Air handling system control, model construction method, apparatus and device, and medium

Abstract

The application discloses an air treatment system control method and device, a method and device for constructing an indoor area temperature prediction model, an electronic device and a computer readable storage medium. The air treatment system control method comprises the following steps: acquiring a plurality of sets of parameter information of a target air treatment unit; determining an influence factor of the target air treatment unit according to parameter information of other air treatment units; combining the influence factor and each set of parameter information into input parameters respectively, inputting each set of input parameters into an indoor area temperature prediction model respectively, and obtaining a predicted area temperature of an indoor area where the target air treatment unit is located corresponding to each set of input parameters; determining input parameters corresponding to predicted area temperatures satisfying a preset condition as target input parameters, and controlling the target air treatment unit based on parameter information in the target input parameters. The application improves the control accuracy and adjustment efficiency of indoor temperature.

Description

Technical Field

[0001] This application relates to the field of control technology, and more specifically, to an air handling system control method and apparatus, a method and apparatus for constructing an indoor zone temperature prediction model, an electronic device, and a computer-readable storage medium. Background Technology

[0002] An AHU (Air Handling Unit) is a centralized air handling system whose main function is to extract indoor air and a portion of fresh air to control the outlet air temperature and airflow, thereby maintaining the indoor temperature. In related technologies, multiple AHUs are typically present indoors, each regulating the temperature of its designated area. This is achieved by manually adjusting the AHU's inlet valve, water inlet valve, and fan speed to keep the temperature of its assigned area within the set range, thus ensuring the overall indoor temperature remains within the set range. However, manual adjustment often requires multiple adjustments to achieve the desired temperature, resulting in poor accuracy and low efficiency.

[0003] Therefore, how to improve the control accuracy and regulation efficiency of indoor temperature is a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this application is to provide an air handling system control method and apparatus, a method and apparatus for constructing an indoor zone temperature prediction model, an electronic device, and a computer-readable storage medium, which improve the control accuracy and regulation efficiency of indoor temperature.

[0005] To achieve the above objectives, this application provides an air handling system control method, comprising:

[0006] Obtain multiple sets of parameter information for the target air handling unit;

[0007] The influence factor of the target air handling unit is determined based on the parameter information of other air handling units; wherein, the other air handling units are air handling units other than the target air handling unit in the group to which the target air handling unit belongs, and the influence factor is used to describe the influence of the other air handling units on the target air handling unit;

[0008] The influencing factors and each set of parameter information are combined into input parameters, and each set of input parameters is input into the indoor area temperature prediction model to obtain the predicted area temperature of the indoor area where the target air handling unit is located, corresponding to each set of input parameters.

[0009] The input parameters corresponding to the predicted temperature of the region that meet the preset conditions are determined as target input parameters, and the target air handling unit is controlled based on the parameter information in the target input parameters.

[0010] This also includes:

[0011] Air handling units that control the same connected area indoors are grouped together.

[0012] The parameter information includes any one or a combination of temperature parameters, valve parameters, and fan parameters; the temperature parameters include any one or a combination of outlet air temperature, return air temperature, outdoor temperature, and inlet water temperature; the valve parameters include the opening degree of the inlet water valve and / or the opening degree of the inlet air valve; and the fan parameters include the fan frequency and / or the fan speed.

[0013] The step of determining the influencing factors of the target air handling unit based on parameter information of other air handling units includes:

[0014] The influence factor of the target air handling unit is determined based on the fan parameters of other air handling units and the ambient temperature of the indoor area.

[0015] The step of determining the influencing factors of the target air handling unit based on the fan parameters of other air handling units and the zone temperature of the indoor area includes:

[0016] Determine the product between the fan frequency of each other air handling unit and the zone temperature of the indoor area it is located in;

[0017] The sum of all the products is determined as the first summation value, and the sum of the fan frequencies of all the other air handling units is determined as the second summation value;

[0018] The ratio of the first summation value to the second summation value is determined as the influence factor of the target air handling unit.

[0019] The step of controlling the target air handling unit based on the parameter information in the target input parameters includes:

[0020] The energy consumption corresponding to the parameter information in the target input parameters is determined, the parameter information with the lowest energy consumption is determined, and the target air handling unit is controlled based on the parameter information with the lowest energy consumption.

[0021] The step of determining the energy consumption corresponding to the parameter information in the target input parameters, determining the parameter information with the lowest energy consumption, and controlling the target air handling unit based on the parameter information with the lowest energy consumption includes:

[0022] The parameter information in the target input parameters that meet the constraint conditions is determined as the target parameter information; wherein, the constraint condition is that the included wind turbine frequency is less than a preset value;

[0023] Determine the energy consumption corresponding to the target parameter information, and control the target air handling unit based on the target parameter information with the lowest energy consumption.

[0024] This also includes:

[0025] Obtain a training set; wherein the training set includes multiple training samples, each training sample including parameter information of the air handling unit, the area temperature of the corresponding indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit;

[0026] The initial model is trained using the training samples, and the trained model is used as the indoor area temperature prediction model.

[0027] The step of training an initial model using the training samples and using the trained model as the indoor area temperature prediction model includes:

[0028] Use the training samples to train different types of initial models;

[0029] Obtain a validation set; wherein the validation set includes multiple validation samples, each validation sample includes parameter information of the air handling unit, the area temperature of the corresponding indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit;

[0030] The parameter information from the verification samples is input into different types of trained models to obtain the corresponding predicted region temperature.

[0031] The evaluation parameters of the different types of models that have been trained are calculated based on the predicted region temperature and the region temperature in the validation sample.

[0032] The indoor area temperature prediction model is determined based on the evaluation parameters among the different types of models that have been trained.

[0033] To achieve the above objectives, this application provides a method for constructing an indoor zone temperature prediction model, comprising:

[0034] Obtain a training set; wherein the training set includes multiple training samples, each training sample including parameter information of the air handling unit, the area temperature of the corresponding indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit;

[0035] The initial model is trained using the training samples, and the trained model is used as an indoor area temperature prediction model to predict the area temperature.

[0036] The parameter information includes any one or a combination of temperature parameters, valve parameters, and fan parameters; the temperature parameters include any one or a combination of outlet air temperature, return air temperature, outdoor temperature, and inlet water temperature; the valve parameters include the opening degree of the inlet water valve and / or the opening degree of the inlet air valve; and the fan parameters include the fan frequency and / or the fan speed.

[0037] The step of training an initial model using the training samples and using the trained model as an indoor area temperature prediction model includes:

[0038] Use the training samples to train different types of initial models;

[0039] Obtain a validation set; wherein the validation set includes multiple validation samples, each validation sample includes parameter information of the air handling unit, the area temperature of the corresponding indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit;

[0040] The parameter information from the verification samples is input into different types of trained models to obtain the corresponding predicted region temperature.

