Intelligent hydraulic equilibrium method, equipment, medium and product for branch lines of heat supply secondary network

Abstract

The invention relates to the technical field of heat supply control, in particular to a heat supply secondary network branch line intelligent hydraulic equilibrium method and device, a medium and a product. The method comprises the following steps: constructing a branch topological graph of a heat supply secondary network in a target heat supply area; the environment temperature is obtained in real time, the heat supply station is controlled to supply heat to each heating single body in the target heat supply area based on the dynamic flow control strategy, and the node flow and the node temperature of each node in the branch topological graph are collected; constructing a branch heat supply loss model of the branch topological graph based on the environment temperature, the node flow and the node temperature; the monomer temperature and heat supply backflow data of each heating monomer are obtained, and a monomer heating model is constructed for each heating monomer based on the environment temperature, the monomer temperature and the heat supply backflow data; and determining a flow regulation and control strategy based on the monomer heating model and the branch line heat supply loss model, and adjusting the monomer heat supply flow of the heat supply secondary network based on the flow regulation and control strategy. According to the method, heat supply hydraulic balance can be achieved through precise flow regulation and control precision.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of heat supply control, in particular to a heat supply secondary network branch line intelligent water balance method, device, medium and product. BACKGROUND

[0002] In a central heating system, the heat supply secondary network is a key link connecting the heat supply station and the terminal user, and whether the water balance of the heat supply secondary network is balanced directly affects the heating quality and energy utilization efficiency. If the water balance is unbalanced, the room temperature of the near-end user will be too high, causing energy waste, and the room temperature of the far-end user will be insufficient, affecting the heating experience. Therefore, it is of great significance to carry out heat balance control to improve the stability of heat supply and reduce energy consumption.

[0003] The related art generally uses static water balance valves, manual adjustment based on experience, or simple temperature difference feedback control to adjust the flow of the heat supply secondary network. However, these methods have the technical defect of being unable to dynamically adapt to changes in environmental temperature, fluctuations in user heat demand, and differences in pipe network topology characteristics, resulting in insufficient control accuracy and failing to achieve truly intelligent and accurate water balance. SUMMARY

[0004] To solve the problem of insufficient flow control accuracy in the prior art, which makes it difficult to achieve heat supply water balance, the present application provides a heat supply secondary network branch line intelligent water balance method, device, medium and product.

[0005] In a first aspect, the present application provides a heat supply secondary network branch line intelligent water balance method, which adopts the following technical solution: A heat supply secondary network branch line intelligent water balance method, comprising: constructing a branch line topology graph of the heat supply secondary network in a target heating area; wherein the nodes in the branch line topology graph represent heating units or three-way pipe connection points, and the edges represent heat supply pipes; real-time acquisition of environmental temperature, control of the heat supply station to supply heat to each heating unit in the target heating area based on a dynamic flow control strategy, and collection of node flow and node temperature of each node in the branch line topology graph; constructing a branch line heat loss model of the branch line topology graph based on the environmental temperature, the node flow and the node temperature; acquisition of unit temperature and heat supply return data of each heating unit, and construction of a unit heat receiving model for each heating unit based on the environmental temperature, the unit temperature and the heat supply return data; determination of a flow control strategy based on the unit heat receiving model and the branch line heat loss model, and adjustment of the unit heat supply flow of the heat supply secondary network based on the flow control strategy.

[0006] By adopting the technical scheme, the branch line topology graph of the secondary heating network in the target heating area is constructed, a clear pipe network structure basis is provided for subsequent flow and temperature regulation, the node and pipe relationship of the entire heating system is visualized, accurate positioning and management are facilitated, the environment temperature is acquired in real time, the heating station is controlled to heat according to a dynamic strategy, the node flow and temperature are collected, the current system operation state and external environment influence are grasped in time, real-time and accurate data support is provided for model construction, the branch line heating loss model is constructed based on the environment temperature, node flow and temperature, the heat loss in the pipe network can be accurately calculated, and the heat loss law in the transmission process is clear; the monomer heating model is constructed for the heating monomer in combination with the environment temperature, monomer temperature and heating backflow data, the heating characteristics and temperature change law of each heating monomer can be grasped, and the regulation is more in line with the actual demand of the monomer; the flow regulation strategy is determined based on the above two models, and the monomer heating flow is adjusted, on-demand heating is realized, the temperature of each heating monomer can be ensured to reach the standard, and energy waste can be avoided, and the hydraulic balance and heating efficiency of the secondary heating network are effectively improved.

[0007] In a preferred example, the application can be further configured to: constructing, based on the environment temperature, the node flow and the node temperature, a branch line heating loss model of the branch line topology graph, comprising: determining a pipe inlet temperature and a pipe outlet temperature of a target pipe section based on the node temperature, and calculating a difference between the pipe inlet temperature and the pipe outlet temperature as a heat loss temperature difference of the target pipe section; wherein the target pipe section is a pipe section between any two nodes in the branch line topology graph; retrieving pipe attribute information of the target pipe section from the branch line topology graph; constructing a branch line heating loss model based on the environment temperature, the pipe attribute information of each pipe section, the node flow, the pipe inlet temperature and the heat loss temperature difference.

[0008] By adopting the technical scheme, the pipe inlet and outlet temperatures are determined based on the node temperature, and the heat loss temperature difference is calculated, the heat loss degree of a single pipe section can be directly quantified; the attribute information of the target pipe section is retrieved from the branch line topology graph, the pipe itself characteristics (such as material, pipe diameter, etc.) can be included in the heat loss analysis, and the model is more in line with the actual pipe network situation; the branch line heating loss model is constructed based on the environment temperature, pipe attribute, node flow and other multi-dimensional data, various influencing factors can be comprehensively considered, the heat loss law output by the model is more accurate, a reliable heat loss basis is provided for subsequent flow regulation strategy formulation, and help is provided for reducing invalid heating loss.

[0009] The application can be further configured in a preferred example as follows: the monomer heating model is constructed for each heating monomer based on the ambient temperature, the monomer temperature and the heat supply return data, including: determining the water supply temperature and the monomer flow rate from the heat supply return data of the target heating monomer; determining the average ambient temperature, the average water supply temperature and the average monomer flow rate in each preset heat supply period based on the ambient temperature, the water supply temperature and the monomer flow rate, and determining the monomer temperature initial value and the monomer temperature change value in each preset heat supply period based on the monomer temperature; training the monomer heating model of the target heating monomer based on the average ambient temperature, the average water supply temperature, the average monomer flow rate, the monomer temperature initial value and the monomer temperature change value in each preset heat supply period, and the monomer heating model is used to output the monomer temperature change value.

