Regional heat distribution prediction system based on floor heating heat source point distribution position

Abstract

The invention discloses a regional heat distribution prediction system based on distribution positions of floor heating heat source points, relates to the technical field of building heating distribution prediction, and is used for solving the problems of low energy efficiency and the like caused by non-uniform heat distribution, lagging regulation response and inaccurate prediction in the prior art. According to the method, distribution positions, real-time temperatures, flow parameters and historical heating operation data of all heat source points in the floor heating equipment are obtained to serve as heat source data of the floor heating equipment, and a three-dimensional heat conduction model corresponding to the floor heating equipment is constructed based on the distribution positions and environment parameters of the heat source points; the heat dynamic distribution change of each heat source area is predicted based on the heat source data, the heat of the heat source areas is regulated and controlled according to the regulation and control instruction, and finally the final heat distribution conditions of different heat source areas are visually displayed, so that the accurate prediction of the heat distribution of the areas formed by different heat source points of floor heating is realized. And efficient building heating is effectively guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of building heating distribution prediction, in particular to a regional heat distribution prediction system based on the distribution positions of floor heating heat source points. Background Art

[0002] Floor heating is a heating method that uses heat source pipes or electric heating elements buried under the floor to transfer heat to the room by radiation. Its advantages are uniform temperature distribution, energy saving and high efficiency. However, in actual application, the following problems still exist:

[0003] 1. Uneven heat distribution: Due to unreasonable layout of heat source points or defects in pipeline design, local areas may be overheated or overcooled.

[0004] 2. Dynamic response lag: Traditional control systems rely on fixed threshold adjustments and are unable to optimize heat output in real time based on environmental changes (such as outdoor temperature fluctuations and indoor human activities) to accurately predict the required heat.

[0005] Some existing solutions rely on installing temperature sensors to monitor local temperatures, but the number of sensors is limited and they cannot cover the entire area. Other solutions use numerical simulations to predict heat distribution, but these methods are computationally complex and difficult to apply in real time. Therefore, there is an urgent need for an efficient prediction system that can combine the distribution characteristics of heat sources, environmental parameters, and dynamic data to optimize heat distribution and energy efficiency management in floor heating systems. Summary of the Invention

[0006] In order to solve the above problems, the purpose of the present invention is to provide a regional heat distribution prediction system based on the distribution positions of floor heating heat source points.

[0007] The object of the present invention can be achieved by the following technical solutions: a regional heat distribution prediction system based on the distribution location of floor heating heat source points, comprising a cloud terminal, wherein the cloud terminal is communicatively connected to a heat source data acquisition module, a thermodynamic modeling module, a dynamic prediction module, an optimization module, and a visualization module;

[0008] The heat source data acquisition module is used to obtain the distribution location, real-time temperature, flow parameters and historical heating operation data of all heat source points in the floor heating equipment, and authorize and encrypt them as the heat source data of the floor heating equipment;

[0009] The thermodynamic modeling module constructs a three-dimensional heat conduction model corresponding to the floor heating equipment based on the distribution location of the heat source points and environmental parameters;

[0010] The dynamic prediction module predicts the dynamic distribution change of heat in each heat source area based on the heat source data;

[0011] The tuning module is used to generate control instructions to perform heat control on the heat source area;

[0012] The visualization module is used to visualize the final heat distribution of different heat source areas.

[0013] Furthermore, the process of marking the distribution positions of all heat source points corresponding to the floor heating equipment and performing coordinate processing specifically includes:

[0014] The floor heating equipment is composed of several heat source points and a central heating node, and each of the heat source points is connected to the central heating node through a heat transmission pipeline;

[0015] Number each heat source point, construct a three-dimensional coordinate system corresponding to the floor heating equipment, and record the corresponding coordinate position of each heat source point in the three-dimensional coordinate system;

[0016] Record the type of relevant equipment performing heat treatment at each heat source point accordingly.

[0017] Furthermore, the heat source data collection module collects real-time temperature, flow parameters, and historical heating operation data of the heat source point corresponding to each distribution location, including:

[0018] The real-time temperature collected at each heat source point is recorded as T k ;

[0019] The flow parameter collected corresponding to each heat source point is the real-time flow of heat transported by the heat source point;

[0020] The real-time flow rate of each heat source point is recorded as Q k ;

[0021] Obtain all operating data corresponding to the operation of relevant equipment performing heat treatment at each heat source point at a historical time node as the historical heating operating data corresponding to the corresponding heat source point, and perform data cleaning on the historical heating operating data.