[0041] The evaluation parameters of the different types of models that have been trained are calculated based on the predicted region temperature and the region temperature in the validation sample.

[0042] Based on the evaluation parameters, an indoor zone temperature prediction model is determined among the different types of models that have been trained.

[0043] This also includes:

[0044] The influence factor of the air handling unit is determined based on the parameter information of other air handling units; wherein, the other air handling units are air handling units other than the air handling unit in the group to which the air handling unit belongs, and the influence factor is used to describe the influence of the other air handling units on the air handling unit.

[0045] The step of determining the influencing factors of the air handling unit based on parameter information of other air handling units includes:

[0046] The influence factor of the air handling unit is determined based on the fan parameters of other air handling units and the zone temperature of the indoor area.

[0047] The step of determining the influencing factors of the air handling unit based on the fan parameters of other air handling units and the zone temperature of the indoor area includes:

[0048] Determine the product between the fan frequency of each other air handling unit and the zone temperature of the indoor area it is located in;

[0049] The sum of all the products is determined as the first summation value, and the sum of the fan frequencies of all the other air handling units is determined as the second summation value;

[0050] The ratio of the first summation value to the second summation value is determined as the influence factor of the air handling unit.

[0051] To achieve the above objectives, this application provides an air handling system control device, comprising:

[0052] The first acquisition module is used to acquire multiple sets of parameter information of the target air handling unit;

[0053] The first determining module is used to determine the influence factor of the target air handling unit based on the parameter information of other air handling units; wherein, the other air handling units are air handling units other than the target air handling unit in the group to which the target air handling unit belongs, and the influence factor is used to describe the influence of the other air handling units on the target air handling unit;

[0054] The input module is used to combine the influencing factors and each set of parameter information into input parameters, and input each set of input parameters into the indoor area temperature prediction model to obtain the predicted area temperature of the indoor area where the target air handling unit is located, corresponding to each set of input parameters.

[0055] The control module is used to determine the input parameters corresponding to the predicted temperature of the region that meet the preset conditions as the target input parameters, and to control the target air handling unit based on the parameter information in the target input parameters.

[0056] To achieve the above objectives, this application provides an apparatus for constructing an indoor zone temperature prediction model, comprising:

[0057] The second acquisition module is used to acquire a training set; wherein, the training set includes multiple training samples, each training sample includes parameter information of the air handling unit, the area temperature of the corresponding indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit;

[0058] The training module is used to train an initial model using the training samples and to use the trained model as an indoor area temperature prediction model, which is used to predict the area temperature.

[0059] To achieve the above objectives, this application provides an electronic device, comprising:

[0060] Memory, used to store computer programs;

[0061] A processor is used to implement the steps of the air handling system control method or the indoor zone temperature prediction model construction method described above when executing the computer program.

[0062] To achieve the above objectives, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the air handling system control method or the indoor zone temperature prediction model construction method described above.

[0063] As can be seen from the above scheme, the air handling system control method provided in this application includes: acquiring multiple sets of parameter information of the target air handling unit; determining the influence factor of the target air handling unit based on the parameter information of other air handling units; wherein, the other air handling units are air handling units other than the target air handling unit in the group to which the target air handling unit belongs, and the influence factor is used to describe the influence of the other air handling units on the target air handling unit; combining the influence factor and each set of parameter information into input parameters, inputting each set of input parameters into an indoor area temperature prediction model, and obtaining the area temperature of the indoor area where the target air handling unit is located corresponding to each set of input parameters; determining the input parameter corresponding to the area temperature that meets the preset conditions as the target input parameter, and controlling the target air handling unit based on the parameter information in the target input parameter.

[0064] The air handling system control method provided in this application pre-establishes an indoor area temperature prediction model based on historical parameter information of the air handling unit, the influence factors of other air handling units, and the corresponding area temperature of the indoor zone. This model predicts the corresponding indoor area temperature based on the air handling unit's parameter information and influence factors. By considering the influence of other air handling units on the target air handling unit, the accuracy of the indoor area temperature prediction model is improved. When controlling indoor temperature using multiple air handling units, multiple sets of input parameters, consisting of different parameter information and influence factors for each air handling unit, are input into the indoor area temperature prediction model to predict the corresponding indoor area temperature. This determines the target input parameters corresponding to the indoor area temperature that meets the preset conditions. Based on the parameter information in these target input parameters, the air handling units are controlled to ensure that the indoor area temperature meets the preset conditions, thereby ensuring that the overall indoor temperature meets the preset conditions. Therefore, the air handling system control method provided in this application does not require repeated adjustments to the parameters of each air handling unit. Instead, it uses an indoor zone temperature prediction model to simulate and predict the target input parameters that will allow the indoor zone temperature to meet preset conditions, enabling batch control of each air handling unit. Simultaneously, it considers the influence of other air handling units on the target air handling unit, improving the control accuracy and regulation efficiency of the indoor temperature. This application also discloses an air handling system control device, a method and apparatus for constructing an indoor zone temperature prediction model, an electronic device, and a computer-readable storage medium, which can achieve the same technical effects.

[0065] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description

[0066] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. The drawings are used to provide a further understanding of this disclosure and constitute a part of the specification. They are used together with the following detailed description to explain this disclosure, but do not constitute a limitation of this disclosure. In the drawings:

[0067] Figure 1 A flowchart illustrating an air handling system control method is provided in this embodiment.

[0068] Figure 2 This is a schematic diagram of an air handling unit shown in an embodiment;

[0069] Figure 3 This is a schematic diagram illustrating the distribution of an indoor air handling unit as shown in an embodiment;

[0070] Figure 4 A flowchart illustrating another air handling system control method in an embodiment;

[0071] Figure 5 A flowchart illustrating a method for constructing an indoor zone temperature prediction model is provided as an example.

[0072] Figure 6 A flowchart for AI (Artificial Intelligence) processing in the AHU system;

[0073] Figure 7 This is a structural diagram of an air handling system control device shown in an embodiment;

[0074] Figure 8 This is a structural diagram of a device for constructing an indoor zone temperature prediction model, as shown in an embodiment.

[0075] Figure 9 This is a structural diagram of an electronic device as shown in an embodiment. Detailed Implementation

[0076] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Furthermore, in the embodiments of this application, "first," "second," etc., are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0077] This application provides an air handling system control method.

