Air conditioning load prediction model generation method, air conditioning load prediction method and device

Abstract

The application provides an air conditioner load prediction model generation method, an air conditioner load prediction method and device, and relates to the technical field of computers. The method comprises the following steps: constructing an initial prediction model of an air conditioner in a preset place, wherein the initial prediction model comprises an association relationship between a heat regulation term of the air conditioner and multiple-dimension load terms; wherein the load term is an influencing factor of heat regulation of the air conditioner; obtaining heat regulation data of the air conditioner in a plurality of preset continuous historical time periods and multiple-dimension load data of each historical time period; solving coefficients corresponding to the multiple-dimension load terms in the association relationship according to the heat regulation data and the multiple-dimension load data, to obtain multiple-dimension coefficients; and obtaining a target prediction model of the air conditioner according to the initial prediction model and the multiple-dimension coefficients. The application can provide a general air conditioner load prediction model, and realize heat prediction of air conditioners in various places.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically, to a method for generating an air conditioning load prediction model, an air conditioning load prediction method, and an apparatus. Background Technology

[0002] With the rapid development of the rail transit industry, how to reduce operational energy consumption has gradually become a research hotspot for rail transit operators.

[0003] Rail transit has a large energy consumption base, among which the energy consumption of the air conditioning system in the station accounts for a very large proportion, exceeding 40% of the electricity consumption. Therefore, reducing the energy consumption of the air conditioning system in rail transit stations is very important.

[0004] Existing technologies mainly use neural network models as the primary technology for predicting air conditioning load. However, since neural network models are black box models, on the one hand, they require specific training for different locations and lack universality; on the other hand, technicians find it difficult to understand their internal structure and cannot adjust and optimize the model according to heat regulation needs. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of the prior art by providing a method for generating an air conditioning load prediction model, an air conditioning load prediction method, and an apparatus, so as to provide a universal air conditioning load prediction model and enable the prediction of heat from air conditioning equipment in various locations.

[0006] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: In a first aspect, embodiments of this application provide a method for generating an air conditioning load prediction model, the method comprising: An initial prediction model for air conditioning equipment in a pre-defined location is constructed. The initial prediction model includes the correlation between the heat regulation item of the air conditioning equipment and load items of multiple dimensions; wherein, the load item is the influencing factor for the heat regulation of the air conditioning equipment. Acquire the heat regulation data of the air conditioning equipment in multiple preset consecutive historical time periods and the load data of the multiple dimensions in each historical time period; Based on the heat regulation data and the load data of the multiple dimensions, the coefficients corresponding to the load items of the multiple dimensions in the correlation are solved to obtain the coefficients of the multiple dimensions; Based on the initial prediction model and the coefficients of the multiple dimensions, the target prediction model of the air conditioning equipment is obtained.

[0007] Optionally, the construction of the initial prediction model for the air conditioning equipment in the preset location includes: Based on the parameter items of each dimension and the coefficients of each dimension, construct the load item for each dimension; The heat regulation item is constructed based on the operating parameters of the air conditioning equipment; The initial prediction model is constructed based on the load terms of the multiple dimensions and the heat regulation term.

[0008] Optionally, the load terms of the multiple dimensions include: an air enthalpy difference load term, the coefficient of which is an air quality coefficient; the step of constructing the load term for each dimension based on the parameter terms of each dimension and the coefficients of each dimension includes: The air enthalpy difference load term is constructed based on the air quality coefficient, the indoor air enthalpy parameter at adjacent times, and the time difference between adjacent times.

[0009] Optionally, the load items of the multiple dimensions further include: a personnel load item, the coefficient of which is an average heat generation power coefficient; the step of constructing the load item of each dimension based on the parameter items of each dimension and the coefficient of each dimension includes: The personnel load term is constructed based on the average heat generation power coefficient and the personnel flow parameter.

[0010] Optionally, the load items of the multiple dimensions further include: a device load item, wherein the coefficient of the device load item is a device heat generation power coefficient; the step of constructing the load item of each dimension based on the parameter items of each dimension and the coefficient of each dimension includes: Based on the device's heat generation power coefficient, construct the device load term.

[0011] Optionally, the load terms of the multiple dimensions further include: an infiltration air load term, wherein the coefficient of the infiltration air load term is an air infiltration rate coefficient; the construction of the load term for each dimension based on the parameter terms of each dimension and the coefficients of each dimension includes: The infiltration wind load term is constructed based on the air infiltration rate coefficient, the indoor air enthalpy parameter of the preset location, and the outdoor air enthalpy parameter of the preset location.

[0012] Optionally, the load items of the multiple dimensions further include: a fan load item, wherein the coefficient of the fan load item is a unit air volume coefficient; the step of constructing the load item of each dimension based on the parameter items of each dimension and the coefficient of each dimension includes: The fan load is determined based on the unit air volume coefficient, the indoor air enthalpy parameter of the preset location, the outdoor air enthalpy parameter of the preset location, and the fan operating parameters of the air conditioning equipment.

[0013] Secondly, embodiments of this application also provide an air conditioning load forecasting method, the method comprising: Obtain load data from multiple dimensions of the air conditioning equipment in the preset location at the current moment; Based on the load data from the multiple dimensions, the target prediction model of the air conditioning equipment is used to calculate the heat adjustment parameters for the future time, so as to adjust the heat transport capacity of the air conditioning equipment according to the heat adjustment parameters. The target prediction model is obtained by the air conditioning load prediction model generation method as described in any of the first aspects above.

