Heat exchange station thermal load correction method considering building thermal characteristics

Abstract

A heat exchange station heat load correction method considering building heat characteristics mainly comprises the following steps that S1, operation parameters and weather parameters of a heating station and a user position are obtained, and the operation parameters and the weather parameters mainly comprise the heat supply amount of the heat exchange station, the secondary network water supply temperature, the secondary network water return temperature, the heat supply area of the user and the outdoor dry-bulb temperature; s2, the indoor temperature Tin, 0 of a user at a certain moment or in a certain period of time is collected, and a building heat exchange characteristic parameter BC0 is calculated according to the outdoor dry-bulb temperature and the two-network supply and return water temperature at the current moment or in the current period of time; and S3, complementing the indoor temperature of the user at other moments according to the building heat exchange characteristic parameter BC0. And S4, according to the two-network supply and return water temperature and the outdoor dry-bulb temperature at each moment and the building heat exchange characteristic parameter BC0 obtained through calculation in the step S2, actual indoor temperatures at all moments are obtained through calculation. And S5, according to the outdoor dry-bulb temperature, the indoor temperature of the user and the heat supply area of the user, a relation model of the indoor temperature of the user and the heat load of the heat exchange station is constructed. And according to the existing operation parameters, identifying the heat capacity C'of the unit heat supply area in the model and the indoor heat loss mu under the unit temperature difference of the unit heat supply area by adopting a particle swarm algorithm. And S6, the heat load of the heat exchange station is corrected by using the relation model of the indoor temperature of the user and the heat load of the heating station, and the corrected heat load can be used as input data of load prediction.

Description

Technical Field

[0001] The invention relates to the field of heating pipe networks, and in particular to a heat load correction method for a heat exchange station taking into account thermal characteristics of a building. Background Art

[0002] In my country, building energy consumption accounts for 36.3% of the total national energy consumption, and building energy consumption in the operation stage accounts for 60.4% of building energy consumption; among them, building heating is an important part of building energy consumption in the operation stage. The regional heating system is the main means to solve the problem of building heating. In order to ensure the economic and stable operation of the heating system, it is necessary to accurately predict the heat load at the user end at each moment, so as to formulate a reasonable scheduling plan. At present, the heat load of the heat exchange station is generally predicted by setting sensors at the heat exchange station and using the historical heat load data of the heat exchange station. However, there is a difference between the heat load of the heat exchange station and the actual user load, and the heat supply at the heat exchange station may exceed or fail to reach the heat supply required by the user, that is, overheating and insufficient heating. At this time, the historical heat load data cannot accurately reflect the changes in the heat load on the user side. Therefore, when these data are used to predict the heat load, there may be a large deviation between the predicted results and the actual heat load required by the user.

[0003] At present, in order to determine whether the heat supply of the heat exchange station can just meet the heat load demand on the user side, it is necessary to install a temperature sensor on the user side to correct the heat load of the heat exchange station through the change of indoor temperature. However, in engineering applications, most district heating systems do not have indoor temperature sensors installed on the user side, making it difficult to correct the heat load. It is a reasonable solution to determine the thermal characteristics of the building through the indoor temperature values ​​at a few moments, thereby completing the user's indoor temperature and then correcting the heat load of the heat exchange station. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and provide a heat exchange station heat load correction method taking into account the thermal characteristics of the building.

[0005] The object of the present invention can be achieved by the following technical solution: A method for correcting the heat load of a heat exchange station considering the thermal characteristics of a building, mainly comprising the following steps:

[0006] Step S1: Obtain the historical operation data of the heat exchange station at each time and the corresponding outdoor meteorological parameters. The historical operation data includes the secondary network water supply temperature T s2,i (℃), secondary network return water temperature T r2,i (℃); Outdoor meteorological parameters mainly include outdoor dry bulb temperature T out,i (℃), subscript i represents time i. In addition, it is also necessary to obtain the user's heating area (m 2 ).

[0007] Step S2: Obtain the user's indoor temperature T at a certain time or period within the time range of the historical operation data in,0 , and calculate the building heat transfer characteristic parameter BC0 according to the following formula:

[0008]

[0009] Where: T in,0 is the indoor temperature of the user at a certain moment, ℃; T out,0 is the outdoor dry-bulb temperature at that moment, ℃; T s2,0 is the water supply temperature of the second network at that moment, ℃; T r2,0 is the return water temperature of the second network at that moment, ℃.