[0078] See Figure 1 A flowchart of an air handling system control method, the air handling system control method comprising:

[0079] S101: Obtain multiple sets of parameter information for the target air handling unit;

[0080] The purpose of this embodiment is to use an indoor air handling unit to control the indoor temperature to meet preset conditions. For example, the indoor temperature of the workshop can be controlled to meet preset conditions by using an indoor air handling unit.

[0081] In this step, the parameter information may include temperature parameters, valve parameters, and fan parameters. Temperature parameters may include outlet air temperature, return air temperature, outdoor temperature, and inlet water temperature. Valve parameters may include the opening degree of the inlet water valve and the opening degree of the inlet air valve. Fan parameters may include fan frequency and fan speed. In some embodiments, the parameter information includes any one or a combination of temperature parameters, valve parameters, and fan parameters. In some embodiments, the temperature parameters include any one or a combination of outlet air temperature, return air temperature, outdoor temperature, and inlet water temperature. In some embodiments, the valve parameters include the opening degree of the inlet water valve and / or the opening degree of the inlet air valve. In some embodiments, the fan parameters include fan frequency and / or fan speed.

[0082] In some implementations, this step may include: collecting the current temperature parameters of the air handling unit; acquiring multiple sets of valve parameters and multiple sets of fan parameters of the air handling unit; and combining the current temperature parameters, the multiple sets of valve parameters, and the multiple sets of fan parameters into multiple sets of parameter information. In specific implementations, the current temperature parameters of the air handling unit are collected, i.e., real-time outlet air temperature, return air temperature, outdoor temperature, and inlet water temperature, etc., and multiple sets of valve parameters and multiple sets of fan parameters are enumerated and then combined into multiple sets of parameter information.

[0083] In some implementations, air handling units such as Figure 2 As shown, the unit includes an air inlet valve SW1, a water inlet valve SW2, and a fan. Adjusting the opening of the air inlet valve controls the amount of fresh air entering the unit, while adjusting the opening of the water inlet valve controls the amount of water entering the unit. It can also be configured to accept either chilled or hot water; chilled water is selected in summer, and hot water in winter. Fresh air enters the air handling unit through SW1, where a filter removes impurities. The fresh air mixes with the return air from the room and passes through the chilled / hot water coil controlled by SW2. After being cooled / heated, the air is compressed by the fan and enters the room.

[0084] S102: Determine the influence factor of the target air handling unit based on the parameter information of other air handling units; wherein, the other air handling units are air handling units other than the target air handling unit in the group to which the target air handling unit belongs, and the influence factor is used to describe the influence of the other air handling units on the target air handling unit;

[0085] The indoor air handling units are pre-divided into multiple groups. The air handling units in the same group can affect each other. For example, a group may include AHU01, AHU02 and AHU03. The operation of AHU02 and AHU03 will affect the temperature of the indoor area where AHU01 is located.

[0086] In some implementations, air handling units that control the same connected area can be grouped into the same group. It should be noted that since one air handling unit can control different connected areas, it can be divided into multiple groups. For example, ... Figure 3 As shown, there are 9 air handling units in the room, namely AHU01, AHU02, AHU03, AHU04, AHU05, AHU06, AHU07, AHU08, and AHU09. Among them, AHU01, AHU02, AHU04, and AHU05 are divided into one group, AHU03 and AHU06 are divided into another group, AHU06 and AHU09 are divided into another group, and AHU07 and AHU08 are divided into another group.

[0087] In addition, if there are many air handling units in the same group, they can be divided into multiple groups.

[0088] In this step, the influence factors of other air handling units on the target air handling unit can be determined based on parameter information of other air handling units in the same group. As a possible implementation, this step may include: determining the influence factor of the target air handling unit based on the fan parameters of other air handling units and the ambient temperature of the indoor area where they are located. In specific implementations, the fan parameters of other air handling units and the ambient temperature of the indoor area where they are located will affect the ambient temperature of the indoor area where the target air handling unit is located; therefore, the influence factor of the target air handling unit can be calculated based on the fan parameters of other air handling units and the ambient temperature of the indoor area where they are located.

[0089] This embodiment does not limit the specific calculation method of the influence factor. As a preferred implementation, determining the influence factor of the target air handling unit based on the fan parameters of other air handling units and the regional temperature of the indoor area includes: determining the product between the fan frequency of each other air handling unit and the regional temperature of the indoor area; determining the sum of all the products as a first summation value, and determining the sum of the fan frequencies of all the other air handling units as a second summation value; determining the ratio of the first summation value to the second summation value as the influence factor of the target air handling unit. In the above example, if the fan frequencies of AHU02 and AHU03 are A and B respectively, and the regional temperatures of the indoor areas where AHU02 and AHU03 are located are T1 and T2 respectively, then the calculated influence factor of AHU01 is (A×T1+B×T2) / (A+B).

[0090] S103: Combine the influencing factors and the parameter information of each group into input parameters, and input each group of input parameters into the indoor area temperature prediction model to obtain the predicted area temperature of the indoor area where the target air handling unit is located, corresponding to each group of input parameters.

[0091] Based on historical parameter information of the air handling units, the influencing factors of other air handling units, and the corresponding regional temperature of the indoor area, an indoor regional temperature prediction model is pre-established. This model is used to predict the corresponding indoor regional temperature based on the air handling unit's parameter information and influencing factors. In this step, multiple sets of different parameter information and influencing factors are combined to form multiple sets of input parameters, which are then input into the indoor regional temperature prediction model to predict the corresponding regional temperature.

[0092] S104: Determine the input parameter corresponding to the predicted area temperature that meets the preset conditions as the target input parameter, and control the target air handling unit based on the parameter information in the target input parameter.

[0093] The preset conditions are pre-defined regional temperature ranges, i.e., indoor temperature ranges, such as 24-28 degrees Celsius in summer and 16-20 degrees Celsius in winter. In this step, the target input parameters corresponding to the predicted regional temperature that meets the preset conditions are determined based on the predicted regional temperature obtained from the indoor predicted temperature prediction model. The air intake valve is adjusted based on the air intake valve opening, the water intake valve opening, and the fan parameters, respectively, to ensure that the regional temperature meets the preset conditions. By adjusting the air intake valve, water intake valve, and fan of each air handling unit in the above manner, the regional temperature of the indoor area where each air handling unit is located meets the preset conditions, thereby ensuring that the overall indoor temperature meets the preset conditions.

