has inherent drawbacks. In actual operation of the heat supply network, the effective conveying path and the function primary-secondary relationship of the heat supply network can be changed due to valve state switching, pipeline transformation, user access condition change and the like. The static model cannot sense the actual change of the topology level, so that the model and a physical system are gradually mismatched, and the simulation prediction deviation is increased. When the deviation occurs, the prior art lacks a mechanism for automatically judging whether the deviation is caused by the change of the underlying network structure, and the basic topology and the function cognition of the model cannot be dynamically reconstructed in operation, so that the simulation model is difficult to accurately service the scheduling decision for a long time. A method is needed that enables a heating network model to have self-diagnostic and structural update capabilities. The key is how to define the criterion of model misalignment and automatically trigger reconstruction, and how to re-identify the real connection state and the core hydraulic path of the network according to the actual operation data during reconstruction, thereby breaking the limitation of a static model and realizing the synchronization of the dynamic evolution of the model and a physical pipe network. Disclosure of Invention The invention aims to provide a heating network model optimization method based on heating pipeline network topology transformation, so as to solve the problems in the background technology. To achieve the above object, the present invention provides a heating network model optimization method based on a heating pipeline network topology transformation, the method comprising: Receiving an original operation signal set from a heat supply system monitoring platform, wherein the original operation signal set comprises time sequence data of a heat source, a heating power station, a pipeline valve and a pressure sensor; Performing reliability screening on the original operation signal set, screening out stable and reliable heat supply operation signals, and removing abnormal signals with data loss or physical contradiction to obtain a heat supply basic data set; Describing the actual connection state of a heat supply pipe network by using a topological graph, wherein a heating station and a key valve are used as graph nodes, and a connecting pipeline is used as a graph edge to construct a basic topological graph of the heat supply pipe network; Identifying a core conveying channel with high influence and a secondary standby branch channel in the basic topological graph, and generating a pipe network framework structure with a master-slave level characteristic; Based on the heat supply basic data set and the pipe network framework structure, establishing a heat supply pipe network hydraulic operation simulation model; Continuously comparing the predicted value of the hydraulic operation simulation model of the heat supply pipe network with the observed value of the heat supply basic data set in the operation process of the heat supply system, and triggering a pipe network structure re-identification instruction when the deviation continuously exceeds a threshold value; executing the pipe network structure re-identification instruction, dynamically updating the basic topological graph, and re-dividing a core conveying channel and a standby branch channel; and correcting the heat supply pipe network hydraulic operation simulation model by using the updated pipe network framework structure to obtain an updated heat supply pipe network hydraulic operation simulation model. Preferably, the credibility screening includes: Checking the continuity of each signal in the original running signal set item by item in a preset time