Multi-connected air conditioning system, control method thereof, and storage medium

Abstract

The application discloses a multi-connected air conditioning system and a control method and a storage medium thereof. The control method comprises the following steps: obtaining a load prediction parameter of the air conditioning system; obtaining a predicted total load rate of the air conditioning system based on the load prediction parameter; obtaining a correction coefficient based on an actual total load rate of the air conditioning system; correcting the predicted total load rate by using the correction coefficient; obtaining a control target value based on the corrected predicted total load rate, and controlling the air conditioning system by using the control target value. In this way, the application corrects the predicted total load rate by using the correction coefficient, thereby improving the accuracy of the predicted total load rate, improving the prediction accuracy of the air conditioning system, and improving the reliability of the air conditioning system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of air conditioning, in particular to a multi-split air conditioning system, a control method thereof, and a storage medium. BACKGROUND

[0002] The multi-split air conditioning system is usually applied in buildings such as shopping malls, office buildings, or hospitals. The multi-split air conditioning system can include one indoor unit and multiple indoor units, each of which is used to independently control a room or a thermal zone, and each of which is connected to an outdoor unit through an expansion valve. The multi-split air conditioning system controls the opening degree of the expansion valve to achieve the distribution of refrigerating capacity or heating capacity for each indoor unit.

[0003] In the process of predicting the load, the multi-split air conditioning system cannot avoid the error of prediction because it does not have feedback, thus resulting in low prediction accuracy of the multi-split air conditioning system. SUMMARY

[0004] The present application provides a multi-split air conditioning system, a control method thereof, and a storage medium to solve the technical problem of low prediction accuracy in the prior art.

[0005] To solve the above technical problems, one technical solution adopted by the present application is to provide a control method applied to a multi-split air conditioning system, which comprises the following steps:

[0006] Obtaining a load prediction parameter of the air conditioning system;

[0007] Obtaining a predicted total load rate of the air conditioning system based on the load prediction parameter;

[0008] Obtaining a correction coefficient based on an actual total load rate of the air conditioning system;

[0009] Correcting the predicted total load rate by using the correction coefficient;

[0010] Obtaining a control target value based on the corrected predicted total load rate, and controlling the air conditioning system by using the control target value.

[0011] The step of obtaining the correction coefficient based on the actual total load rate of the air conditioning system comprises the following steps:

[0012] Calculating an average value of the actual total load rate of the air conditioning system in a first preset time period to obtain a first average value;

[0013] Calculating an average value of the predicted total load rate of the air conditioning system in the first preset time period to obtain a second average value;

[0014] calculating a ratio between the first average value and the second average value to obtain the correction coefficient within a second preset time period after the first preset time period.

[0015] The step of calculating the average value of the actual total load rate of the air conditioning system within the first preset time period comprises:

[0016] According to the operation data of the air conditioning system at a plurality of first time points within the first preset time period, an actual total load value corresponding to the first time point is calculated.

[0017] A ratio between each of the actual total load values and a rated total load value of the air conditioning system is calculated to obtain the actual total load rate corresponding to the first time point.

[0018] The actual total load rates corresponding to the plurality of first time points are averaged to obtain the average value of the actual total load rate.

[0019] The step of obtaining the predicted total load rate of the air conditioning system based on the load prediction parameter comprises:

[0020] The load prediction parameter is input into a load prediction model to obtain a predicted total load value of the air conditioning system.

[0021] A ratio between the predicted total load value and a rated total load value of the air conditioning system is calculated to obtain the predicted total load rate.

[0022] The load prediction parameter comprises at least one or a combination of meteorological data, an indoor temperature measurement value, an indoor temperature set value, or indoor heat source information.

[0023] The load prediction model comprises a pre-operation model, and the step of obtaining the predicted total load rate of the air conditioning system based on the load prediction parameter comprises:

[0024] In a pre-operation stage after the air conditioning system is started, the load prediction parameter is input into the pre-operation model.

[0025] The load prediction model further comprises an official model, and the step of obtaining the predicted total load rate of the air conditioning system based on the load prediction parameter further comprises:

[0026] In an official operation stage after the air conditioning system is operated for a preset time, the official model is trained using operation data of the air conditioning system, and the load prediction parameter is input into the official model.

[0027] The step of training the official model using the operation data of the air conditioning system comprises:

[0028] updating the formal model based on the operation data in a preset period.

[0029] The step of controlling the air conditioning system by the control target value comprises:

[0030] obtaining a first energy consumption of the air conditioning system based on the control target value currently used by the air conditioning system;

[0031] obtaining a second energy consumption of the air conditioning system based on the control target value currently calculated by the air conditioning system;

[0032] obtaining an energy saving rate of the air conditioning system based on the first energy consumption and the second energy consumption.