[0014] Thirdly, embodiments of this application also provide an air conditioning load prediction model generation device, the device comprising: An initial model building module is used to build an initial prediction model for air conditioning equipment in a preset location. The initial prediction model includes the correlation between the heat regulation item of the air conditioning equipment and load items of multiple dimensions; wherein, the load item is the influencing factor for the heat regulation of the air conditioning equipment. The historical data acquisition module is used to acquire the heat regulation data of the air conditioning equipment in a preset continuous series of historical time periods and the load data of the multiple dimensions in each historical time period. The coefficient calculation module is used to solve for the coefficients corresponding to the load items of the multiple dimensions in the correlation relationship based on the heat regulation data and the load data of the multiple dimensions, so as to obtain the coefficients of the multiple dimensions. The target model generation module is used to obtain the target prediction model of the air conditioning equipment based on the initial prediction model and the coefficients of the multiple dimensions.

[0015] Optionally, the initial model building module includes: The load term construction unit is used to construct the load term for each dimension based on the parameter terms of each dimension and the coefficients of each dimension. A heat regulation item construction unit is used to construct the heat regulation item based on the operating parameters of the air conditioning equipment; An initial model building unit is used to build the initial prediction model based on the load items of the multiple dimensions and the heat regulation item.

[0016] Optionally, the load items of the multiple dimensions include: an air enthalpy difference load item, the coefficient of which is an air quality coefficient; the load item construction unit is specifically used to construct the air enthalpy difference load item based on the air quality coefficient, the indoor air enthalpy parameter item at adjacent times, and the time difference between adjacent times.

[0017] Optionally, the load items of the multiple dimensions further include: personnel load item, the coefficient of which is the average heat generation power coefficient; the load item construction unit is specifically used to construct the personnel load item based on the average heat generation power coefficient and the personnel flow parameter item.

[0018] Optionally, the load items of the multiple dimensions further include: a device load item, wherein the coefficient of the device load item is a device heat generation power coefficient; the load item construction unit is specifically used to construct the device load item based on the device heat generation power coefficient.

[0019] Optionally, the load items of the multiple dimensions further include: an infiltration air load item, the coefficient of which is an air infiltration rate coefficient; the load item construction unit is specifically used to construct the infiltration air load item based on the air infiltration rate coefficient, the indoor air enthalpy parameter of the preset location, and the outdoor air enthalpy parameter of the preset location.

[0020] Optionally, the load items of the multiple dimensions further include: a fan load item, wherein the coefficient of the fan load item is a unit air volume coefficient; the load item construction unit is specifically used to construct and determine the fan load item based on the unit air volume coefficient, the indoor air enthalpy parameter item of the preset location, the outdoor air enthalpy parameter item of the preset location, and the fan operating parameter item of the air conditioning equipment.

[0021] Fourthly, embodiments of this application also provide an air conditioning load prediction device, the device comprising: The data acquisition module is used to acquire load data of air conditioning equipment in a preset location at the current moment from multiple dimensions. The heat calculation module is used to calculate the heat adjustment parameters for a preset future time based on the load data of the multiple dimensions and the target prediction model of the air conditioning equipment, so as to adjust the heat transport capacity of the air conditioning equipment according to the heat adjustment parameters. The target prediction model is obtained by the air conditioning load prediction model generation method as described in any of the first aspects above.

[0022] Fifthly, embodiments of this application also provide a computer device, including: a processor, a storage medium, and a bus, wherein the storage medium stores program instructions executable by the processor, and when the computer device is running, the processor communicates with the storage medium via the bus, and the processor executes the program instructions to perform the steps of the air conditioning load forecasting model generation method as described in any of the first aspects, or the steps of the air conditioning load forecasting method as described in the second aspect.

[0023] In a sixth aspect, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the air conditioning load forecasting model generation method as described in any of the first aspects, or the steps of the air conditioning load forecasting method as described in the second aspect.

[0024] The beneficial effects of this application are: The air conditioning load prediction model generation method, air conditioning load prediction method and device provided in this application predict the heat adjustment data of air conditioning equipment at a preset future time based on the target prediction model. On the one hand, it can provide a basis for the advance adjustment of air conditioning equipment, avoid the lag in the system's response to the control of air conditioning equipment, and save energy consumption while ensuring the comfort of the internal temperature of the preset place. On the other hand, since the load items of air conditioning equipment in various places are basically the same, the target prediction model is more universal. Moreover, the prediction model constructed by using the correlation between load items and heat adjustment items in various dimensions makes it easier for technicians to understand the meaning of each input item of the prediction model and the degree of influence on the predicted heat, and facilitates the structural optimization and parameter adjustment of the prediction model based on different places. Attached Figure Description

[0025] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is an architecture diagram of the air conditioning load forecasting system provided in the embodiments of this application; Figure 2 A flowchart illustrating the air conditioning load prediction model generation method provided in this application embodiment. Figure 1 ; Figure 3 A flowchart illustrating the air conditioning load prediction model generation method provided in this application embodiment. Figure 2 ; Figure 4 A flowchart illustrating the air conditioning load forecasting method provided in this application embodiment; Figure 5 This is a schematic diagram of the structure of the air conditioning load prediction model generation device provided in the embodiments of this application; Figure 6 This is a schematic diagram of the structure of the air conditioning load prediction device provided in the embodiments of this application; Figure 7 A schematic diagram of a computer device provided in the embodiments of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments.

