A method for predicting load of heating system

Through the GIS geographic information system, the heating system is divided and modeled, load prediction is carried out in combination with historical and current data, and the heat loss of the pipeline network is calculated, which solves the problem of low load prediction accuracy in the existing technology and achieves a higher level of Accurate heating system load prediction.

CN117057481BActive Publication Date: 2024-11-29HUANENG SUZHOU THERMAL POWER CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202311188343.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-09-14
Publication Date
2024-11-29
Estimated Expiration
2043-09-14

AI Technical Summary

Technical Problem

The existing heating system load prediction methods are uncertain in small-range load prediction, and the actual use of heat users and network management heat loss are not calculated, resulting in low prediction accuracy.

Method used

By dividing the heating system based on the GIS geographic information system, establishing multiple prediction models, obtaining historical data and current feature data, performing load predictions, and calculating the heat loss of the pipeline network, correcting the prediction value to improve accuracy.

Benefits of technology

The accuracy of load prediction of heating system is improved, and the load changes and heat losses of heating system can be predicted more accurately.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117057481B_ABST
    Figure CN117057481B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of load prediction of heating systems, and more specifically to a method for load prediction of heating systems, including: modeling the pipe network of the heating system based on a GIS geographic information system; dividing the heating system into regions according to the load type of heat users in the heating system model; establishing a prediction model within the heating region based on historical data; acquiring characteristic data of the current time, and inputting the data into the prediction model to obtain a first predicted load; calculating the heat loss of the pipe network according to the first predicted load value, and correcting the first predicted load according to the heat loss value to obtain a second predicted load; calculating the predicted load of the heating system according to the second predicted load of all heating regions; dividing the scope of the heating system into regions according to the heating type, and performing load prediction for each region separately. At the same time, the heat loss of the pipe network in each region is calculated, thereby improving the accuracy of the load prediction of the heating system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of heat supply system load prediction, and more specifically to a heat supply system load prediction method. Background Art

[0002] The heating system is a centralized heating facility used to provide heat energy to buildings and areas within the city. It transports heat energy from the production source to the user area through a series of heating equipment, pipeline networks and heat exchange stations to meet various heating needs such as residents, commerce and industry.

[0003] In my country, due to the large scale of heating, multiple heat sources, many users and complex parameters, the load fluctuates greatly when the heating system is adjusted. Frequent adjustments are not conducive to the stability of the system and can easily cause safety problems in the thermal system.

[0004] In the prior art, most of the above problems are solved by using historical load data of the heating system to study the load change law, generate a load forecasting model, and then input the current data for forecasting. This method cannot determine the load in a small range, and does not calculate the actual use of heat users in the heating system and the heat loss consumption of the network management, so the forecasting results are less accurate.

[0005] Therefore, how to improve the accuracy of load prediction of heating systems is an urgent problem that technicians in this field need to solve. Summary of the invention

[0006] In view of this, the present invention provides a method for load prediction of a heating system, which divides the scope of the heating system into regions according to the heating type, and performs load prediction for each region separately. At the same time, the heat loss of the pipe network in each region is calculated, thereby improving the accuracy of load prediction of the heating system.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] Preferably, the above-mentioned method for predicting load of a heating system comprises:

[0009] Modeling the pipe network of the heating system based on the GIS geographic information system; the heating system model includes the pipe network direction, system heat source, heat users, pipes, valves, steam traps, and compensators;

[0010] According to the load type of the heat user in the heating system model, the heating system is divided into multiple heating areas;

[0011] Acquire historical data of the heating system in the heating area, and establish multiple prediction models in the heating area based on characteristic data affecting the heating load in the historical data;

[0012] Acquire characteristic data at the current time, match the corresponding prediction model, and input the data into the prediction model to predict the heating load in the heating area to obtain a first predicted load;

[0013] According to the first predicted load, the operation status of the heating system in the heating area is predicted, and the heat loss of the pipe network is calculated according to the operation status of the heating system, and the first predicted load is corrected according to the heat loss value to obtain a second predicted load;

[0014] The predicted load of the heating system is obtained by calculating according to the second predicted loads of all the heating areas.

[0015] Preferably, in the above-mentioned method for predicting the load of a heating system, the modeling of the pipe network of the heating system based on the GIS geographic information system includes:

[0016] Obtain the location, length, size and connection relationship information of the heating pipes in the heating system, and the location and equipment information of the heating stations;

[0017] Obtain the load type of heat users in the heating system;

[0018] Obtain topographic data, land use information and water flow data within the heating system coverage area;

[0019] Convert the acquired data into a data format supported by the GIS geographic information system, and process outliers and missing values ​​on the converted data;

[0020] Import the processed geographic data into GIS software and draw pipelines in GIS according to the pipe network data of the heating system;

[0021] Heat users are marked in GIS software according to their load types to form a static model of the heating system.

