Air conditioning equipment

Abstract

The invention provides air conditioning equipment, the air conditioning equipment comprises a shell, a compressor arranged in the shell and a controller arranged in the shell, the controller is configured to obtain operation data of the compressor, and the operation data comprises the total number of starting times, the total number of stopping times, the total operation duration and the total stopping duration of the compressor; inputting the operation data into a temperature prediction model to obtain an indoor average temperature output by the temperature prediction model; if the air conditioning equipment is in the heating mode, the indoor average temperature is larger than or equal to a first temperature threshold value, and the return air temperature is larger than or equal to a second temperature threshold value, the compressor is controlled to stop running; and if the air conditioning equipment is in the refrigeration mode, the indoor average temperature is smaller than or equal to the first temperature threshold value, and the return air temperature is smaller than or equal to the second temperature threshold value, the compressor is controlled to stop running. Accurate control over the air conditioner compressor can be achieved at low cost, so that the comfort level of a user is guaranteed, and the energy-saving control effect of the air conditioner equipment is improved.

Description

Technical Field

[0001] The present application relates to the technical field of air conditioning, and in particular to an air conditioning device. Background Art

[0002] Air conditioning equipment is an essential environmental regulator in modern buildings, providing users with a comfortable living and working environment. During operation, air conditioning equipment typically regulates temperature by starting and stopping the compressor to ensure efficient operation and optimize energy management.

[0003] Most air conditioners use sensors to collect the temperature of the air conditioner's return air outlet and use this as a feedback signal to control the compressor's operating status. However, these sensors can only capture the temperature of the return air outlet. Furthermore, due to the fixed installation location of the sensors, the collected return air temperature is difficult to reflect the overall indoor temperature. This results in poor accuracy when the air conditioner controls the compressor shutdown, affecting the precision of indoor temperature regulation. Some air conditioners use temperature sensors in multiple locations indoors to obtain more comprehensive temperature information, but this significantly increases hardware costs and complicates the wiring and installation of the air conditioner. Summary of the Invention

[0004] The present application provides an air-conditioning device that can achieve precise control of the air-conditioning compressor at a low cost, thereby ensuring user comfort and improving the energy-saving control effect of the air-conditioning device.

[0005] In a first aspect, some embodiments of the present application provide an air conditioning device, comprising: a housing; a compressor disposed in the housing; and a controller disposed in the housing;

[0006] The controller is configured to:

[0007] Acquiring operating data of the compressor, the operating data including a total number of starts, a total number of stops, a total operating time, and a total stopping time of the compressor;

[0008] Inputting the operating data into a temperature prediction model to obtain an indoor average temperature output by the temperature prediction model, wherein the temperature prediction model is used to perform feature extraction processing on the total number of starts, the total number of shutdowns, the total operating time, and the total shutdown time in the operating data, and perform weighted calculation based on each extracted feature vector and the weight corresponding to the feature vector, and process the weighted feature vector based on a set activation function to obtain the indoor average temperature;

[0009] When the air conditioner is in heating mode, the indoor average temperature is greater than or equal to a first temperature threshold, and the return air temperature is greater than or equal to a second temperature threshold, controlling the compressor to stop running, the return air temperature is used to reflect the temperature at the return air point of the air conditioner, and the first temperature threshold and the second temperature threshold are determined according to the expected temperature of the environment space where the air conditioner is located;

[0010] When the air-conditioning device is in cooling mode, the indoor average temperature is less than or equal to the first temperature threshold, and the return air temperature is less than or equal to the second temperature threshold, the compressor is controlled to stop running.

[0011] In the embodiment of the present application, since the start-up, shutdown and corresponding operating time of the compressor directly affect the change of the overall indoor temperature, and the indoor temperature in turn affects the start-up and shutdown of the compressor, that is, there is a complex correlation between the operating data of the compressor and the overall indoor temperature, and the temperature prediction model can better learn the complex relationship therein, therefore, when the temperature prediction model performs weighted calculation based on the feature vectors of each extracted data and their corresponding weights, it can accurately quantify the contribution of each feature vector to the prediction of the indoor average temperature, and at the same time can fully consider the impact of different features on the indoor average temperature, thereby improving the accuracy of the feature vector obtained by weighted calculation. Then, the weighted feature vector is processed based on the activation function, and nonlinear factors are introduced through the activation function, so that the temperature prediction model can accurately capture the complex relationship in the data, thereby accurately predicting the average temperature of the environmental space where the air-conditioning equipment is located, and obtaining the required indoor average temperature. Furthermore, combined with the functional mode of the air-conditioning equipment, it is determined whether the predicted indoor average temperature and the detected return air temperature meet the corresponding temperature thresholds, so as to determine whether to control the compressor to stop running. Compared with using a single return air temperature as the basis, it can effectively improve the accuracy of compressor shutdown control, thereby improving the accuracy of temperature regulation, ensuring user comfort and improving the energy-saving control effect of the air-conditioning equipment. There is no need to install multiple sensors additionally, which effectively reduces the hardware cost and the complexity of the wiring installation of the air-conditioning equipment.

[0012] In a possible implementation of the first aspect, when the controller controls the compressor to stop operating, the controller is configured to:

[0013] When each data in the operating data is less than or equal to a predetermined threshold value corresponding to the data, the compressor is controlled to stop operating.

[0014] In the above technical solution, when the controller determines that the relationship between the average indoor temperature and the return air temperature and their corresponding temperature thresholds meets the requirements of the functional mode, and each data in the operating data is less than or equal to the predetermined threshold corresponding to the data, it controls the compressor to stop running, thereby avoiding frequent starting and stopping of the compressor and improving the energy-saving control effect of the air-conditioning equipment.

[0015] In a possible implementation of the first aspect, before the controller controls the compressor to stop operating when each data in the operating data is less than or equal to a predetermined threshold corresponding to the data, the controller is further configured to:

[0016] The predetermined threshold corresponding to each data is determined based on the first operating data and the second operating data of the compressor, wherein the first operating data includes the operating data of the compressor during the current operation of the air-conditioning device, and the second operating data includes the operating data of the compressor during the historical operation of the air-conditioning device.

[0017] In the above technical solution, the predetermined threshold values ​​corresponding to each operating data are dynamically calculated based on the real-time operating data of the compressor during the current operation of the air-conditioning equipment and the operating data of the historical operation process, so as to realize the flexible adjustment of each predetermined threshold value in combination with the actual operating conditions of the air-conditioning equipment. Compared with the use of fixed threshold values, it can accurately avoid controlling the compressor shutdown too early or too late, resulting in energy waste or reduced user comfort, and improve the control effect of the air-conditioning equipment.

[0018] In a possible implementation of the first aspect, when the controller determines the predetermined threshold corresponding to each data based on the first operating data and the second operating data of the compressor, the controller is configured to:

[0019] Calculating an average value of each data in the operating data based on the first operating data and the second operating data;

[0020] Determining an offset value for each data item based on a temperature deviation and a standard deviation of each data item, wherein the temperature deviation is used to reflect a deviation between a historical indoor average temperature and a corresponding first temperature threshold;

[0021] The predetermined threshold value of each data is determined according to the average value and the offset value.

[0022] In the above technical solution, since the temperature deviation can reflect the residual between the temperature of the ambient space in which the air-conditioning equipment is located and the expected temperature threshold, and the standard deviation of each data in the operating data can accurately reflect the degree of discreteness of each data, the offset value of each data is calculated based on the temperature deviation and the standard deviation of the data, and then the predetermined threshold of each data is calculated based on the average value of the data and the offset value ratio. The predetermined threshold can be accurately adjusted in combination with the actual distribution status, overall changes and actual temperature deviation of the data. Compared with the fixed threshold, the adaptability and accuracy of the predetermined threshold can be improved, thereby improving the accuracy and reliability of the compressor shutdown control.

[0023] In a possible implementation of the first aspect, the operating data includes first start / stop data and second start / stop data, and when the controller acquires the operating data of the compressor, the controller is configured to:

[0024] acquiring the first start / stop data based on the switch control circuit of the compressor;

[0025] The second start-stop data is acquired based on the operating current of the compressor and a set current threshold.

[0026] In the above technical solution, the first start-stop data is obtained through the start-stop control circuit that intuitively reflects the start-stop control status of the compressor. At the same time, the second start-stop data is obtained through the working current that accurately reflects the actual working condition of the compressor and the set current threshold, taking into account both the efficiency and accuracy of obtaining the start-stop data.

[0027] In a possible implementation of the first aspect, when the controller inputs the operating data into a temperature prediction model to obtain an average indoor temperature output by the temperature prediction model, the controller is configured to:

[0028] When the difference between the first start-stop data and the second start-stop data is less than or equal to a set difference threshold, the first start-stop data and / or the second start-stop data are input into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model.

[0029] In the above technical solution, due to differences in measurement accuracy or measurement methods, there may be differences between the first start-stop data and the second start-stop data obtained in different ways in the operating data. Therefore, whether the difference between the first start-stop data and the second start-stop data is reasonable is judged based on whether the difference between them is less than or equal to the set difference threshold. It can accurately judge whether there are abnormalities in the first start-stop data and the second start-stop data, avoid directly predicting the indoor average temperature based on the first start-stop data and the second start-stop data that may have abnormalities, and improve the accuracy and reliability of subsequent predictions of the indoor average temperature.