[0028] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0029] In the description of this application, it should be noted that if the terms "upper", "lower", etc. appear to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship that the product of this application is usually placed in, it is only for the convenience of describing this application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0030] Furthermore, the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Additionally, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] It should be noted that, where there is no conflict, the features in the embodiments of this application can be combined with each other.

[0032] Before introducing the air conditioning load prediction model generation method, air conditioning load prediction method and device provided in this application, the application scenario will be explained first.

[0033] The air conditioning load prediction model generation method, air conditioning load prediction method and device provided in this application can be applied to the preset location of rail transit stations, such as subway stations. Of course, they can also be applied to other places that need to regulate heat through air conditioning equipment, such as shopping malls, hospitals, office buildings, etc. This application does not limit them.

[0034] Please refer to Figure 1 Here is an architecture diagram of the air conditioning load forecasting system provided in this application embodiment, as shown below. Figure 1 As shown, the air conditioning load prediction system includes: air conditioning equipment, indoor temperature sensor, indoor humidity sensor, outdoor temperature sensor, outdoor humidity sensor, image sensor (or infrared sensor), air conditioning return water temperature sensor, air conditioning outlet water temperature sensor, flow rate sensor, and computer equipment. The computer equipment is communicatively connected to the air conditioning equipment and each sensor to obtain the operating data of the air conditioning equipment and the detection data of each sensor.

[0035] The indoor temperature sensor and indoor humidity sensor are installed at preset locations in the preset location to acquire indoor temperature and humidity data, so that the computer equipment can calculate the indoor air enthalpy data of the preset location based on the indoor temperature and humidity data.

[0036] Outdoor temperature and humidity sensors are installed at preset outdoor locations in a preset environment to acquire outdoor temperature and humidity data, enabling computer equipment to calculate the outdoor air enthalpy value of the preset environment based on the outdoor temperature and humidity data.

[0037] An image sensor (or infrared sensor) is installed at a predetermined indoor location in a predetermined venue to acquire images or infrared data within the venue, enabling computer equipment to analyze pedestrian traffic data based on the images or infrared data.

[0038] An air conditioner return water temperature sensor is installed at the inlet of the air conditioner to obtain the return water temperature data. An air conditioner outlet water temperature sensor is installed at the outlet of the air conditioner to obtain the outlet water temperature data. A flow rate sensor is installed inside the water pipe of the air conditioner to obtain the water flow rate data in the water pipe. This allows the computer equipment to calculate the heat regulation data of the air conditioner based on the return water temperature data, outlet water temperature data, and water flow rate data.

[0039] In addition, the pre-designed venue also includes a variety of indoor heating devices. Indoor heating devices are various devices that generate heat when in operation within the pre-designed venue, such as lighting equipment, escalators, vertical lifts, automatic ticket vending machines, advertising light boxes, etc. The types of heating devices vary in different venues and can be determined according to actual needs. Since the heat generated by the heating devices is generally steady-state heat, the change is not significant at different times of the day.

[0040] It should be noted that although the above text states that the indoor temperature sensor, indoor humidity sensor, and image sensor (or infrared sensor) are all installed in preset indoor locations, it does not mean that these sensors are all installed in the same indoor location. The specific installation location and number can be set according to requirements. Similarly, the outdoor temperature sensor and outdoor humidity sensor are not necessarily installed in the same outdoor location. The specific installation location and number can be set according to requirements, and this application does not impose too many restrictions on this.

[0041] Please refer to Figure 2 This is a flowchart illustrating the air conditioning load prediction model generation method provided in this application embodiment. Figure 1 ,like Figure 2 As shown, the method may include: S10: Construct an initial prediction model for the air conditioning equipment in the preset location.

[0042] The initial prediction model includes the correlation between the heat regulation term of the air conditioning equipment and the load terms of multiple dimensions; among which, the load terms are the influencing factors of the heat regulation of the air conditioning equipment.

[0043] In this embodiment, the heat adjustment item of the air conditioning equipment is used to indicate the heat transfer capacity of the air conditioning equipment. If the air conditioning equipment is used for cooling, the heat transfer capacity is the total amount of heat removed by the air conditioning equipment from the preset location; if the air conditioning equipment is used for heating, the heat transfer capacity is the total amount of heat provided by the air conditioning equipment in the preset location.

[0044] Multiple load items are used to indicate the load that causes heat changes or the presence of heat in the preset location. The load refers to the rate of change of heat transport over time, that is, the power of heat transport. As a factor affecting the heat regulation of air conditioning equipment, the more load items there are, the greater the impact on the heat regulation of air conditioning equipment; or the greater the heat of the load item and the greater the heat change it causes, the greater the impact on the heat regulation of air conditioning equipment.

[0045] The load items of multiple dimensions can be multiple influencing factors that affect the heat regulation of air conditioning equipment, such as: air enthalpy dimension, equipment heat dimension, personnel heat dimension, etc.