[0022] Preferably, in the above-mentioned method for predicting the load of a heating system, the step of dividing the heating system into regions according to the load types of the heat users in the heating system model includes:

[0023] Obtaining the load type of the heat user, and dividing the range of the heating system into multiple type areas according to the load type;

[0024] Acquire distribution information of the type area, and divide the type area into a plurality of type sub-areas according to the distribution information;

[0025] The area of ​​the type sub-region is obtained. If the area of ​​the type sub-region is greater than the preset maximum area threshold, the current type sub-region is divided, and each area after division is the heating area, and the heating area is greater than the preset minimum area threshold; if the area of ​​the type sub-region is less than the preset maximum area threshold, the current type sub-region is used as the heating area.

[0026] Preferably, in the above-mentioned method for predicting the load of a heating system, the historical data of the heating system in the heating area is obtained, and based on the characteristic data affecting the heating load in the historical data, a plurality of prediction models in the heating area are established, including:

[0027] Acquiring historical data of heat user loads in the heating area and historical data of weather in the target area to obtain first historical data;

[0028] Preprocessing the first historical data, removing abnormal data in the first historical data, and obtaining second historical data;

[0029] Setting screening characteristic data, grouping the second historical data to obtain a first data group;

[0030] A neural network model is used to perform data training and verification based on the first data set to obtain a prediction model corresponding to the feature data.

[0031] Preferably, in the above-mentioned method for predicting the load of a heating system, the step of acquiring the characteristic data at the current time, matching the corresponding prediction model, and inputting the data into the prediction model to predict the heating load in the heating area to obtain a first predicted load includes:

[0032] According to the historical data, the weights of the characteristic data in different time periods are determined by sorting them according to time, and the historical statistical analysis method is used;

[0033] Obtain all feature data at the current time, and select the feature data with the largest weight to match the prediction model;

[0034] If the remaining feature data exceeds the corresponding preset data threshold, the weight of the remaining feature data is determined according to the proportion of the feature data exceeding the preset data threshold;

[0035] After determining the weights of all characteristic data, the data are input into the prediction model to predict the load of the heating area to obtain a first predicted load.

[0036] Preferably, in the above-mentioned method for predicting the load of a heating system, the heat loss of the pipe network is calculated according to the operation status of the heating system, and the first predicted load is corrected according to the heat loss value to obtain the second predicted load, including:

[0037] The operation data of the pipelines in the heating area are obtained, and the heat dissipation loss of the pipelines is calculated according to the operation data. The calculation formula is:

[0038] Q 散 =∑(πD 2i L i q i )

[0039] Among them, D2i is the outer diameter of the insulation layer of each pipeline, in m; Li is the length of pipelines with different pipe diameters and different outer diameters of the insulation layer, in m; qi is the heat loss per unit area of ​​pipelines with different pipe diameters and different outer diameters of the insulation layer, in W / m2;

[0040] The calculation formula of qi is:

[0041]

[0042] Wherein, T is the steam temperature in the pipeline, unit K; Ta is the external environment temperature, unit K; D2 is the insulation outer diameter of the pipeline, unit m; λ is the equivalent thermal conductivity of the insulation material, unit W / (m*K); D1 is the outer diameter of the metal pipeline, unit m; α is the heat transfer coefficient between the outer surface of the insulation layer and the surrounding air, unit W / (m2*K);

[0043] The data information of the heat source and the heat user in the heating area is obtained, and the drainage quality loss of the heating is calculated. The calculation formula is:

[0044]

[0045] Among them, Q is the heat loss of the pipe network; H0 is the enthalpy of the steam at the heat source outlet in the superheated state; Hbq is the enthalpy of the overall saturated state at the heat source outlet; Hi is the enthalpy of the steam at the inlet of each heat user in the superheated state; Hbqi is the enthalpy of the steam at the inlet of each heat user in the saturated state; M0 is the outlet quality of the heat source; Mi is the gas quality of each heat user; H is the latent heat of vaporization of steam;

[0046] The air leakage mass loss in the heating area is calculated using the following formula:

[0047] ∑M qi =(M0-∑M i )-∑M si

[0048] The heat loss of the heating area is calculated by the heat dissipation loss of the pipe network, the water drainage mass loss and the air leakage mass loss, and the calculation formula is:

[0049] ΔQ=Q 散 +∑(M si H si )+Σ(M qi H qi )

[0050] Wherein, ΔQ is the heat loss value of the heating area; Msi is the hydrophobic mass loss of each heat user; Hsi is the hydrophobic enthalpy value of each heat user; Mqi is the air leakage mass loss of each heat user; Hqi is the air leakage enthalpy value of each heat user;

[0051] The first predicted load is corrected according to the heat loss value of the heating area to obtain a second predicted load.