[0094] The air handling system control method provided in this application pre-establishes an indoor area temperature prediction model based on historical parameter information of the air handling unit, the influence factors of other air handling units, and the corresponding area temperature of the indoor zone. This model predicts the corresponding indoor area temperature based on the parameter information and influence factors of the air handling unit. By considering the influence of other air handling units on the target air handling unit, the accuracy of the indoor area temperature prediction model is improved. When controlling the indoor temperature using multiple air handling units, multiple sets of input parameters, consisting of different parameter information and influence factors for each air handling unit, are input into the indoor area temperature prediction model to predict the corresponding indoor area temperature. This determines the target input parameters corresponding to the indoor area temperature that meets the preset conditions. Based on the parameter information in these target input parameters, the air handling units are controlled to ensure that the indoor area temperature meets the preset conditions, thereby ensuring that the overall indoor temperature meets the preset conditions. Therefore, the air handling system control method provided in this application does not require multiple adjustments to the parameters of each air handling unit. Instead, it uses an indoor zone temperature prediction model to simulate and predict the target input parameters that can make the indoor zone temperature meet the preset conditions, and controls each air handling unit in batches. At the same time, it takes into account the influence of other air handling units on the target air handling unit, thereby improving the control accuracy and adjustment efficiency of indoor temperature.

[0095] This embodiment discloses a control method for an air handling system. In some implementations, the technical solution is further described and optimized. Specifically:

[0096] See Figure 4 A flowchart of another air handling system control method, which includes:

[0097] S201: Obtain multiple sets of parameter information for the target air handling unit;

[0098] S202: Determine the influence factor of the target air handling unit based on the parameter information of other air handling units; wherein, the other air handling units are air handling units other than the target air handling unit in the group to which the target air handling unit belongs, and the influence factor is used to describe the influence of the other air handling units on the target air handling unit;

[0099] S203: Combine the influencing factors and the parameter information of each group into input parameters, and input each group of input parameters into the indoor area temperature prediction model to obtain the predicted area temperature of the indoor area where the target air handling unit is located, corresponding to each group of input parameters.

[0100] S204: Determine the input parameter corresponding to the predicted area temperature that meets the preset conditions as the target input parameter;

[0101] S205: Determine the energy consumption corresponding to the parameter information in the target input parameters, determine the parameter information with the lowest energy consumption, and control the target air handling unit based on the parameter information with the lowest energy consumption.

[0102] After determining the target input parameters, the energy consumption of the air handling unit is calculated under the control of the parameter information of each set of target input parameters. The parameter information with the lowest energy consumption is selected to control the air handling unit. From the perspective of energy saving, the indoor temperature meets the preset conditions with the lowest energy consumption.

[0103] In some implementations, the energy consumption corresponding to the parameter information in the target input parameters can be determined based on the valve parameters and / or fan parameters in the target input parameters. It should be noted that the energy consumption of the air handling unit is related to the valve parameters and fan parameters of the air handling unit. The intake valve can be considered to have no energy consumption, while the water inlet valve has greater energy consumption than the fan. Therefore, when adjusting the parameters of the air handling unit, the intake valve opening should be adjusted first, followed by the fan speed, and finally the water inlet valve opening.

[0104] In some implementations, a cost model can be used to calculate the energy consumption of the air handling unit under different parameter control conditions. The energy consumption calculation can be divided into two parts. One part calculates the energy consumption of the inlet valve. Given a fixed pipe diameter, different inlet valve openings correspond to different power consumptions. Multiple sets of data can be recorded based on actual operating conditions, each set including the inlet valve opening and corresponding power consumption. These sets of data are then fitted to obtain a theoretical formula for calculating the inlet valve's energy consumption. For example: Inlet valve energy consumption = (50^(inlet valve opening / 100-1)) × (pipe diameter width^2) / 4 × 10^(-6) × 3.14 × 3600 × (return water temperature - supply water temperature) / 3.024. The other part calculates the energy consumption of the fan. Different fan frequencies correspond to different power consumptions. Again, multiple sets of data can be recorded based on actual operating conditions, each set including the fan frequency and corresponding power consumption. These sets of data are then fitted to obtain a theoretical formula for calculating the fan's energy consumption. For example, the energy consumption of a fan is calculated as ((fan frequency / rated frequency)^3) × rated frequency. It's understandable that the theoretical formula for air handling units may deviate after prolonged use. In such cases, multiple sets of data from actual operation can be recorded again, and the theoretical formula in the cost model can be refitted and updated to improve the accuracy of calculating the energy consumption of the air handling unit.

[0105] In some implementations, determining the energy consumption corresponding to the parameter information in the target input parameters, determining the parameter information with the lowest energy consumption, and controlling the target air handling unit based on the parameter information with the lowest energy consumption includes: determining the parameter information in the target input parameters constrained by preset conditions as target parameter information; wherein the constraint condition is that the included fan frequency is less than a preset value; determining the energy consumption corresponding to the target parameter information, and controlling the target air handling unit based on the target parameter information with the lowest energy consumption. It is understood that in actual operation, as the fan frequency increases, the fan's operating power increases exponentially. Therefore, to reduce fan power consumption, it is necessary to control the fan frequency to be less than a preset value. That is, only the power consumption corresponding to the target parameter information containing the fan frequency being less than a preset value can be calculated, and the target parameter information with the lowest power consumption can be selected to control the target air handling unit.

[0106] For example, in step S204, three sets of target input parameters are determined, namely target input parameters A, B, and C. Target input parameter A includes an outlet air temperature of 25 degrees Celsius, a return air temperature of 25 degrees Celsius, an outdoor temperature of 28 degrees Celsius, an inlet water temperature of 10 degrees Celsius, an inlet water valve opening of 70%, an air inlet valve opening of 70%, a fan frequency of 20Hz, and an influence factor of 0.5. Target input parameter B includes an outlet air temperature of 25 degrees Celsius, a return air temperature of 25 degrees Celsius, and a return air temperature of 25 degrees Celsius. The target input parameters are: outdoor temperature 30°C, inlet water temperature 10°C, inlet valve opening 100%, air inlet valve opening 100%, fan frequency 20Hz, and influence factor 0.5. The target input parameter C includes outlet air temperature 25°C, return air temperature 25°C, outdoor temperature 30°C, inlet water temperature 10°C, inlet valve opening 100%, air inlet valve opening 100%, fan frequency 40Hz, and influence factor 0.5. The constraint is that the included fan frequency must be less than 30Hz. Target input parameters A and B contain fan frequencies less than 30Hz, satisfying the constraint. However, target input parameter C contains a fan frequency greater than 30Hz, disqualifying it. Therefore, only the power consumption corresponding to the parameters in target input parameters A and B is calculated, and the parameter with the lowest power consumption is selected to control the target air handling unit.

