Air conditioner refrigerating capacity control method and device, air conditioner and storage medium

Abstract

The application discloses a kind of air conditioner refrigeration capacity control method, device, air conditioner and storage medium, belong to air conditioning technical field.Wherein, the method includes: obtaining the operating parameter that influences air conditioner refrigeration capacity;The operating parameter is carried out short-time Fourier transform, obtains the first time-frequency data corresponding to the operating parameter;The first time-frequency data is input into the neural network model that is trained in advance, obtains the predicted value of air conditioner refrigeration capacity that the neural network model outputs;According to the predicted value, the air conditioner refrigeration capacity that air conditioner exports is controlled.By the present application, the technical problem that refrigeration capacity control is not accurate in the related art is solved.

Description

Technical Field

[0001] This application relates to the field of air conditioning technology, and more specifically, to a method, apparatus, air conditioner, and storage medium for controlling the cooling capacity of an air conditioner. Background Technology

[0002] With continuous social progress and the development of science and technology, people are paying increasing attention to the environment. To alleviate energy pressure, it is necessary to address the issue from both the perspectives of increasing supply and reducing demand. As an indispensable appliance in daily life, air conditioning plays a crucial role in energy conservation. Controlling the cooling capacity of air conditioners to save system energy has become a key direction for air conditioning energy saving.

[0003] In related technologies, the method for determining the cooling capacity of an air conditioning system is mainly based on sensor measurement. However, sensor measurement is susceptible to interference and has insufficient accuracy, leading to inaccurate cooling capacity control.

[0004] There are currently no effective solutions to the aforementioned problems in the relevant technologies. Summary of the Invention

[0005] This application provides a method, device, air conditioner, and storage medium for controlling the cooling capacity of an air conditioner, in order to solve the technical problem of inaccurate cooling capacity control in related technologies.

[0006] According to one aspect of the embodiments of this application, a method for controlling the cooling capacity of an air conditioner is provided, comprising: acquiring operating parameters that affect the cooling capacity of the air conditioner; performing a short-time Fourier transform on the operating parameters to obtain first time-frequency data corresponding to the operating parameters; inputting the first time-frequency data into a pre-trained neural network model to obtain a predicted value of the cooling capacity of the air conditioner output by the neural network model; and controlling the cooling capacity of the air conditioner output according to the predicted value.

[0007] According to another aspect of the embodiments of this application, an air conditioning cooling capacity control device is also provided, comprising: an acquisition module for acquiring operating parameters affecting the air conditioning cooling capacity; a transformation module for performing a short-time Fourier transform on the operating parameters to obtain first time-frequency data corresponding to the operating parameters; a prediction module for inputting the first time-frequency data into a pre-trained neural network model to obtain a predicted value of the air conditioning cooling capacity output by the neural network model; and a control module for controlling the air conditioning cooling capacity according to the predicted value.

[0008] Furthermore, the transformation module includes a first transformation unit, used to perform short-time Fourier transform on the temperature data, the humidity data, and the air conditioning pressure data respectively to obtain second time-frequency data corresponding to the temperature data, third time-frequency data corresponding to the humidity data, and fourth time-frequency domain data corresponding to the air conditioning pressure data; and to concatenate the second time-frequency data, the third time-frequency data, and the fourth time-frequency data to obtain first time-frequency data. The operating parameters include the temperature data and humidity data of the environment where the air conditioner is located, as well as the air conditioning pressure data.

[0009] Furthermore, the prediction module includes a prediction unit, used to input the first time-frequency data into a feature extraction model to obtain the time-frequency features output by the feature extraction model, wherein the first time-frequency data is a time-frequency data graph with time as the horizontal axis and frequency as the vertical axis; and to input the time-frequency features into a cooling capacity prediction model to obtain the predicted value of the air conditioner cooling capacity output by the cooling capacity prediction model, wherein the neural network model includes the feature extraction model and the cooling capacity prediction model.

[0010] Furthermore, the control device also includes a training module for acquiring time-frequency data training samples, training a convolutional neural network using the time-frequency data training samples to obtain a feature extraction model; acquiring time-frequency feature training samples output by the feature extraction model, training a recurrent neural network using the time-frequency feature training samples to obtain a cooling capacity prediction model, wherein the neural network model includes the feature extraction model and the cooling capacity prediction model.