[0052] Preferably, in the above-mentioned method for predicting the load of a heating system, after obtaining the predicted load of the heating system, the method further comprises:

[0053] The actual heat loss of the heating area is obtained by the following calculation formula:

[0054] ΔQ 实测 =M0H0-∑(M i H i )

[0055] Among them, M0 is the outlet mass of the heat source; H0 is the outlet enthalpy of the heat source; Mi is the outlet mass of the heat user; Hi is the outlet enthalpy of the heat user;

[0056] The deviation value is calculated by comparing the actual heat loss with the calculated heat loss. The calculation formula is:

[0057]

[0058] If the η deviation value is greater than the preset deviation threshold, α is adjusted according to the difference between the η deviation value and the deviation threshold.

[0059] It can be seen from the above technical solution that, compared with the prior art, the beneficial effects of the present invention are:

[0060] 1. The scope of the heating system is divided into regions according to the heating type, and the load forecast is carried out separately for each region. At the same time, the heat loss of the pipeline network in each region is calculated, which improves the accuracy of the load forecast of the heating system. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0062] Figure 1 The accompanying drawing is a schematic flow diagram of the method of the present invention. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention. The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0064] In the present invention, the terms "first", "second", and "third" are used for descriptive purposes only and should not be understood as indicating or implying relative importance; the term "plurality" refers to two or more, unless otherwise clearly defined. The terms "installed", "connected", "connected", "fixed", etc. should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; "connected" can be a direct connection or an indirect connection through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0065] In the description of the present invention, it is necessary to understand that the directions or positional relationships indicated by terms such as “upper”, “lower”, “left”, “right”, “front” and “back” are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or unit referred to must have a specific direction, be constructed and operated in a specific orientation, and therefore, cannot be understood as a limitation on the present invention.

[0066] In the description of this specification, the description of the terms "one embodiment", "some embodiments", "specific embodiments", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0067] Example 1

[0068] like Figure 1 As shown, an embodiment of the present invention discloses a method for predicting load of a heating system, comprising:

[0069] Model the pipe network of the heating system based on GIS; the heating system model includes the pipe network direction, system heat source, heat users, pipes, valves, steam traps, and compensators;

[0070] According to the load type of heat users in the heating system model, the heating system is divided into multiple heating areas.

[0071] Obtain historical data of the heating system in the heating area, and establish multiple prediction models in the heating area based on the characteristic data affecting the heating load in the historical data;

[0072] Acquire characteristic data of the current time, match the corresponding prediction model, and input the data into the prediction model to predict the heating load in the heating area to obtain a first predicted load;

[0073] According to the first predicted load, the operation of the heating system in the heating area is predicted, and the heat loss of the pipe network is calculated according to the operation of the heating system, and the first predicted load is corrected according to the heat loss value to obtain the second predicted load;

[0074] The predicted load of the heating system is obtained by calculating according to the second predicted loads of all heating areas.

[0075] In the above embodiment, the types of heat users are divided into residential areas, commercial areas, industrial areas, and public facilities areas. It should be noted that each area has its own heating usage rules, and load forecasting by region can improve the accuracy of load forecasting.

[0076] In the above embodiment, the data features preferably include meteorological data (temperature, humidity, wind speed and weather), date data (holidays, heating time period), and factors that have a greater impact on heating as characteristic data.

[0077] In the above embodiment, the load of each heating area is predicted and then added together to obtain the overall load of the heating system.

[0078] The beneficial effects of the above embodiment are: the range of the heating system is divided into regions according to the heating type, and the load forecast is performed separately for each region. At the same time, the heat loss of the pipe network in each region is calculated, thereby improving the accuracy of the load forecast of the heating system.