[0107] This application also discloses a method for constructing an indoor zone temperature prediction model, specifically:

[0108] See Figure 5 A flowchart illustrating a method for constructing an indoor zone temperature prediction model, the method comprising:

[0109] S301: Obtain a training set; wherein the training set includes multiple training samples, each training sample including parameter information of the air handling unit, the area temperature of the corresponding indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit;

[0110] In this step, historical data from air handling units is collected as training samples. Each training sample includes the air handling unit's parameter information, the influence factors of other air handling units in its group, and the corresponding indoor area temperature. Parameter information may include temperature parameters, valve parameters, and fan parameters. Temperature parameters may include outlet air temperature, return air temperature, outdoor temperature, and inlet water temperature. Valve parameters may include inlet water valve opening and inlet air valve opening. Fan parameters may include fan frequency and fan speed. For example, a training sample may include the following information: outlet air temperature 25 degrees Celsius, return air temperature 25 degrees Celsius, outdoor temperature 30 degrees Celsius, inlet water temperature 10 degrees Celsius, inlet water valve opening 70%, inlet air valve opening 70%, fan frequency 20Hz, influence factor 0.5, and area temperature 26 degrees Celsius.

[0111] It is understood that this embodiment also includes: determining the influence factor of the air handling unit based on the parameter information of other air handling units; wherein, the other air handling units are air handling units other than the air handling unit in the group to which the air handling unit belongs, and the influence factor is used to describe the influence of the other air handling units on the air handling unit. The process of calculating the influence factor of each air handling unit in the training sample is similar to the process of calculating the influence factor of the target air handling unit described in the previous embodiment, and will not be repeated here.

[0112] S302: Train an initial model using the training samples, and use the trained model as an indoor area temperature prediction model, which is used to predict area temperature.

[0113] In this step, an initial model is trained using training samples. This initial model can be a machine learning model. The trained model is used to predict the corresponding indoor zone temperature based on the parameter information and influencing factors of the air handling unit.

[0114] In a preferred embodiment, this step may include: training different types of initial models using the training samples; obtaining a validation set; wherein the validation set includes multiple validation samples, each validation sample including parameter information of the air handling unit, the corresponding area temperature of the indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit; inputting the parameter information in the validation samples into the different types of models that have been trained respectively to obtain the corresponding predicted area temperature; calculating the evaluation parameters of the different types of models that have been trained based on the predicted area temperature and the area temperature in the validation samples; and determining the indoor area temperature prediction model among the different types of models that have been trained according to the evaluation parameters.

[0115] In practical implementation, different types of initial models can be selected. These initial models have different model parameters, which may include the penalty coefficient (C) and kernel function coefficient (gamma). The penalty coefficient represents the tolerance for error; a higher penalty coefficient indicates a lower tolerance for error and a higher risk of overfitting, while a lower penalty coefficient indicates a higher risk of underfitting. Both excessively large and small penalty coefficients will worsen generalization ability. The kernel function coefficient can affect the training and prediction speed to some extent. Different types of initial models are trained using training samples, and then a validation set is obtained. Similar to the training set, the validation set can be obtained by collecting historical data from the air handling unit. The validation set includes multiple validation samples, each containing the air handling unit's parameter information and the corresponding indoor temperature. Parameter information may include temperature parameters, valve parameters, and fan parameters. Temperature parameters may include outlet air temperature, return air temperature, outdoor temperature, and inlet water temperature. Valve parameters may include inlet water valve opening and inlet air valve opening. Fan parameters may include fan frequency and fan speed. For example, a training sample may include the following information: outlet air temperature is 25 degrees Celsius, return air temperature is 25 degrees Celsius, outdoor temperature is 30 degrees Celsius, inlet water temperature is 10 degrees Celsius, inlet water valve opening is 70%, inlet air valve opening is 70%, fan frequency is 20Hz, influence factor is 0.5, and area temperature is 26 degrees Celsius. Further, the trained models are validated using validation samples in the validation set to verify their predictive performance. The model with the best predictive performance is selected as the indoor temperature prediction model. This involves inputting the parameter information from the validation samples into each trained model to predict the corresponding indoor temperature. Based on the predicted indoor temperature and the actual indoor temperature (the indoor temperature in the validation samples), evaluation parameters are calculated for each model. These evaluation parameters are used to evaluate the model's predictive performance. Evaluation parameters may include the coefficient of determination (R-squared), the mean squared error (MSE) between the predicted and actual indoor area temperatures, and the mean absolute error (MAE). The formula for calculating the coefficient of determination is:

[0116]

[0117] Where Y_actual is the actual indoor temperature, which is the indoor temperature in the validation sample, Y_predict is the predicted indoor temperature, and Y_mean is the average of the actual indoor temperature.

[0118] A higher coefficient of determination indicates better predictive performance, while lower mean squared error and mean absolute error also indicate better predictive performance. For example, among the models in Table 1, Model 2 has the best predictive performance.

[0119] Table 1

[0120] Model Model parameters Coefficient of determination Mean square error Mean Absolute Error Model 1 C = 20, gamma = 8 0.93766 0.06049 0.13709 Model 2 C = 10, gamma = 6 0.95724 0.04257 0.12405 Model 3 C = 12, gamma = 8 0.87612 0.1216 0.20402 Model 4 C = 17, gamma = 8 0.93924 0.05994 0.14738 Model 5 C = 17, gamma = 4 0.88183 0.11637 0.17899 Model 6 C = 17, gamma = 4 0.88806 0.11453 0.20188

[0121] Since temperature is continuous data and there is clear target data in the training set, the trained SVR (Support Vector Regression) model can be used as the indoor area temperature prediction model.

[0122] Therefore, by training different types of initial models using training samples, and then testing the prediction performance of each trained model using validation samples in the validation set, and selecting the model with the best prediction performance as the indoor area temperature prediction model, the accuracy of the indoor area temperature prediction model in predicting indoor area temperature can be improved.

[0123] The following describes an application embodiment provided by this application, specifically:

[0124] See Figure 6 , Figure 6 A flowchart for AI (Artificial Intelligence) processing in the AHU system.

[0125] like Figure 6 As shown, the AI ​​processing of the AHU system consists of three parts: data processing feature engineering, offline machine learning modeling, and online model prediction.