[0011] Furthermore, the transformation module includes a second transformation unit, used to obtain a window function for short-time Fourier transform, wherein the time window corresponding to the window function is fixed; the operating parameters are truncated into multiple operating sub-parameters according to the time window; the operating sub-parameters are analyzed segment by segment to obtain the frequency domain characteristics of each operating sub-parameter; and the frequency domain characteristics of all operating sub-parameters are used as the first time-frequency data.

[0012] Furthermore, the control module includes a control unit, used to acquire the actual cooling capacity output by the air conditioner based on the operating parameters; calculate the difference between the predicted value and the actual cooling capacity; and adjust the actual cooling capacity output by the air conditioner based on the difference so that the adjusted actual cooling capacity is the same as the predicted value.

[0013] Furthermore, the acquisition module includes an acquisition unit for collecting the operating parameters of the air conditioner; deleting other interfering parameters from the operating parameters except those affecting the air conditioner's cooling capacity to obtain the remaining parameters; and performing data cleaning on the remaining parameters using Kalman filtering to obtain the operating parameters.

[0014] According to another aspect of the embodiments of this application, a storage medium is also provided, the storage medium including a stored program that executes the above steps when the program is run.

[0015] According to another aspect of the embodiments of this application, an electronic device is also provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; wherein: the memory is used to store computer programs; and the processor is used to execute the steps in the above method by running the programs stored in the memory.

[0016] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps in the above-described method.

[0017] This application obtains operating parameters affecting the cooling capacity of an air conditioner, performs a short-time Fourier transform on these parameters to obtain the corresponding first time-frequency data, inputs the first time-frequency data into a pre-trained neural network model to obtain the predicted value of the air conditioner's cooling capacity output by the neural network model, and controls the air conditioner's cooling capacity output based on the predicted value. By collecting operating parameters affecting the air conditioner's cooling capacity, the basic operating data of the air conditioner can be understood. By performing a short-time Fourier transform on the basic operating data, data in the time and frequency domains are obtained. Features are extracted from the time and frequency domains from a multi-dimensional perspective based on the neural network, improving the measurement accuracy of the air conditioner's cooling capacity and thus improving the control accuracy of the cooling capacity. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0021] Figure 1 This is a hardware structure block diagram of a computer according to an embodiment of this application;

[0022] Figure 2This is a flowchart of a method for controlling the cooling capacity of an air conditioner according to an embodiment of this application;

[0023] Figure 3 This is a flowchart of an embodiment of the air conditioning cooling capacity calculation method based on frequency domain analysis and deep neural networks in this application;

[0024] Figure 4 This is a structural block diagram of an air conditioning cooling capacity control device according to an embodiment of this application. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of them. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of the present application can be combined with each other.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] Example 1

[0028] The method embodiment provided in Embodiment 1 of this application can be executed in an air conditioner, a computer, or a similar computing device. Taking its operation on an air conditioner as an example, Figure 1 This is a hardware structure block diagram of an air conditioner according to an embodiment of this application. Figure 1 As shown, an air conditioner may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. Optionally, the air conditioner may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1The structure shown is for illustrative purposes only and does not limit the structure of the air conditioner described above. For example, the air conditioner may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0029] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to an air conditioning cooling capacity control method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thus implementing the aforementioned method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the air conditioner via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0030] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the air conditioner's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0031] This embodiment provides a method for controlling the cooling capacity of an air conditioner. Figure 2 This is a flowchart of a method for controlling the cooling capacity of an air conditioner according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps:

[0032] Step S10: Obtain operating parameters that affect the cooling capacity of the air conditioner;

[0033] In this embodiment, air conditioning operating parameters affecting the air conditioning cooling capacity are collected by sensors and data acquisition devices. The collected operating parameters are raw time series signals, including but not limited to temperature and humidity data of the environment where the air conditioner is located, as well as air conditioning pressure data.

[0034] Step S20: Perform a short-time Fourier transform on the operating parameters to obtain the first time-frequency data corresponding to the operating parameters;

[0035] Step S30: Input the first time-frequency data into a pre-trained neural network model to obtain the predicted value of the air conditioning cooling capacity output by the neural network model;

[0036] Step S40: Control the cooling capacity output of the air conditioner according to the predicted value.