[0033] The step of controlling the air conditioning system by the control target value further comprises:

[0034] in response to the energy saving rate being greater than or equal to a preset threshold, replacing the control target value currently used by the control target value currently calculated;

[0035] in response to the energy saving rate being less than the preset threshold, keeping the control target value currently used.

[0036] To solve the above technical problems, one technical solution adopted by the present application is to provide an air conditioning system of a multi-connected machine, which comprises a processor and a memory; the memory stores a computer program, and the processor is configured to execute the computer program to implement the above control method.

[0037] To solve the above technical problems, one technical solution adopted by the present application is to provide a computer readable storage medium, which stores program instructions, and the program instructions can be executed to implement the above control method.

[0038] The control method of the present application obtains the load prediction parameter of the air conditioning system, obtains the predicted total load rate of the air conditioning system based on the load prediction parameter, obtains the correction coefficient based on the actual total load rate of the air conditioning system, corrects the predicted total load rate by using the correction coefficient, obtains the control target value based on the corrected predicted total load rate, and controls the air conditioning system by using the control target value. The present application corrects the predicted total load rate by using the correction coefficient, thereby improving the accuracy of the predicted total load rate, improving the prediction accuracy of the air conditioning system, and improving the reliability of the air conditioning system. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0040] Figure 1 is a frame schematic diagram of an air conditioning system of a multi-split unit according to an embodiment of the present application;

[0041] Figure 2 is a flow schematic diagram of a control method according to an embodiment of the present application;

[0042] Figure 3 is a flow schematic diagram of step S202 in Figure 2

[0043] Figure 4 is a flow schematic diagram of step S203 in Figure 2

[0044] Figure 5 is a flow schematic diagram of step S401 in Figure 4

[0045] Figure 6 is a flow schematic diagram of step S205 in Figure 2

[0046] Figure 7 is a corresponding relationship diagram of an evaporation temperature set value and a predicted total load rate of an air conditioning system according to the present application;

[0047] Figure 8 is a simulation diagram of an air conditioning system according to the present application;

[0048] Figure 9 is a frame schematic diagram of an air conditioning system according to an embodiment of the present application;

[0049] Figure 10 is a frame schematic diagram of another embodiment of an air conditioning system according to the present application;

[0050] Figure 11 is a structure schematic diagram of a computer storage medium according to an embodiment of the present application. DETAILED DESCRIPTION

[0051] ​​​​The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It can be understood that the specific embodiments described herein are only used to explain the present application, rather than limit the present application. In addition, it should be noted that, for the convenience of description, only the parts related to the present application are shown in the drawings, rather than all the structures. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of the present application.

[0052] As shown in Figure 1 The multi-split air conditioning system 1 of the present application can include an outdoor unit 11 and a plurality of indoor units 12, and the plurality of indoor units 12 are connected with the outdoor unit 11. The outdoor unit 11 includes, but is not limited to, a controller 111, a compressor 112 and an outdoor fan 113; Figure 1 The number of indoor units 12 is 3, and each indoor unit 12 is connected with the outdoor unit 11 through an expansion valve (not shown in the figure), and the multi-split air conditioning system 1 adjusts the opening degree of the expansion valve to realize the adjustment of the refrigerant flow rate input into the indoor unit 12.

[0053] In an embodiment, the multi-split air conditioning system 1 realizes control by using PID (Proportion Integral Differential), and the outdoor dry-bulb temperature of the multi-split air conditioning system 1, the heat exchanger surface temperature of the indoor unit 12, the heat exchanger surface temperature of the outdoor unit 11, the heat exchanger surface temperature of the indoor unit 12 and the inlet and outlet pressures of the compressor 112 are used as observation quantities, and the frequency of the compressor 112 of the multi-split air conditioning system 1, the rotating speed of the outdoor fan 113, the rotating speed of the fan of the indoor unit 12 and the opening degree of the expansion valve are used as control quantities. The multi-split air conditioning system 1 adjusts the control quantities of the multi-split air conditioning system 1 by the difference between the measured values and the set values of the above observation quantities.

[0054] The multi-split air conditioning system 1 uses PID control, and cannot obtain the required refrigeration or heating capacity to reach the set temperature, so the compressor 112 and the outdoor fan 113 operate at the preset maximum rotating speed to make the multi-split air conditioning system 1 reach the set temperature; then the compressor 112 and the outdoor fan 113 operate at a reduced frequency to maintain the set value. When the load of the multi-split air conditioning system 1 changes and the indoor temperature exceeds the set value to reach a predetermined range, the multi-split air conditioning system 1 controls the compressor 112 and the outdoor fan 113 to operate at a variable frequency; when the indoor temperature exceeds the set value without reaching the predetermined range, the multi-split air conditioning system 1 maintains the set value; therefore, the refrigeration or heating capacity of the present embodiment cannot be matched with the load in real time.