[0046] The correlation between the heat regulation term of the air conditioning equipment and the load term of each dimension is used to indicate the degree of influence of the load term of each dimension on the heat regulation of the air conditioning equipment. Based on the degree of influence of the load terms of multiple dimensions on the heat regulation of the air conditioning equipment, an initial prediction model is constructed, wherein the degree of influence of the load term of each dimension on the heat regulation of the air conditioning equipment in the initial prediction model is an unknown coefficient.

[0047] S20: Obtain heat regulation data of the air conditioning equipment in multiple preset consecutive historical time periods and load data of multiple dimensions in each historical time period.

[0048] In this implementation, in order to determine the degree of influence of the load item of each dimension in the initial prediction model on the heat regulation of the air conditioning equipment, it is necessary to perform calculations based on historical heat regulation data and historical load data of multiple dimensions. For this purpose, it is necessary to obtain the heat regulation data of the air conditioning equipment in multiple preset consecutive historical time periods, as well as the load data of multiple dimensions corresponding to the heat regulation data of each historical time period.

[0049] Among them, heat regulation data and load data from multiple dimensions can be obtained through methods such as... Figure 1 The data is obtained from various sensors in the air conditioning load prediction system shown.

[0050] S30: Based on heat regulation data and load data of multiple dimensions, solve for the coefficients corresponding to the load items of multiple dimensions in the correlation to obtain the coefficients of multiple dimensions.

[0051] In this embodiment, heat regulation data from multiple historical time periods and load data from multiple dimensions corresponding to the heat regulation data in each historical time period are substituted into the heat regulation term and the load term from multiple dimensions in the initial prediction model, respectively. The unknown coefficients corresponding to the load term from multiple dimensions in the initial prediction model are solved to obtain the coefficients of multiple dimensions. The coefficient of each dimension is used to represent the degree of influence of the load term from each dimension on the heat regulation of the air conditioning equipment.

[0052] In some embodiments, since the prediction model is designed to predict the heat regulation data of air conditioning equipment at future times, when solving for the coefficients corresponding to the load items in multiple dimensions, it is necessary to solve for the degree of influence of the load data in multiple dimensions at the previous time on the heat regulation data at the current time, or the degree of influence of the load data in multiple dimensions at the current time on the heat regulation data at the next time. In this case, the method for solving for the coefficients corresponding to the load items in multiple dimensions in the correlation relationship based on the heat regulation data and the load data in multiple dimensions can be as follows: Substituting the load data from the previous time step and the heat regulation data from the current time step into the initial prediction model, and also substituting the influence of the load data from the current time step and the heat regulation data from the next time step into the initial prediction model, we obtain multiple solution equations corresponding to the initial prediction model. By solving these multiple solution equations, we obtain coefficients for multiple dimensions. For example, the solution method for solving these multiple solution equations can be linear regression fitting.

[0053] S40: Based on the initial prediction model and coefficients of multiple dimensions, obtain the target prediction model for the air conditioning equipment.

[0054] In this embodiment, based on the values ​​of the coefficients of multiple dimensions obtained from the solution, the unknown coefficients of multiple dimensions in the initial prediction model are assigned values ​​to obtain the target prediction model of the air conditioning equipment. The target prediction model determines the power of the air conditioning equipment to transport heat at a preset future time based on the many factors affecting indoor heat in the preset location. The target prediction model can obtain the predicted heat adjustment data for the preset future time based on the load data of multiple dimensions at the current time, so that the air conditioning equipment can adjust the heat of the preset location at the preset future time according to the predicted heat adjustment data.

[0055] The air conditioning load prediction model generation method provided in the above embodiments predicts the heat adjustment data of air conditioning equipment at a preset future time based on the target prediction model. On the one hand, it can provide a basis for the advance adjustment of air conditioning equipment, avoid the lag in the system's response to the control of air conditioning equipment, and save energy consumption while ensuring the comfort of the internal temperature of the preset place. On the other hand, since the load items of air conditioning equipment in various places are basically the same, the target prediction model is more universal. Moreover, the prediction model constructed by utilizing the correlation between load items and heat adjustment items in various dimensions makes it easier for technicians to understand the meaning of each input item of the prediction model and the degree of influence on the predicted heat, and facilitates the structural optimization and parameter adjustment of the prediction model based on different places.

[0056] The following describes one possible implementation of the above-described method for constructing the initial prediction model, with reference to an example.

[0057] Please refer to Figure 3 This is a flowchart illustrating the air conditioning load prediction model generation method provided in this application embodiment. Figure 2 ,like Figure 3 As shown, the process of constructing the initial prediction model of the air conditioning equipment in the preset location in S10 can include: S11: Construct the load term for each dimension based on the parameter terms and coefficients of each dimension.

[0058] In this embodiment, the load item of each dimension includes at least one parameter item of each dimension. Each parameter item is used to indicate the influencing factors that cause the heat change of the load item of each dimension. The coefficient of each dimension is used to indicate the degree of influence of the load item of each dimension on the heat regulation item. The load item of each dimension is constructed based on the correlation between at least one parameter item of each dimension and the load item of each dimension, as well as the coefficient of each dimension.

[0059] S12: Construct a heat regulation item based on the operating parameters of the air conditioning equipment.

[0060] In this embodiment, the operating parameter item of the air conditioning equipment is used to indicate the parameter item of the air conditioning equipment that affects the heat regulation. The heat regulation item can be constructed based on the correlation between the operating parameter item of the air conditioning equipment and the heat regulation item.