[0037] Since the collected operating parameters are raw time-series signals, i.e., time-domain data, this embodiment performs a short-time Fourier transform on the operating parameters to obtain the first time-frequency data corresponding to the operating parameters. The first time-frequency data is a time-frequency data graph showing the frequency of the operating parameters changing over time. The first time-frequency data is input into a pre-trained neural network model to obtain the predicted value of the air conditioning cooling capacity output by the neural network model. Then, the actual cooling capacity output by the air conditioner is controlled according to the predicted value. The cooling capacity is the total amount of heat removed from a closed space, room, or area per unit time when the air conditioner or other refrigeration unit is running. Optionally, this embodiment can also control the heating capacity of the air conditioner based on a similar scheme: obtain the operating parameters that affect the heating capacity of the air conditioner; perform a short-time Fourier transform on the operating parameters that affect the heating capacity of the air conditioner to obtain the corresponding time-frequency data; input the time-frequency data into a pre-trained neural network model to obtain the predicted value of the heating capacity output by the neural network model; and control the heating capacity output by the air conditioner according to the predicted value.

[0038] Through the above steps, operating parameters affecting the air conditioner's cooling capacity are obtained. Short-time Fourier transform is performed on these parameters to obtain the corresponding first time-frequency data. This first time-frequency data is then input into a pre-trained neural network model to obtain the predicted value of the air conditioner's cooling capacity output by the neural network model. Based on this predicted value, the air conditioner's cooling capacity is controlled. By collecting operating parameters affecting the air conditioner's cooling capacity, the basic operating data of the air conditioner can be understood. By performing a short-time Fourier transform on this basic operating data, first time-frequency data in both the time and frequency domains is obtained. Features are extracted from the neural network from multiple dimensions in both the time and frequency domains, improving the measurement accuracy of the air conditioner's cooling capacity and thus enhancing the control accuracy of the cooling capacity.

[0039] In one embodiment of this example, considering that the cooling capacity required by the air conditioner varies under different environments, i.e., ambient temperature and humidity are important indicators affecting the cooling capacity, and air conditioner pressure is also a key operating parameter affecting the cooling capacity, in this embodiment, the operating parameters include temperature and humidity data of the environment where the air conditioner is located, as well as air conditioner pressure data. Performing a short-time Fourier transform on the operating parameters yields the first time-frequency data corresponding to the operating parameters, including:

[0040] S21, perform short-time Fourier transform on the temperature data, humidity data and air conditioning pressure data respectively to obtain the second time-frequency data corresponding to the temperature data, the third time-frequency data corresponding to the humidity data and the fourth time-frequency domain data corresponding to the air conditioning pressure data;

[0041] S22, the second time-frequency data, the third time-frequency data and the fourth time-frequency data are concatenated to obtain the first time-frequency data.

[0042] In this embodiment, the short-time Fourier transform is used to decompose each time-domain signal (including temperature data, humidity data, and air conditioning pressure data) into its own time-frequency data, that is, to obtain the second time-frequency data corresponding to the temperature data, the third time-frequency data corresponding to the humidity data, and the fourth time-frequency domain data corresponding to the air conditioning pressure data. The second time-frequency data, the third time-frequency data, and the fourth time-frequency data are concatenated to obtain the first time-frequency data.

[0043] This implementation method calculates the time-frequency data corresponding to temperature, humidity, and air conditioning pressure, and splices the time-frequency data corresponding to each operating parameter to obtain the first time-frequency data. Based on multiple operating parameters that affect the air conditioning cooling capacity, the cooling capacity is predicted, which further improves the measurement accuracy of the cooling capacity.

[0044] In another embodiment of this example, inputting the first time-frequency data into a pre-trained neural network model to obtain the predicted value of the air conditioning cooling capacity output by the neural network model includes:

[0045] S31, input the first time-frequency data into the feature extraction model to obtain the time-frequency features output by the feature extraction model, wherein the first time-frequency data is a time-frequency data graph with time as the horizontal axis and frequency as the vertical axis;

[0046] S32, input the time-frequency features into the cooling capacity prediction model to obtain the predicted value of the air conditioner cooling capacity output by the cooling capacity prediction model, wherein the neural network model includes the feature extraction model and the cooling capacity prediction model.