[0055] In order to solve the problem that the refrigeration or heating capacity cannot be matched with the load in real time, the present application provides a control method. Please refer toFigure 2 As shown in FIG. 1, Figure 2 FIG. 1 is a schematic diagram of a control method according to an embodiment of the present application. The control method according to the embodiment is applied to an air conditioning system 1 as shown in FIG. 1; in other embodiments, the control method can be applied to an air conditioning system of a multi-connected air conditioner with other structures. The control method comprises the following steps: Figure 1

[0056] S201: Obtain a load prediction parameter of the air conditioning system 1.

[0057] The load prediction parameter comprises at least one or a combination of meteorological data, an indoor temperature measurement value, an indoor temperature set value, or indoor heat source information. The air conditioning system 1 can obtain the load prediction parameter of the air conditioning system 1 through local collection or network.

[0058] The meteorological data collected by the air conditioning system 1 comprises outdoor meteorological data; the outdoor meteorological data can comprise outdoor temperature, outdoor relative humidity, or the angle of solar radiation, etc. Specifically, the air conditioning system 1 obtains weather forecast through network to obtain the outdoor meteorological data from the weather forecast; or the air conditioning system 1 directly detects the outdoor meteorological data through the outdoor unit 11, and the outdoor unit 11 can be provided with a temperature sensor or a temperature detection device for detecting the outdoor meteorological data.

[0059] The temperature value measured by each indoor unit 12 of the air conditioning system 1 in the room or heat area where the indoor unit 12 is located is taken as the indoor temperature measurement value. The air conditioning system 1 can directly measure the temperature value of the room or heat area where the indoor unit 12 is located. The indoor temperature set value represents the temperature value of the indoor set in advance by the air conditioning system 1, and the air conditioning system 1 operates based on the indoor temperature set value to make the indoor temperature measurement value reach the indoor temperature set value. Specifically, the controller 111 obtains the indoor temperature set value and controls the compressor 112 and the outdoor fan 113 to operate based on the indoor temperature set value.

[0060] The indoor heat source information can comprise indoor heat source equipment information or indoor personnel information, the indoor heat source equipment can be an indoor heat generating equipment, and the indoor heat source equipment can comprise a gas stove; the indoor personnel information can comprise personnel information and position information of the personnel in the room.

[0061] ​In an embodiment, after collecting the load prediction parameter, the air conditioning system 1 can pre-process the load prediction parameter to verify the validity of the load prediction parameter. If the air conditioning system 1 does not detect that the load prediction parameter has an error, the air conditioning system 1 stores the collected load prediction parameter locally, so that the air conditioning system 1 operates based on the load prediction parameter. If the air conditioning system 1 detects that the load prediction parameter has an error, the air conditioning system 1 deletes the load prediction parameter and obtains the load prediction parameter stored by the air conditioning system 1 at the last time, so that the air conditioning system 1 operates based on the load prediction parameter at the last time.

[0062] In the above manner, the air conditioning system 1 of the embodiment verifies the validity of the load prediction parameter, thereby improving the accuracy of the load prediction parameter. Optionally, the air conditioning system 1 can be provided with a data update period, and the air conditioning system 1 uploads the locally stored data to a server (not shown in the figure) for storage according to the data update period. Specifically, the data update period is set to 24 hours, and the air conditioning system 1 uploads the locally stored data to the server for storage every 24 hours, so as to prevent the loss of the data stored locally by the air conditioning system 1.

[0063] S202: Obtain a predicted total load rate of the air conditioning system 1 based on the load prediction parameter.

[0064] The air conditioning system 1 obtains the load prediction parameter from local storage or a server, and obtains a predicted total load rate of the air conditioning system 1 based on the load prediction parameter. The air conditioning system 1 is provided with a load prediction model in advance, or the server stores a load prediction model, and the air conditioning system 1 obtains the load prediction model from the server. The load prediction model is used to predict the air conditioning system 1, as shown in Figure 3 S202 includes the following steps:

[0065] S301: Input the load prediction parameter into the load prediction model to obtain a predicted total load value of the air conditioning system 1.

[0066] The air conditioning system 1 inputs the obtained load prediction parameter into the load prediction model, that is, the load prediction model operates based on the load prediction parameter, so that the load prediction model predicts a predicted total load value. The predicted total load value can include a predicted cooling load value and a predicted heating load value. When the air conditioning system 1 is in a cooling mode, the predicted total load value is the predicted cooling load value; when the air conditioning system 1 is in a heating mode, the predicted total load value is the predicted heating load value.

[0067] The predicted total load value can be a load value predicted by the air conditioning system 1 for each room or thermal zone, or the predicted total load value can be a load value predicted by the air conditioning system 1 for all rooms or thermal zones of the air conditioning system 1.

[0068] S302: Calculate the ratio between the predicted total load value and the rated total load value of the air conditioning system 1 to obtain the predicted total load rate.