[0030] In a possible implementation of the first aspect, when the controller inputs the operating data into a temperature prediction model to obtain an average indoor temperature output by the temperature prediction model, the controller is configured to:

[0031] When a difference between the first start-stop data and the second start-stop data is greater than the difference threshold, determining abnormal start-stop data based on the first start-stop data and the second start-stop data, where the abnormal start-stop data is start-stop data having an abnormal jump between the first start-stop data and the second start-stop data;

[0032] Correcting the abnormal start-stop data according to a set correction method to obtain corrected start-stop data;

[0033] The corrected start-stop data and the non-abnormal start-stop data are input into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model.

[0034] In the above technical solution, if the difference between the first start-stop data and the second start-stop data obtained by different methods exceeds a reasonable range, the first start-stop data and the second start-stop data can be detected for abnormality, the abnormal start-stop data can be determined, and the abnormal start-stop data can be corrected using a set correction method. The corrected start-stop data and the non-abnormal start-stop data are then input into the temperature prediction model to predict the average indoor temperature, thereby improving the reliability of the input data of the temperature prediction model and avoiding prediction errors caused by data abnormalities.

[0035] In a possible implementation of the first aspect, when the controller controls the compressor to stop operating, the controller is configured to:

[0036] When the energy consumption benefit is greater than or equal to the set benefit threshold, the compressor is controlled to stop running. The energy consumption benefit is used to reflect the benefit that can be generated by the energy saved when the compressor is currently controlled to stop running.

[0037] In the above technical solution, whether the compressor can be stopped in advance is judged by conditions in different dimensions such as the average indoor temperature, return air temperature and energy efficiency. By considering factors such as the overall indoor temperature and energy efficiency, the rationality and reliability of the compressor shutdown control are improved, while ensuring that energy-saving control of air-conditioning equipment is achieved on the basis of meeting user needs.

[0038] In a possible implementation of the first aspect, before the controller inputs the operating data into a temperature prediction model to obtain the indoor average temperature output by the temperature prediction model, the controller is further configured to:

[0039] Acquiring return air temperature data, the return air temperature data including a plurality of return air temperatures collected at different times during the operation of the air conditioning equipment;

[0040] Preprocessing the return air temperature data to obtain processed return air temperature data, wherein the preprocessing includes filtering and / or interpolation;

[0041] Correspondingly, when the controller inputs the operating data into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model, it is configured to:

[0042] The processed return air temperature data and the operating data are input into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model. The temperature prediction model is used to perform feature extraction processing on the total number of starts, the total number of shutdowns, the total operating time, the total shutdown time and the processed return air temperature data, and perform weighted calculation based on the extracted feature vectors and the weights corresponding to the feature vectors. The weighted feature vectors are processed based on the set activation function to obtain the indoor average temperature.

[0043] In the above technical solution, multiple data such as the total number of starts, start-stop data, and operating time of the air-conditioning equipment are input into the temperature prediction model to predict the indoor average temperature, fully considering the multiple factors affecting the overall temperature of the environmental space where the air-conditioning equipment is located and the degree of influence of different factors on the temperature, thereby more comprehensively considering the reasons for changes in the indoor average temperature and improving the reliability and accuracy of the indoor average temperature obtained by the temperature prediction model.

[0044] In a possible implementation of the first aspect, after the controller controls the compressor to stop running, the controller is further configured to:

[0045] When it is detected that the temperature change rate is greater than or equal to a set change threshold, the compressor is controlled to start, and the temperature change rate reflects the rate of temperature change in the environment space where the air-conditioning equipment is located.

[0046] In the above technical solution, since the temperature change rate can better reflect the dynamic changes in the temperature in the environmental space where the air-conditioning equipment is located, whether to control the compressor to start is determined based on whether the temperature change rate is greater than or equal to the change threshold. Compared with methods based on fixed temperature thresholds, the compressor can be controlled more accurately, thereby more accurately maintaining the stability of the indoor temperature and improving the user's comfort. Moreover, by determining whether to start the compressor through the temperature change rate and the change threshold, it can adapt to the differences in indoor temperature changes caused by different environmental conditions, thereby improving the flexibility and reliability of the air-conditioning equipment.

[0047] In a second aspect, some embodiments of the present application further provide a method for controlling an air conditioning device, the method comprising:

[0048] Acquiring operating data of the compressor through a controller, the operating data including a total number of starts, a total number of stops, a total operating time, and a total stopping time of the compressor;

[0049] Inputting the operating data into a temperature prediction model to obtain an indoor average temperature output by the temperature prediction model, wherein the temperature prediction model is used to perform feature extraction processing on the total number of starts, the total number of shutdowns, the total operating time, and the total shutdown time in the operating data, and perform weighted calculation based on each extracted feature vector and the weight corresponding to the feature vector, and process the weighted feature vector based on a set activation function to obtain the indoor average temperature;

[0050] When the air conditioner is in heating mode, the indoor average temperature is greater than or equal to a first temperature threshold, and the return air temperature is greater than or equal to a second temperature threshold, controlling the compressor to stop running, the return air temperature is used to reflect the temperature at the return air point of the air conditioner, and the first temperature threshold and the second temperature threshold are determined according to the expected temperature of the environment space where the air conditioner is located;

[0051] When the air-conditioning device is in cooling mode, the indoor average temperature is less than or equal to the first temperature threshold, and the return air temperature is less than or equal to the second temperature threshold, the compressor is controlled to stop running.

[0052] In a third aspect, an embodiment of the present application provides a control device comprising a module for executing the air-conditioning equipment control method in the second aspect.

[0053] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the air-conditioning equipment control method described in the second aspect are implemented.

[0054] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on an air-conditioning device, the air-conditioning device executes the air-conditioning device control method described in the second aspect above.

[0055] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 A schematic diagram of an operation scenario between an air-conditioning device and a control device provided in some embodiments of the present application;

[0058] Figure 2 A schematic diagram of the hardware configuration of a control device provided in some embodiments of the present application;

[0059] Figure 3 A schematic structural diagram of an air-conditioning device provided in some embodiments of the present application;

[0060] Figure 4 A timing interaction diagram of an air conditioning equipment control method provided in some embodiments of the present application;

[0061] Figure 5 A flowchart of a method for controlling an air-conditioning device provided in some embodiments of the present application;

[0062] Figure 6 A flowchart of a method for controlling an air-conditioning device provided in some embodiments of the present application;

[0063] Figure 7 A flowchart of a method for controlling an air-conditioning device provided in some embodiments of the present application;

[0064] Figure 8 A timing interaction diagram of an air conditioning equipment control method provided in some embodiments of the present application;

[0065] Figure 9 A timing interaction diagram of an air conditioning equipment control method provided in some embodiments of the present application;

[0066] Figure 10 A flowchart of a method for controlling an air-conditioning device provided in some embodiments of the present application;

[0067] Figure 11 A flowchart of a method for controlling an air-conditioning device provided in some embodiments of the present application;

[0068] Figure 12 A flowchart of a method for controlling an air-conditioning device provided in some embodiments of the present application;

[0069] Figure 13A flowchart of a method for controlling an air-conditioning device provided in some embodiments of the present application;

[0070] Figure 14 A schematic structural diagram of an air conditioning equipment control device provided in some embodiments of the present application. DETAILED DESCRIPTION

[0071] The following embodiments are described in detail, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numbers in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following embodiments are not intended to represent all possible implementations consistent with the present application. They are merely examples of systems and methods consistent with certain aspects of the present application, as detailed in the claims.

[0072] It should be noted that the brief descriptions of terms in this application are only for the purpose of facilitating the understanding of the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their ordinary and usual meanings.

[0073] In the specification and claims of this application and the accompanying drawings, the terms "first," "second," "third," etc. are used to distinguish similar or similar objects or entities, and are not necessarily intended to limit a particular order or sequence, unless otherwise noted. It should be understood that the terms used in this manner are interchangeable under appropriate circumstances.

[0074] The terms "comprise," "include," and "have," and any variations thereof, are intended to cover but not exclude inclusion; for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0075] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functionality associated with that element.

[0076] Figure 1 This is a schematic diagram of the operation scenario between the air conditioning equipment and the control device provided in some embodiments of the present application. Figure 1 As shown in FIG, a user can operate the air conditioning device 200 through touch operation, the mobile terminal 300 and the control device 100. For example, the control device 100 can be a remote controller, a stylus pen or a handle.

[0077] In some embodiments, the control device 100 may be a remote control or a smart home controller. For example, if the control device is a remote control, the remote control and the air conditioner may communicate using, but not limited to, infrared protocol communication, Bluetooth protocol communication, or other short-range communication methods, to control the air conditioner 200 wirelessly or wired. The user may control the air conditioner 200 by inputting user commands through buttons on the remote control, voice input, or control panel input.

[0078] In some embodiments, a mobile terminal 300 (such as a tablet computer, a computer, or a mobile phone) can also be used to control the air conditioning device 200. For example, the air conditioning device 200 can be controlled using an application running on the mobile terminal 300.

[0079] In some embodiments, the air conditioning device may not use the above-mentioned mobile terminal 300 or control device 100 to receive instructions, but may receive user control through buttons set on the air conditioning device.