[0010] By adopting the above technical solution, the water supply temperature and the monomer flow rate are determined from the heat supply return data, which provides basic heat supply parameters for the monomer heating model and ensures the accuracy of the core data input into the model; the average parameters, the temperature initial value and the change value are calculated in the preset heat supply period, which can filter short-term data fluctuations, reflect the periodic heat supply and temperature change rule, and improve the stability and representativeness of the data; the model is trained based on these periodic data, which can accurately capture the correlation between the environment, the heat supply parameters and the monomer temperature change, so that the output temperature change value is more reliable, and a scientific basis is provided for subsequent targeted regulation of the heating monomer temperature.

[0011] The application can be further configured in a preferred example as follows: the flow regulation strategy is determined based on the monomer heating model and the branch heat supply loss model, including: obtaining a target heat supply temperature, and determining a heating monomer to be regulated based on the target heat supply temperature and the monomer temperature of each heating monomer in the target heat supply area; determining the monomer flow rate from the heat supply return data of the heating monomer to be regulated, and generating a plurality of initial flow regulation strategies based on the monomer flow rate of the heating monomer to be regulated; sequentially simulating the execution of each initial flow regulation strategy based on the branch heat supply loss model and the monomer heating model, and determining the estimated monomer temperature change value of the heating monomer to be regulated under each initial flow regulation strategy; the initial flow regulation strategy corresponding to the estimated monomer temperature change value meeting the target heat supply temperature is taken as the flow regulation strategy.

[0012] By adopting the technical scheme, the heating monomer to be regulated is determined according to the target and actual monomer temperature, the object to be adjusted can be accurately locked, and meaningless regulation is avoided; a plurality of initial strategies are generated based on the monomer flow of the monomer to be regulated, sufficient choices are provided for subsequent screening of the optimal scheme; the initial strategy is simulated and executed by the two models, and the temperature change is predicted, the effects of different strategies can be known in advance, and the actual regulation risk is reduced; the strategy meeting the target temperature is selected as the final scheme, the heating monomer temperature after regulation can be guaranteed to meet the standard, and precise and efficient heat supply regulation is realized.

[0013] In a preferred example, the application can be further configured to: sequentially simulate the execution of each initial flow regulation strategy based on the branch heat loss model and the monomer heating model, and determine the estimated monomer temperature change value of the heating monomer to be regulated under each initial flow regulation strategy, comprising: Obtain the heat supply basic data of the heat supply station, and collect the current environment temperature and the current monomer temperature in real time; Substitute the heat supply basic data into the branch heat loss model, and based on the node flow at each node in the branch heat loss model determined under the current environment temperature and the current initial flow regulation strategy, estimate the estimated node temperature of each node in the branch topology graph; Take the estimated node temperature of the node connected with the heating monomer to be regulated in the branch topology graph as the estimated water supply temperature of the heating monomer to be regulated, and take the node flow of the node connected with the heating monomer to be regulated as the estimated monomer flow of the heating monomer to be regulated; Substitute the current environment temperature, the current monomer temperature, the estimated monomer flow and the estimated water supply temperature into the monomer heating model of the heating monomer to be regulated, to obtain the estimated monomer temperature change value of the heating monomer to be regulated in the preset heat supply period output by the monomer heating model; Determine the estimated target monomer temperature based on the current monomer temperature and the estimated monomer temperature change value, if the estimated target monomer temperature is not less than the target heat supply temperature, it is determined that the estimated monomer temperature change value of the current initial flow regulation strategy meets the target heat supply temperature.

[0014] By adopting the technical scheme, the basic data of the heat supply station and real-time environment and monomer temperature are obtained, comprehensive and real-time basic parameters are provided for simulation calculation, and the accuracy of the simulation starting point is ensured; the basic data is substituted into the branch heat supply loss model to estimate the node temperature, the temperature change in heat transmission can be accurately calculated in combination with the characteristics of the pipe network and the current strategy, reliable front-end data is provided for subsequent monomer heat supply analysis, the estimated water supply temperature and flow of the heating monomer to be controlled are determined, the accurate association of the pipe network data and monomer heat supply is realized, and the monomer analysis is more in line with the actual heat supply condition; the estimated temperature change value is obtained by substituting the monomer heat supply model, and it is determined whether the standard is reached, the monomer temperature effect under different strategies can be accurately predicted, a scientific basis is provided for screening effective strategies, and the blindness of actual regulation and control is reduced.

[0015] In a preferred example, the application can be further configured as follows: The monomer heat supply flow, the target heat supply temperature of the target heating monomer adjusted based on the flow regulation strategy, and the unit heating data of the target heating monomer are obtained; wherein the unit heating data includes the actual unit temperature and the unit flow; The monomer heat supply flow, the target heat supply temperature, and the unit heating data are input into a pre-trained unit flow regulation model, and the unit flow of each heating unit in the target heating monomer is adjusted based on the output of the unit flow regulation model.

[0016] By adopting the technical scheme, the relevant data after the flow regulation strategy is adjusted are obtained, including the monomer heat supply flow, the target heat supply temperature, and the unit heating data, which provides a comprehensive and actual basis for the accurate regulation of the unit flow; the data are input into the pre-trained unit flow regulation model, and the flow of each heating unit is adjusted accordingly, which can make the regulation more in line with the actual heating demand of each unit, effectively improve the temperature uniformity of each unit in the monomer, and further improve the accuracy and energy saving of heat supply.

[0017] In a preferred example, the application can be further configured as follows: each heating monomer includes a plurality of heating units; and the training process of the unit flow regulation model includes: Initializing a model network; Defining a constraint condition based on the monomer heat supply flow; wherein the constraint condition is that the sum of the unit flows of all heating units in the target heating monomer is equal to the monomer heat supply flow; Defining a reward function and a target function; wherein the optimization target of the target function includes: unit temperature compliance rate, system energy consumption, unit temperature uniformity, and regulation action frequency; Obtaining training sample data, and performing model training based on the training sample data, the model network, the constraint condition, the reward function, and the target function to obtain the unit flow regulation model.

[0018] By adopting the technical solution, the initialization model network builds a basic framework for the unit flow regulation model, ensuring the model has the ability to learn and operate; based on the definition of constraints of single heating flow, it can ensure that each heating unit flow is reasonably allocated, avoiding the imbalance of total flow affecting the overall heating; the definition of reward function and objective function containing multiple optimization objectives can guide the model to optimize in the direction of temperature compliance, energy saving, temperature uniformity and reducing regulation frequency; training the model with training sample data combined with the above elements can enable the model to master the correlation between flow and temperature, etc., and the final obtained model can output a scientific unit flow regulation scheme, improving the heating effect and efficiency.

[0019] In a second aspect, the present application provides an electronic device, which adopts the following technical solution: one or more processors; a memory; at least one application program, wherein the at least one application program is stored in the memory and is configured to be executed by the at least one processor, and the at least one application program is configured to execute the heating secondary network branch intelligent water balance method according to any one of the first aspect.