[0069] The air conditioning system 1 divides the predicted total load value by the rated total load value of the air conditioning system 1 to obtain an operation result, and takes the operation result as the predicted total load rate. The rated total load value of the air conditioning system 1 includes the rated total cooling load value and the rated total heating load value. When the air conditioning system 1 is in the cooling mode, the air conditioning system 1 divides the predicted cooling load value by the rated total cooling load value to obtain the predicted total load rate; when the air conditioning system 1 is in the heating mode, the air conditioning system 1 divides the predicted heating load value by the rated total heating load value to obtain the predicted total load rate.

[0070] Specifically, the air conditioning system 1 collects the load prediction parameter at the current time, the load prediction parameter at the previous N1 time, and the outdoor weather data at the next N2 time, N1 time is N1 time before the current time, N2 time is N2 time after the current time, N1 ranges from 0 to 23 hours, and N2 ranges from 1 to 24 hours.

[0071] The air conditioning system 1 obtains the outdoor weather data at the next N2 time through weather forecast, and inputs the load prediction parameter at the current time, the load prediction parameter at the previous N1 time, and the outdoor weather data at the next N2 time into the load prediction model to predict the predicted total load rate of the air conditioning system 1 at the next N2 time through the load prediction model.

[0072] S203: Obtain a correction coefficient based on the actual total load rate of the air conditioning system 1.

[0073] The air conditioning system 1 obtains the correction coefficient through the actual total load rate of the air conditioning system 1, and the actual total load rate is the total load rate calculated in real time when the air conditioning system 1 operates at the current time.

[0074] S204: Correct the predicted total load rate by using the correction coefficient.

[0075] The air conditioning system 1 operates the predicted total load rate based on the correction coefficient to realize correction. Specifically, the air conditioning system 1 multiplies the predicted total load rate by the correction coefficient to obtain the corrected predicted total load rate. In other embodiments, the air conditioning system 1 divides the predicted total load rate by the correction coefficient to obtain the corrected predicted total load rate. The application operates the predicted total load rate by using the correction coefficient, so that the corrected predicted total load rate is closer to the actual total load rate.

[0076] S205: Obtain a control target value based on the corrected predicted total load rate, and control the air conditioning system 1 by using the control target value.

[0077] After the air conditioning system 1 operates the predicted total load rate based on the correction coefficient, the air conditioning system 1 obtains the control target value based on the corrected predicted total load rate, which can include but is not limited to the evaporating temperature set value Tes, the condensing temperature set value Tcs and the indoor temperature set value of the air conditioning system 1. Among them, the air conditioning system 1 uses the existing calculation method to calculate the control target value based on the predicted total load rate. The air conditioning system 1 controls the compressor 112 and the outdoor fan 113 of the air conditioning system 1 to operate based on the evaporating temperature set value Tes, the condensing temperature set value Tcs and the indoor temperature set value, so as to control the operation of the air conditioning system 1.

[0078] Specifically, the air conditioning system 1 adjusts the corresponding control quantity based on the control target value, wherein the air conditioning system 1 adjusts the frequency of the compressor 112, the rotating speed of the outdoor fan 113 and the opening degree of the expansion valve and other control quantities, so that the observation quantity of the air conditioning system 1 reaches the control target value, wherein the observation quantity of the air conditioning system 1 can be the indoor temperature, the outer surface temperature of the indoor heat exchanger, the outer surface temperature of the outdoor heat exchanger and the inlet and outlet pressure of the compressor 112. Therefore, the air conditioning system 1 of the embodiment can output the heating capacity or the refrigerating capacity matched with the control target value with lower energy consumption.

[0079] The air conditioning system 1 of the embodiment corrects the predicted total load rate by using the correction coefficient, so as to realize online correction of the predicted total load rate. The corrected predicted total load rate is closer to the actual total load rate, thereby improving the accuracy of the predicted total load rate, improving the prediction accuracy of the air conditioning system 1 and improving the reliability of the air conditioning system 1. In addition, the load prediction parameter includes indoor heat source information (i.e. the load of the air conditioning system 1), and the air conditioning system 1 obtains the predicted total load rate of the air conditioning system 1 based on the load prediction parameter, i.e. when the load of the air conditioning system 1 changes, the load prediction parameter also changes in real time, so as to solve the problem that the refrigerating capacity or the heating capacity cannot be matched with the load in real time, and improve the performance of the air conditioning system 1.

[0080] Please refer to Figure 4 as shown in Figure 4 is Figure 2 the flowchart of an embodiment of step S203 in

[0081] S401: Calculate the average value of the actual total load rate of the air conditioning system 1 in the first preset time period to obtain a first average value.

[0082] Wherein, the first preset time can include the current time and the previous N1 time before the current time. Specifically, the air conditioning system 1 calculates the sum of the actual total load rate at the current time and the previous N1 time, and divides the sum of the actual total load rate at the current time and the previous N1 time by the number of all actual total load rates to obtain the first average value.