[0010] If there is only one user indoor temperature at a time, BC0 is calculated according to the above formula; if there is one period or multiple times of user indoor temperature data, BC0 is calculated at each time and its average value is calculated. As a building heat transfer characteristic parameter.

[0011] Step S3: Using the already obtained building heat exchange characteristic parameters and the historical operation data of the heat exchange station, the missing user indoor temperature at other times is completed according to the following formula:

[0012]

[0013] Where: T in,i is the indoor temperature at time i, ℃; T out,i is the outdoor dry-bulb temperature at time i, ℃; T s2,i is the water supply temperature of the second network at time i, ℃; T r2,i is the return water temperature of the second network at time i, ℃; BC0 is the building heat exchange characteristic parameter.

[0014] Step S4: construct a relationship model between the user's indoor temperature and the heat load of the heat exchange station, and use a particle swarm algorithm to identify the parameters in the model.

[0015] Step S401: construct a relationship model between the user's indoor temperature and the heat load of the heat exchange station according to the following formula:

[0016] k3t in,i -T in,i-1 =k1H i +k2T out,i

[0017]

[0018] Where: H i is the heat load of the heat exchange station at time i, W; T in,i is the indoor temperature at time i, ℃; T in,i-1is the indoor temperature at time i-1, ℃; T out,i is the outdoor dry-bulb temperature at time i, ℃; Δt is the data collection interval, s; C' is the heat capacity per unit heating area, J / (m 2 ·℃); S is the user's heating area, m 2 ; μ is the indoor heat loss per unit heating area per unit temperature difference, W / (m 2 ·℃).

[0019] Step S402: Taking the user's indoor temperature, outdoor dry-bulb temperature, data collection interval and user's heating area at each moment as input data, a particle swarm algorithm is used to identify the heat capacity C' per unit heating area and the indoor heat loss μ per unit heating area per unit temperature difference. The specific steps are as follows:

[0020] Step S4021: The heat capacity C' per unit heating area and the indoor heat loss μ per unit heating area per unit temperature difference are used as variables to set the size of the particle swarm and the number of iterations.

[0021] Step S4022: Initialize the initial position and initial velocity of the particle swarm;

[0022] Step S4023: Calculate the objective function f of each particle and find the optimal value of the individual and the group. The objective function is defined as follows:

[0023]

[0024] In the formula, f is the objective function value; n is the total number of historical operation data moments. In addition, the optimization range of each optimization variable is as follows:

[0025] μ,C'∈[0,1×10 8 ]

[0026] Step S4024: Update the speed and position of each particle according to the following formula:

[0027]

[0028] Where: ω is the inertia factor; C1 and C2 are acceleration constants, generally C1=C2∈[0,4]; random(0,1) is a random number on [0,1]. id is the individual optimal solution, P gd It is the global optimal solution.

[0029] Step S4025: The termination condition is whether the maximum number of iterations is reached. It is determined whether the termination condition is currently met. If so, the calculation ends and the global optimal solution C' and μ are output; if not, steps S4023-S4024 are repeated until the termination condition is met.

[0030] Step S5: Bring the optimized C' and μ back to the relationship model between the user's indoor temperature and the heat load of the heat exchange station, as shown in the following formula:

[0031] k3t in,i,set -T in,i-1,set =k1H i +k2T out,i

[0032] Among them, T in,i,set and T in,i-1,set are the ideal indoor temperatures at time i and time i-1 respectively. The above formula can be used to obtain the heat load correction value of the heat exchange station at each time during the historical operation, so that the corrected heat load data can be used as the training data of the load prediction model.

[0033] Compared with the prior art, the advantages and positive effects of the present invention are:

[0034] (1) Taking into account the thermal characteristics of the building, a small amount of indoor temperature data is used to complete the indoor temperature values ​​of the entire historical operation period, thus avoiding the difficulty of heat load correction caused by insufficient indoor temperature data.

[0035] (2) In the process of heat load correction, the heat exchange station operation data, the completed indoor temperature data and the outdoor temperature data are taken into account at the same time, thereby improving the accuracy of the model.