[0020] In a third aspect, the present application provides a computer readable storage medium, which adopts the following technical solution: A computer readable storage medium having a computer program stored thereon, when the computer program is executed in a computer, the computer is caused to execute the heating secondary network branch intelligent water balance method according to any one of the first aspect.

[0021] In a fourth aspect, the present application provides a computer program product, which adopts the following technical solution: A computer program product comprising a computer program, when the computer program is executed by a processor, the heating secondary network branch intelligent water balance method according to any one of the first aspect is realized.

[0022] In summary, the present application has the following beneficial technical effects: The application constructs a branch topology graph of the secondary heating network in the target heating area, provides a clear pipe network structure basis for subsequent flow and temperature regulation, visualizes the node and pipe relationship of the entire heating system, and facilitates accurate positioning and management; the environment temperature is acquired in real time, the heating station is controlled to heat according to a dynamic strategy, the node flow and temperature are collected, the current running state of the system and the external environment influence are grasped in time, real-time and accurate data support is provided for model construction; the branch heating loss model is constructed based on the environment temperature, the node flow and the temperature, the heat loss in the pipe network can be accurately calculated, and the loss law of heat in the transmission process is clear; the monomer heating model is constructed for the heating monomer in combination with the environment temperature, the monomer temperature and the heating backflow data, the heating characteristics and the temperature change law of each heating monomer can be grasped, and the regulation is more in line with the actual demand of the monomer; the flow regulation strategy is determined based on the above two models, and the monomer heating flow is adjusted, on-demand heating is realized, the temperature of each heating monomer can be ensured to reach the standard, and energy waste can be avoided, and the hydraulic balance and the heating efficiency of the secondary heating network are effectively improved. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 is a flow schematic diagram of a kind of intelligent hydraulic balance method of secondary heating network branch provided by the embodiment of the application; Figure 2 is a structure schematic diagram of an electronic device provided by the embodiment of the application. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings of the embodiment of the application Figure 1 to the drawings of the embodiment of the application Figure 2 The application will be further described in detail.

[0025] The specific embodiment is only the explanation of the application, and it is not the limitation of the application, the person skilled in the art can make the modification of the embodiment without the contribution of creativity after reading the present application, but as long as in the scope of the claims of the application, it is protected by the patent law.

[0026] In order to make the purpose, technical scheme and advantages of the embodiment of the application more clear, the technical scheme in the embodiment of the application will be described clearly and completely in the following with the drawings of the embodiment of the application, obviously, the described embodiment is a part of the embodiment of the application, not all the embodiments. Based on the embodiment in the present application, all other embodiments obtained by the person skilled in the art without making creative labor are within the scope of protection of the present application.

[0027] In addition, the term "and / or" in this document is only used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects unless otherwise specified.

[0028] It should be noted that in the optional embodiments of the present application, the object information and other related data involved in the embodiments of the present application when applied to specific products or technologies need to obtain the permission or consent of the object, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of the country and region. That is, if the embodiments of the present application involve data related to the object, the data needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant department, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the consent of the individual is required for obtaining all personal information, and the separate consent of the information subject is required for sensitive information. The embodiments also need to be implemented with the authorization and consent of the object.

[0029] The embodiments of the present application provide a heat supply secondary network branch line intelligent water force balancing method, as shown in Figure 1 The method provided in the embodiments of the present application is executed by an electronic device, which can be a server or a terminal device. The server can be a physical server, a server cluster composed of multiple physical servers, or a distributed system, and can also be a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be connected directly or indirectly through wired or wireless communication, which is not limited in the embodiments of the present application. The method includes steps S101-S105, wherein: S101, constructing a branch line topology graph of the heat supply secondary network in a target heat supply area; wherein the nodes in the branch line topology graph represent heating monomers or three-way pipe connection points, and the edges represent heat supply pipes.

[0030] Specifically, the target heat supply area can be a school, a community, a hospital, etc. The heating monomer represents an independent building in the target heat supply area. The pipe distribution, heating monomer position and pipe connection relationship of the target heat supply area are obtained by calling the BIM model, and the heating monomers and three-way pipe connection points are abstracted as nodes and the heat supply pipes are abstracted as edges. The visualization branch line topology graph is generated by using a graph theory modeling tool, and the pipe diameter, length, material and other attribute information of each pipe and the identification information of each node are associated in the graph.

[0031] S102, real-time acquisition of ambient temperature, control of the heating station to supply heat to each heating unit in the target heating area based on a dynamic flow control strategy, collection of node flow and node temperature of each node in the branch line topology.

[0032] Specifically, the ambient temperature is acquired in real time by meteorological data published by a meteorological monitoring station or an ambient temperature monitoring station arranged in the target heating area. Flow sensors and temperature sensors are installed at each node (including heating unit inlets, tee junctions, etc.) of the heating secondary network to collect node flow and node temperature data in real time. The heating station starts heating according to a preset dynamic flow control strategy and receives real-time data returned by the sensors.

[0033] The dynamic flow control strategy can be determined according to historical heating data. Any heating unit in the target heating area is taken as a target heating unit, and historical heating data of the target heating unit or a heating unit with a similar structure to the target heating unit is acquired. The historical heating data includes inlet flow data delivered into the heating unit, and a plurality of unit flows are extracted from the inlet flow data as initial unit flows of the target heating unit. The initial unit flows of each heating unit in the target heating area are randomly combined to obtain a plurality of flow control strategies (i.e., dynamic flow control strategies).

[0034] For each flow control strategy, based on the unit flow corresponding to the flow control strategy and the attribute information of the heating pipeline contained in the branch line topology, the time difference from the start of heating at the heating station to the successful heating of each heating unit by the heat medium (water) (indicative of the flow of the heat medium through all the pipelines in the heating unit and the continuous heating for a preset period of time to stabilize the heating) is calculated. The obtained time difference is taken as the execution duration of the corresponding flow control strategy. When the execution duration of any flow control strategy reaches, the next flow control strategy is switched, and the node flow and node temperature of each node in the branch line topology under each flow control strategy are recorded. The ambient temperature, node flow and node temperature are all time series data that change with time.

[0035] S103, construction of a branch heating loss model of the branch line topology based on the ambient temperature, node flow and node temperature.

[0036] Specifically, a pipeline segment between any two nodes in the straight line topology is taken as a target pipeline segment, the pipeline inlet temperature and the pipeline outlet temperature of the target pipeline segment are determined according to the temperature data of the two end nodes of the target pipeline segment, and the difference between the two is calculated as the heat loss temperature difference.

[0037] The pipe diameter, length, insulation thickness and other pipe attribute information of the target pipe section are extracted from the branch line topology, the pipe sections are classified by pipe structure attributes (same pipe diameter, same material, same insulation standard), for each level, the branch line heat loss model of the level is constructed by combining the ambient temperature, the pipe attribute information of the pipe sections in the level, the node flow, the import temperature and the heat loss temperature difference, so as to quantify the heat loss in the pipe transmission process and the relationship between parameters.