[0022] Furthermore, the process of authorizing and encrypting the generated heat source data is as follows:

[0023] Assign an authorization resolution credential to each heat source point;

[0024] Each heat source point packages its real-time temperature and flow parameters into a file to be uploaded, associates it with the authorization parsing certificate, and pushes it to the cloud terminal. The cloud terminal then determines whether the authorization parsing certificate has changed.

[0025] If so, the file to be uploaded is returned to the corresponding hot source point for destruction or modification;

[0026] If not, the data of the file to be uploaded is encrypted at the cloud terminal to generate an encrypted file package.

[0027] Furthermore, the process of constructing a three-dimensional heat conduction model corresponding to the floor heating equipment includes:

[0028] Divide the building space corresponding to the building where the floor heating equipment is located into several grid units, calculate the building volume of each grid unit, and associate the building volume with the heat source point in the floor heating equipment that is closest to the grid unit;

[0029] Based on Fourier's heat conduction law and environmental parameters, the heat balance equation corresponding to each grid unit is established;

[0030] Construct a three-dimensional heat conduction model corresponding to all heat source points based on the heat balance equation;

[0031] The three-dimensional heat conduction model is discretized and solved using the finite element method to generate an initial heat distribution benchmark map consisting of different heat source points corresponding to the floor heating equipment.

[0032] Furthermore, the process of predicting the dynamic distribution change of heat in each heat source area based on the heat source data includes:

[0033] Input the real-time collected heat source data and environmental parameters into the 3D heat conduction model, and then update the boundary conditions of the 3D heat conduction model;

[0034] Set a monitoring period, intercept the heat source data corresponding to each heat source point within the monitoring period, analyze the temperature change trend of the heat source data intercepted by each heat source point during the monitoring period, use Monte Carlo simulation to evaluate the confidence interval of the heat distribution corresponding to each heat source point, and integrate the heat change values ​​of each heat source point within the confidence interval as the heat dynamic distribution change data set of the corresponding heat source point;

[0035] Statistically analyze the heat dynamic distribution change data set corresponding to each heat source point to obtain the heat source area with different heat distribution conditions in the building where the current floor heating equipment is located. Different heat distribution conditions include heat deficiency, heat balance and heat excess.

[0036] Furthermore, the tuning module generates corresponding control instructions according to the heat distribution of different heat source areas;

[0037] When the heat distribution is insufficient, a priority calculation instruction is generated to calculate the control priority of each heat source point in the heat source area with insufficient heat, and adjust the output power or output flow of the relevant equipment of the heat treatment under the corresponding heat source point in descending order of control priority;

[0038] When the heat distribution is heat balanced, no control instruction is generated;

[0039] When the heat distribution is excessive, a device sleep instruction is generated, the heat source point under the corresponding heat source area is marked as a redundant heat source point, and the relevant equipment performing heat treatment at the redundant heat source point is changed to sleep mode.

[0040] Furthermore, the visualization module performs visualization display as follows: the visualization display of heat distribution in different heat source areas includes thermal map overlay and dynamic curve comparison; the behavioral interaction between the operation object and the data elements of the visualization display is completed by constructing a three-dimensional interactive model, the operation object refers to the relevant users who view the heat distribution in different heat source areas of the current building, and the data element refers to the heat distribution in different heat source areas of the building. The heat distribution is visualized through thermal maps and dynamic curves.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] 1. A three-dimensional heat conduction model is constructed through the thermodynamic modeling module. Combined with building structure, material parameters and real-time heat source data, the finite element method is used to accurately solve the temperature changes in each heat source area. The dynamic prediction module further integrates time series analysis and Monte Carlo simulation to predict the changes in heat distribution in the future time period and derive the type of heat distribution at the corresponding heat source point, thus achieving high-precision prediction of heat distribution.

[0043] 2. The tuning module decides in real time whether to generate a control instruction and what kind of control instruction to generate based on the prediction results. In the heat source area with insufficient heat, the control priority of the heat source points included in the heat source area is defined, and the output power and flow distribution of the corresponding heat source points are dynamically adjusted. In the heat source area with excess heat, the relevant equipment for heat treatment is changed to sleep mode, and the heat control response is carried out in time, so as to achieve relatively uniform heat distribution in different heat source areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a system principle diagram of the present invention.