[0083] S402: Calculate the average value of the predicted total load rate of the air conditioning system 1 in the first preset time period to obtain a second average value.

[0084] The air conditioning system 1 further calculates the average value of the predicted total load rate of the air conditioning system 1 at the current time and the previous N1 times. Specifically, the air conditioning system 1 obtains the predicted total load rate at the current time and the previous N1 times, calculates the sum of the predicted total load rate at the current time and the previous N1 times, and divides the sum of the predicted total load rate at the current time and the previous N1 times by the number of all predicted total load rates to obtain a second average value.

[0085] S403: Calculate the ratio between the first average value and the second average value to obtain a correction coefficient in a second preset time period after the first preset time period.

[0086] The air conditioning system 1 divides the first average value by the second average value to obtain a correction coefficient in a second preset time period after the current time. The second preset time period can include N2 times after the current time, i.e. N2 future times. At this time, in step S204, the air conditioning system 1 can multiply the predicted total load rate by the correction coefficient to obtain a corrected predicted total load rate.

[0087] In other embodiments, the air conditioning system 1 divides the second average value by the first average value to obtain a correction coefficient in a second preset time period after the current time. At this time, in step S204, the air conditioning system 1 can divide the predicted total load rate by the correction coefficient to obtain a corrected predicted total load rate.

[0088] The present embodiment can improve the accuracy of the correction coefficient by dividing the first average value by the second average value to obtain a correction coefficient in a second preset time period after the current time, thereby improving the prediction accuracy of the air conditioning system 1 and improving the reliability of the air conditioning system 1.

[0089] Please refer to Figure 5 , Figure 5 is Figure 4 a flowchart of an embodiment of step S401 in

[0090] S501: According to the operation data of the air conditioning system 1 at a plurality of first time points in the first preset time period, the actual total load value corresponding to the first time point is calculated.

[0091] The air conditioning system 1 obtains operation data at the current time and the previous N1 times, wherein the current time and the previous N1 times are a plurality of first time points, and the operation data can include but is not limited to observation and control of the air conditioning system 1. The air conditioning system 1 calculates the actual total load value corresponding to the first time point based on the operation data of the first time point. For example, the first time point is the current time, the air conditioning system 1 obtains the operation data at the current time, and calculates the corresponding actual total load value based on the operation data at the current time.

[0092] S502: Calculate the ratio between each actual total load value and the rated total load value of the air conditioning system 1 to obtain the actual total load rate corresponding to the first time point.

[0093] The air conditioning system 1 calculates a plurality of actual total load values corresponding to the current time and the previous N1 times, and divides each actual total load value by the rated total load value of the air conditioning system 1 to obtain the actual total load rate corresponding to the first time point. The actual total load value can include an actual heat load value and an actual cold load value. When the air conditioning system 1 is in a cooling mode, the air conditioning system 1 calculates the ratio between the actual cold load value and the rated cooling total load value. When the air conditioning system 1 is in a heating mode, the air conditioning system 1 calculates the ratio between the actual heat load value and the rated heating total load value.

[0094] S503: Average the actual total load rates corresponding to the plurality of first time points to obtain the average value of the actual total load rate. The air conditioning system 1 calculates the sum of the actual total load rates corresponding to the current time and the previous N1 times, and divides the sum of the actual total load rates by the number of the plurality of first time points to obtain the average value of the actual total load rate.

[0095] The air conditioning system 1 of the present application includes a pre-operation stage after starting and a formal operation stage, that is, the air conditioning system 1 enters the pre-operation stage after starting up; the air conditioning system 1 enters the formal operation stage after running for a preset time. The load prediction model includes a pre-operation model and a formal model.

[0096] Step S301 further includes: in the pre-operation stage after the air conditioning system 1 starts, inputting the load prediction parameter into the pre-operation model. Specifically, after the air conditioning system 1 starts up, the air conditioning system 1 is in the pre-operation stage, so the air conditioning system 1 can obtain the pre-operation model, and obtain the predicted total load rate of the air conditioning system 1 in the pre-operation stage through the load prediction parameter and the pre-operation model. For example: the air conditioning system 1 locally stores the pre-operation model, so the air conditioning system 1 directly obtains the pre-operation model from the local storage; or the server is used to store the pre-operation model, so the air conditioning system 1 obtains the pre-operation model from the server to obtain the predicted total load rate of the air conditioning system 1 in the pre-operation stage through the load prediction parameter and the pre-operation model.

[0097] The pre-operation model does not require operation data of the air conditioning system 1, that is, the air conditioning system 1 has no historical operation data in the pre-operation stage, so that the air conditioning system 1 calls the pre-operation model, and the predicted total load rate cannot be obtained in the case of no historical operation data, thereby improving the prediction accuracy of the air conditioning system 1. Specifically, the pre-operation model can obtain a data model based on load data of a typical building similar to the building environment of the air conditioning system 1, for example, the building environment of the air conditioning system 1 is a hotel, and the server can obtain a data model trained offline based on load data of the hotel.