[0080] Figure 2 Some embodiments of this application provide Figure 1 The hardware configuration diagram of the control device in the figure is as follows. Figure 2 As shown, the control device 100 may include: a controller 110, a communication interface 130, a user input / output interface, a memory, and a power supply.

[0081] The control device 100 is configured to control the air conditioning device 200, and can receive the user's input operation instructions, and convert the operation instructions into instructions that the air conditioning device 200 can recognize and respond to, playing the role of an interactive intermediary between the user and the air conditioning device 200.

[0082] In some embodiments, the control device 100 may be a smart device. For example, the control device 100 may be installed with various applications for controlling the air conditioning device 200 according to user needs.

[0083] In some embodiments, as Figure 1 As shown, the mobile terminal 300 or other intelligent electronic devices can play a similar function as the control device 100 after installing the application for controlling the air-conditioning device 200 .

[0084] The controller 110 includes a processor 112, RAM 113, ROM 114, a communication interface 130, and a communication bus. The controller 110 is used to control the operation and operation of the control device 100, as well as the communication and cooperation between internal components and external and internal data processing functions.

[0085] The communication interface 130 communicates control signals and data signals with the air conditioner 200 under the control of the controller 110. The communication interface 130 may include at least one of a WiFi chip 131, a Bluetooth module 132, an NFC module 133, or other near field communication modules.

[0086] The user input / output interface 140 includes at least one of a microphone 141 , a touch panel 142 , a sensor 143 , a button 144 and other input interfaces.

[0087] In some embodiments, the control device 100 includes at least one of a communication interface 130 and an input / output interface 140. The control device 100 is configured with the communication interface 130, such as a WiFi, Bluetooth, or NFC module, to encode user input commands via the WiFi protocol, Bluetooth protocol, or NFC protocol and transmit them to the air conditioning device 200.

[0088] The memory 190 is used to store various operating programs, data and applications for driving and controlling the control device 100 under the control of the controller. The memory 190 can store various control signal instructions input by the user.

[0089] The power supply 180 is used to provide operating power support for each component of the control device 100 under the control of the controller.

[0090] Figure 3 A structural schematic diagram of the air-conditioning equipment provided by some embodiments of the present application is shown. For the sake of convenience of explanation, only the parts related to the embodiments of the present application are shown.

[0091] Reference Figure 3 The air conditioning device includes a housing 310, a compressor 320 and a controller 330.

[0092] The compressor 320 is disposed in the housing 310 .

[0093] The controller 330 is disposed in the housing 310 and is configured to:

[0094] Acquiring operating data of the compressor, the operating data including a total number of starts, a total number of stops, a total operating time, and a total stopping time of the compressor;

[0095] Inputting the operating data into a temperature prediction model to obtain an indoor average temperature output by the temperature prediction model, wherein the temperature prediction model is used to perform feature extraction processing on the total number of starts, the total number of shutdowns, the total operating time, and the total shutdown time in the operating data, and perform weighted calculation based on each extracted feature vector and the weight corresponding to the feature vector, and process the weighted feature vector based on a set activation function to obtain the indoor average temperature;

[0096] When the air conditioner is in heating mode, the indoor average temperature is greater than or equal to a first temperature threshold, and the return air temperature is greater than or equal to a second temperature threshold, controlling the compressor to stop running, the return air temperature being used to reflect the temperature at the return air point of the air conditioner, and the first temperature threshold and the second temperature threshold being determined based on the expected temperature of the ambient space where the air conditioner is located;

[0097] When the air-conditioning device is in cooling mode, the indoor average temperature is less than or equal to the first temperature threshold, and the return air temperature is less than or equal to the second temperature threshold, the compressor is controlled to stop running.

[0098] Figure 4 The following diagram shows a timing interaction diagram of the air conditioning equipment control method provided by some embodiments of the present application. Figure 4 , the controller is configured to perform the following steps:

[0099] S401. Obtaining operating data of the compressor, the operating data including the total number of starts, the total number of stops, the total operating time, and the total stopping time of the compressor.

[0100] It should be understood that the operating state of the compressor can generally include a start-up state and a stop state. After the controller controls the compressor to start, the compressor generally switches from the stop state to the start-up state; after the controller controls the compressor to stop, the compressor generally switches from the start-up state to the stop state.

[0101] In an embodiment of the present application, the operating data may include the total number of starts, the total number of stops, the total operating time, and the total stop time of the compressor. In other embodiments, the operating data may include, but is not limited to, the compressor start time, stop time, the duration of operation after startup (i.e., the duration of the startup running state), and the duration of shutdown after shutdown (i.e., the duration of the shutdown state).

[0102] Among them, the total operating time of the compressor usually refers to the total time the compressor is in the operating state, that is, the sum of the running time of the compressor after each startup; the shutdown time of the compressor usually refers to the total time the compressor is in the shutdown state, that is, the sum of the shutdown time after each shutdown of the compressor.

[0103] Optionally, the operating data of the compressor can be determined based on one or more of the compressor's current data, pressure data, temperature data, vibration data, and status data. The embodiment of the present application does not impose any specific restrictions on the method of obtaining the compressor operating data.

[0104] S402. Input the above-mentioned operating data into the temperature prediction model to obtain the indoor average temperature output by the above-mentioned temperature prediction model. The above-mentioned temperature prediction model is used to perform feature extraction processing on the above-mentioned total number of starts, the above-mentioned total number of shutdowns, the above-mentioned total operating time and the above-mentioned total shutdown time in the above-mentioned operating data, and perform weighted calculation based on each extracted feature vector and the weight corresponding to the above-mentioned feature vector, and process the weighted feature vector based on the set activation function to obtain the above-mentioned indoor average temperature.

[0105] It should be understood that the feature vector is the vector form of data obtained by the temperature prediction model when performing feature extraction on the input data. When the temperature prediction model performs feature extraction on the input data, it can extract features in the data that can reflect the characteristics of the data, and at the same time convert the original data into a more concise and easy-to-process vector form to obtain the feature vector corresponding to the data.

[0106] It should be understood that the weight corresponding to each eigenvector is also the weight corresponding to each data. This weight is typically learned during the temperature prediction model training process and can reflect the contribution of the data to the indoor average temperature prediction task (that is, the importance of the data to the indoor average temperature prediction task). In other embodiments, the weight corresponding to each eigenvector can also be obtained by adjusting the learned weight based on user input or other intelligent algorithms by the controller.

[0107] In some embodiments, the average indoor temperature can be expressed as follows:

[0108]

[0109] in, represents the average indoor temperature predicted by the temperature prediction model, w i Represents the feature vector of the i-th data in the data input to the temperature prediction model, x i represents the weight corresponding to the eigenvector of the i-th data, b represents the set bias, and σ represents the set activation function.

[0110] In some embodiments, the data input into the temperature prediction model may include the following seven data: total number of starts, total number of shutdowns, total operating time, total shutdown time, return air temperature data, start-stop data, and operating time of the air conditioning equipment.

[0111] Among them, the start-stop data (such as the first start-stop data and / or the second start-stop data) can reflect the time of each start-up of the compressor, the time of each shutdown, the duration of operation after each start-up, and the duration of shutdown after each shutdown; the operating time of the air-conditioning equipment refers to the duration of the current operation of the air-conditioning equipment; the return air temperature data can include the return air temperature (reflecting the temperature at the return air of the air-conditioning equipment) detected at a set detection frequency (such as once per minute) during the current operation of the air-conditioning equipment, and can also include the average return air temperature. Optionally, the average return air temperature can include the average return air temperature during the current operation of the air-conditioning equipment, the average return air temperature during each startup and operation state of the compressor, and the average return air temperature during each shutdown state of the compressor.

[0112] Optionally, the temperature prediction model can be constructed based on a network structure such as a recurrent neural network (RNN), a convolutional neural network (CNN), a long short-term memory network (LSTM) or a transformer.

[0113] Optionally, when training a temperature prediction model, the input data of the training sample can be determined based on the operating data of the compressor during the historical operation of the air-conditioning equipment (i.e., the historical operating data of the compressor), and the output label of the training sample can be determined based on the actual average temperature corresponding to the historical operating data to construct a training sample; after the training sample is constructed, the input data of the training sample is input into the constructed temperature prediction model, and the temperature prediction model extracts features from the input data, and then predicts the average temperature of the environment space where the air-conditioning equipment is located based on the extracted features to obtain the predicted average temperature output by the temperature prediction model; the model parameters of the temperature prediction model are adjusted based on the difference between the predicted average temperature and the output label, thereby obtaining a trained temperature prediction model. It should be understood that the actual average temperature corresponding to the historical operating data can be calculated based on the temperature measured by multiple temperature sensors set in the room, or it can be obtained based on user input.

[0114] In some embodiments, when constructing training samples based on the operating data of the compressor during the historical operation of the air-conditioning equipment, the division time can be calculated in combination with information such as the operating characteristics of the air-conditioning equipment and the periodicity of temperature changes. Based on the division time, the historical operating data of the compressor is divided into multiple operating sub-data corresponding to different time periods, and then training samples are constructed based on each operating sub-data. In the above processing, the operating process of the air-conditioning equipment is divided into multiple representative stages through time period division, and then training samples are constructed for each stage. This can provide more structured samples for the training of the temperature prediction model. At the same time, the temperature prediction model can accurately learn the relationship between the total number of compressor starts, the total number of shutdowns, the total shutdown time, the total operating time, etc. in different operating stages of the air-conditioning equipment and the changes in the average indoor temperature, thereby improving the accuracy of the temperature prediction model.