[0079] Example 2

[0080] In one embodiment, a method for predicting load of a heating system is provided, which models a pipe network of the heating system based on a GIS geographic information system, and includes:

[0081] Obtain the location, length, size and connection relationship information of the heating pipes in the heating system, and the location and equipment information of the heating stations;

[0082] Obtain the load type of heat users in the heating system;

[0083] Obtain topographic data, land use information and water flow data within the heating system coverage area;

[0084] Convert the acquired data into a data format supported by the GIS geographic information system, and process outliers and missing values ​​on the converted data;

[0085] Import the processed geographic data into GIS software and draw pipelines in GIS according to the pipe network data of the heating system;

[0086] Heat users are marked in GIS software according to their load types to form a static model of the heating system.

[0087] In the above embodiment, the static model construction by GIS software is an existing technology, the load type of the heat user is added to the model, and the static model is used to divide the area.

[0088] Example 3

[0089] In one embodiment, a method for predicting load of a heating system divides the heating system into regions according to load types of heat users in a heating system model, including:

[0090] Obtain the load type of the heat user, and divide the heating system range into multiple type areas according to the load type;

[0091] Obtaining distribution information of the type area, and dividing the type area into a plurality of type sub-areas according to the distribution information;

[0092] Get the area of ​​the type sub-area. If the area of ​​the type sub-area is larger than the preset maximum area threshold, divide the current type sub-area into two parts. Each part is a heating area after division, and the heating area is larger than the preset minimum area threshold. If the area of ​​the type sub-area is smaller than the preset maximum area threshold, use the current type sub-area as the heating area.

[0093] In the above embodiment, the maximum area threshold and the minimum area threshold are set according to the experience of skilled personnel. It should be noted that the purpose of performing regional division for load calculation is to improve the accuracy of prediction. The size of the regional division affects the accuracy of prediction; too small an area is likely to result in a small amount of data, which affects the stability of the prediction result.

[0094] Example 4

[0095] In one embodiment, a method for predicting the load of a heating system obtains historical data of a heating system in a heating area, and establishes multiple prediction models in the heating area based on characteristic data affecting the heating load in the historical data, including:

[0096] Acquiring historical data of heat user loads in the heating area and historical data of weather in the target area to obtain first historical data;

[0097] Preprocessing the first historical data, removing abnormal data in the first historical data, and obtaining second historical data;

[0098] Setting filtering characteristic data, grouping the second historical data to obtain a first data group;

[0099] The neural network model is used to perform data training and verification based on the first data group to obtain a prediction model corresponding to the feature data.

[0100] In the above embodiment, the use of a neural network model to establish a data prediction model is an existing technology. Screening and establishing multiple prediction models based on different feature data can improve the prediction accuracy, such as prediction models for holidays and prediction models for severe weather.

[0101] Example 5

[0102] In one embodiment, a method for predicting a load of a heating system obtains characteristic data of the current time, matches a corresponding prediction model, and inputs the data into the prediction model to predict a heating load in a heating area to obtain a first predicted load, including:

[0103] According to the historical data, the weights of the characteristic data in different time periods are determined by sorting them according to time, and the historical statistical analysis method is used to determine the weights of the characteristic data in different time periods;

[0104] Get all feature data at the current time, and select the feature data with the largest weight to match the prediction model;

[0105] If the remaining feature data exceeds the corresponding preset data threshold, the weight of the remaining feature data is determined according to the proportion of the feature data exceeding the preset data threshold;

[0106] After determining the weights of all characteristic data, the data is input into the prediction model to predict the load of the heating area and obtain the first predicted load.

[0107] In the above embodiment, current characteristic data is obtained, such as weekends, heavy snow, and noon. The weights of the data are different for areas with different heating types. First, it is determined that weekends have a greater impact on each area as a screening condition, and heavy snow has a smaller impact on office areas and a greater impact on residential areas and commercial areas. The remaining characteristic data are weighted, which can improve the accuracy of load forecasting.

[0108] Example 6

[0109] In one embodiment, a method for predicting a load of a heating system calculates heat loss of a pipe network according to an operation condition of the heating system, and corrects a first predicted load according to the heat loss value to obtain a second predicted load, including:

[0110] Obtain the operation data of the pipelines in the heating area, and calculate the heat dissipation loss of the pipelines based on the operation data. The calculation formula is:

[0111] Q 散 =∑(πD 2i L i q i )

[0112] Among them, D2i is the outer diameter of the insulation layer of each pipeline, in m; Li is the length of pipelines with different pipe diameters and different outer diameters of the insulation layer, in m; qi is the heat loss per unit area of ​​pipelines with different pipe diameters and different outer diameters of the insulation layer, in W / m2;