[0038] In S104, the monomer temperature and heat supply return data of each heating monomer are acquired, and a monomer heating model is constructed for each heating monomer based on the ambient temperature, the monomer temperature and the heat supply return data.

[0039] Specifically, any heating monomer in the target heating area is taken as a target heating monomer, the heat supply return data of the target heating monomer includes the water supply temperature and the monomer flow, there is a node connected to the target heating monomer in the branch line topology, the node temperature at the node is collected as the water supply temperature of the target heating monomer, and the node flow at the node is collected as the monomer flow of the target heating monomer.

[0040] The preset heat supply period is set according to the actual demand in advance, and the preset heat supply period represents the desired time length for the monomer temperature of the heating monomer to reach the target heat supply temperature when adjusting the node flow in the branch line topology so that the monomer temperature of the heating monomer meets the target heat supply temperature.

[0041] Because different heating monomers have different structures, the same monomer heating model can be constructed for the heating monomers with the same structure, and the monomer heating models are constructed for the heating monomers with different structures. Taking the target heating monomer as an example, the process of constructing the monomer heating loss model for the target heating monomer includes: based on the preset heat supply period, dividing the period, in each preset heat supply period, the average value of the ambient temperature is calculated to obtain the average ambient temperature, the average value of the water supply temperature of the target heating monomer is calculated to obtain the average water supply temperature, the average value of the monomer flow of the target heating monomer is calculated to obtain the average monomer flow, the monomer temperature of the target heating monomer is real-time collected data, the monomer temperature at the starting time of the current preset heat supply period is determined as the initial value of the monomer temperature, and the monomer temperature difference between the starting time and the ending time of the current preset heat supply period is calculated as the monomer temperature change value.

[0042] The obtained average ambient temperature, average water supply temperature, average monomer flow, monomer temperature initial value and monomer temperature change value of each preset heating period are taken as one piece of data, and a plurality of pieces of data of the target heating monomer (including a heating monomer with the same structure as the target heating monomer) are acquired for model training. The model can use regression analysis or machine learning algorithms (such as linear regression, random forest, etc.). The average ambient temperature, average water supply temperature, average monomer flow and monomer temperature initial value are taken as model inputs, and the monomer temperature change value is taken as model output. The monomer heating model of the target heating monomer is trained to reflect the correlation between the monomer temperature change and the influencing factors.

[0043] In S105, a flow regulation strategy is determined based on the monomer heating model and the branch heat loss model, and the monomer heating flow of the secondary heating network is adjusted based on the flow regulation strategy.

[0044] Specifically, after the monomer heating model and the branch heat loss model are trained, the flow of each node remains unchanged in the current state, and enters the flow regulation phase. The target heating temperature is set, such as the temperature of a residential building being 20-24℃. Based on the target heating temperature and the monomer temperature of each heating monomer in the target heating area, the heating monomers to be regulated are determined. The monomer flow is determined from the heating return data of the heating monomers to be regulated, and a plurality of initial flow regulation strategies (such as different flow increase / decrease amplitude schemes) are generated based on the monomer flow of the heating monomers to be regulated. Based on the branch heat loss model and the monomer heating model, each initial flow regulation strategy is simulated and executed in turn to determine the estimated monomer temperature change value of the heating monomers to be regulated under each initial flow regulation strategy. The initial flow regulation strategy corresponding to the estimated monomer temperature change value meeting the target heating temperature is taken as the flow regulation strategy.

[0045] In this embodiment, the branch topology graph of the secondary heating network in the target heating area is constructed, providing a clear pipe network structure basis for subsequent flow and temperature regulation, visualizing the node and pipe relationship of the entire heating system, and facilitating accurate positioning and management. The ambient temperature is acquired in real time, and the heating station is controlled to heat according to the dynamic strategy, while the node flow and temperature are collected, enabling the current system operation state and external environmental influence to be grasped in time, and providing real-time and accurate data support for model construction. The branch heat loss model is constructed based on the ambient temperature, node flow and temperature, enabling the heat loss in the pipe network to be accurately calculated, and the heat loss law in the transmission process to be determined. The monomer heating model is constructed for the heating monomer based on the ambient temperature, monomer temperature and heating return data, enabling the heating characteristics and temperature change law of each heating monomer to be grasped, and the regulation to be more in line with the actual needs of the monomer. The flow regulation strategy is determined based on the above two models, and the monomer heating flow is adjusted, realizing on-demand heating, ensuring that the temperature of each heating monomer meets the standard, and avoiding energy waste, thereby effectively improving the hydraulic balance and heating efficiency of the secondary heating network.

[0046] In a possible implementation of the embodiment of the application, a branch heat supply loss model of a branch topology graph is constructed based on an ambient temperature, a node flow and a node temperature, and includes the following steps: A pipe inlet temperature and a pipe outlet temperature of the target pipe section are determined based on the node temperature, and a difference between the pipe inlet temperature and the pipe outlet temperature is calculated as a heat loss temperature difference of the target pipe section; the target pipe section is a pipe section between any two nodes in the branch topology graph; Pipe attribute information of the target pipe section is called from the branch topology graph; The branch heat supply loss model is constructed based on the ambient temperature, the pipe attribute information of each pipe section, the node flow, the pipe inlet temperature and the heat loss temperature difference.

[0047] In the embodiment, the direction of two adjacent nodes in the branch topology graph is consistent with the direction of the heat medium flow. For a target pipe section formed by any two adjacent nodes (the direction of the heat medium flow is from node A to node B) in the branch topology graph, a temperature value of node A is extracted from the real-time collected node temperature data as the inlet temperature of the target pipe section, and a temperature value of node B is extracted from the real-time collected node temperature data as the outlet temperature of the target pipe section. The node flow at node A is determined, and the transmission time of the heat medium from node A to node B is estimated based on the node flow QA (m³ / h) of node A and the pipe structure attribute (including the length L and the pipe diameter of the target pipe section) of the target pipe section, including: the pipe cross-sectional area S is calculated in combination with the pipe diameter of the target pipe section, the flow velocity v (unit: m / s) of the heat medium in the target pipe section is calculated through the formula v=QA / (3600×S), and then the transmission time Δt=L / v (unit: seconds) of the heat medium from node A to node B is obtained.

[0048] The node temperature data sequence of node A and the node temperature data sequence of node B are called, and the node temperature data sequence includes a collection time stamp corresponding to each temperature value. Taking node A as an example: TA(t1), TA(t2), TA(t3)..., t1, t2, t3, etc. are specific collection time points. For the temperature value TB(t) of node B collected at time t, the temperature value TA(t-Δt) of node A collected at time t-Δt is found, and the two temperature values are paired and regarded as the temperature of the same flow of heat medium flowing through node A and node B. If the temperature sampling is periodic sampling and the transmission time is not an integer multiple of the sampling period, a linear interpolation method is used to supplement the temperature value at the intermediate time. The aligned node temperature data sequence of node A and the node temperature data sequence of node B are calculated to obtain the temperature difference as the heat loss temperature difference. The time stamp corresponding to any heat loss temperature difference can be selected from the node temperature time stamp of node A, the node temperature time stamp of node B or the median of the node temperature time stamps of node A and node B, which is not limited in the embodiment.