[0115] Optionally, during the training of the temperature prediction model, the difference between the predicted average temperature and the output label is calculated based on a set loss function to obtain a loss value. An improved stochastic gradient descent algorithm can be used to optimize the model parameters of the temperature prediction model based on the loss value to obtain a trained temperature prediction model. This process allows the model parameters to be dynamically adjusted during the training process, making the resulting temperature prediction model more adaptable to different operating environments and working conditions, thereby improving the accuracy and reliability of the temperature prediction model.

[0116] As an example, the adjusted model parameters can be expressed as follows:

[0117]

[0118] Among them, w i Represents the adjusted model parameters i, w i,prev represents the model parameter i before adjustment; η represents the learning rate, which can be determined based on the size of the training data and the complexity of the temperature prediction model to better control the step size of model parameter adjustment; L represents the set loss function; and λ represents the set momentum factor, which is usually used to accelerate the convergence of the temperature prediction model. λ can be set or input by the user or calculated by the controller.

[0119] In the embodiment of the present application, it is considered that the number of starts and stops of the compressor, as well as the length of operation and the length of shutdown will directly affect the overall temperature of the room, and the overall temperature of the room will affect the temperature of the return air outlet of the air-conditioning equipment, thereby inversely affecting the start and stop of the compressor, that is, there is a complex correlation between the operating data of the compressor and the overall temperature of the room, and the temperature prediction model can accurately learn the complex linear or nonlinear relationship therein during the training process. Therefore, when the controller uses the trained temperature prediction model to perform weighted calculation based on the extracted features and their corresponding weights, it can accurately quantify the contribution of each feature vector to the prediction of the average indoor temperature, while fully considering the impact of different features on the average indoor temperature, thereby improving the accuracy of the feature vector obtained by weighted calculation. Then, the weighted feature vector is processed based on the activation function, and nonlinear factors can be introduced through the activation function, so that the temperature prediction model can accurately capture the complex relationship in the data and improve the accuracy of the predicted average indoor temperature.

[0120] S403. When the air-conditioning device is in heating mode, the average indoor temperature is greater than or equal to the first temperature threshold, and the return air temperature is greater than or equal to the second temperature threshold, the compressor is controlled to stop running. The return air temperature is used to reflect the temperature at the return air point of the air-conditioning device. The first temperature threshold and the second temperature threshold are determined according to the temperature expected to be reached in the environmental space where the air-conditioning device is located.

[0121] S404. When the air-conditioning device is in cooling mode, the average indoor temperature is less than or equal to the first temperature threshold, and the return air temperature is less than or equal to the second temperature threshold, control the compressor to stop running.

[0122] It should be understood that since the conditions for controlling the compressor to stop running are usually different when the air-conditioning equipment is in different functional modes (i.e., cooling mode or heating mode), in order to accurately control the compressor to stop running, after the controller obtains the indoor average temperature output by the temperature prediction model, it can determine how to determine whether to control the compressor to stop running in combination with the current functional model mode of the air-conditioning equipment, that is, select to execute step S403 or step S404 based on the functional mode of the air-conditioning equipment.

[0123] It should be understood that the temperature expected to be reached in the environmental space where the air-conditioning equipment is located usually refers to the target temperature of the air-conditioning equipment. The target temperature can be obtained based on user input or settings, or it can be calculated based on historical target temperatures or climate data through intelligent algorithms such as large models. The embodiments of this application do not impose specific restrictions on this.

[0124] It should be understood that the first temperature threshold and the second temperature threshold may be the same temperature threshold or different temperature thresholds.

[0125] See also Figure 4 When the controller stops the compressor, it can send a shutdown control signal to the compressor. After receiving the shutdown control signal, the compressor can stop its own operation in a corresponding manner according to the needs. For example, the compressor can stop by directly cutting off its power supply or gradually reducing the motor frequency until the motor stops running.

[0126] As an example, the controller can send a preset shutdown control signal (such as 1, indicating stop running) to the relay control circuit of the compressor. After receiving the shutdown control signal, the relay control circuit of the compressor can cut off the power supply of the compressor, thereby quickly controlling the compressor to stop running.

[0127] In some embodiments, since hot air with lower density usually rises naturally during the heating process, the uneven heat distribution causes a relatively large difference between the return air temperature and the actual average temperature in the room, while cold air with higher density usually sinks naturally during the cooling process, and the difference between the return air temperature and the actual average temperature in the room is relatively small. Therefore, in order to improve the accuracy of the return air temperature judgment, the second temperature threshold corresponding to the return air temperature can be determined in combination with the current functional mode and target temperature of the air-conditioning equipment.

[0128] In some embodiments, when the current function mode of the air conditioner is heating mode, the second temperature threshold can be calculated based on a set heating weighting coefficient (greater than 1, such as 1.1) and a target temperature; when the current function mode of the air conditioner is cooling mode, the second temperature threshold can be calculated based on a set cooling weighting coefficient (less than 1, such as 0.95) and the target temperature. The absolute value of the difference between the heating weighting coefficient and 1 is greater than the absolute value of the difference between the cooling weighting coefficient and 1.

[0129] For example, assume the air conditioner is currently in heating mode with a target temperature of 28°C. Assume that, based on user settings, the first temperature threshold is determined to be equal to the target temperature, i.e., the first temperature threshold is 28°C. Assume that the heating weighted coefficient calculated by the intelligent algorithm is 1.08, then the second temperature threshold is 30.24°C (calculated based on 28*1.08). Accordingly, when the air conditioner is in heating mode, the average indoor temperature is greater than or equal to the first temperature threshold (28°C), and the return air temperature is greater than or equal to the second temperature threshold (30.24°C), the compressor can be controlled to stop.

[0130] For another example, assume that the air conditioner is currently in cooling mode and the target temperature is 20°C; assume that, according to user settings, the first temperature threshold is determined to be 0.975 times the target temperature, that is, the first temperature threshold is 19.5°C (calculated based on 20*0.975); assume that the cooling weighted coefficient calculated by the intelligent algorithm is 0.9, then the second temperature threshold is 18°C ​​(calculated based on 20*0.9). Correspondingly, when the air conditioner is in cooling mode, the average indoor temperature is less than or equal to the first temperature threshold (19.5°C), and the return air temperature is less than or equal to the second temperature threshold (18°C), the compressor can be controlled to stop running.

[0131] In the embodiment of the present application, since the start and stop of the compressor and the corresponding duration will directly affect the change of the overall indoor temperature, and the indoor temperature in turn affects the start and stop of the compressor, that is, there is a complex correlation between the operating data of the compressor and the overall indoor temperature, and the temperature prediction model can accurately learn the complex relationship therein, therefore, when the temperature prediction model performs weighted calculation based on the feature vectors of each extracted data and their corresponding weights, it can accurately quantify the contribution of each feature vector to the prediction of the indoor average temperature, while fully considering the impact of different features on the indoor average temperature, thereby improving the accuracy of the feature vector obtained by weighted calculation. Then, the weighted feature vector is processed based on the activation function, and nonlinear factors are introduced through the activation function, so that the temperature prediction model can accurately capture the complex relationship in the data, thereby accurately predicting the average temperature of the environmental space where the air-conditioning equipment is located, and obtaining the required indoor average temperature. Furthermore, based on the functional mode of the air-conditioning equipment, a comprehensive judgment is made on whether to control the compressor to stop running according to the relationship between the average indoor temperature and the detected return air temperature and its corresponding temperature threshold. Compared with using a single return air temperature as the basis, the accuracy of the compressor shutdown control is improved, thereby improving the accuracy of temperature regulation, and there is no need to install multiple additional sensors, effectively reducing the hardware cost and the complexity of the wiring installation of the air-conditioning equipment.

[0132] Figure 5 A flow chart of a method for controlling an air-conditioning device according to some embodiments is shown. Figure 5 When the controller controls the compressor to stop running, it is configured to perform the following steps:

[0133] When each data in the above-mentioned operating data is less than or equal to the predetermined threshold value corresponding to the above-mentioned data, the above-mentioned compressor is controlled to stop operating.

[0134] It should be understood that in the embodiment of the present application, the operating data includes at least the total number of starts, the total number of stops, the total operating time, and the total stopping time of the compressor. Therefore, before the controller controls the compressor to stop running, it also performs the following judgments:

[0135] Whether the total number of compressor starts is less than or equal to the predetermined threshold value of the total number of starts (such as 3 times); whether the total number of compressor shutdowns is less than or equal to the predetermined threshold value of the total number of shutdowns (such as 4 times); whether the total running time of the compressor is less than or equal to the predetermined threshold value of the total running time (such as 120 minutes); whether the total shutdown time of the compressor is less than or equal to the predetermined threshold value of the total shutdown time (such as 100 minutes).

[0136] It should be understood that the predetermined threshold corresponding to each data can be determined by user input or setting, or can be calculated by an intelligent algorithm such as a large model based on information such as the actual application requirements of the air-conditioning equipment.