[0098] The pre-operation model includes but is not limited to a multivariable linear regression model (MLR), a long short-term memory neural network model (LSTM), a multilayer perceptron model (MLP), and an XGBoost model. The air conditioning system 1 inputs the load prediction parameters into the pre-operation model, for example, the load prediction parameters include outdoor weather data at the current time, time parameters, indoor temperature set values, indoor population, device heat dissipation data, outdoor weather data at the N2 time, and indoor temperature set values, so that the air conditioning system 1 obtains the predicted total load rate based on the pre-operation model.

[0099] The existing model needs to be established based on certain operation data, so it cannot be used for prediction until the system has been running for a period of time. The pre-operation model of the present application does not require operation data of the air conditioning system 1, so the air conditioning system 1 can directly call the pre-operation model without waiting, thereby improving efficiency. Further, the control method of the present application corrects the predicted total load rate by the correction coefficient, realizes online correction of the predicted total load rate, improves the reliability of the prediction, and increases the robustness of the air conditioning system 1. In the pre-operation stage, the pre-operation model is limited by universality, and may not be adapted to the building environment of the air conditioning system 1. By online correction of the predicted total load rate, the deviation of the predicted total load rate is reduced.

[0100] In other embodiments, the server stores load data of the building environment of the air conditioning system 1, so that the server can establish a formal model based on the load data, and the air conditioning system 1 obtains the formal model from the server. In the above manner, the server or the air conditioning system 1 does not need to call the pre-operation model, which can reduce the operation amount of the server or the air conditioning system 1 and improve the operation speed.

[0101] After the air conditioning system 1 runs for a preset time, the air conditioning system 1 uploads the locally stored data to the server, so that the server obtains the running data of the air conditioning system 1. When the server obtains sufficient running data, the server trains the pre-operation model through the running data to obtain the formal model.

[0102] Therefore, step S301 further comprises: in the formal operation stage after the air conditioning system 1 runs for a preset time, training the formal model by using the running data of the air conditioning system 1, and inputting the load prediction parameter into the formal model. The formal model can include but is not limited to the type of pre-operation model, and can be a multivariate linear regression model or a long short-term memory neural network model.

[0103] Optionally, the step of training the formal model by using the running data of the air conditioning system 1 further comprises: updating the formal model based on the running data in a preset period. The air conditioning system 1 stores the running data in the preset period to the server, the server obtains the running data in the preset period, and trains the formal model by using the running data in the preset period to update the formal model. The preset period can be 24 hours.

[0104] The server of the present application is used to establish and update the load prediction model to improve the prediction accuracy of the air conditioning system; the air conditioning system 1 obtains the predicted total load rate and the control target value of the air conditioning system 1 through the controller 111, avoids the communication delay between the air conditioning system 1 and the server, and improves the stability of the air conditioning system 1.

[0105] Please refer to Figure 6 shown, Figure 6 is Figure 2 an embodiment of step S205 in FIG. 5. Step S205 further comprises the following steps:

[0106] S601: Obtain the first energy consumption of the air conditioning system 1 based on the currently used control target value of the air conditioning system 1.

[0107] The air conditioning system 1 obtains the currently used control target value, calculates the first energy consumption of the air conditioning system 1 through the currently used control target value, and obtains the energy consumption of the air conditioning system 1 at the current time.

[0108] S602: Obtain the second energy consumption of the air conditioning system 1 based on the control target value currently calculated by the air conditioning system 1.

[0109] The air conditioning system 1 calculates the control target value through the above steps S201-S205, that is, the control target value predicted by the air conditioning system 1 through the load prediction model; and predicts the second energy consumption of the air conditioning system 1 through the control target value currently calculated, that is, the energy consumption of the air conditioning system 1 at the future N2 time.

[0110] S603: Obtain the energy-saving rate of the air conditioning system 1 based on the first energy consumption and the second energy consumption.

[0111] Specifically, the air conditioning system 1 can calculate the difference between the first energy consumption and the second energy consumption, calculate the ratio between the difference and the first energy consumption, and obtain the energy-saving rate of the air conditioning system 1. In order to improve the energy-saving rate of the air conditioning system 1, the air conditioning system 1 is provided with a preset threshold value in advance, and the energy-saving rate is compared with the preset threshold value. The preset threshold value can be 0.5%-1%, for example, the preset threshold value is 0.5%, 0.75% or 1%.

[0112] S604: In response to the energy-saving rate being greater than or equal to the preset threshold value, the control target value obtained by the current calculation is used to replace the control target value currently used.

[0113] The air conditioning system 1 judges that the energy-saving rate is greater than or equal to the preset threshold value, and the air conditioning system 1 replaces the control target value obtained by the current calculation with the control target value currently used, and controls the air conditioning system 1 to run at time N2 by using the control target value obtained by the current calculation, so as to achieve energy saving.