[0049] In constructing the branch topology, complete pipe information has been associated with each edge (each pipe section), including pipe structure attributes (pipe diameter, pipe material, pipe insulation structure) and a unique identification ID. All pipe sections are clustered and grouped according to pipe structure attributes, and each group constitutes a level. The pipe sections in the same level have consistent pipe structure attributes.

[0050] For model training, the training data set can be historical heating data in the historical period, or heating data collected after the current heating process starts. For heating data collected in the current heating process, in order to avoid too large data errors caused by too low pipe temperature at the beginning of heating, the training set data collection period can be set according to actual experience, such as collecting data for training after a period of time after starting heating to ensure stable heating. This time period can be set by technical personnel according to actual experience, and can also be estimated according to the flow and the pipe diameter and length, which is not limited in the embodiment.

[0051] After the collection time period of the model training set is delineated, in the time period, any level is taken as a target level, the target level includes a target pipe section, any collection time of the node temperature of node A is taken as a starting time of the time period, and the transmission time length of the heat medium from node A to node B is taken as a termination time of the time period, so as to obtain a time period composed of the starting time and the termination time. The environmental temperature in the time period (the average value of the environmental temperature in the time period), the node flow (the average value of the node flow at node A and node B in the time period), the pipe inlet temperature (the node temperature of node A at the starting time of the time period), and the heat loss temperature difference (the node temperature of node A at the starting time of the time period and the node temperature of node B at the termination time of the time period) are collected as a piece of data.

[0052] The data of each pipe section contained in the target level in the branch topology is summarized as the training set of the target level, and the corresponding branch heat loss model is trained for the target level. All pipe sections in the branch topology can also be summarized to train the overall branch heat loss model corresponding to the branch topology, which is not limited in the embodiment. Among them, the pipe attribute information, the node flow, and the pipe inlet temperature are used as the model input, and the heat loss temperature difference is used as the model output for model training.

[0053] The embodiment determines the pipe inlet and outlet temperatures based on the node temperature and calculates the heat loss temperature difference, can directly quantify the heat loss degree of a single pipe section; the attribute information of the target pipe section is called from the branch line topology diagram, the characteristics of the pipe itself (such as material, pipe diameter, etc.) can be brought into the heat loss analysis, so that the model is more in line with the actual pipe network situation; the branch line heat supply loss model is constructed based on the environmental temperature, pipe attribute, node flow and other multi-dimensional data, which can comprehensively consider various influencing factors, so that the heat loss law output by the model is more accurate, and reliable heat loss basis is provided for subsequent flow regulation strategy making, and help to reduce invalid heat supply loss.

[0054] In a possible implementation of the embodiment of the present application, a monomer heating model is constructed for each heating monomer based on the environmental temperature, monomer temperature and heat supply backflow data, including: determining the water supply temperature and the monomer flow from the heat supply backflow data of the target heating monomer; determining the average environmental temperature, the average water supply temperature and the average monomer flow in each preset heat supply period based on the environmental temperature, the water supply temperature and the monomer flow, and determining the monomer temperature initial value and the monomer temperature change value in each preset heat supply period based on the monomer temperature; training the monomer heating model of the target heating monomer based on the average environmental temperature, the average water supply temperature, the average monomer flow, the monomer temperature initial value and the monomer temperature change value in each preset heat supply period, and the monomer heating model is used to output the monomer temperature change value.

[0055] The embodiment determines the water supply temperature and the monomer flow from the heat supply backflow data, provides basic heat supply parameters for the monomer heating model, and ensures the accuracy of the core data input by the model; the average parameters, temperature initial value and change value are calculated in each preset heat supply period, which can filter short-term data fluctuations, reflect the periodic heat supply and temperature change law, and improve the stability and representativeness of the data; the model is trained based on these periodic data, which can accurately capture the correlation between the environment, heat supply parameters and monomer temperature change, so that the output temperature change value is more reliable, and provides a scientific basis for subsequent targeted regulation of the heating monomer temperature.

[0056] In a possible implementation of the embodiment of the present application, a flow regulation strategy is determined based on the monomer heating model and the branch line heat supply loss model, including: obtaining a target heat supply temperature, and determining a heating monomer to be regulated based on the target heat supply temperature and the monomer temperature of each heating monomer in a target heat supply area; determining the monomer flow from the heat supply backflow data of the heating monomer to be regulated, and generating a plurality of initial flow regulation strategies based on the monomer flow of the heating monomer to be regulated; sequentially simulating the execution of each initial flow regulation strategy based on the branch line heat supply loss model and the monomer heating model, and determining the estimated monomer temperature change value of the heating monomer to be regulated under each initial flow regulation strategy; The initial flow regulation strategy satisfying the target heating temperature corresponding to the estimated monomer temperature change value is taken as the flow regulation strategy.

[0057] In this embodiment, the target heating temperature can be set according to the heating standard of the target heating area, and can also be dynamically adjusted in combination with the time period. The target heating temperature is a temperature range. The monomer temperature of the target heating monomer is the average temperature collected by the temperature sensor distributed in different regions of the monomer. Comparing the target heating temperature and the monomer temperature of the target heating monomer, if the monomer temperature of each heating monomer reaches the target heating temperature (within the range of the target heating temperature), the flow of the branch topology graph is not adjusted; if the monomer temperature of the heating monomer does not reach the target heating temperature (lower than the lower limit of the target heating temperature or higher than the upper limit of the target heating temperature), the heating monomer that does not meet the target heating temperature is taken as a to-be-regulated heating monomer, and the flow of the branch topology graph is adjusted.

[0058] Specifically, the number of to-be-regulated heating monomers can be one or more. The to-be-regulated heating monomer with a monomer temperature lower than the lower limit of the target heating temperature is determined as an under-temperature heating monomer, and the to-be-regulated heating monomer with a monomer temperature higher than the upper limit of the target heating temperature is determined as an over-temperature heating monomer.

[0059] The current monomer flow is obtained from the heating return flow data of the to-be-regulated heating monomer, and the pipe network complete operation constraint (such as the first preset proportion of the minimum flow not lower than the design flow, and the second preset proportion of the maximum flow not exceeding the design flow) is called. For the under-temperature heating monomer, the range between the current monomer flow and the maximum flow is determined as the flow adjustment interval; for the over-temperature heating monomer, the range between the minimum flow and the current monomer flow is determined as the flow adjustment interval. Then, a plurality of flow intermediate values are generated in the flow adjustment interval at a fixed step. The fixed step can be set according to experience, which is not limited in the embodiment.