[0045] Figure 2 This is a schematic diagram of the connection structure between all heat source points and central heating nodes in the floor heating equipment.

[0046] Figure 3 Flowchart of the method for building a 3D heat conduction model for the dynamic prediction module. DETAILED DESCRIPTION

[0047] like Figure 1 As shown, the regional heat distribution prediction system based on the distribution location of floor heating heat source points includes a cloud terminal, which is communicatively connected to a heat source data acquisition module, a thermodynamic modeling module, a dynamic prediction module, an optimization module, and a visualization module;

[0048] The heat source data acquisition module is used to obtain the distribution location, real-time temperature, flow parameters and historical heating operation data of all heat source points in the floor heating equipment, and authorize and encrypt them as the heat source data of the floor heating equipment;

[0049] The thermodynamic modeling module constructs a three-dimensional heat conduction model corresponding to the floor heating equipment based on the distribution location of the heat source points and environmental parameters;

[0050] The dynamic prediction module predicts the dynamic distribution change of heat in each heat source area based on the heat source data;

[0051] The tuning module is used to generate control instructions to perform heat control on the heat source area;

[0052] The visualization module is used to visualize the final heat distribution of different heat source areas.

[0053] It should be further explained that, in a specific implementation process, the process of marking the distribution positions of all heat source points corresponding to the floor heating equipment and processing the coordinates is as follows:

[0054] like Figure 2 As shown, the floor heating equipment is composed of several heat source points and a central heating node, and each of the heat source points is connected to the central heating node through a heat transmission pipeline;

[0055] The heat source points included in the floor heating equipment are marked, and the corresponding symbol is denoted by k, where k = 1, 2, 3, ..., n, where n is a natural number greater than 0. The location of the central heating node is used as the coordinate origin to construct a three-dimensional coordinate system corresponding to the floor heating equipment. The coordinate position of each heat source point in the three-dimensional coordinate system is recorded and recorded as follows:

[0056] P k =(X k , Y k , Z k );

[0057] Among them, P k Indicates the coordinate position of the kth heat source point, X k is the horizontal coordinate of the kth heat source point corresponding to the coordinate position, Y k is the ordinate of the kth heat source point corresponding to the coordinate position, Z k is the vertical coordinate of the kth heat source point corresponding to the coordinate position;

[0058] The types of related equipment for heat treatment at each heat source point are recorded accordingly, and the types of related equipment for heat treatment include warm water pumps, electric heating films and heat storage devices.

[0059] It should be further explained that, in the specific implementation process, the heat source data acquisition module collects the real-time temperature, flow parameters and historical heating operation data of the heat source point corresponding to each distribution location as follows:

[0060] Start the heat source data acquisition module, set the corresponding acquisition frequency, and perform real-time data acquisition according to the acquisition frequency;

[0061] The real-time temperature collected at each heat source point is recorded as T k ;

[0062] The flow parameter collected corresponding to each heat source point is the real-time flow of heat transported by the heat source point;

[0063] The real-time flow rate of each heat source point is recorded as Q k ;

[0064] Obtain all operating data corresponding to the operation of relevant equipment performing heat treatment at each heat source point at a historical time node as the historical heating operating data corresponding to the corresponding heat source point, and remove the alienated data that does not meet the regulations at each current heat source point after data cleaning.

[0065] Furthermore, the process of determining whether the running data is alienated data is as follows:

[0066] Obtaining temperature extremes and flow extremes of relevant equipment undergoing heat treatment at historical time nodes, wherein temperature extremes include temperature maximums and temperature minimums, and flow extremes include flow maximums and flow minimums;

[0067] Set the temperature threshold range according to the maximum and minimum temperature values;

[0068] The temperature threshold interval is denoted as [Ta, Tb];

[0069] Where Ta = temperature minimum × δ1, δ1 is the screening ratio of temperature minimum;

[0070] Tb = maximum temperature × δ2, δ2 is the screening ratio of the maximum temperature;

[0071] Ta≥minimum temperature, Tb≤maximum temperature;

[0072] Similarly, the flow threshold interval is set according to the maximum flow value and the minimum flow value;

[0073] The flow threshold interval is recorded as [Qa, Qb];

[0074] Wherein, Qa = minimum flow value × η1, η1 is the screening ratio of the minimum flow value;

[0075] Qb = maximum flow rate × η2, η2 is the screening ratio of the maximum flow rate;

[0076] Qa≥minimum flow rate, Qb≤maximum flow rate.