[0061] In some embodiments, the heat regulation item of the air conditioning equipment is the heat regulation power of the air conditioning equipment to the preset location. This embodiment takes the air conditioning equipment cooling the preset location as an example for illustration.

[0062] The heat regulation item of the air conditioning equipment is the cooling capacity Q of the air conditioning equipment for the preset location. 冷 (kW), the operating parameters of the air conditioning equipment may include: the chilled water outlet temperature (t) of the air conditioning equipment. 出 (°C), chilled water return temperature of air conditioning equipment (t) 回 (°C), chilled water flow rate V (m) 3 The heat regulation term constructed based on the operating parameters of the air conditioning equipment ( / h) can be expressed as: Q 冷 =k*(t 回 -t 出 )*V, where k=1.163(kJ·h / m 3 ·°C·3600s).

[0063] S13: Construct an initial prediction model based on multiple dimensions of load terms and heat regulation terms.

[0064] In this embodiment, an initial prediction model is constructed based on the correlation between the heat regulation term and load terms of multiple dimensions.

[0065] In one possible implementation, the multi-dimensional load terms include: an air enthalpy difference load term, the coefficient of which is an air quality coefficient; the process of constructing the load term for each dimension in S11 based on the parameter terms and coefficients of each dimension includes: An air enthalpy difference load term is constructed based on the air quality coefficient, the indoor air enthalpy parameter at adjacent times, and the time difference between adjacent times.

[0066] In this embodiment, the air enthalpy difference is used to indicate the increase or decrease of heat in the air within a preset time period. It is typically expressed as the difference between the air enthalpy values ​​at two different times. The air enthalpy difference load term Q... 焓差 Used to indicate the heat dissipation power of indoor air enthalpy difference in a preset location, the indoor air enthalpy parameter at adjacent times includes: the indoor air enthalpy parameter H at the current time. in (kJ / kg) and the indoor air enthalpy parameter H' at the next moment in Given that the time difference between the current moment and the next moment is Δt (kJ / kg), then the air enthalpy difference load term Q... 焓差It can be represented as: Q 焓差 =ω1*(H in -H' in ) / Δt, where ω1(kg) is the air quality coefficient, used to indicate the indoor air quality of the preset location.

[0067] In one possible implementation, the load items of multiple dimensions also include: a personnel load item, the coefficient of which is the average heat generation power coefficient; the process of constructing the load item of each dimension in S11 based on the parameter items and coefficients of each dimension includes: Based on the average heat generation power coefficient and the personnel flow parameter, a personnel load term is constructed.

[0068] In this embodiment, the personnel load item Q 人 The personnel load is used to indicate the heat and humidity load generated by people in a pre-defined location, and the personnel load is used to indicate the heat generated by people in the pre-defined location. The personnel load is a dynamic load, and its magnitude is determined by the number of people in the pre-defined location and the time people stay in the pre-defined location. The number of people and the time people stay in the pre-defined location are represented by the personnel flow parameter q (thousands of people). Therefore, the personnel load term Q... 人 It can be represented as: Q 人 =ω2*q, where ω2(W) is the average heating power coefficient per person.

[0069] In one possible implementation, the load items of multiple dimensions further include: a device load item, the coefficient of which is the device heat generation power coefficient; the process of constructing the load item of each dimension in S11 based on the parameter items of each dimension and the coefficient of each dimension includes: Based on the equipment's heat generation power coefficient, construct the equipment load term.

[0070] In this embodiment, the equipment load term Q 设备 This term indicates the heat load generated by fixed equipment within a predetermined location. It represents the heat generated by the fixed equipment operating within the predetermined location. The equipment load term is a steady-state load term, and generally, its variation is small throughout the day. Therefore, the equipment heat generation power coefficient can be used to represent the equipment load term, i.e., the equipment load term Q. 设备 It can be represented as Q 设备 =C3, where C3(kW) is the equipment's heating power coefficient.

[0071] In some embodiments, the heat generation power of fixed equipment varies with different usage frequencies. For example, ticket vending machines, turnstiles, escalators, and vertical lifts are used significantly more frequently during morning and evening peak hours than at other times. Therefore, the initial prediction model for air conditioning equipment can be divided into an initial prediction model for peak hours and an initial prediction model for off-peak hours. The heat generation power coefficient obtained after solving the initial prediction models for different time periods will have different values. The division between peak and off-peak hours can be set according to requirements and is not limited here.

[0072] In one possible implementation, the multi-dimensional load terms further include: a permeable air load term, the coefficient of which is an air permeation rate coefficient; the process of constructing the load term for each dimension in S11 based on the parameter terms and coefficients of each dimension includes: Based on the air infiltration rate coefficient, the indoor air enthalpy parameter of the preset location, and the outdoor air enthalpy parameter of the preset location, the infiltration wind load term is constructed.

[0073] In this embodiment, the infiltration air load term Q 渗透 This is used to indicate the heat transfer from the soil to the building envelope of a pre-designated site, as well as the heat transfer from the outside at the entrances and exits of the pre-designated site, and is related to the indoor air enthalpy parameter H of the pre-designated site. in (kJ / kg) and outdoor air enthalpy parameter H out If there is a correlation (kJ / kg), then the infiltration wind load term Q 渗透 It can be represented as: Q 渗透 =ω4*(H out -H in ), where ω4 (kg / s) is the air permeation rate coefficient.