[0126] Data processing primarily includes data collection via switches, data cleaning processes such as outlier removal and null value filling, and acquisition of historical data from air handling units. All data comprises multiple samples, each containing air handling unit parameter information, influencing factors, and corresponding regional temperatures. Parameter information includes temperature parameters, valve parameters, and fan parameters. Temperature parameters include outlet air temperature, return air temperature, outdoor temperature, and inlet water temperature; valve parameters include inlet valve opening and inlet valve opening; and fan parameters include fan frequency and fan speed. All data is integrated into a wide table, with one row representing a sample and one column representing a parameter or influencing factor and regional temperature. Feature filtering and derivation are then performed on all data to assess data quality. Data quality primarily considers accuracy, completeness, consistency, validity, uniqueness, and stability. Accuracy describes whether the data is consistent with the characteristics of its corresponding objective entity. For example, whether temperature parameters or valve parameters are within their preset ranges. Completeness describes whether there are any missing records or fields. Consistency describes whether the value of the same parameter for the same entity is consistent across different systems or datasets. For example, whether the return air temperature in the same sample is consistent between the training and validation sets. Validity describes whether the data meets user-defined conditions or falls within a certain value range. For example, if the user sets the fan frequency to be less than 30Hz, it's necessary to evaluate whether the fan frequency in each sample is less than 30Hz. Uniqueness describes whether duplicate records exist in the data. For example, whether duplicate samples exist in the training set. Stability describes whether the data is stable and within its validity period. For example, whether the collected samples were collected within the specified validity period. If the data quality is poor, it needs to be re-analyzed; if the quality is good, it proceeds to the modeling stage.

[0127] Offline modeling involves obtaining the AHU system dataset through data processing, selecting an algorithm based on data characteristics, choosing a suitable parameter set, and splitting it into training, validation, and test sets. The parameters in the training set are validated to ensure they are acceptable; if not, new parameters are selected. If acceptable, different initial models are iteratively trained using the training set to obtain multiple trained models. The validation set is used to evaluate the predictive performance of each model, selecting the model with the best prediction performance. Specifically, the parameter information and influencing factors from the validation samples are input into each trained model to predict the temperature of the corresponding prediction area. The coefficient of determination, mean squared error, and mean absolute error between the predicted and actual temperatures are calculated for each model. The model with the largest coefficient of determination and the smallest mean squared error and mean absolute error is selected as the indoor temperature prediction model. The indoor area temperature prediction model is evaluated using a test set. Specifically, the test set includes multiple test samples. The parameter information and influencing factors in each test sample are input into the indoor area temperature prediction model to predict the corresponding area temperature. The prediction accuracy of the indoor area temperature prediction model is calculated based on the predicted area temperature and the area temperature (actual area temperature) in the test samples. If the prediction accuracy of the indoor area temperature prediction model is high, it is used as the official model for real-time prediction. If it is not ideal, the model is retrained.

[0128] Online prediction collects real-time field data from the AHU system via an interface. After data processing, multiple sets of parameter information are generated, which are then imported into the model to predict the regional temperature in real time. This process also obtains target parameter information for each air handling unit under the current environmental conditions that meet preset conditions, thereby controlling each air handling unit.

[0129] The following describes an apparatus for constructing an indoor area temperature prediction model according to an embodiment of this application. The apparatus for constructing an indoor area temperature prediction model described below and the method for constructing an indoor area temperature prediction model described above can be referred to each other.

[0130] See Figure 7 A structural diagram of a device for constructing an indoor zone temperature prediction model, as shown below. Figure 7 As shown, it includes:

[0131] The first acquisition module 701 is used to acquire multiple sets of parameter information of the target air handling unit;

[0132] The first determining module 702 is used to determine the influence factor of the target air handling unit based on the parameter information of other air handling units; wherein, the other air handling units are air handling units other than the target air handling unit in the group to which the target air handling unit belongs, and the influence factor is used to describe the influence of the other air handling units on the target air handling unit;

[0133] Input module 703 is used to combine the influencing factors and each set of parameter information into input parameters, input each set of input parameters into the indoor area temperature prediction model, and obtain the predicted area temperature of the indoor area where the target air handling unit is located corresponding to each set of input parameters.

[0134] The control module 704 is used to determine the input parameters corresponding to the predicted area temperature that meets the preset conditions as target input parameters, and to control the target air handling unit based on the parameter information in the target input parameters.

[0135] The air handling system control device provided in this application pre-establishes an indoor area temperature prediction model based on historical parameter information of the air handling unit, the influence factors of other air handling units, and the corresponding area temperature of the indoor zone. This model predicts the corresponding indoor area temperature based on the parameter information and influence factors of the air handling unit. By considering the influence of other air handling units on the target air handling unit, the accuracy of the indoor area temperature prediction model is improved. When controlling the indoor temperature using multiple air handling units, multiple sets of input parameters, consisting of different parameter information and influence factors for each air handling unit, are input into the indoor area temperature prediction model to predict the corresponding indoor area temperature. This determines the target input parameters corresponding to the indoor area temperature that meets the preset conditions. Based on the parameter information in these target input parameters, the air handling unit is controlled to ensure that the indoor area temperature meets the preset conditions, thereby ensuring that the overall indoor temperature meets the preset conditions. Therefore, the air handling system control device provided in this application embodiment does not require multiple adjustments to the parameters of each air handling unit. Instead, it uses an indoor area temperature prediction model to simulate and predict the target input parameters that can make the indoor area temperature meet the preset conditions, and controls each air handling unit in batches. At the same time, it takes into account the influence of other air handling units on the target air handling unit, thereby improving the control accuracy and adjustment efficiency of indoor temperature.

[0136] In some embodiments, it also includes:

[0137] The partitioning module is used to group air handling units that control the same connected area within an indoor space into the same group.

[0138] In some embodiments, the parameter information includes any one or a combination of temperature parameters, valve parameters, and fan parameters; the temperature parameters include any one or a combination of outlet air temperature, return air temperature, outdoor temperature, and inlet water temperature; the valve parameters include the opening degree of the inlet water valve and / or the opening degree of the inlet air valve; and the fan parameters include the fan frequency and / or the fan speed.

[0139] In some embodiments, the first determining module 702 is specifically used to: determine the influence factor of the target air handling unit based on the fan parameters of other air handling units and the area temperature of the indoor area.

[0140] In some embodiments, the first determining module 702 is specifically configured to: determine the product between the fan frequency of each other air handling unit and the zone temperature of the indoor area where it is located; determine the sum of all the products as a first summation value, determine the sum of the fan frequencies of all the other air handling units as a second summation value; and determine the ratio of the first summation value to the second summation value as the influence factor of the target air handling unit.

[0141] In some embodiments, the control module 704 includes:

[0142] The determining unit is used to determine the input parameters corresponding to the temperature of the region that meets the preset conditions as the target input parameters;

[0143] The control unit is used to determine the energy consumption corresponding to the parameter information in the target input parameters, determine the parameter information with the lowest energy consumption, and control the target air handling unit based on the parameter information with the lowest energy consumption.

[0144] In some embodiments, the control unit is specifically used to: determine the parameter information in the target input parameters of the constraint preset conditions as target parameter information; wherein the constraint condition is that the included fan frequency is less than a preset value; determine the energy consumption corresponding to the target parameter information, and control the target air handling unit based on the target parameter information with the lowest energy consumption.