[0036] (3) The particle swarm algorithm is used to identify the parameters in the model, which improves the identification effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 Flow chart of a heat exchange station heat load correction method considering building thermal characteristics

[0038] Figure 2 The indoor temperature completion result for a certain day in the embodiment

[0039] Figure 3 The heat load correction result of the heat exchange station in the embodiment is DETAILED DESCRIPTION

[0040] The present invention will be described in more detail below with reference to the accompanying drawings, in which preferred embodiments of the present invention are shown, and it should be understood that those skilled in the art can modify the present invention described herein and still achieve the beneficial effects of the present invention. Therefore, the following description should be understood as being widely known to those skilled in the art, and not as a limitation of the present invention.

[0041] For the sake of clarity, not all features of the actual embodiments are described. In the following description, well-known functions and structures are not described in detail because they would obscure the present invention with unnecessary details. It should be recognized that in the development of any actual embodiment, a large number of implementation details must be made to achieve the specific goals of the developer.

[0042] In order to make the purpose and features of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are further described below in conjunction with the accompanying drawings. The present application first provides a heat exchange station heat load correction method considering the thermal characteristics of the building, comprising the following steps: Figure 1 shown.

[0043] Step S1: Obtain the historical operation data of the heat exchange station at each time and the corresponding outdoor meteorological parameters. The historical operation data includes the secondary network water supply temperature T s2,i (℃), secondary network return water temperature T r2,i (℃); Outdoor meteorological parameters mainly include outdoor dry bulb temperature T out,i (℃), subscript i represents time i. In addition, it is also necessary to obtain the user's heating area (m 2 ).

[0044] The example is the Agricultural Bank of China heat exchange station in Lanzhou New District’s heating network, which has a heating area of ​​approximately 35,000 m 2 The historical operating data of some moments are shown in the following table.

[0045] Table 1 Historical operation data of Agricultural Bank of China heat exchange station in Lanzhou New District heating network (partial)

[0046]

[0047]

[0048] Step S2: Obtain the user's indoor temperature T at a certain time or period within the time range of the historical operation data in,0 , and calculate the building heat transfer characteristic parameter BC0 according to the following formula:

[0049]

[0050] Where: T in,0 is the indoor temperature of the user at a certain moment, ℃; T out,0 is the outdoor dry-bulb temperature at that moment, ℃; T s2,0 is the water supply temperature of the second network at that moment, ℃; T r2,0 is the return water temperature of the second network at that moment, ℃.

[0051] If there is only one user indoor temperature at a time, BC0 is calculated according to the above formula; if there is one period or multiple times of user indoor temperature data, BC0 is calculated at each time and its average value is calculated. As a building heat transfer characteristic parameter.

[0052] In the embodiment, the indoor temperature collected at 0:00 on December 1, 2021 is 20.12° C. Based on the indoor temperature, the building heat exchange characteristic parameter BC0 is calculated to be 0.6028.

[0053] Step S3: Using the already obtained building heat exchange characteristic parameters and the historical operation data of the heat exchange station, the missing user indoor temperature at other times is completed according to the following formula:

[0054]

[0055] Where: T in,i is the indoor temperature at time i, ℃; T out,i is the outdoor dry-bulb temperature at time i, ℃; T s2,i is the water supply temperature of the second network at time i, ℃; T r2,i is the return water temperature of the second network at time i, ℃; BC0 is the building heat exchange characteristic parameter.

[0056] In the embodiment, the indoor temperature of the user during the heating operation cycle is obtained by using the building heat exchange characteristic parameter BC0. Taking December 1, 2021 as an example, the indoor temperature curve is as follows: Figure 2 shown.

[0057] Step S4: construct a relationship model between the user's indoor temperature and the heat load of the heat exchange station, and use a particle swarm algorithm to identify the parameters in the model.

[0058] Step S401: construct a relationship model between the user's indoor temperature and the heat load of the heat exchange station according to the following formula:

[0059] k3t in,i -T in,i-1 =k1H i +k2T out,i

[0060]

[0061] Where: H i is the heat load of the heat exchange station at time i, W; T in,i is the indoor temperature at time i, ℃; T in,i-1 is the indoor temperature at time i-1, ℃; T out,i is the outdoor dry-bulb temperature at time i, ℃; Δt is the data collection interval, s; C' is the heat capacity per unit heating area, J / (m 2 ·℃); S is the user's heating area, m 2 ; μ is the indoor heat loss per unit heating area per unit temperature difference, W / (m 2 ·℃).