[0113] The calculation formula of qi is:

[0114]

[0115] Wherein, T is the steam temperature in the pipeline, unit K; Ta is the external environment temperature, unit K; D2 is the insulation outer diameter of the pipeline, unit m; λ is the equivalent thermal conductivity of the insulation material, unit W / (m*K); D1 is the outer diameter of the metal pipeline, unit m; α is the heat transfer coefficient between the outer surface of the insulation layer and the surrounding air, unit W / (m2*K);

[0116] Obtain the data information of heat sources and heat users in the heating area, and calculate the drainage quality loss of heating. The calculation formula is:

[0117]

[0118] Among them, Q is the heat loss of the pipe network; H0 is the enthalpy of the steam at the heat source outlet in the superheated state; Hbq is the enthalpy of the overall saturated state at the heat source outlet; Hi is the enthalpy of the steam at the inlet of each heat user in the superheated state; Hbqi is the enthalpy of the steam at the inlet of each heat user in the saturated state; M0 is the outlet quality of the heat source; Mi is the gas quality of each heat user; H is the latent heat of vaporization of steam;

[0119] The air leakage mass loss in the heating area is calculated using the following formula:

[0120] ∑M qi =(M0-∑M i )-∑M si

[0121] The heat loss of the heating area is calculated through the heat dissipation loss of the pipe network, the water drainage mass loss and the air leakage mass loss. The calculation formula is:

[0122] ΔQ=Q 散 +∑(M si H si )+∑(M qi H qi )

[0123] Among them, ΔQ is the heat loss value of the heating area; Msi is the drainage mass loss of each heat user; Hsi is the drainage enthalpy value of each heat user; Mqi is the leakage mass loss of each heat user; Hqi is the leakage enthalpy value of each heat user;

[0124] The first predicted load is corrected according to the heat loss value of the heating area to obtain the second predicted load.

[0125] In the above embodiment, it should be noted that when the pipeline network is constructed, relevant meters are provided at the outlet of the heat source and the entrances of all heat users, so as to monitor the temperature, pressure and flow of the pipeline network.

[0126] Example 7

[0127] In one embodiment, a method for predicting load of a heating system, after obtaining the predicted load of the heating system, further comprises:

[0128] Get the actual heat loss of the heating area, the calculation formula is:

[0129] ΔQ 实测 =M0H0-∑(M i H i)

[0130] Among them, M0 is the outlet mass of the heat source; H0 is the outlet enthalpy of the heat source; Mi is the outlet mass of the heat user; Hi is the outlet enthalpy of the heat user;

[0131] The deviation value is calculated by comparing the actual heat loss with the calculated heat loss. The calculation formula is:

[0132]

[0133] If the η deviation value is greater than the preset deviation threshold, α is adjusted according to the difference between the η deviation value and the deviation threshold.

[0134] In the above embodiment, the heat transfer coefficient α is adjusted based on the comparison between the actual measured value and the predicted calculated value to improve the accuracy of the load prediction;

[0135] It should be noted that the above embodiments are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiments can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.

[0136] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus / device.