[0114] S605: In response to the energy-saving rate being less than the preset threshold value, the control target value currently used is retained.

[0115] The air conditioning system 1 judges that the energy-saving rate is less than the preset threshold value, and the air conditioning system 1 retains the control target value currently used.

[0116] The existing air conditioning system sets the evaporating temperature set value Tes to be lower, for example, the evaporating temperature set value Tes is 8-10℃ lower than the dew point temperature of the return air, and the evaporating temperature set value Tes is 5℃, in order to meet the temperature control needs of different building environments and different load rates, resulting in low efficiency of the existing air conditioning system. The air conditioning system 1 of the present application can obtain the predicted total load rate through the above control method, calculate the evaporating temperature set value Tes based on the predicted total load rate, and further control the frequency of the compressor 112 and the speed of the outdoor fan 113 and other control quantities, wherein the corresponding relationship between the evaporating temperature set value Tes and the predicted total load rate is as shown in Figure 7 .

[0117] As shown in Figure 7 , after the air conditioning system 1 is started and started, it is in a pre-operation stage, and the upper limit value Tesmax of the evaporating temperature set value of the air conditioning system 1 can be set to 10℃, so as to facilitate the air conditioning system 1 to have sufficient adjustment margin to meet the case that the pre-operation model underestimates the load of the air conditioning system 1.

[0118] The air conditioning system 1 is in the formal operation stage after running for a preset time, and the air conditioning system 1 can increase the upper limit value Tesmax of the evaporating temperature set value, for example, the upper limit value Tesmax of the evaporating temperature set value is set to 12℃, so that the predicted total load rate of the air conditioning system 1 obtained by the formal model matches the real-time evaporating temperature, and energy saving is realized.

[0119] In an application scenario embodiment, the air conditioning system 1 of the multi-connected machine is a multi-connected machine air conditioning system of one-to-four, and the rated refrigerating capacity of the air conditioning system 1 of the multi-connected machine is set to 30KW. The air conditioning system 1 is installed in an office building, and under the premise of running for one week in May, the simulation diagram of the air conditioning system 1 is as shown in Figure 8 .

[0120] Figure 8 The curve 81 in Figure 8 represents the simulation result of the air conditioning system 1 using the control method of the prior art, The curve 82 in

[0121] represents the simulation result of the air conditioning system 1 using the control method disclosed in the above embodiment, and by comparing the curve 81 and the curve 82, it can be obtained that when the air conditioning system 1 is in the pre-operation stage, compared with the existing control method, the energy saving rate of the air conditioning system 1 using the above control method is 6%; when the air conditioning system 1 is in the formal operation stage after running for a preset time, compared with the existing control method, the energy saving rate of the air conditioning system 1 using the above control method is 9%, so as to realize energy saving. Figure 9 Figure 9 Please refer to , which is a frame schematic diagram of an embodiment of the air conditioning system of the present application. The air conditioning system 1 of the embodiment includes a data processing module 130, a load prediction module 131, a control module 132 and a load correction module 133, wherein the data processing module 130 is connected with the load prediction module 131, the control module 132 and the load correction module 133 respectively, and the load prediction module 131 is connected with the control module 132 through the load correction module 133.

[0122] Among them, the data processing module 130 is used for collecting, preprocessing, transmitting and storing data, which includes the data disclosed in the above embodiment, specifically, operation data, load prediction parameters, corrected predicted total load rate, predicted total load rate, control target value, control amount and observation value, etc. The data processing module 130 can be used to collect the measured values of the above data, for example, the data processing module 130 collects the actual total load rate of the air conditioning system 1 and the load prediction parameters; the data processing module 130 can also obtain the weather forecast through the network to obtain the outdoor meteorological data.

[0123] The data processing module 130 can be configured to pre-process the collected data, and the data processing module 130 pre-processes the load prediction parameter to verify the validity of the load prediction parameter. The data processing module 130 further stores the pre-processed data, for example, the data processing module 130 stores the pre-processed load prediction parameter. The data processing module 130 further uploads the locally stored data to the server storage according to a data update period.

[0124] The load prediction module 131 is provided with a pre-operation model and a formal model, which is configured to obtain a predicted total load rate by the load prediction parameter and the pre-operation model in a pre-operation stage after the air conditioning system 1 is started, and is configured to obtain a formal model by training the pre-operation model by operation data of the air conditioning system 1 in a formal operation stage after the air conditioning system 1 is operated for a preset time, and is configured to obtain the predicted total load rate by the load prediction parameter and the formal model.

[0125] The load correction module 133 is configured to obtain a correction coefficient based on an actual total load rate of the air conditioning system 1, and correct the predicted total load rate by the correction coefficient. The control module 132 is configured to obtain a control target value based on the corrected predicted total load rate, and control the air conditioning system 1 by the control target value.