[0062] Step S402: Taking the user's indoor temperature, outdoor dry-bulb temperature, data collection interval and user's heating area at each moment as input data, a particle swarm algorithm is used to identify the heat capacity C' per unit heating area and the indoor heat loss μ per unit heating area per unit temperature difference. The specific steps are as follows:

[0063] Step S4021: The heat capacity C' per unit heating area and the indoor heat loss μ per unit heating area per unit temperature difference are used as variables to set the size of the particle swarm and the number of iterations.

[0064] In the embodiment, the size of the particle swarm and the number of iterations are both assumed to be 100.

[0065] Step S4022: Initialize the initial position and initial velocity of the particle swarm;

[0066] In the embodiment, a random generation method is used to initialize the initial position and initial velocity of the particle group.

[0067] Step S4023: Calculate the objective function f of each particle and find the optimal value of the individual and the group. The objective function is defined as follows:

[0068]

[0069] In the formula, f is the objective function value; n is the total number of historical operation data moments. In addition, the optimization range of each optimization variable is as follows:

[0070] μ,C'∈[0,1×10 8 ]

[0071] Step S4024: Update the speed and position of each particle according to the following formula:

[0072]

[0073] Where: ω is the inertia factor; C1 and C2 are acceleration constants, generally C1=C2∈[0,4]; random(0,1) is a random number on [0,1]. id is the individual optimal solution, P gd It is the global optimal solution.

[0074] In the embodiment, it is assumed that ω = 0.5, C1 = C2 = 2. The above parameter values ​​are used to perform the solution.

[0075] Step S4025: The termination condition is whether the number of iterations reaches the specified number of generations. It is determined whether the termination condition is currently met. If so, the calculation ends and the global optimal solution C' and μ are output; if not, steps S4023-S4024 are repeated until the termination condition is met.

[0076] In the embodiment, the historical operation data of the Agricultural Bank of China heat exchange station from 0:00 on December 1, 2021 to 23:00 on January 15, 2022 is used as the data for objective function calculation. After optimization using the particle swarm algorithm, the parameter identification results are obtained as follows:

[0077] μ=0.2824

[0078] C'=1.8125×10 4

[0079] Step S5: Bring the optimized C' and μ back to the relationship model between the user's indoor temperature and the heat load of the heat exchange station, as shown in the following formula:

[0080] k3t in,i,set -T in,i-1,set =k1H i +k2T out,i

[0081] Among them, T in,i,set and T in,i-1,set are the ideal indoor temperatures at time i and time i-1 respectively. The above formula can be used to obtain the heat load correction value of the heat exchange station at each time during the historical operation, so that the corrected heat load data can be used as the training data of the load prediction model.

[0082] In the embodiment, let T in,i,set and T in,i-1,set The ideal indoor temperature is set to 20°C. By inputting the user's indoor temperature and outdoor dry-bulb temperature into the model, the load correction value from 0:00 on January 16, 2022 to 23:00 on February 8, 2022 is as follows: Figure 3 As shown in the figure, it can be seen that compared with the heat load provided by the heat exchange station, the corrected heat load has a stronger periodicity, and the load changes regularly within a range without a more drastic increase or decrease in the amount of heat supplied. Such heat exchange station heat load data is more in line with the user's heat usage characteristics and can improve the quality of input data when training the load prediction model.

Claims

1. A heat exchange station heat load correction method considering building thermal characteristics, characterized in that: The following steps are involved: Step S1: Obtain the operating parameters and weather parameters of the heating station and the user, including: secondary network water supply temperature, secondary network return water temperature, user heating area and outdoor dry bulb temperature. Step S2: Collect the user's indoor temperature T at a certain time or a certain period of time in,0 , and calculate the building heat exchange characteristic parameter BC0 according to the outdoor dry bulb temperature and the second network supply and return water temperature at the current time or time period; step S3: supplement the user's indoor temperature at other times according to the building heat exchange characteristic parameter BC0. Step S4: calculate the actual indoor temperature at all times according to the second network supply and return water temperature and the outdoor dry bulb temperature at each time, and the building heat exchange characteristic parameter BC0 calculated in step S2. Step S5: construct a relationship model between the user's indoor temperature and the heat load of the heat exchange station according to the outdoor dry bulb temperature, the user's indoor temperature and the user's heating area. And according to the existing operating parameters, the particle swarm algorithm is used to identify the heat capacity C' per unit heating area in the model and the indoor heat loss μ per unit temperature difference per unit heating area. Step S6: Use the relationship model between the user's indoor temperature and the heat load of the thermal power station to correct the heat load of the heat exchange station, and the corrected heat load can be used as input data for load prediction.