[0077] when or When , it is determined that the operating data of the current heat source point is alienated data; otherwise, it is determined that the operating data of the current heat source point is not alienated data.

[0078] It should be further explained that, in the specific implementation process, the process of authorizing encryption to generate heat source data is as follows:

[0079] Assign an authorization parsing credential to each heat source point;

[0080] After each heat source point obtains the real-time temperature and flow parameters at its distribution location, the real-time temperature and flow parameters are packaged into a file to be uploaded for the corresponding heat source point, the authorization parsing certificate is associated with the file to be uploaded, and the file is pushed to the cloud terminal;

[0081] The cloud terminal determines whether the authorization resolution credentials have changed;

[0082] If so, the file to be uploaded is returned to the corresponding hot source point, which will destroy or modify it.

[0083] To further explain, the content of the files to be uploaded that the hot source selects to destroy or modify includes the following:

[0084] Count the number of data attacks on the hot source point and the number of data attacks it resists, and then calculate the attack interception rate. Attack interception rate = number of data attacks resisted / number of data attacks;

[0085] If the attack interception rate exceeds the preset upper threshold, the files to be uploaded at the corresponding hot source point will be destroyed;

[0086] Otherwise, the file to be uploaded is analyzed by building a bag-of-words model, all the tampered data parts in the file to be uploaded are filtered out, and context analysis is performed through computer text language technology to restore the original data corresponding to the tampered data part to complete the modification.

[0087] If not, the data of the file to be uploaded is encrypted at the cloud terminal to generate an encrypted file package.

[0088] It should be further explained that, in the specific implementation process, the process of constructing the three-dimensional heat conduction model corresponding to the floor heating equipment includes:

[0089] The steps for building a three-dimensional heat conduction model are as follows: Figure 3 As shown;

[0090] Divide the building space corresponding to the building where the floor heating equipment is located into several grid units;

[0091] Count the building volume corresponding to each grid unit and record the building volume as Vi j k, and associate the building volume with the closest heat source point in the floor heating equipment;

[0092] Based on Fourier's heat conduction law, the heat balance equation corresponding to each grid unit is established;

[0093] The heat balance equation is expressed as follows:

[0094]

[0095] Where ρ is the material density, Cp is the specific heat capacity, k is the thermal conductivity, and S is the heat source term;

[0096] The material density, specific heat capacity, thermal conductivity and heat source term of the building are derived from the environmental parameters of the building's environment, including the building's architectural structure and the material thermal conductivity of the building materials corresponding to different building parts, as well as the temperature difference between the indoor and outdoor areas of the building.

[0097] Construct a three-dimensional heat conduction model corresponding to all heat source points based on the heat balance equation;

[0098] The three-dimensional heat conduction model is discretized and solved using the finite element method to generate an initial heat distribution reference map composed of different heat source points corresponding to the floor heating equipment. The initial heat distribution reference map is used to characterize the initial heat distribution of different heat source points.

[0099] It should be further explained that, in the specific implementation process, the process of predicting the dynamic distribution change of heat in each heat source area based on heat source data is as follows:

[0100] Input the real-time collected heat source data and environmental parameters into the 3D heat conduction model, and then update the boundary conditions of the 3D heat conduction model. The boundary conditions are used to represent the upper and lower boundary heat values ​​of each heat source point in the building. The upper and lower boundary heat values ​​include the minimum and maximum heat values ​​of each heat source point under normal conditions.

[0101] Set the monitoring period and intercept the heat source data corresponding to each heat source point within the monitoring period;

[0102] Analyze the temperature change trend of the heat source data intercepted at each heat source point during the monitoring period, use Monte Carlo simulation to evaluate the confidence interval of the heat distribution corresponding to each heat source point, and integrate the heat change values ​​of each heat source point within the confidence interval as the heat dynamic distribution change data set of the corresponding heat source point;

[0103] Statistically analyze the heat dynamic distribution change data set corresponding to each heat source point to obtain the heat source area with different heat distribution conditions in the building where the current floor heating equipment is located. Different heat distribution conditions include heat deficiency, heat balance and heat excess.