[0074] In some embodiments, taking the cooling of a predetermined location by an air conditioning unit as an example, the heat transfer from the soil to the building envelope of the predetermined location is very small and can be ignored. The infiltration of hot air from outside at the entrances and exits of the predetermined location brings more heat to the predetermined location. This heat is related to the indoor air enthalpy parameter H. in and outdoor air enthalpy parameter H out There is a correlation, where ω4 is the inlet and outlet air infiltration rate coefficient.

[0075] In one possible implementation, the load items of multiple dimensions also include: a fan load item, the coefficient of which is a unit air volume coefficient; the process of constructing the load item of each dimension in S11 based on the parameter items and coefficients of each dimension includes: Based on the unit air volume coefficient, the indoor air enthalpy parameter of the preset location, the outdoor air enthalpy parameter of the preset location, and the fan operating parameters of the air conditioning equipment, the fan load parameter is constructed and determined.

[0076] In this embodiment, during the operation of the air handling system (e.g., fresh air system) of the air conditioning equipment, the fan of the air conditioning equipment introduces heat when it draws air from the outside of the preset location, and the fan load term Q... 风量 This parameter indicates the amount of heat brought in by the fan when it draws air from outside the preset location. This heat is related to the indoor air enthalpy parameter H of the preset location. in (kJ / kg), outdoor air enthalpy parameter H out (kJ / kg), operating frequency of the fan in the air handling system f i If there is a correlation between (HZ) and the proportion of the opened mixing valves to all mixing valves σ(0-1), then the fan load term Q 风量 It can be represented as: Q 风量 =ω5*(H out * f i *(1-σ)-H in * f i *σ), where ω5(kg / s·HZ) is the unit air volume coefficient, used to indicate the air volume delivered by the fan at a unit operating frequency.

[0077] Based on the expressions for the load and heat regulation terms in the above dimensions, the initial prediction model can be expressed as: Q 冷 =Q 焓差 +Q 人 +Q 设备 +Q 渗透 +Q 风量 Then we can determine: k*(t) 回 -t 出 )*V=ω1*(H in -H' in ) / Δt+ω2*q+C3+ω4*(H out -H in )+ω5*(H out * f i *(1-σ)-H in * f i*σ), based on heat regulation data and load data of multiple dimensions, the coefficients corresponding to the load terms of multiple dimensions in the correlation are solved. When the coefficients of multiple dimensions are obtained, the heat regulation data on the left side of the equation is the heat regulation data corresponding to the current time t, and the load data of multiple dimensions on the right side of the equation is the load data corresponding to the previous time t-1. In order to solve for the coefficients ω1, ω2, C3, ω4, ω5 of multiple dimensions through linear regression fitting, the target prediction model can be expressed as: Q 冷 =ω1*(H in -H set ) / Δt+ω2*q+C3+ω4*(H out -H in )+ω5*(H out * f i *(1-σ)-H in * f i *σ), where H set The indoor enthalpy is a fixed value, and Δt is the time difference between the preset future time and the current time.

[0078] The air conditioning load prediction model generation method provided in the above embodiments constructs a target prediction model based on the correlation between multiple load items affecting the heat regulation of air conditioning equipment and the heat regulation items of air conditioning equipment. It can accurately predict the control data of air conditioning equipment in the future, avoid the lag in the system's response to the control of air conditioning equipment, and save energy consumption while ensuring the comfort of the internal temperature of the preset place.

[0079] Based on the above-described method for generating the air conditioning load forecasting model, this application also provides an air conditioning load forecasting method that applies the above-described target forecasting model. Please refer to... Figure 4 This is a flowchart illustrating the air conditioning load forecasting method provided in the embodiments of this application, as shown below. Figure 4 As shown, the method may include: S50: Obtain load data of air conditioning equipment in a preset location at the current moment in multiple dimensions.

[0080] S60: Based on load data from multiple dimensions, the target prediction model of the air conditioning equipment is used to calculate the preset heat adjustment parameters for future times, so as to adjust the heat transfer capacity of the air conditioning equipment according to the heat adjustment parameters.

[0081] The target prediction model is obtained using the air conditioning load prediction model generation method described in the above embodiments.

[0082] In this embodiment, the following is adopted: Figure 1The multiple sensors shown acquire load data in multiple dimensions at the current moment. The load data in multiple dimensions is input into the target prediction model. The target prediction model calculates the heat regulation parameters for the preset future time based on the load data in multiple dimensions and the coefficients in multiple dimensions. The air conditioning equipment can control the heat transfer capacity of the air conditioning equipment at the preset future time according to the heat regulation parameters.

[0083] The air conditioning load prediction method provided in the above embodiments can predict the heat adjustment data of air conditioning equipment at a preset future time based on the target prediction model, which can provide a basis for the advance control of air conditioning equipment, avoid the lag in the system's control response to air conditioning equipment, and save energy consumption while ensuring the comfort of the internal temperature of the preset place.