[0137] In an embodiment of the present application, when the controller determines that the relationship between the average indoor temperature and the return air temperature and their corresponding temperature thresholds meets the requirements of the functional mode, and each data in the operating data is less than or equal to the predetermined threshold corresponding to the data, the controller controls the compressor to stop running, thereby avoiding frequent starting and stopping of the compressor and improving the energy-saving control effect of the air-conditioning equipment.

[0138] Figure 6 FIG. 1 shows a flow chart of a method for controlling an air-conditioning device according to some embodiments. Figure 6 As shown, before the controller stops the compressor, it can also determine whether the compressor control interval is greater than or equal to a set interval threshold (e.g., 20 minutes). The control interval can be the time interval since the controller last controlled the compressor (e.g., started or stopped). The interval threshold can be determined by user input or setting, or calculated by an intelligent algorithm such as a large model based on information such as the actual application requirements of the air conditioning equipment.

[0139] If the control time interval is greater than or equal to the interval threshold, the compressor is controlled to stop. If the control time interval is less than the interval threshold, the compressor may be controlled to stop after the control time interval is greater than or equal to the interval threshold. In other embodiments, if the control time interval is less than the interval threshold, the compressor may not be controlled to stop, but the process may return to the step of obtaining the compressor's operating data.

[0140] Through the above settings, continuous control of the compressor in a short period of time is avoided, thereby avoiding large temperature fluctuations and compressor damage in a short period of time, thereby ensuring the reliability of the air-conditioning equipment and user comfort.

[0141] Figure 7 A flow chart of a method for controlling an air-conditioning device according to some embodiments is shown. Figure 7Before the controller controls the compressor to stop running when each of the operating data is less than or equal to a predetermined threshold value corresponding to the data, the controller is further configured to execute the following steps:

[0142] The above-mentioned predetermined threshold values ​​corresponding to each data are determined based on the first operating data and the second operating data of the compressor, the above-mentioned first operating data includes the operating data of the above-mentioned compressor during the current operation of the above-mentioned air-conditioning equipment, and the above-mentioned second operating data includes the operating data of the above-mentioned compressor during the historical operation of the above-mentioned air-conditioning equipment.

[0143] In some embodiments, the second operating data may include operating data of the compressor during the previous N times (N is greater than or equal to 1) of the air-conditioning device operation, where N may be obtained based on user input or settings, or calculated through an intelligent algorithm.

[0144] Optionally, when determining the predetermined threshold corresponding to each data based on the first operating data and the second operating data of the compressor, the required predetermined threshold can be determined according to the first operating data and the second operating data through intelligent algorithms, fuzzy logic or statistical analysis.

[0145] For example, the first operating data and the second operating data of the compressor can be input into a trained threshold analysis model. The threshold analysis model extracts features from the input first operating data and the second operating data, and obtains predetermined thresholds corresponding to each data based on the extracted features. It should be understood that the threshold analysis model can be trained based on input data including the first operating data and the second operating data and output labels including predetermined thresholds corresponding to each data, so that the threshold analysis model can accurately learn the complex correlation between the first operating data, the second operating data, and the predetermined thresholds corresponding to each data of the operating data during the training process. Furthermore, in actual applications, based on the trained threshold analysis model, dynamic calculations of each predetermined threshold can be performed quickly and accurately, thereby improving the calculation efficiency and accuracy of the predetermined thresholds.

[0146] In an embodiment of the present application, based on the operating data of the compressor during the current operation of the air-conditioning equipment and the operating data of the historical operation process, the predetermined threshold values ​​corresponding to each operating data are dynamically calculated, so as to realize flexible adjustment of each predetermined threshold value in combination with the actual operating conditions of the air-conditioning equipment. Compared with the use of fixed threshold values, it can accurately avoid controlling the compressor shutdown too early or too late, resulting in energy waste or reduced user comfort, and improve the control effect of the air-conditioning equipment.

[0147] In some embodiments, when the controller determines the predetermined threshold corresponding to each data based on the first operating data and the second operating data of the compressor, the controller is configured to perform the following steps:

[0148] Based on the first operating data and the second operating data, average values ​​of the respective data in the operating data are calculated.

[0149] The offset value of each data is determined based on the temperature deviation and the standard deviation of each data. The temperature deviation is used to reflect the deviation between the historical indoor average temperature and the corresponding first temperature threshold.

[0150] The predetermined thresholds for each data are determined respectively according to the average value and the offset value.

[0151] It should be understood that the temperature deviation can be calculated based on the difference between the indoor average temperature obtained from the previous prediction and the corresponding first temperature threshold, or it can be calculated based on the difference between each indoor average temperature obtained from the previous M predictions (M is an integer greater than 1) and the corresponding first temperature threshold (such as the average value of the difference between each indoor average temperature and the corresponding first temperature threshold). The embodiments of the present application do not impose specific restrictions on this.

[0152] In an embodiment of the present application, since the temperature deviation can reflect the residual between the temperature of the ambient space in which the air-conditioning equipment is located and the expected temperature threshold, and the standard deviation of each data in the operating data can accurately reflect the degree of discreteness of each data, the offset value of each data is calculated based on the temperature deviation and the standard deviation of the data, and then the predetermined threshold of each data is calculated based on the average value of the data and the offset value ratio. The predetermined threshold can be accurately adjusted in combination with the actual distribution status, overall changes and actual temperature deviation of the data. Compared with the fixed threshold, the adaptability and accuracy of the predetermined threshold can be improved, thereby improving the accuracy and reliability of the compressor shutdown control.

[0153] In some embodiments, each predetermined threshold value can be expressed as follows:

[0154]

[0155] Among them, N on The predetermined threshold value representing the total number of compressor starts, N off The predetermined threshold value representing the total number of compressor shutdowns, ΔT on The predetermined threshold value representing the total operating time of the compressor, ΔT off A predetermined threshold representing the total length of time the compressor has been off.

[0156] Indicates the average number of compressor starts, N off Indicates the average value of the total number of compressor shutdowns, ΔT on Indicates the average value of the total operating time of the compressor, ΔT offRepresents the average value of the total compressor downtime. It should be understood that the above-mentioned average values ​​are generally calculated based on the first operating data and the second operating data. In other embodiments, the average value of each data can also be calculated based on the second operating data.

[0157] γ represents the set adjustment coefficient, while γ1, γ2, γ3, and γ4 correspond to the adjustment coefficients for the total number of compressor starts, the total number of compressor stops, the total compressor operating time, and the total compressor downtime, respectively. Optionally, the adjustment coefficient corresponding to each data point can be dynamically adjusted based on the current operating status of the air conditioner, thereby dynamically controlling the change range of each predetermined threshold value through adjustment of the adjustment coefficient.

[0158] σ represents the standard deviation, and This corresponds to the standard deviation of the total number of compressor starts, the total number of compressor shutdowns, the total compressor operating time, and the total compressor shutdown time.

[0159] Indicates the average indoor temperature obtained in the previous forecast, T s In other embodiments, T s It may also be the target temperature corresponding to the average indoor temperature (ie, the temperature expected to be reached in the environment where the air-conditioning equipment is located).

[0160] Figure 8 A timing interaction diagram of an air conditioning equipment control method provided by some embodiments is shown. Figure 8 The operating data includes first start-stop data and second start-stop data. When the controller obtains the operating data of the compressor, it is configured to perform the following steps:

[0161] S1001. Acquire the first start / stop data based on the switch control circuit of the compressor.

[0162] S1002. Acquire the second start / stop data based on the operating current of the compressor and a set current threshold.

[0163] A compressor's on / off control circuit typically refers to the circuit used to control the power supply to the compressor motor. When the controller starts the compressor, it typically sends a start control signal to the compressor. Upon detecting the start control signal, the compressor's on / off control circuit switches on the motor power, thereby controlling the compressor to begin operation. When the controller stops the compressor, it typically sends a stop control signal to the compressor. Upon detecting the stop control signal, the compressor's on / off control circuit switches off the motor power, thereby controlling the compressor to stop operation.

[0164] The operating current of a compressor generally refers to the current flowing through the compressor motor. Since current usually flows through the compressor motor when the compressor motor power is turned on, by monitoring the compressor operating current, the operating status of the compressor can be more intuitively judged.

[0165] It should be understood that the first start-stop data obtained by the controller based on the switch control circuit and the second start-stop data obtained based on the working current can both include the total number of starts, total number of stops, total operating time and total stop time of the compressor.

[0166] Alternatively, the compressor's operating current can be obtained through sensors, vector control algorithms, or calculations based on motor parameters. For example, the compressor's operating current can be directly obtained by monitoring the compressor motor's current using a highly accurate current sensor, eliminating the need for various calculations and reducing the computational complexity and power consumption of the air conditioning equipment.

[0167] Among them, in order to improve the accuracy of the data obtained by the controller, when obtaining the second start-stop data based on the working current of the compressor, the operating status of the compressor can be comprehensively judged in combination with the set current threshold to avoid interference from currents such as fault current or abnormal current.