[0104] The tuning module generates control instructions to control the heat of the heat source area. Specifically, the content is:

[0105] The tuning module generates corresponding control instructions based on the heat distribution in different heat source areas;

[0106] When the heat distribution is insufficient, a priority calculation instruction is generated, and the priority calculation instruction is used to calculate the control priority corresponding to each heat source point in the heat source area with insufficient heat;

[0107] The control priority is recorded as Priority k , then Priority k It is expressed as follows:

[0108]

[0109] Among them, α and β are the weight coefficients of real-time temperature and real-time flow respectively;

[0110] And α>0, β>0, α+β=1;

[0111] According to the order of control priority from high to low, the heat source points under the corresponding heat source area are heat-controlled, and the output power or output flow of the relevant equipment performing heat treatment at the corresponding heat source points is adjusted;

[0112] When the heat distribution is heat balanced, no control instruction is generated;

[0113] When the heat distribution is excessive, a device sleep instruction is generated, the heat source point under the corresponding heat source area is marked as a redundant heat source point, and the related equipment performing heat treatment at the redundant heat source point is changed to sleep mode to reduce the energy consumption of the related equipment when working, thereby reducing the heat in the heat source area.

[0114] It should be further explained that, in the specific implementation process, the visualization module performs the following visual display process:

[0115] The visualization module visualizes the heat distribution of different heat source areas in a manner including thermal map superposition and dynamic curve comparison;

[0116] Furthermore, the specific contents of the heat map overlay include the following:

[0117] The visualization module constructs a building plan and overlays the real-time heat changes of buildings corresponding to different heat source points on the building plan to generate the corresponding regional heat map. The heat map of the area with abnormal heat is highlighted on the building plan.

[0118] Furthermore, the specific contents of the dynamic curve comparison include the following:

[0119] Construct a coordinate system Ps, and on the coordinate system Ps, draw a dynamic curve of the regional temperature change over time in the abnormal area under each heat source area, and based on the relevant data when the heat source area is normal, draw a dynamic curve of the regional temperature change over time in the normal area, and mark the corresponding dynamic curve as the reference curve;

[0120] Compare the dynamic curve corresponding to each heat source area with the benchmark curve in turn;

[0121] Then, the temperature deviation between the actual temperature and the normal temperature of each heat source point included in the heat source area is determined. Specifically, the dynamic curve of the regional temperature change over time in each abnormal area is used to record the actual temperature of several heat source points included in the heat source area, and the reference curve is used to record the normal temperature of several heat source points included in the corresponding heat source area.

[0122] Furthermore, the difference between the actual temperature and the normal temperature of each heat source point at the same position of the dynamic curve and the reference curve is taken as the temperature deviation of the corresponding heat source point, and the temperature deviation is marked at the corresponding position on the dynamic curve.

[0123] The visualization module completes the behavioral interaction between the operation object and the visually displayed data elements by constructing a three-dimensional interaction model;

[0124] The operation object refers to a user who views the heat distribution of different heat source areas of the current building. The data element refers to the heat distribution of different heat source areas of the building. The heat distribution is visualized through a thermal map and a dynamic curve.

[0125] The three-dimensional interactive model supports the operating objects to perform behavioral interactions such as rotating, scaling, segment positioning of thermal maps and dynamic curves, and viewing detailed heat distribution of different building sections. The behavioral interactions are performed by relevant users through their respective tablet computers, that is, the relevant users operate the three-dimensional interactive model on the tablet computer.

[0126] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A regional heat distribution prediction system based on the distribution location of floor heating heat source points, including a cloud terminal, characterized in that: The cloud terminal is communicatively connected to a heat source data acquisition module, a thermodynamic modeling module, a dynamic prediction module, an optimization module, and a visualization module; The heat source data acquisition module is used to obtain the distribution location, real-time temperature, flow parameters and historical heating operation data of all heat source points in the floor heating equipment, and authorize and encrypt them as the heat source data of the floor heating equipment; The thermodynamic modeling module constructs a three-dimensional heat conduction model corresponding to the floor heating equipment based on the distribution location of the heat source points and environmental parameters; The dynamic prediction module predicts the dynamic distribution change of heat in each heat source area based on the heat source data; The tuning module is used to generate control instructions to perform heat control on the heat source area; The visualization module is used to visualize the final heat distribution of different heat source areas.

2. The regional heat distribution prediction system based on the distribution position of floor heating heat source points according to claim 1 is characterized in that: The process of marking the distribution positions of all heat source points corresponding to the floor heating equipment and performing coordinate processing specifically includes: The floor heating equipment is composed of several heat source points and a central heating node, and each of the heat source points is connected to the central heating node through a heat transmission pipeline; Number each heat source point, construct a three-dimensional coordinate system corresponding to the floor heating equipment, and record the corresponding coordinate position of each heat source point in the three-dimensional coordinate system; Record the type of relevant equipment performing heat treatment at each heat source point accordingly.