[0060] If the number of to-be-regulated heating monomers is one, each flow intermediate value of the to-be-regulated heating monomer is taken as an initial flow regulation strategy.

[0061] If the number of to-be-regulated heating monomers is greater than one, one is selected from the flow intermediate values corresponding to each to-be-regulated heating monomer, and the selected flow intermediate values are combined. Each combination constitutes an initial flow regulation strategy. For example, if there are 3 to-be-regulated heating monomers, and each to-be-regulated heating monomer corresponds to 2 flow intermediate values, according to the permutation and combination principle, the number of initial flow regulation strategies that can be determined is 2x2x2=8.

[0062] In each initial flow regulation strategy, the flow of the remaining nodes in the branch topology graph remains unchanged, and only the flow of the node connected to the to-be-regulated heating monomer is adjusted to the corresponding flow intermediate value.

[0063] The embodiment determines the to-be-regulated heating monomer according to the target and actual monomer temperature, can accurately lock the object to be adjusted, and avoids meaningless regulation; generates multiple initial strategies based on the to-be-regulated monomer flow, provides sufficient choices for subsequent screening of the optimal scheme; simulates the execution of the initial strategy and predicts the temperature change through two models, can know the effect of different strategies in advance, and reduces the actual regulation risk; selects the strategy meeting the target temperature as the final scheme, can guarantee that the heating monomer temperature after regulation meets the standard, and realizes accurate and efficient heating regulation.

[0064] In a possible implementation of the embodiment of the present application, the branch heating loss model and the monomer heating model are used to simulate the execution of each initial flow regulation strategy in sequence, to determine the estimated monomer temperature change value of the to-be-regulated heating monomer under each initial flow regulation strategy, including: obtaining the heating basic data of the heating station, and collecting the current environment temperature and the current monomer temperature in real time; substituting the heating basic data into the branch heating loss model, and determining the estimated node temperature of each node in the estimated branch topology graph based on the current environment temperature and the node flow of each node in the branch heating loss model under the current initial flow regulation strategy; taking the estimated node temperature of the node connected with the to-be-regulated heating monomer in the branch topology graph as the estimated water supply temperature of the to-be-regulated heating monomer, and taking the node flow of the node connected with the to-be-regulated heating monomer as the estimated monomer flow of the to-be-regulated heating monomer; substituting the current environment temperature, the current monomer temperature, the estimated monomer flow and the estimated water supply temperature into the monomer heating model of the to-be-regulated heating monomer, to obtain the estimated monomer temperature change value of the to-be-regulated heating monomer in the preset heating period output by the monomer heating model; determining the estimated target monomer temperature based on the current monomer temperature and the estimated monomer temperature change value, and determining that the estimated monomer temperature change value of the current initial flow regulation strategy meets the target heating temperature if the estimated target monomer temperature is not less than the target heating temperature.

[0065] In the embodiment, the node flow of each node in the branch line topology graph can be determined based on the current initial flow regulation strategy. Taking the outlet of the heat supply station as the starting point, the total water supply temperature of the heat supply station is extracted from the heat supply basic data as the starting point temperature, and the downstream node temperature is calculated in turn according to the direction of the heat medium flow, and the iteration is repeated until the calculation of all node temperatures is completed. Specifically, each pipe section needs to be iterated, and the current environmental temperature, the pipe attribute information of the current pipe section, the node flow of the upstream node of the current pipe section, and the node temperature (pipe inlet temperature) of the upstream node of the current pipe section are input into the branch line heat supply loss model, and the model outputs the heat loss temperature difference. The difference between the node temperature of the upstream node of the current pipe section and the heat loss temperature difference is calculated to obtain the node temperature of the downstream node of the current pipe section. The node temperature of the downstream node of the current pipe section is taken as the node temperature of the upstream node of the next pipe section, and the node temperature of the downstream node of the next pipe section is calculated according to the above process until the iteration is completed. The node temperature of each node in the branch line topology graph determined in the iteration process is taken as the estimated node temperature.

[0066] For the initial flow regulation strategy that meets the condition, the deviation value of the estimated target monomer temperature and the median value of the target heat supply temperature is sorted from small to large (the smaller the deviation, the higher the priority), which provides a basis for subsequent strategy screening. The initial flow regulation strategy with the smallest deviation value can be directly determined as the final flow regulation strategy.

[0067] The embodiment obtains the heat supply station basic data and real-time environment and monomer temperature, provides comprehensive and real-time basic parameters for simulation calculation, and guarantees the accuracy of the simulation starting point; the basic data is substituted into the branch line heat supply loss model to estimate the node temperature, which can accurately calculate the temperature change in heat transfer in combination with the characteristics of the pipe network and the current strategy, and provide reliable front-end data for subsequent monomer heat supply analysis; the estimated water supply temperature and flow of the to-be-regulated heating monomer are determined, the accurate association of the pipe network data and the monomer heat supply is realized, and the monomer analysis is more in line with the actual heat supply condition; the estimated temperature change value is obtained by substituting the monomer heating model, and it is judged whether the standard is reached, the monomer temperature effect under different strategies can be accurately predicted, a scientific basis for screening effective strategies is provided, and the blindness of actual regulation is reduced.

[0068] In one possible implementation of the embodiment of the application, the method further includes: obtaining the monomer heat supply flow, the target heat supply temperature of the target heating monomer based on the flow regulation strategy adjustment, and the unit heating data of the target heating monomer; wherein the unit heating data includes the unit actual temperature and the unit flow; inputting the monomer heat supply flow, the target heat supply temperature, and the unit heating data into the pre-trained unit flow regulation model, and adjusting the unit flow of each heating unit in the target heating monomer based on the output of the unit flow regulation model.

[0069] In the embodiment, the above flow regulation strategy can ensure that the heat supplied to each heating unit can meet the heating demand, and the purpose of adjusting the unit flow of each heating unit in the heating unit is to ensure the balance of internal heating of the heating unit. Each heating unit includes a plurality of heating units, and the heating unit can be a single room.

[0070] A temperature sensor is installed in each heating unit (such as a single household of a residential building or a single room of a commercial building) to collect the actual temperature of the unit. An ultrasonic flow meter is installed on the water inlet branch pipe of each heating unit to collect the unit flow in real time (sampling frequency 1 time / minute). The unit heating flow (total flow), target heating temperature (which can be a unit target value or a unified target value), and unit heating data (actual temperature of each unit and unit flow) are associated according to the unit ID-unit ID-time stamp and arranged as structured data.