[0168] For example, assuming the current time is T10, the controller obtains the operating current of the compressor at 10 times T0-T10, and the current values ​​are (0A, 3.3A, 3.5A, 3.4A, 0A, 0A, 0A, 0A, 3.4A, 3.4A, 3.4A); assuming the set current threshold is 3A, the judgment logic is: when the operating current is greater than or equal to the current threshold, the compressor is judged to be in the starting state; when the operating current is less than the current threshold, the compressor is judged to be in the stopping state. Based on the above operating current and current threshold, the following judgment results can be obtained: the compressor is in the stopping state at T0, in the starting state from T1 to T3, in the stopping state from T4 to T7, and in the starting state from T8 to T10. Furthermore, based on the above judgment results, the following second start-stop data can be obtained: shutdown at T0; start at T1 and continue running for 3 moments; shutdown at T4 and continue shutdown for 4 moments; start at T8 and continue running until now.

[0169] In some embodiments, the compressor's operating status is determined based on the compressor's operating current and a set current threshold. To obtain the second start-stop data, the compressor can be determined to be started if the operating current is greater than or equal to the set current threshold and the duration of the start-up duration is greater than or equal to a set start-up duration threshold (e.g., 3 seconds). Otherwise, the compressor is determined to be stopped. This process fully considers the different characteristics of the compressor's startup phase and avoids misjudgments due to current fluctuations.

[0170] In an embodiment of the present application, the first start-stop data is obtained through a start-stop control circuit that intuitively reflects the start-stop control status of the compressor. At the same time, the second start-stop data is obtained through the working current that accurately reflects the actual working condition of the compressor and the set current threshold, which can better balance the efficiency and accuracy of obtaining the start-stop data.

[0171] Figure 9 A timing interaction diagram of an air conditioning equipment control method provided by some embodiments is shown. Figure 9 When the controller inputs the operating data into the temperature prediction model and obtains the indoor average temperature output by the temperature prediction model, the controller is configured to perform the following steps:

[0172] When the difference between the first start-stop data and the second start-stop data is less than or equal to the set difference threshold, the first start-stop data and / or the second start-stop data are input into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model.

[0173] Optionally, when determining the difference between the first start-stop data and the second start-stop data, the difference between the first start-stop data and the second start-stop data can be determined through analysis methods such as statistical distribution, error analysis or correlation analysis; correspondingly, the value of the difference threshold can be adjusted accordingly according to the analysis method adopted.

[0174] In some embodiments, since the first start-stop data and the second start-stop data obtained by different methods can reflect the start time and stop time of the same compressor, when determining the difference between the first start-stop data and the second start-stop data, the start time of each compressor in the first start-stop data can be compared with the start time of each compressor in the second start-stop data, and the start time difference value (such as the average value of the difference of each start time) is calculated based on the difference between each start time; the stop time of each compressor in the first start-stop data is compared with the stop time of each compressor in the second start-stop data, and the stop time difference value (such as the average value of the difference of each start time) is calculated based on the difference between each stop time; and it is determined whether the start time difference value and the stop time difference value are both less than or equal to a set difference threshold (such as 3 seconds), or whether any value of the start time difference value and the stop time difference value is less than or equal to the set difference threshold.

[0175] Due to differences in measurement accuracy or measurement methods, there may be differences between the first start-stop data and the second start-stop data obtained in different ways in the operating data. Therefore, to ensure the accuracy of the operating data, it is possible to judge whether the difference between the first start-stop data and the second start-stop data is less than or equal to the set difference threshold to determine whether the difference is reasonable.

[0176] If it is determined that the difference between the first start-stop data and the second start-stop data is less than or equal to the difference threshold (such as the difference is less than or equal to the difference threshold), it can be considered that the difference is a reasonable deviation caused by differences in measurement accuracy, etc., and the first start-stop data and the second start-stop data in the operating data are relatively accurate data. The first start-stop data and the second start-stop data can be directly input into the temperature prediction model to predict the average indoor temperature.

[0177] Alternatively, in order to reduce the calculation amount of the prediction model as much as possible, either the first start-stop data or the second start-stop data can be input into the temperature prediction model, and the first start-stop data and the second start-stop data can both more accurately reflect the start-stop status of the compressor and the duration of each operating state. Therefore, through the above processing, the computational efficiency and accuracy of the prediction model can be taken into account, thereby improving the actual application effect.

[0178] See also Figure 9 If it is determined that the difference between the first start-stop data and the second start-stop data is greater than the difference threshold, the process can return to the step of obtaining the operating data of the compressor (i.e., the first start data and the second start-stop data) to determine whether the difference between the first start-stop data and the second start-stop data is less than or equal to the difference threshold, until the difference between the obtained first start-stop data and the second start-stop data is less than or equal to the difference threshold.

[0179] It should be understood that Figure 9 The steps of returning to obtain the operating data of the compressor (i.e., the first start data and the second start-stop data) and determining whether the difference between the first start-stop data and the second start-stop data is less than or equal to the difference threshold are used as an example for explanation. In other embodiments, the controller may also perform abnormality detection on the first start-stop data and the second start-stop data, or obtain abnormal start-stop data through other means, etc., which may be specifically set according to actual application requirements.

[0180] In an embodiment of the present application, due to differences in measurement accuracy or measurement methods, there may be differences between the first start-stop data and the second start-stop data obtained in different ways in the operating data. Therefore, whether the difference between the first start-stop data and the second start-stop data is reasonable is judged based on whether the difference between them is less than or equal to the set difference threshold, so as to better judge whether there are abnormalities in the first start-stop data and / or the second start-stop data, avoid directly predicting the indoor average temperature based on the first start-stop data and the second start-stop data that may have abnormalities, and effectively ensure the accuracy and reliability of the subsequent prediction of the indoor average temperature.

[0181] Figure 10 Schematic diagram showing a flow chart of an air conditioning equipment control method provided by other embodiments. Figure 10When the controller inputs the operating data into the temperature prediction model and obtains the indoor average temperature output by the temperature prediction model, the controller is configured to perform the following steps:

[0182] When the difference between the first start-stop data and the second start-stop data is greater than the difference threshold, abnormal start-stop data is determined based on the first start-stop data and the second start-stop data, and the abnormal start-stop data is start-stop data with abnormal jumps between the first start-stop data and the second start-stop data.

[0183] The abnormal start-stop data is corrected according to the set correction method to obtain the corrected start-stop data.

[0184] The corrected start-stop data and the non-abnormal start-stop data are input into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model.

[0185] It should be understood that when the first start-stop data has an abnormal jump, the abnormal start-stop data may include the first start-stop data; when the second start-stop data has an abnormal jump, the abnormal start-stop data may include the second start-stop data.

[0186] Abnormal jumps in start-stop data typically refer to abnormal jumps in the compressor's operating state (i.e., startup or shutdown). For example, a compressor's operating state typically alternates between startup and shutdown. If, in a continuous recording of start-stop data, there are two consecutive starts without a shutdown, or two consecutive shutdowns without a start, it can be assumed that the abnormal jumps in the acquired start-stop data are due to sensor failure or interference.

[0187] It should be understood that the correction method used can be determined according to actual application requirements. For example, if it is detected that the user has set a correction method for the start-stop data, the user-set correction method can be used as the set correction method to correct the abnormal start-stop data.

[0188] In some embodiments, the set correction method may be: based on one or more data points adjacent to the abnormal data point in the abnormal start-stop data, the abnormal data point is removed or corrected.

[0189] For example, assuming that the abnormal start-stop data includes the first start-stop data, wherein the operating status of the compressor at time t in the first start-stop data has an abnormal jump, and the operating status at time t needs to be corrected; then when correcting the operating status at time t, the operating status at time t can be corrected according to the operating status at the previous moment and the next moment (i.e., time t-1 and time t+1) and the set correction logic to obtain the corrected operating status at time t.

[0190] In other embodiments, the set correction method may be: when the abnormal start-stop data includes one of the first start-stop data and the second start-stop data, the abnormal start-stop data is corrected based on the other start-stop data (for example, when the abnormal start-stop data includes the first start-stop data, the abnormal first start-stop data is corrected based on the second start-stop data); when the abnormal start-stop data includes the first start-stop data and the second start-stop data, the third start-stop data that can reflect the total number of starts, total number of stops, total operating time and total stop time of the compressor is obtained through a set acquisition method (such as based on the change data of the return air temperature), and the abnormal start-stop data is corrected based on the third start-stop data.

[0191] It should be understood that non-abnormal start-stop data generally refers to the start-stop data obtained without abnormal jumps (excluding corrected start-stop data). For example, if the first start-stop data has abnormal jumps and the second start-stop data does not, the non-abnormal start-stop data includes the second start-stop data; if both the first start-stop data and the second start-stop data have abnormal jumps, the non-abnormal start-stop data may include the third start-stop data used to correct them.

[0192] In an embodiment of the present application, if the difference between the first start-stop data and the second start-stop data obtained by different methods exceeds a reasonable range, the first start-stop data and the second start-stop data can be detected for abnormality, the abnormal start-stop data can be determined, and the abnormal start-stop data can be corrected using a set correction method. The corrected start-stop data and the non-abnormal start-stop data are then input into the temperature prediction model to predict the average indoor temperature, thereby ensuring the reliability of the input data of the temperature prediction model and avoiding prediction errors caused by data abnormalities.