[0145] In some embodiments, it also includes:

[0146] The second acquisition module is used to acquire a training set; wherein, the training set includes multiple training samples, each training sample includes parameter information of the air handling unit, the area temperature of the corresponding indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit;

[0147] The training module is used to train an initial model using the training samples and to use the trained model as the indoor area temperature prediction model.

[0148] In some embodiments, the training module is specifically used for: training different types of initial models using the training samples; obtaining a validation set; wherein the validation set includes multiple validation samples, each validation sample including parameter information of the air handling unit, the corresponding area temperature of the indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit; inputting the parameter information in the validation samples into the different types of models that have been trained respectively to obtain the corresponding predicted area temperature; calculating the evaluation parameters of the different types of models that have been trained based on the predicted area temperature and the area temperature in the validation samples; and determining the indoor area temperature prediction model in the different types of models that have been trained according to the evaluation parameters.

[0149] The following describes an air handling system control device provided in an embodiment of this application. The air handling system control device described below and the air handling system control method described above can be referred to each other.

[0150] See Figure 8 A structural diagram of an air handling system control device, as shown below. Figure 8 As shown, it includes:

[0151] The second acquisition module 801 is used to acquire a training set; wherein, the training set includes multiple training samples, each training sample includes parameter information of the air handling unit, the area temperature of the corresponding indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit;

[0152] The training module 802 is used to train an initial model using the training samples and to use the trained model as an indoor area temperature prediction model, which is used to predict the area temperature.

[0153] In some embodiments, the parameter information includes any one or a combination of temperature parameters, valve parameters, and fan parameters; the temperature parameters include any one or a combination of outlet air temperature, return air temperature, outdoor temperature, and inlet water temperature; the valve parameters include the opening degree of the inlet water valve and / or the opening degree of the inlet air valve; and the fan parameters include the fan frequency and / or the fan speed.

[0154] In some embodiments, the training module 802 is specifically used for: training different types of initial models using the training samples; obtaining a validation set; wherein the validation set includes multiple validation samples, each validation sample including parameter information of the air handling unit, the corresponding area temperature of the indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit; inputting the parameter information in the validation samples into the different types of models that have been trained respectively to obtain the corresponding predicted area temperature; calculating the evaluation parameters of the different types of models that have been trained based on the predicted area temperature and the area temperature in the validation samples; and determining an indoor area temperature prediction model in the different types of models that have been trained according to the evaluation parameters.

[0155] In some embodiments, it also includes:

[0156] The second determining module is used to determine the influence factor of the air handling unit based on the parameter information of other air handling units; wherein, the other air handling units are air handling units other than the air handling unit in the group to which the air handling unit belongs, and the influence factor is used to describe the influence of the other air handling units on the air handling unit.

[0157] In some embodiments, the second determining module is specifically used to: determine the influence factor of the air handling unit based on the fan parameters of other air handling units and the area temperature of the indoor area.

[0158] In some embodiments, the second determining module is specifically configured to: determine the product between the fan frequency of each other air handling unit and the zone temperature of the indoor area where it is located; determine the sum of all the products as a first summation value, determine the sum of the fan frequencies of all the other air handling units as a second summation value; and determine the ratio of the first summation value to the second summation value as the influence factor of the air handling unit.

[0159] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0160] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiments of this application, the embodiments of this application also provide an electronic device. Figure 9 This is a structural diagram of an electronic device according to an exemplary embodiment, such as... Figure 9 As shown, the electronic device includes:

[0161] Communication interface 1 enables information exchange with other devices, such as network devices;

[0162] Processor 2 is connected to communication interface 1 to enable information exchange with other devices. When running a computer program, it executes the air handling system control method or the indoor zone temperature prediction model construction method provided by one or more of the above-mentioned technical solutions. The computer program is stored in memory 3.

[0163] Of course, in practical applications, the various components in an electronic device are coupled together through bus system 4. It can be understood that bus system 4 is used to achieve communication and connection between these components. In addition to the data bus, bus system 4 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 9 The general will label all buses as Bus System 4.

[0164] In this embodiment, memory 3 is used to store computer programs to support the operation of electronic devices. It is understood that memory 3 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memory 3 described in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0165] The methods disclosed in the embodiments of this application can be applied to processor 2, or implemented by processor 2. Processor 2 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 2 or by instructions in the form of software. The processor 2 may be a general-purpose processor, DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 2 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly manifested as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in memory 3. Processor 2 reads the program in memory 3 and completes the steps of the aforementioned method in combination with its hardware.

[0166] When processor 2 executes the program, it implements the corresponding processes in the various methods of the embodiments of this application. For the sake of brevity, these will not be described in detail here.

[0167] In an exemplary embodiment, this application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as a memory 3 that stores a computer program, which can be executed by a processor 2 to complete the steps described in the aforementioned method. The computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM.

[0168] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0169] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0170] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A control method for an air handling system, characterized in that, include: Air handling units that control the same connected area indoors should be grouped into the same group; Obtain multiple sets of parameter information for the target air handling unit; The influence factor of the target air handling unit is determined based on the parameter information of other air handling units; wherein, the other air handling units are air handling units other than the target air handling unit in the group to which the target air handling unit belongs, and the influence factor is used to describe the influence of the other air handling units on the target air handling unit; The influencing factors and the parameter information of each group of the target air handling unit are combined into input parameters, and each group of input parameters is input into the indoor area temperature prediction model to obtain the predicted area temperature of the indoor area where the target air handling unit is located, corresponding to each group of input parameters. The input parameter corresponding to the predicted temperature of the region that meets the preset conditions is determined as the target input parameter, and the target air handling unit is controlled based on the parameter information in the target input parameter. The step of determining the influencing factors of the target air handling unit based on parameter information of other air handling units includes: The influence factor of the target air handling unit is determined based on the fan parameters of other air handling units and the ambient temperature of the indoor area.

2. The air handling system control method according to claim 1, characterized in that, The parameter information includes any one or a combination of temperature parameters, valve parameters, and fan parameters; the temperature parameters include any one or a combination of outlet air temperature, return air temperature, outdoor temperature, and inlet water temperature; the valve parameters include the opening degree of the inlet water valve and / or the opening degree of the inlet air valve; the fan parameters include the fan frequency and / or the fan speed.

3. The air handling system control method according to claim 1, characterized in that, The determination of the influencing factors of the target air handling unit based on the fan parameters of other air handling units and the ambient temperature of the indoor area includes: Determine the product between the fan frequency of each other air handling unit and the zone temperature of the indoor area it is located in; The sum of all the products is determined as the first summation value, and the sum of the fan frequencies of all the other air handling units is determined as the second summation value; The ratio of the first summation value to the second summation value is determined as the influence factor of the target air handling unit.