[0071] The processed data is input into the trained unit flow regulation model, the model outputs the target flow of each unit based on the historical optimization logic (in the form of unit ID and target flow value key-value pair), and the sum of all unit target flows is strictly equal to the unit heating flow (satisfying the constraint condition). The output result includes a regulation range prompt (such as adjusting the flow of unit A from 2.5 m³ / h to 2.8 m³ / h (+12%)), and the adjustment priority is marked (such as the unit with a temperature deviation of >2°C is given priority). The target flow output by the model is transmitted to the electric regulating valve on the unit water inlet branch pipe through the Internet of Things, and the electric regulating valve is automatically adjusted.

[0072] The embodiment obtains the relevant data after the flow regulation strategy is adjusted, including the unit heating flow, the target heating temperature, and the unit heating data, which provides a comprehensive and current actual situation basis for subsequent accurate regulation of the unit flow; inputting these data into the pre-trained unit flow regulation model and adjusting the flow of each heating unit according to the model can make the regulation more in line with the actual heating demand of each unit, effectively improve the temperature uniformity of each unit in the unit, and further improve the accuracy and energy saving of heating.

[0073] In one possible implementation of the embodiment, each heating unit includes a plurality of heating units; and the training process of the unit flow regulation model includes: initializing the model network; defining a constraint condition based on the unit heating flow; wherein the constraint condition is that the sum of the unit flows of all heating units in the target heating unit is equal to the unit heating flow; defining a reward function and a target function; wherein the optimization target of the target function includes: unit temperature compliance rate, system energy consumption, unit temperature uniformity, and regulation action frequency; Obtain training sample data, and perform model training based on the training sample data, a model network, a constraint condition, a reward function, and an objective function to obtain a unit flow regulation model.

[0074] In this embodiment, a hybrid architecture of feedforward neural network and reinforcement learning is adopted: the feedforward neural network (input layer-hidden layer-output layer) is used to fit the mapping relationship between flow and temperature, and the reinforcement learning (such as DQN algorithm) is used to optimize the regulation strategy. The number of input layer neurons = the number of units x 3 (current unit flow, current unit temperature, and target unit temperature of each unit) + 1 (heating unit flow); the hidden layer is set to two layers (64 neurons in the first layer and 32 neurons in the second layer), and the activation function is ReLU; the number of output layer neurons = the number of units (corresponding to the target flow ratio of each unit). The model network is initialized, including initializing network parameters and an experience replay pool.

[0075] The constraint condition is defined: assuming that a target heating unit contains n heating units, the target flow of the i-th unit is Qᵢ (i = 1, 2, …, n), and the total unit heating flow is Qtotal, the constraint condition is: Q1+Q2+…+Q n =Qtotal (unit: m³ / h). Auxiliary constraints can also be set, and the target flow Qᵢ of each unit needs to satisfy unit minimum safety flow ≤ Qᵢ ≤ unit maximum design flow, and the minimum safety flow and the maximum design flow can be artificially set according to the pipe properties. A flow checking module is added to the output layer of the model: when the sum of the output unit flows deviates from Qtotal by > deviation threshold, it is automatically corrected in proportion (such as allocating the deviation value according to the current unit flow proportion), until the sum constraint is satisfied; if the unit flow is out of the auxiliary constraint range after correction, the unit flow is preferentially ensured within the safety range, and then the flow of other units is adjusted.

[0076] The reward function R = α x R1 + β x R2 + γ x R3 + δ x R4 is defined, where α, β, γ, and δ are weight coefficients (the sum is 1); R1 (unit temperature compliance rate reward): if the actual unit temperature is within a preset range of the target temperature, R1 = 1; if it exceeds the range, it is calculated as “1 - |actual temperature - target temperature| / 2” (the minimum is 0), and the average value is taken after all units are aggregated; R2 (system energy consumption reward): based on the correlation between unit flow and heat loss, the closer the flow is to the optimal energy-saving flow (the value with the lowest flow and the temperature meeting the standard in historical data), the higher R2 is (the highest is 1 and the lowest is 0); R3 (temperature uniformity reward): the standard deviation of all unit actual temperatures is calculated, and when the standard deviation < 1℃, R3 = 1, and R3 decreases by 0.2 (the minimum is 0) for every increase of 0.5℃; R4 (regulation action frequency reward): if the time interval between this regulation and the last regulation < a preset time length, R4 = 0; if the interval ≥ the preset time length, R4 = 1 (to avoid frequent regulation leading to valve wear).

[0077] The objective function is to maximize the cumulative reward in the training period, that is, through iterative training, the model meets the optimization objectives of unit temperature compliance rate, system energy consumption, unit temperature uniformity and control action frequency in long-term operation.

[0078] The sample source can be historical operation data, including fields such as monomer flow, unit flow, unit temperature, environment temperature, control strategy, temperature change, covering different seasons (mainly winter heating period), different time periods (morning and evening peak, night valley). Iterative training: each time, a predetermined number of samples are randomly extracted from the experience replay pool, input into the model for forward calculation, and the predicted unit flow is obtained; the predicted result is compared with the actual compliance flow in the sample, the loss value (mean square error loss) is calculated, and the network weight is updated through back propagation. After the optimization objective is met, the training is stopped; the candidate optimal model with the best performance in the validation set is selected as the final model.

[0079] The initialization of the model network provides a basic framework for the unit flow control model, ensuring that the model has the ability to learn and operate; based on the definition of monomer heating flow constraints, it can ensure that each heating unit flow is reasonably allocated, avoiding total flow imbalance affecting overall heating; the reward function and the objective function containing multiple optimization objectives can guide the model to optimize in the direction of temperature compliance, energy saving, temperature uniformity and reducing control frequency; training the model with training sample data combined with the above elements can help the model master the correlation between flow and temperature, etc. The final model can output a scientific unit flow control scheme to improve heating effect and efficiency.

[0080] An electronic device is provided in the embodiments of the present application, as shown in Figure 2 The electronic device 200 shown in Figure 2 The electronic device 200 shown in

[0081] The processor 201 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute various exemplary logical blocks, modules and circuits described in connection with the disclosure. The processor 201 can also be a combination of computing functions, such as one or more microprocessor combinations, combinations of DSP and microprocessor, etc.

[0082] The bus 202 can include a path for transmitting information between the above-mentioned components. The bus 202 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 202 can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 2 In the figure, only one thick line is used, but it does not mean that there is only one bus or one type of bus.

[0083] The memory 203 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, an optical disk storage (including a compact disk, a laser disk, an optical disk, a digital versatile disk, a Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer, but not limited thereto.

[0084] The memory 203 is configured to store application program codes for implementing the scheme of the present application, and the processor 201 is configured to control the execution of the application program codes. The processor 201 is configured to execute the application program codes stored in the memory 203 to implement the content shown in the foregoing embodiment of the heat supply secondary network branch intelligent hydraulic balance method.

[0085] Figure 2 The electronic device shown is merely an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0086] The embodiments of the present application provide a computer readable storage medium, which stores a computer program. When the computer program is run on a computer, the computer can execute the content shown in the foregoing embodiment of the heat supply secondary network branch intelligent hydraulic balance method.