3. The regional heat distribution prediction system based on the distribution position of floor heating heat source points according to claim 2 is characterized in that: The heat source data acquisition module collects real-time temperature, flow parameters, and historical heating operation data at the corresponding heat source point at each distribution location, including: The real-time temperature collected at each heat source point is recorded as T k ; The flow parameter collected corresponding to each heat source point is the real-time flow of heat transported by the heat source point; The real-time flow rate of each heat source point is recorded as Q k； Obtain all operating data corresponding to the operation of relevant equipment performing heat treatment at each heat source point at a historical time node as the historical heating operating data corresponding to the corresponding heat source point, and perform data cleaning on the historical heating operating data.

4. The regional heat distribution prediction system based on the distribution position of floor heating heat source points according to claim 3 is characterized in that: The process of authorizing and encrypting heat source data is as follows: Assign an authorization resolution credential to each heat source point; Each heat source point packages its real-time temperature and flow parameters into a file to be uploaded, associates it with the authorization parsing certificate, and pushes it to the cloud terminal. The cloud terminal then determines whether the authorization parsing certificate has changed. If so, the file to be uploaded is returned to the corresponding hot source point for destruction or modification; If not, the data of the file to be uploaded is encrypted at the cloud terminal to generate an encrypted file package.

5. The regional heat distribution prediction system based on the distribution position of floor heating heat source points according to claim 4 is characterized in that: The process of building a three-dimensional heat conduction model corresponding to floor heating equipment includes: Divide the building space corresponding to the building where the floor heating equipment is located into several grid units, calculate the building volume of each grid unit, and associate the building volume with the heat source point in the floor heating equipment that is closest to the grid unit; Based on Fourier's heat conduction law and environmental parameters, the heat balance equation corresponding to each grid unit is established; Construct a three-dimensional heat conduction model corresponding to all heat source points based on the heat balance equation; The three-dimensional heat conduction model is discretized and solved using the finite element method to generate an initial heat distribution benchmark map consisting of different heat source points corresponding to the floor heating equipment.

6. The regional heat distribution prediction system based on the distribution position of floor heating heat source points according to claim 5 is characterized in that: The process of predicting the dynamic distribution changes of heat in each heat source area based on heat source data includes: Input the real-time collected heat source data and environmental parameters into the 3D heat conduction model, and then update the boundary conditions of the 3D heat conduction model; Set a monitoring period, intercept the heat source data corresponding to each heat source point within the monitoring period, analyze the temperature change trend of the heat source data intercepted by each heat source point during the monitoring period, use Monte Carlo simulation to evaluate the confidence interval of the heat distribution corresponding to each heat source point, and integrate the heat change values ​​of each heat source point within the confidence interval as the heat dynamic distribution change data set of the corresponding heat source point; Statistically analyze the heat dynamic distribution change data set corresponding to each heat source point to obtain the heat source area with different heat distribution conditions in the building where the current floor heating equipment is located. Different heat distribution conditions include heat deficiency, heat balance and heat excess.

7. The regional heat distribution prediction system based on the distribution position of floor heating heat source points according to claim 6 is characterized in that: The tuning module generates corresponding control instructions according to the heat distribution of different heat source areas; When the heat distribution is insufficient, a priority calculation instruction is generated to calculate the control priority of each heat source point in the heat source area with insufficient heat, and adjust the output power or output flow of the relevant equipment of the heat treatment under the corresponding heat source point in descending order of control priority; When the heat distribution is heat balanced, no control instruction is generated; When the heat distribution is excessive, a device sleep instruction is generated, the heat source point under the corresponding heat source area is marked as a redundant heat source point, and the relevant equipment performing heat treatment at the redundant heat source point is changed to sleep mode.

8. The regional heat distribution prediction system based on the distribution position of floor heating heat source points according to claim 7 is characterized in that: The process of visualization display in the visualization module is as follows: the visualization of the heat distribution in different heat source areas includes thermal map superposition and dynamic curve comparison; the behavioral interaction between the operation object and the data elements of the visualization display is completed by constructing a three-dimensional interactive model. The operation object refers to the relevant users who view the heat distribution in different heat source areas of the current building, and the data element refers to the heat distribution in different heat source areas of the building. The heat distribution is visualized through thermal maps and dynamic curves.

Images