[0193] Figure 11 A flow chart of a method for controlling an air-conditioning device according to some embodiments is shown. Figure 11 When the controller controls the compressor to stop running, it is configured to perform the following steps:

[0194] When the energy consumption benefit is greater than or equal to the set benefit threshold, the compressor is controlled to stop running. The energy consumption benefit is used to reflect the benefit that can be generated by the energy saved when the compressor is currently controlled to stop running.

[0195] It should be understood that the benefit threshold can be obtained based on user input or settings, or calculated by an intelligent algorithm based on the second operating data and corresponding user feedback data, or determined through experimental testing and corresponding user feedback data. No specific restrictions are given here.

[0196] It should be understood that the benefits that can be generated by the saved energy consumption include but are not limited to economic benefits (such as electricity bills or air conditioning equipment maintenance costs, etc.), environmental benefits (such as carbon emissions or other pollutant emissions) and health benefits (such as indoor air quality or noise pollution, etc.).

[0197] In some embodiments, the energy efficiency includes at least an energy comfort ratio, which may be the ratio of the energy saved when the compressor is currently controlled to stop running to the target user comfort. The target user comfort may refer to the comfort of people in the environmental space where the air-conditioning equipment is located during the early shutdown time period (i.e., the time period between the current moment and the set shutdown time).

[0198] Because when the user sets the shutdown time of the air-conditioning equipment or compressor, the controller usually waits until the set shutdown time before turning off the compressor. The temperature in the environment space where the air-conditioning equipment is located may have already reached the set temperature. Continuous operation of the compressor may cause the indoor temperature to be too high or too low, or energy consumption to be wasted. Therefore, in order to reduce unnecessary energy consumption as much as possible while meeting user needs, when the relationship between the indoor average temperature and return air temperature and their corresponding temperature thresholds meets the requirements of the functional mode, it is possible to analyze whether the current energy consumption benefit is greater than or equal to the set benefit threshold.

[0199] If the current energy consumption benefit is greater than or equal to the set benefit threshold (such as 2), the compressor can be directly controlled to stop running without waiting for the downtime.

[0200] If the current energy consumption benefit is less than the set benefit threshold, the process can return to the step of obtaining the compressor's operating data to determine whether the energy consumption benefit is greater than or equal to the benefit threshold, until it is determined that the current energy consumption benefit is greater than or equal to the benefit threshold, or the set shutdown time has been reached, and the compressor is controlled to stop running.

[0201] In the embodiment of the present application, whether the compressor can be controlled to stop running in advance is judged by conditions in different dimensions such as the average indoor temperature, return air temperature and energy efficiency. This can more comprehensively consider factors such as the overall indoor temperature and energy efficiency, improve the rationality and reliability of the compressor shutdown control, and at the same time ensure that energy-saving control of the air-conditioning equipment is achieved on the basis of meeting user needs.

[0202] Figure 12 A flow chart of a method for controlling an air-conditioning device according to some embodiments is shown. Figure 12 Before the controller inputs the operating data into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model, the controller is further configured to perform the following steps:

[0203] Return air temperature data is obtained, where the return air temperature data includes multiple return air temperatures collected at different times during the operation of the air conditioning equipment.

[0204] The return air temperature data is preprocessed to obtain processed return air temperature data, wherein the preprocessing includes filtering processing and / or interpolation processing.

[0205] Correspondingly, when the controller inputs the operating data into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model, the controller is configured to perform the following steps:

[0206] The processed return air temperature data and the operating data are input into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model. The temperature prediction model is used to perform feature extraction processing on the total number of starts, the total number of shutdowns, the total operating time, the total shutdown time and the processed return air temperature data, and perform weighted calculation based on the extracted feature vectors and the weights corresponding to the feature vectors. The weighted feature vectors are processed based on the set activation function to obtain the indoor average temperature.

[0207] It should be understood that the return air temperature can be collected by a temperature sensor installed at the return air of the air-conditioning equipment, or it can be predicted by a prediction model based on input data (such as air-conditioning equipment operating data, compressor operating data or hot and cold channel temperatures, etc.). The embodiment of the present application does not impose specific restrictions on the method of collecting the return air temperature.

[0208] In some embodiments, during the operation of the air-conditioning equipment, the return air temperature may be collected at a set collection frequency (eg, once every 10 minutes) to obtain multiple return air temperatures collected at different times.

[0209] To improve the accuracy of the return air temperature data, the controller can preprocess the return air temperature data after obtaining it. Through preprocessing, any abnormal data in the return air temperature data can be corrected to obtain a more reliable processed return air temperature.

[0210] Among them, in order to reduce the impact of factors such as electromagnetic interference on the return air temperature data, the return air temperature data can be filtered. The filtering process can remove random noise in the return air temperature data and make the return air temperature data smoother, thereby more clearly reflecting the actual change trend of the return air temperature and improving the reliability of the return air temperature data.

[0211] It should be understood that the filtering process includes but is not limited to low-pass filtering, high-pass filtering, or sliding window filtering.

[0212] In some embodiments, the return air temperature data can be subjected to sliding window filtering based on a set sliding window. The length of the window can be obtained according to user settings or inputs, or through experimental testing to comprehensively balance the stability and real-time performance of the data.

[0213] As an example, the filtered return air temperature data can be expressed as follows:

[0214]

[0215] Among them, T filtered represents the return air temperature data of a window after filtering, n represents the length of the sliding window (that is, the number of data points contained in the window), i represents the number of data points in the return air temperature data, T j In the sliding window filtering process, the return air temperature within the window is averaged to smooth the return air temperature within the window and remove outliers, providing more stable and accurate return air temperature data for subsequent indoor average temperature prediction.

[0216] Alternatively, to improve the resolution of the return air temperature data, the return air temperature data can be interpolated. Since interpolation can add new data points or fill in abnormally missing data points, interpolating the return air temperature data can obtain more complete and continuous return air temperature data, improving the accuracy of subsequent average temperature predictions.

[0217] It should be understood that the interpolation processing includes but is not limited to linear interpolation, polynomial interpolation, nearest neighbor interpolation and other interpolation processing.

[0218] In some embodiments, the return air temperature data can be first detected for anomalies. If missing return air temperature data is detected, the return air temperature data can be interpolated. Alternatively, the return air temperature corresponding to the missing time point can be interpolated based on the return air temperatures corresponding to the two data points preceding and following the missing data point.

[0219] As an example, the return air temperature corresponding to the missing data point can be expressed as follows:

[0220]

[0221] Among them, T filled Indicates the missing data points obtained by interpolation (i.e., t m The return air temperature corresponding to the time T m-1 Indicates that m Adjacent time t m-1 Return air temperature corresponding to the moment;)T m+1 Indicates thatm Adjacent time t m+1 In the above process, interpolation is used to properly fill in missing data, avoid analysis errors caused by missing data, and ensure the accuracy and reliability of the indoor average temperature prediction.

[0222] In some embodiments, in order to further improve the reliability and smoothness of the return air temperature data, the return air temperature data can be filtered and interpolated. The filtering process can be used to remove noise interference and smooth the return air temperature data, and the interpolation process can be used to further smooth the return air temperature data and fill in missing data.

[0223] In an embodiment of the present application, the return air temperature data is filtered and / or interpolated to smooth the return air temperature data, remove noise in the return air temperature data, and correct abnormal data, thereby improving the reliability and accuracy of the processed return air temperature data. Furthermore, the processed return air temperature data and operating data are input into a temperature prediction model to predict the indoor average temperature, thereby improving the accuracy of the indoor average temperature prediction.

[0224] In an embodiment of the present application, multiple data such as the total number of starts, start-stop data, and operating time of the air-conditioning equipment are input into a temperature prediction model to predict the indoor average temperature, fully considering multiple factors affecting the overall temperature of the environmental space in which the air-conditioning equipment is located and the degree of influence of different factors on the temperature, thereby more comprehensively considering the reasons for changes in the indoor average temperature and improving the reliability and accuracy of the indoor average temperature obtained by the temperature prediction model.

[0225] Figure 13 A flow chart of a method for controlling an air-conditioning device according to some embodiments is shown. Figure 13 After the controller controls the compressor to stop running, it is further configured to perform the following steps:

[0226] When it is detected that the temperature change rate is greater than or equal to a set change threshold, the compressor is controlled to start. The temperature change rate reflects the rate of temperature change in the environment space where the air-conditioning equipment is located.

[0227] It should be understood that the temperature change rate is usually calculated based on the temperature data of the environmental space where the air-conditioning equipment is located in unit time (such as return air temperature), and is used to reflect the rate of temperature change in the environmental space where the air-conditioning equipment is located (such as ℃ / min, that is, degrees Celsius per minute).

[0228] For example, the rate of temperature change in the environmental space where the air-conditioning equipment is located can be calculated based on the temperature data of the environmental space where the air-conditioning equipment is located within a set past time period (such as the time period from the last time the compressor was controlled to stop to the current moment) to obtain the required temperature change rate.

[0229] Optionally, the above-mentioned temperature change rate can be the return air temperature change rate, or the indoor average temperature change rate, or the change rate obtained by weighted calculation based on the return air temperature change rate, the indoor average temperature change rate and their corresponding weighted coefficients. The specific setting can be based on actual application requirements.