2. A heat exchange station heat load correction method considering building thermal characteristics according to claim 1, characterized in that: Obtain the historical operation data of the heat exchange station at each time and the corresponding outdoor meteorological parameters. The historical operation data includes the secondary network water supply temperature T s2,i (℃), secondary network return water temperature T r2,i (℃); Outdoor meteorological parameters mainly include outdoor dry bulb temperature T out,i (℃), subscript i represents time i. In addition, it is also necessary to obtain the user's heating area (m 2 ).

3. A heat exchange station heat load correction method considering building thermal characteristics according to claim 1, characterized in that: Get the user's indoor temperature T at a certain time or period within the time range of historical operation data in,0 , and calculate the building heat transfer characteristic parameter BC0 according to the following formula: Where: T in,0 is the indoor temperature of the user at a certain moment, ℃; T out,0 is the outdoor dry-bulb temperature at that moment, ℃; T s2,0 is the water supply temperature of the second network at that moment, ℃; T r2,0 is the return water temperature of the second network at that moment, ℃. If there is only one user indoor temperature at a time, BC0 is calculated according to the above formula; if there is one period or multiple times of user indoor temperature data, BC0 is calculated at each time and its average value is calculated. As a building heat transfer characteristic parameter.

4. A heat exchange station heat load correction method considering building thermal characteristics according to claim 1, characterized in that: Using the already obtained building heat exchange characteristic parameters and the historical operation data of the heat exchange station, the missing user indoor temperature at other times is completed according to the following formula: Where: T in,i is the indoor temperature at time i, ℃; T out,i is the outdoor dry-bulb temperature at time i, ℃; T s2,i is the water supply temperature of the second network at time i, ℃; T r2,i is the return water temperature of the second network at time i, ℃; BC0 is the building heat exchange characteristic parameter.

5. The method for correcting heat load of a heat exchange station considering thermal characteristics of a building according to claim 1, characterized in that: Construct a relationship model between the user's indoor temperature and the heat load of the heat exchange station as follows: k3T in,i -T in,i-1 =k1H i +k2T out,i Where: H i is the heat load of the heat exchange station at time i, W; T in,i is the indoor temperature at time i, ℃; T in,i-1 is the indoor temperature at time i-1, ℃; T out,i is the outdoor dry-bulb temperature at time i, °C; Δt is the data collection interval, s; C' is the heat capacity per unit heating area, J / (m 2 ·℃); S is the user's heating area, m 2 ; μ is the indoor heat loss per unit heating area per unit temperature difference, W / (m 2 ·℃).

6. A heat exchange station heat load correction method considering building thermal characteristics according to claim 5, characterized in that: The user's indoor temperature, outdoor dry-bulb temperature, data collection interval and user's heating area at each moment are taken as input data, and the particle swarm algorithm is used to identify the heat capacity C' per unit heating area and the indoor heat loss μ per unit heating area and unit temperature difference.

7. A heat exchange station heat load correction method considering building thermal characteristics according to claim 6, characterized in that: The heat capacity C' per unit heating area and the indoor heat loss μ per unit heating area and unit temperature difference are taken as optimization variables.

8. A heat exchange station heat load correction method considering building thermal characteristics according to claim 7, characterized in that: When using the particle swarm algorithm for parameter identification, the objective function is set according to the following formula: Where f is the objective function value; n is the total number of moments of historical operation data.

9. A heat exchange station heat load correction method considering building thermal characteristics according to claim 8, characterized in that: When using the particle swarm algorithm for parameter identification, the following conditions are set for the optimization range of the optimization variables: μ,C'∈[0.1×10 8 ] 10. The method for correcting heat load of a heat exchange station considering thermal characteristics of a building according to claim 1, characterized in that: The identified parameters are input into the relationship model between the user's indoor temperature and the heat load of the heat exchange station, as shown in the following formula: k3T in,i,set -T in,i-1,set =k1H i +k2T out,i Among them, T in,i,set and T in,i-1,set are the ideal indoor temperatures at time i and time i-1 respectively. The above formula can be used to obtain the heat load correction value of the heat exchange station at each time during the historical operation, so that the corrected heat load data can be used as the training data of the load prediction model.

Images