[0084] Based on the above method embodiments, this application also provides an air conditioning load prediction model generation device. Please refer to... Figure 5 This is a schematic diagram of the structure of the air conditioning load prediction model generation device provided in the embodiments of this application, as shown below. Figure 5 As shown, the device may include: The initial model building module 10 is used to build an initial prediction model for the air conditioning equipment in the preset location. The initial prediction model includes the correlation between the heat regulation item of the air conditioning equipment and the load items of multiple dimensions; wherein, the load item is the influencing factor for the heat regulation of the air conditioning equipment. The historical data acquisition module 20 is used to acquire the heat regulation data of the air conditioning equipment in multiple preset consecutive historical time periods and the load data of multiple dimensions in each historical time period. The coefficient calculation module 30 is used to solve the coefficients corresponding to the load items in multiple dimensions in the correlation based on the heat regulation data and the load data in multiple dimensions, so as to obtain the coefficients in multiple dimensions. The target model generation module 40 is used to obtain the target prediction model of the air conditioning equipment based on the initial prediction model and coefficients of multiple dimensions.

[0085] Optional, the initial model building module 10 includes: The load term construction unit is used to construct the load term for each dimension based on the parameter terms and coefficients of each dimension. The heat regulation item construction unit is used to construct heat regulation items based on the operating parameters of the air conditioning equipment; The initial model building unit is used to build an initial prediction model based on multiple dimensions of load terms and heat regulation terms.

[0086] Optionally, the multi-dimensional load items include: an air enthalpy difference load item, the coefficient of which is the air quality coefficient; and a load item construction unit, which is specifically used to construct the air enthalpy difference load item based on the air quality coefficient, the indoor air enthalpy parameter item at adjacent times, and the time difference between adjacent times.

[0087] Optionally, the multi-dimensional load items also include: personnel load item, the coefficient of which is the average heat generation power coefficient; and load item construction unit, which is specifically used to construct the personnel load item based on the average heat generation power coefficient and personnel flow parameter item.

[0088] Optionally, the multi-dimensional load items also include: equipment load items, the coefficient of which is the equipment heat generation power coefficient; and load item construction units, specifically used to construct equipment load items based on the equipment heat generation power coefficient.

[0089] Optionally, the multi-dimensional load items also include: infiltration air load item, the coefficient of which is the air infiltration rate coefficient; and load item construction unit, which is specifically used to construct the infiltration air load item based on the air infiltration rate coefficient, the indoor air enthalpy parameter of the preset location, and the outdoor air enthalpy parameter of the preset location.

[0090] Optionally, the multi-dimensional load items also include: fan load item, the coefficient of which is the unit air volume coefficient; and load item construction unit, which is specifically used to construct and determine the fan load item based on the unit air volume coefficient, the indoor air enthalpy parameter of the preset location, the outdoor air enthalpy parameter of the preset location, and the fan operating parameter of the air conditioning equipment.

[0091] Based on the above method embodiments, this application also provides an air conditioning load prediction device. Please refer to... Figure 6 This is a schematic diagram of the structure of the air conditioning load prediction device provided in the embodiments of this application, as shown below. Figure 6 As shown, the device may include: The data acquisition module 50 is used to acquire load data of air conditioning equipment in a preset location at the current moment in multiple dimensions; The heat calculation module 60 is used to calculate the heat adjustment parameters for a preset future time based on load data from multiple dimensions and using the target prediction model of the air conditioning equipment, so as to adjust the heat transport capacity of the air conditioning equipment according to the heat adjustment parameters. The target prediction model is obtained by the air conditioning load prediction model generation method as described in any of the above embodiments.

[0092] The above-described device is used to execute the method provided in the foregoing embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

[0093] These modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more microprocessors, or one or more Field Programmable Gate Arrays (FPGAs). Alternatively, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a system-on-a-chip (SOC).

[0094] Please refer to Figure 7 This is a schematic diagram of a computer device provided in an embodiment of this application, such as... Figure 7 As shown, the computer device 100 includes a processor 101, a storage medium 102, and a bus.

[0095] Storage medium 102 stores program instructions executable by processor 101. When computer device 100 is running, processor 101 communicates with storage medium 102 via a bus, and processor 101 executes the program instructions to perform the above-described method embodiments. The specific implementation and technical effects are similar and will not be described in detail here.

[0096] Optionally, the present invention also provides a computer-readable storage medium storing a computer program, which is executed by a processor to perform the above-described method embodiments. The specific implementation and technical effects are similar and will not be repeated here.