[0126] Please refer to Figure 10 , Figure 10 is a frame schematic diagram of another embodiment of the air conditioning system of the application, and the air conditioning device 1 of the embodiment includes a processor 21 and a memory 22. The memory 22 stores a computer program, and the processor 21 is configured to execute the computer program to realize the control method described above.

[0127] The processor 21 can be an integrated circuit chip with signal processing capability. The processor 21 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0128] For the control method of the embodiment shown in Figures 2-6 , the control method can be presented in the form of a computer program, and the application proposes a computer storage medium carrying the computer program. Please refer to Figure 11 , Figure 11 is a structural schematic diagram of an embodiment of the computer storage medium of the application, and the embodiment of the computer storage medium 300 includes a computer program 31, which can be executed to realize the control method described above.

[0129] The computer storage medium 300 in the embodiment can be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and the like, which can store program instructions, or can be a server storing the program instructions, which can send the stored program instructions to other devices for running, or can run the stored program instructions.

[0130] In several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic, for example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0131] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, can be located in one place, or can be distributed to a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0132] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0133] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0134] The above description is only an implementation method of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A control method, characterized in that: Applied to a multi-split air conditioning system, the control method includes: Obtaining load forecast parameters of the air conditioning system; Obtaining a predicted total load rate of the air-conditioning system based on the load prediction parameter; obtaining a correction factor based on an actual total load rate of the air conditioning system; Correcting the predicted total load rate using the correction coefficient; obtaining a control target value based on the corrected predicted total load rate, and controlling the air conditioning system according to the control target value; The step of obtaining the correction coefficient based on the actual total load rate of the air-conditioning system includes: Calculating an average value of the actual total load rate of the air-conditioning system within a first preset time period to obtain a first average value; calculating an average value of the predicted total load rate of the air-conditioning system within the first preset time period to obtain a second average value; A ratio between the first average value and the second average value is calculated to obtain the correction coefficient within a second preset time period after the first preset time period.

2. The control method according to claim 1, characterized in that: The step of calculating the average value of the actual total load rate of the air-conditioning system within the first preset time period includes: Calculating an actual total load value corresponding to a plurality of first time points according to the operating data of the air-conditioning system at the first time points within the first preset time period; calculating a ratio between each of the actual total load values ​​and the rated total load value of the air-conditioning system to obtain the actual total load rate corresponding to the first time point; The actual total load rates corresponding to a plurality of the first time points are averaged to obtain an average value of the actual total load rate.

3. The control method according to claim 1, wherein: The step of obtaining the predicted total load rate of the air-conditioning system based on the load prediction parameter comprises: Inputting the load prediction parameters into a load prediction model to obtain a predicted total load value of the air-conditioning system; The ratio between the predicted total load value and the rated total load value of the air-conditioning system is calculated to obtain the predicted total load rate.

4. The control method according to claim 3, characterized in that: The load prediction parameters include at least one or a combination of meteorological data, indoor temperature measurement values, indoor temperature setting values, or indoor heat source information.

5. The control method according to claim 3, characterized in that: The load forecasting model includes a pre-operation model, and the step of obtaining the predicted total load rate of the air-conditioning system based on the load forecasting parameters includes: In a pre-operation phase after the air-conditioning system is started, the load prediction parameters are input into the pre-operation model.

6. The control method according to claim 5, characterized in that: The load forecasting model further includes a formal model, and the step of obtaining the predicted total load rate of the air-conditioning system based on the load forecasting parameters further includes: In a formal operation phase after the air-conditioning system has been running for a preset time, the formal model is trained using the operating data of the air-conditioning system, and the load forecasting parameters are input into the formal model.

7. The control method according to claim 6, characterized in that: The step of using the operating data of the air-conditioning system to train the formal model comprises: The formal model is updated based on the operating data within a preset period.

8. The control method according to claim 1, characterized in that: The step of controlling the air conditioning system by using the control target value includes: obtaining a first energy consumption of the air-conditioning system based on the control target value currently used by the air-conditioning system; obtaining a second energy consumption of the air-conditioning system based on the control target value currently calculated by the air-conditioning system; An energy saving rate of the air-conditioning system is obtained based on the first energy consumption and the second energy consumption.

9. The control method according to claim 8, characterized in that: The step of controlling the air conditioning system by using the control target value further includes: In response to the energy saving rate being greater than or equal to a preset threshold, replacing the currently used control target value with the currently calculated control target value; In response to the energy saving rate being less than the preset threshold, the currently used control target value is retained.

10. A multi-connected air conditioning system, characterized in that: The air conditioning system includes a processor and a memory; the memory stores a computer program, and the processor is used to execute the computer program to implement the control method according to any one of claims 1 to 9.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores program instructions, and the program instructions can be executed to implement the control method according to any one of claims 1 to 9.

Images