[0230] It should be understood that the change threshold can be obtained through user input or setting, or can be obtained through intelligent algorithms such as large models, fixed empirical thresholds, or physical models of the room. In some embodiments, the change threshold can be determined based on the thermal insulation performance of the environment in which the air conditioning equipment is located and the user's sensitivity to temperature changes.

[0231] In some embodiments, the controller can detect the temperature change rate at a set detection frequency (such as once per minute) after a preset period of time (such as 10 minutes) after controlling the compressor to stop, so as to avoid restarting the compressor in a short period of time. At the same time, the temperature change rate is detected at a certain frequency to ensure that the compressor can be controlled to start in time when the temperature change rate is greater than or equal to the change threshold, while minimizing the number of calculations of the controller as much as possible to reduce the burden on the air-conditioning equipment.

[0232] In the embodiment of the present application, since the temperature change rate can better reflect the dynamic changes in the temperature in the environmental space where the air-conditioning equipment is located, whether to control the compressor to start is determined based on whether the temperature change rate is greater than or equal to the change threshold. Compared with methods based on fixed temperature thresholds, the compressor can be controlled more accurately, thereby better maintaining the stability of the indoor temperature, which helps to improve the user's comfort. Moreover, determining whether to start the compressor by means of the temperature change rate and the change threshold can better adapt to the differences in indoor temperature changes caused by different environmental conditions, and effectively improve the flexibility and reliability of the air-conditioning equipment.

[0233] Combined with the above Figures 4 to 13 , describes the method of the embodiment of the present application in detail, and will be combined with Figure 14 Describing the device embodiments of the present application. It should be understood that the devices in the embodiments of the present application can execute the various methods of the aforementioned embodiments of the present application, that is, the specific working processes of the following various products can refer to the corresponding processes in the aforementioned method embodiments.

[0234] Figure 14 A schematic structural diagram of an air-conditioning equipment control device provided in some embodiments of the present application is shown.

[0235] See also Figure 14 The air conditioning equipment control device includes: an operation data acquisition module 1410, an average temperature prediction module 1420, a heating shutdown control module 1430 and a cooling shutdown control module 1440.

[0236] The operation data acquisition module 1410 is used to obtain the operation data of the above-mentioned compressor, and the above-mentioned operation data includes the total number of starts, the total number of stops, the total operation time and the total stop time of the above-mentioned compressor.

[0237] The average temperature prediction module 1420 is used to input the above-mentioned operating data into the temperature prediction model to obtain the indoor average temperature output by the above-mentioned temperature prediction model. The above-mentioned temperature prediction model is used to perform feature extraction processing on the above-mentioned total number of starts, the above-mentioned total number of shutdowns, the above-mentioned total operating time and the above-mentioned total shutdown time in the above-mentioned operating data, and perform weighted calculation based on the extracted feature vectors and the weights corresponding to the above-mentioned feature vectors, and process the weighted feature vectors based on the set activation function to obtain the above-mentioned indoor average temperature.

[0238] The heating shutdown control module 1430 is used to control the compressor to stop running when the above-mentioned air-conditioning equipment is in heating mode, the above-mentioned indoor average temperature is greater than or equal to the first temperature threshold, and the return air temperature is greater than or equal to the second temperature threshold. The above-mentioned return air temperature is used to reflect the temperature at the return air point of the above-mentioned air-conditioning equipment. The above-mentioned first temperature threshold and the above-mentioned second temperature threshold are determined according to the temperature expected to be reached in the environmental space where the above-mentioned air-conditioning equipment is located.

[0239] The refrigeration shutdown control module 1440 is used to control the compressor to stop running when the air-conditioning equipment is in cooling mode, the indoor average temperature is less than or equal to the first temperature threshold, and the return air temperature is less than or equal to the second temperature threshold.

[0240] Each unit module of the device 1400 can respectively execute the corresponding steps in the above method embodiment, so each unit module will not be described in detail here. Please refer to the description of the corresponding steps above for details.

[0241] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a controller, the steps in the above-mentioned various method embodiments can be implemented.

[0242] An embodiment of the present application provides a computer program product. When the computer program product runs on a controller, the controller can implement the steps of the control method described in each of the above embodiments when the computer program product is executed.

[0243] 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 present application implements all or part of the process in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / electronic device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0244] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0245] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0246] In the embodiments provided in this application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0247] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0248] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. An air conditioning device, characterized in that: include: case; a compressor disposed within the housing; The controller provided in the housing is configured to: Acquiring operating data of the compressor, the operating data including a total number of starts, a total number of stops, a total operating time, and a total stopping time of the compressor; Inputting the operating data into a temperature prediction model to obtain an indoor average temperature output by the temperature prediction model, wherein the temperature prediction model is used to perform feature extraction processing on the total number of starts, the total number of shutdowns, the total operating time, and the total shutdown time in the operating data, and perform weighted calculation based on each extracted feature vector and the weight corresponding to the feature vector, and process the weighted feature vector based on a set activation function to obtain the indoor average temperature; When the air conditioner is in heating mode, the indoor average temperature is greater than or equal to a first temperature threshold, and the return air temperature is greater than or equal to a second temperature threshold, controlling the compressor to stop running, the return air temperature is used to reflect the temperature at the return air point of the air conditioner, and the first temperature threshold and the second temperature threshold are determined according to the expected temperature of the environment space where the air conditioner is located; When the air-conditioning device is in cooling mode, the indoor average temperature is less than or equal to the first temperature threshold, and the return air temperature is less than or equal to the second temperature threshold, the compressor is controlled to stop running.

2. The air conditioning device according to claim 1, characterized in that When the controller controls the compressor to stop running, it is configured to: When each data in the operating data is less than or equal to a predetermined threshold value corresponding to the data, the compressor is controlled to stop operating.

3. The air conditioning device according to claim 2, wherein: Before the controller controls the compressor to stop running when each data in the operating data is less than or equal to a predetermined threshold value corresponding to the data, the controller is further configured to: The predetermined threshold corresponding to each data is determined based on the first operating data and the second operating data of the compressor, wherein the first operating data includes the operating data of the compressor during the current operation of the air-conditioning device, and the second operating data includes the operating data of the compressor during the historical operation of the air-conditioning device.

4. The air conditioning device according to claim 3, characterized in that When the controller determines the predetermined threshold corresponding to each data based on the first operating data and the second operating data of the compressor, the controller is configured to: Calculating an average value of each data in the operating data based on the first operating data and the second operating data; Determining an offset value for each data item based on a temperature deviation and a standard deviation of each data item, wherein the temperature deviation is used to reflect a deviation between a historical indoor average temperature and a corresponding first temperature threshold; The predetermined threshold value of each data is determined according to the average value and the offset value.

5. The air conditioning device according to claim 1, wherein: The operating data includes first start-stop data and second start-stop data. When the controller acquires the operating data of the compressor, it is configured to: acquiring the first start / stop data based on the switch control circuit of the compressor; The second start-stop data is acquired based on the operating current of the compressor and a set current threshold.

6. The air conditioning device according to claim 5, characterized in that When the controller inputs the operating data into a temperature prediction model to obtain an indoor average temperature output by the temperature prediction model, the controller is configured to: When the difference between the first start-stop data and the second start-stop data is less than or equal to a set difference threshold, the first start-stop data and / or the second start-stop data are input into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model.

7. The air conditioning device according to claim 6, characterized in that When the controller inputs the operating data into a temperature prediction model to obtain an indoor average temperature output by the temperature prediction model, the controller is configured to: When a difference between the first start-stop data and the second start-stop data is greater than the difference threshold, determining abnormal start-stop data based on the first start-stop data and the second start-stop data, where the abnormal start-stop data is start-stop data having an abnormal jump between the first start-stop data and the second start-stop data; Correcting the abnormal start-stop data according to a set correction method to obtain corrected start-stop data; The corrected start-stop data and the non-abnormal start-stop data are input into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model.

8. The air conditioning device according to claim 1, wherein: When the controller controls the compressor to stop running, it is configured to: When the energy consumption benefit is greater than or equal to the set benefit threshold, the compressor is controlled to stop running. The energy consumption benefit is used to reflect the benefit that can be generated by the energy saved when the compressor is currently controlled to stop running.

9. The air conditioning device according to claim 1, wherein: Before the controller inputs the operating data into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model, the controller is further configured to: Acquiring return air temperature data, the return air temperature data including a plurality of return air temperatures collected at different times during the operation of the air conditioning equipment; Preprocessing the return air temperature data to obtain processed return air temperature data, wherein the preprocessing includes filtering and / or interpolation; Correspondingly, when the controller inputs the operating data into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model, it is configured to: The processed return air temperature data and the operating data are input into the temperature prediction model to obtain the indoor average temperature output by the temperature prediction model. The temperature prediction model is used to perform feature extraction processing on the input total number of starts, the total number of shutdowns, the total operating time, the total shutdown time and the processed return air temperature data, and perform weighted calculation based on the extracted feature vectors and the weights corresponding to the feature vectors. The weighted feature vectors are processed based on the set activation function to obtain the indoor average temperature.

10. The air conditioning device according to any one of claims 1 to 9, characterized in that: After the controller controls the compressor to stop running, the controller is further configured to: When it is detected that the temperature change rate is greater than or equal to a set change threshold, the compressor is controlled to start, and the temperature change rate reflects the rate of temperature change in the environment space where the air-conditioning equipment is located.

Images