[0097] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0098] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0099] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0100] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0101] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for generating an air conditioning load prediction model, characterized in that, The method includes: An initial prediction model for air conditioning equipment within a pre-defined location is constructed. This initial prediction model includes the correlation between the heat regulation term of the air conditioning equipment and multiple load terms across various dimensions. The load terms represent the influencing factors on the heat regulation of the air conditioning equipment. The multiple load terms include: the air enthalpy difference load term Q. 焓差 Personnel load item Q 人 Equipment load item Q 设备 Infiltration air load item Q 渗透 And fan load item Q 风量 ; Acquire the heat regulation data of the air conditioning equipment in multiple preset consecutive historical time periods and the load data of the multiple dimensions in each historical time period; Based on the heat regulation data and the load data of the multiple dimensions, the coefficients corresponding to the load items of the multiple dimensions in the correlation are solved to obtain the coefficients of the multiple dimensions; Based on the initial prediction model and the coefficients of the multiple dimensions, the target prediction model of the air conditioning equipment is obtained; The construction of the initial prediction model for the air conditioning equipment in the preset location includes: Based on the parameter items of each dimension and the coefficients of each dimension, construct the load item for each dimension; The heat regulation item is constructed based on the operating parameters of the air conditioning equipment; Based on the load terms of the multiple dimensions and the heat regulation term, the initial prediction model is constructed; wherein, the initial prediction model can be expressed as: the heat regulation term Q 冷 =Q 焓差 +Q 人 +Q 设备 +Q 渗透 +Q 风量 ; The coefficient of the air enthalpy difference load term is the air quality coefficient; the construction of the load term for each dimension based on the parameter terms of each dimension and the coefficients of each dimension includes: The air enthalpy difference load term is constructed based on the air quality coefficient, the indoor air enthalpy parameter at adjacent times, and the time difference between adjacent times. The coefficient of the fan load term is the unit air volume coefficient; the construction of the load term for each dimension based on the parameter terms of each dimension and the coefficients of each dimension includes: The fan load is determined based on the unit air volume coefficient, the indoor air enthalpy parameter of the preset location, the outdoor air enthalpy parameter of the preset location, and the fan operating parameters of the air conditioning equipment.

2. The method as described in claim 1, characterized in that, The coefficient of the personnel load item is the average heat generation power coefficient; the construction of the load item for each dimension based on the parameter items of each dimension and the coefficients of each dimension includes: The personnel load term is constructed based on the average heat generation power coefficient and the personnel flow parameter.

3. The method as described in claim 1, characterized in that, The coefficient of the equipment load item is the equipment heat generation power coefficient; the construction of the load item for each dimension based on the parameter items of each dimension and the coefficient of each dimension includes: Based on the device's heat generation power coefficient, construct the device load term.

4. The method as described in claim 1, characterized in that, The coefficient of the infiltration wind load term is the air infiltration rate coefficient; the construction of the load term for each dimension based on the parameter terms of each dimension and the coefficients of each dimension includes: The infiltration wind load term is constructed based on the air infiltration rate coefficient, the indoor air enthalpy parameter of the preset location, and the outdoor air enthalpy parameter of the preset location.

5. A method for predicting air conditioning load, characterized in that, The method includes: Obtain load data from multiple dimensions of the air conditioning equipment in the preset location at the current moment; Based on the load data from the multiple dimensions, the target prediction model of the air conditioning equipment is used to calculate the heat adjustment parameters for the future time, so as to adjust the heat transport capacity of the air conditioning equipment according to the heat adjustment parameters. The target prediction model is obtained by the air conditioning load prediction model generation method as described in any one of claims 1-4.

6. An air conditioning load prediction model generation device, characterized in that, The device includes: An initial model building module is used to construct an initial prediction model for air conditioning equipment in a preset location. The initial prediction model includes the correlation between the heat regulation term of the air conditioning equipment and multiple load terms; wherein the load terms are the influencing factors for the heat regulation of the air conditioning equipment; and wherein the multiple load terms include: the air enthalpy difference load term Q. 焓差 Personnel load item Q 人 Equipment load item Q 设备 Infiltration air load item Q 渗透 And fan load item Q 风量 ; The historical data acquisition module is used to acquire the heat regulation data of the air conditioning equipment in a preset continuous series of historical time periods and the load data of the multiple dimensions in each historical time period. The coefficient calculation module is used to solve for the coefficients corresponding to the load items of the multiple dimensions in the correlation relationship based on the heat regulation data and the load data of the multiple dimensions, so as to obtain the coefficients of the multiple dimensions. The target model generation module is used to obtain the target prediction model of the air conditioning equipment based on the initial prediction model and the coefficients of the multiple dimensions. The initial model building module includes: The load term construction unit is used to construct the load term for each dimension based on the parameter terms of each dimension and the coefficients of each dimension. A heat regulation item construction unit is used to construct the heat regulation item based on the operating parameters of the air conditioning equipment; An initial model building unit is used to construct the initial prediction model based on the load terms of the multiple dimensions and the heat regulation term; wherein, the initial prediction model can be expressed as: the heat regulation term Q 冷 =Q 焓差 +Q 人 +Q 设备 +Q 渗透 +Q 风量 ; The coefficient of the air enthalpy difference load term is the air quality coefficient; the load term construction unit is specifically used to construct the air enthalpy difference load term based on the air quality coefficient, the indoor air enthalpy parameter term at adjacent times, and the time difference between adjacent times. The coefficient of the fan load item is the unit air volume coefficient; the load item construction unit is specifically used to construct and determine the fan load item based on the unit air volume coefficient, the indoor air enthalpy parameter item of the preset location, the outdoor air enthalpy parameter item of the preset location, and the fan operating parameter item of the air conditioning equipment.

7. An air conditioning load prediction device, characterized in that, The device includes: The data acquisition module is used to acquire load data of air conditioning equipment in a preset location at the current moment from multiple dimensions. The heat calculation module is used to calculate the heat adjustment parameters for a preset future time based on the load data of the multiple dimensions and the target prediction model of the air conditioning equipment, so as to adjust the heat transport capacity of the air conditioning equipment according to the heat adjustment parameters. The target prediction model is obtained by the air conditioning load prediction model generation method as described in any one of claims 1-4.

Images