[0137] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0138] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations in the above description of the disclosed embodiments, so that professionals and technicians in the field can implement or use the present invention. Various modifications to these embodiments will be obvious to professionals and technicians in the field, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting load of a heating system, characterized in that: include: Model the pipe network of the heating system based on GIS; The heating system model includes information on the direction of the pipe network, system heat sources, heat users, pipes, valves, steam traps, and compensators; According to the load type of the heat user in the heating system model, the heating system is divided into multiple heating areas; Acquire historical data of the heating system in the heating area, and establish multiple prediction models in the heating area based on characteristic data affecting the heating load in the historical data; Acquire characteristic data at the current time, match the corresponding prediction model, and input the data into the prediction model to predict the heating load in the heating area to obtain a first predicted load; According to the first predicted load, the operation status of the heating system in the heating area is predicted, and the heat loss of the pipe network is calculated according to the operation status of the heating system, and the first predicted load is corrected according to the heat loss value to obtain a second predicted load; Calculate according to the second predicted loads of all the heating areas to obtain the predicted load of the heating system; The pipe network modeling of the heating system based on the GIS geographic information system includes: Obtain the location, length, size and connection relationship information of the heating pipes in the heating system, and the location and equipment information of the heating stations; Obtain the load type of heat users in the heating system; Obtain topographic data, land use information and water flow data within the heating system coverage area; Convert the acquired data into a data format supported by the GIS geographic information system, and process outliers and missing values ​​on the converted data; Import the processed geographic data into GIS software and draw pipelines in GIS according to the pipe network data of the heating system; Mark the load types of heat users in the GIS software to form a static model of the heating system; The step of dividing the heating system into regions according to the load types of the heat users in the heating system model includes: Obtaining the load type of the heat user, and dividing the range of the heating system into multiple type areas according to the load type; Acquire distribution information of the type area, and divide the type area into a plurality of type sub-areas according to the distribution information; Obtaining the area of ​​the sub-region of the type; if the area of ​​the sub-region of the type is greater than a preset maximum area threshold, dividing the current sub-region of the type, each region after division is the heating region, and the heating region is greater than a preset minimum area threshold; if the area of ​​the sub-region of the type is less than a preset maximum area threshold, taking the current sub-region of the type as the heating region; The acquiring of historical data of the heating system in the heating area, and establishing a plurality of prediction models in the heating area based on characteristic data affecting the heating load in the historical data, comprises: Acquiring historical data of heat user loads in the heating area and historical data of weather in the target area to obtain first historical data; Preprocessing the first historical data, removing abnormal data in the first historical data, and obtaining second historical data; Setting screening characteristic data, grouping the second historical data to obtain a first data group; Using a neural network model to perform data training and verification based on the first data group to obtain a prediction model corresponding to the feature data; The acquiring characteristic data of the current time, matching the corresponding prediction model, and inputting the data into the prediction model to predict the heating load in the heating area to obtain a first predicted load includes: According to the historical data, the weights of the characteristic data in different time periods are determined by sorting them according to time, and the historical statistical analysis method is used; Obtain all feature data at the current time, and select the feature data with the largest weight to match the prediction model; If the remaining feature data exceeds the corresponding preset data threshold, the weight of the remaining feature data is determined according to the proportion of the feature data exceeding the preset data threshold; After determining the weights of all characteristic data, the data are input into the prediction model to predict the load of the heating area to obtain a first predicted load; The step of calculating the heat loss of the pipe network according to the operation status of the heating system and correcting the first predicted load according to the heat loss value to obtain the second predicted load includes: The operation data of the pipelines in the heating area are obtained, and the heat dissipation loss of the pipelines is calculated according to the operation data. The calculation formula is: in, is the outer diameter of the insulation layer of each pipeline, in m; is the length of pipes with different diameters and different outer diameters of insulation layers, in meters; It is the heat loss per unit area of ​​pipes with different pipe diameters and different outer diameters of insulation layers, in W / m2; in, The calculation formula is: in, is the steam temperature in the pipeline, unit K; is the external environment temperature, unit K; is the insulation outer diameter of the pipe, in m; is the equivalent thermal conductivity of the insulation material, unit: W / (m*K); is the outer diameter of the metal pipe, in m; is the heat transfer coefficient between the outer surface of the insulation layer and the surrounding air, in units of W / (m2*K); The data information of the heat source and the heat user in the heating area is obtained, and the drainage quality loss of the heating is calculated. The calculation formula is: in, is the heat dissipation loss of the pipe network; is the enthalpy of the superheated steam at the heat source outlet; is the enthalpy of the overall saturated state at the heat source outlet; is the enthalpy value of the superheated steam at the inlet of each heat user; is the enthalpy of the steam saturation state at the inlet of each heat user; is the outlet mass of the heat source; The gas quality for each heat user; Latent is the latent heat of vaporization of steam; The air leakage mass loss in the heating area is calculated using the following formula: The heat loss of the heating area is calculated by the heat dissipation loss of the pipe network, the water drainage mass loss and the air leakage mass loss, and the calculation formula is: in, is the heat loss value of the heating area; The drainage quality loss of each heat user; is the hydrophobic enthalpy of each heat user; The gas leakage quality loss of each heat user; is the leakage enthalpy value of each heat user; Correcting the first predicted load according to the heat loss value of the heating area to obtain a second predicted load; After obtaining the predicted load of the heating system, it also includes: The actual heat loss of the heating area is obtained by the following calculation formula: in, is the outlet mass of the heat source; is the outlet enthalpy of the heat source; Export quality for heat users; is the outlet enthalpy of the heat user; The deviation value is calculated by comparing the actual heat loss with the calculated heat loss. The calculation formula is: like If the deviation is greater than the preset threshold, The difference between the deviation threshold Make adjustments.

Citation Information

Patent Citations

  • Heat supply network system load prediction-based heat supply joint control method and system

    CN116255665A