[0087] It should be understood that, although each step in the flowchart of the accompanying drawings is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other sequences. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be alternately executed with at least part of other steps or sub-steps or stages of other steps.

[0088] The embodiments of the present application provide a computer program product, which includes a computer program. When the computer program is executed by a processor, the content shown in the foregoing embodiment of the heat supply secondary network branch intelligent hydraulic balance method is implemented.

[0089] The above is only some embodiments of the present application. It should be pointed out that, for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should also be considered as the protection scope of the present application.

Claims

1. A method for intelligent hydraulic balancing of secondary heating network branches, characterized in that, include: Construct a branch topology diagram of the secondary heating network within the target heating area; wherein, nodes in the branch topology diagram represent heating units or T-junction pipe connection points, and edges represent heating pipes; The system acquires ambient temperature in real time and controls the heating station to supply heat to each heating unit in the target heating area based on a dynamic flow control strategy. It also collects the node flow and node temperature of each node in the branch topology diagram. A branch heat loss model is constructed based on the ambient temperature, the node flow rate, and the node temperature. Acquire the unit temperature and heat return flow data for each heating unit, and construct a unit heating model for each heating unit based on the ambient temperature, the unit temperature and the heat return flow data; Based on the individual heating model and the branch heating loss model, a flow control strategy is determined, and the individual heating flow of the secondary heating network is adjusted based on the flow control strategy.

2. The intelligent hydraulic balancing method for secondary heating network branches according to claim 1, characterized in that, The branch heat loss model, which constructs the branch topology based on the ambient temperature, the node flow rate, and the node temperature, includes: Based on the node temperature, the pipe inlet temperature and pipe outlet temperature of the target pipe segment are determined, and the difference between the pipe inlet temperature and the pipe outlet temperature is calculated as the heat loss temperature difference of the target pipe segment; wherein, the target pipe segment is the pipe segment between any two nodes in the branch topology diagram. Retrieve the pipeline attribute information of the target pipeline segment from the branch topology map; A branch line heat loss model is constructed based on the ambient temperature, pipeline attribute information of each pipeline segment, node flow rate, pipeline inlet temperature, and heat loss temperature difference.

3. The intelligent hydraulic balancing method for secondary heating network branches according to claim 1, characterized in that, The process of constructing a single-unit heating model for each heating unit based on the ambient temperature, the unit temperature, and the heat return flow data includes: The supply water temperature and unit flow rate are determined from the heat return flow data of the target heating unit; The average ambient temperature, average water supply temperature, and average individual flow rate are determined based on the ambient temperature, the water supply temperature, and the individual flow rate within each preset heating cycle. The initial value of the individual temperature and the change value of the individual temperature within each preset heating cycle are determined based on the individual temperature. The individual heating model of the target heating unit is trained based on the average ambient temperature, average water supply temperature, average unit flow rate, initial unit temperature value and unit temperature change value within each preset heating cycle. The individual heating model is used to output the unit temperature change value.

4. The intelligent hydraulic balancing method for secondary heating network branches according to claim 1, characterized in that, The process of determining the flow control strategy based on the single-unit heating model and the branch heating loss model includes: Obtain the target heating temperature, and determine the heating unit to be regulated based on the target heating temperature and the unit temperature of each heating unit in the target heating area; The flow rate of the heating unit to be regulated is determined from the heat return flow data of the heating unit to be regulated, and multiple initial flow regulation strategies are generated based on the flow rate of the heating unit to be regulated. Based on the branch heating loss model and the individual heating model, each initial flow control strategy is simulated and executed in sequence to determine the estimated temperature change of the heating unit to be controlled under each initial flow control strategy. The initial flow control strategy that satisfies the target heating temperature for the corresponding estimated individual unit temperature change value is used as the flow control strategy.

5. The intelligent hydraulic balancing method for secondary heating network branches according to claim 4, characterized in that, The process of sequentially simulating and executing each initial flow control strategy based on the branch heating loss model and the individual unit heating model to determine the estimated temperature change of the individual heating unit to be controlled under each initial flow control strategy includes: Acquire the basic heating data of the heating station and collect the current ambient temperature and the current temperature of the individual building in real time; Substitute the heating basic data into the branch heating loss model, and based on the node flow rate at each node in the branch heating loss model determined under the current ambient temperature and the current initial flow control strategy, estimate the estimated node temperature of each node in the branch topology diagram. The estimated node temperature of the node connected to the heating unit to be regulated in the branch topology diagram is used as the estimated water supply temperature of the heating unit to be regulated, and the node flow rate of the node connected to the heating unit to be regulated is used as the estimated unit flow rate of the heating unit to be regulated. Based on the current ambient temperature, the current unit temperature, the estimated unit flow rate, and the estimated water supply temperature, the unit heating model of the heating unit to be regulated is substituted into the unit heating model to obtain the estimated unit temperature change value of the heating unit to be regulated within the preset heating cycle output by the unit heating model. The estimated target temperature of a single unit is determined based on the current unit temperature and the estimated unit temperature change value. If the estimated target temperature of a single unit is not less than the target heating temperature, then the estimated unit temperature change value of the current initial flow control strategy is determined to meet the target heating temperature.

6. The intelligent hydraulic balancing method for secondary heating network branches according to claim 1, characterized in that, The method further includes: The system acquires the individual heating flow rate, target heating temperature, and unit heating data of the target heating unit after adjustment based on the flow control strategy; wherein the unit heating data includes the actual unit temperature and unit flow rate. The unit heating flow rate, the target heating temperature, and the unit heating data are input into a pre-trained unit flow rate control model. Based on the output of the unit flow rate control model, the unit flow rate of each heating unit in the target heating unit is adjusted.

7. The intelligent hydraulic balancing method for secondary heating network branches according to claim 6, characterized in that, Each heating unit comprises multiple heating units; The training process of the unit flow control model includes: Initialize the model network; Constraints are defined based on the individual unit heating flow rate; wherein, the constraint is that the sum of the unit flow rates of all heating units within the target heating unit is equal to the individual unit heating flow rate; Define a reward function and an objective function; wherein the optimization objectives of the objective function include: unit temperature compliance rate, system energy consumption, unit temperature uniformity, and frequency of control actions; The unit flow control model is obtained by acquiring training sample data, and training the model based on the training sample data, the model network, the constraints, the reward function, and the objective function.

8. An electronic device, characterized in that, include: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, said at least one application being configured to: perform the intelligent hydraulic balancing method for heating secondary network branches as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed in the computer, the computer is instructed to perform the intelligent hydraulic balancing method for the secondary heating network branch as described in any one of claims 1-7.

10. A computer program product, characterized in that, The method includes a computer program that, when executed by a processor, implements the steps of the intelligent hydraulic balancing method for the secondary heating network branch line as described in any one of claims 1-7.

Images