4. The air handling system control method according to claim 1, characterized in that, The control of the target air handling unit based on the parameter information in the target input parameters includes: The energy consumption corresponding to the parameter information in the target input parameters is determined, the parameter information with the lowest energy consumption is determined, and the target air handling unit is controlled based on the parameter information with the lowest energy consumption.

5. The air handling system control method according to claim 4, characterized in that, The step of determining the energy consumption corresponding to the parameter information in the target input parameters, determining the parameter information with the lowest energy consumption, and controlling the target air handling unit based on the parameter information with the lowest energy consumption includes: The parameter information in the target input parameters that meet the constraint conditions is determined as the target parameter information; wherein, the constraint condition is that the included wind turbine frequency is less than a preset value; Determine the energy consumption corresponding to the target parameter information, and control the target air handling unit based on the target parameter information with the lowest energy consumption.

6. The air handling system control method according to claim 1, characterized in that, Also includes: Obtain a training set; wherein the training set includes multiple training samples, each training sample including parameter information of the air handling unit, the area temperature of the corresponding indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit; The initial model is trained using the training samples, and the trained model is used as the indoor area temperature prediction model.

7. The air handling system control method according to claim 6, characterized in that, The step of training an initial model using the training samples and using the trained model as the indoor area temperature prediction model includes: Use the training samples to train different types of initial models; Obtain a validation set; wherein the validation set includes multiple validation samples, each validation sample includes parameter information of the air handling unit, the area temperature of the corresponding indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit; The parameter information from the verification samples is input into different types of trained models to obtain the corresponding predicted region temperature. The evaluation parameters of the different types of models that have been trained are calculated based on the predicted region temperature and the region temperature in the validation sample. The indoor area temperature prediction model is determined based on the evaluation parameters among the different types of models that have been trained.

8. A method for constructing an indoor zone temperature prediction model, characterized in that, include: Air handling units that control the same connected area indoors should be grouped into the same group; Obtain a training set; wherein the training set includes multiple training samples, each training sample includes parameter information of the target air handling unit, the area temperature of the indoor area where the target air handling unit is located, and the influence factor of other air handling units in the group to which the target air handling unit belongs on the target air handling unit. The influence factor is determined by the fan parameters of other air handling units in the group to which the target air handling unit belongs and the area temperature of the indoor area where they are located. The initial model is trained using the training samples, and the trained model is used as an indoor area temperature prediction model to predict the temperature of the area where the target air handling unit is located.

9. The method for constructing an indoor zone temperature prediction model according to claim 8, characterized in that, The parameter information includes any one or a combination of temperature parameters, valve parameters, and fan parameters; the temperature parameters include any one or a combination of outlet air temperature, return air temperature, outdoor temperature, and inlet water temperature; the valve parameters include the opening degree of the inlet water valve and / or the opening degree of the inlet air valve; the fan parameters include the fan frequency and / or the fan speed.

10. The method for constructing an indoor zone temperature prediction model according to claim 8, characterized in that, The step of training an initial model using the training samples and using the trained model as an indoor area temperature prediction model includes: Use the training samples to train different types of initial models; Obtain a validation set; wherein the validation set includes multiple validation samples, each validation sample includes parameter information of the air handling unit, the area temperature of the corresponding indoor area where the air handling unit is located, and the influence factors of other air handling units in the group to which the air handling unit belongs on the air handling unit; The parameter information from the verification samples is input into different types of trained models to obtain the corresponding predicted region temperature. The evaluation parameters of the different types of models that have been trained are calculated based on the predicted region temperature and the region temperature in the validation sample. Based on the evaluation parameters, an indoor zone temperature prediction model is determined among the different types of models that have been trained.

11. The method for constructing the indoor zone temperature prediction model according to claim 8, characterized in that, Also includes: The influence factor of the target air handling unit is determined based on the parameter information of other air handling units; wherein, the other air handling units are air handling units other than the target air handling unit in the group to which the target air handling unit belongs, and the influence factor is used to describe the influence of the other air handling units on the target air handling unit.

12. The method for constructing an indoor zone temperature prediction model according to claim 11, characterized in that, The step of determining the influencing factors of the target air handling unit based on parameter information of other air handling units includes: Determine the product between the fan frequency of each other air handling unit and the zone temperature of the indoor area it is located in; The sum of all the products is determined as the first summation value, and the sum of the fan frequencies of all the other air handling units is determined as the second summation value; The ratio of the first summation value to the second summation value is determined as the influence factor of the target air handling unit.

13. An air handling system control device, characterized in that, include: The partitioning module is used to group air handling units that control the same connected area within an indoor space into the same group. The first acquisition module is used to acquire multiple sets of parameter information of the target air handling unit; The first determining module is used to determine the influence factor of the target air handling unit based on the parameter information of other air handling units; wherein, the other air handling units are air handling units other than the target air handling unit in the group to which the target air handling unit belongs, and the influence factor is used to describe the influence of the other air handling units on the target air handling unit; The input module is used to combine the influencing factors and each set of parameter information of the target air handling unit into input parameters, and input each set of input parameters into the indoor area temperature prediction model to obtain the predicted area temperature of the indoor area where the target air handling unit is located corresponding to each set of input parameters. The control module is used to determine the input parameters corresponding to the predicted area temperature that meets the preset conditions as the target input parameters, and to control the target air handling unit based on the parameter information in the target input parameters; Specifically, the first determining module is used to: determine the influence factor of the target air handling unit based on the fan parameters of other air handling units and the regional temperature of the indoor area.

14. A device for constructing an indoor zone temperature prediction model, characterized in that, include: The partitioning module is used to group air handling units that control the same connected area within an indoor space into the same group. The second acquisition module is used to acquire a training set; wherein the training set includes multiple training samples, each training sample includes parameter information of the target air handling unit, the area temperature of the indoor area where the target air handling unit is located, and the influence factor of other air handling units in the group to which the target air handling unit belongs on the target air handling unit. The influence factor is determined by the fan parameters of other air handling units in the group to which the target air handling unit belongs and the area temperature of the indoor area where they are located. The training module is used to train an initial model using the training samples and use the trained model as an indoor area temperature prediction model, which is used to predict the temperature of the area where the target air handling unit is located.

15. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the air handling system control method as described in any one of claims 1 to 7 or the method for constructing an indoor zone temperature prediction model as described in any one of claims 8 to 12.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the air handling system control method as described in any one of claims 1 to 7 or the method for constructing an indoor zone temperature prediction model as described in any one of claims 8 to 12.

Images