[0047] In this embodiment, the first time-frequency data is a time-frequency data graph with time as the horizontal axis and frequency as the vertical axis. Each point in the time-frequency data graph corresponds to the amplitude of each operating parameter at that frequency. The neural network model includes a feature extraction model and a cooling capacity prediction model. The first time-frequency data is input into the feature extraction model to extract the frequency domain features of the first time-frequency data, obtaining the time-frequency features output by the feature extraction model. The time-frequency features are then input into the cooling capacity prediction model to obtain the predicted value of the air conditioner's cooling capacity output by the cooling capacity prediction model.

[0048] Before inputting the first time-frequency data into a pre-trained neural network model, the method further includes: acquiring time-frequency data training samples, training a convolutional neural network using the time-frequency data training samples to obtain a feature extraction model; acquiring time-frequency feature training samples output by the feature extraction model, training a recurrent neural network using the time-frequency feature training samples to obtain a cooling capacity prediction model, wherein the neural network model includes the feature extraction model and the cooling capacity prediction model.

[0049] In this embodiment, the time-frequency data training samples are the existing air conditioner operating parameters used for model training, which are obtained by short-time Fourier transform. A convolutional neural network is trained using the time-frequency data training samples to obtain a feature extraction model with a preset accuracy. The feature extraction model is then used to extract features from the time-frequency data training samples to obtain the time-frequency feature training samples output by the feature extraction model. A recurrent neural network is then trained using the time-frequency feature training samples to obtain a cooling capacity prediction model with a preset prediction accuracy. In this embodiment, the recurrent neural network adopts an LSTM (Long Short-Term Memory) network structure and uses time series analysis to improve the accuracy and generalization ability of the model.

[0050] In another embodiment of this example, performing a short-time Fourier transform on the operating parameters to obtain the first time-frequency data corresponding to the operating parameters includes: obtaining a window function for the short-time Fourier transform, wherein the time window corresponding to the window function is fixed; truncating the operating parameters into multiple operating sub-parameters according to the time window; performing segment-by-segment analysis on the operating sub-parameters to obtain the frequency domain characteristics of each operating sub-parameter; and using the frequency domain characteristics of all operating sub-parameters as the first time-frequency data.

[0051] The Short-Time Fourier Transform (SFT) can decompose a signal into several frequency domain components, facilitating subsequent processing and analysis. In this embodiment, the window function for the SFT is obtained. The fixed time of the window function can be set according to actual conditions, for example, 30 seconds. Each time the time window slides, a segment of the running sub-parameters is extracted over 30 seconds. The running parameters are then divided into multiple running sub-parameters, and each segment is analyzed to obtain the frequency domain characteristics of each running sub-parameter. The frequency domain characteristics of all running sub-parameters are used as the first time-frequency data.

[0052] In another embodiment of this example, controlling the air conditioning cooling capacity based on the predicted value includes:

[0053] S41, Obtain the actual cooling capacity output by the air conditioner based on the operating parameters;

[0054] S42, calculate the difference between the predicted value and the actual cooling capacity;

[0055] S43, Based on the difference, adjust the actual cooling capacity output by the air conditioner so that the adjusted actual cooling capacity is the same as the predicted value.

[0056] This method obtains the actual cooling capacity output by the air conditioner based on its operating parameters, acquires the predicted cooling capacity output by the air conditioner based on a neural network model, calculates the error between the actual cooling capacity and the predicted value, and uses this error to control the air conditioner's operating parameters to adjust the actual cooling capacity output so that the adjusted actual cooling capacity matches the predicted value. This implementation compares the predicted value with the actual cooling capacity, and then uses the error between the two values ​​for feedback and adjustment to improve the accuracy and stability of cooling capacity detection. Optimization is performed based on the predicted value to predict how much cooling capacity is needed in the current environment, and the predicted cooling capacity is used to control the air conditioner's output cooling capacity.

[0057] In another embodiment of this example, obtaining the operating parameters affecting the air conditioner's cooling capacity includes:

[0058] S11, Collect the operating parameters of the air conditioner;

[0059] S12, delete the other interfering parameters in the working parameters except those that affect the air conditioning cooling capacity, and obtain the remaining parameters;

[0060] S13, perform data cleaning on the remaining parameters using Kalman filtering to obtain the operating parameters.

[0061] In this embodiment, the operating parameters of the air conditioner are collected, and other interfering parameters other than those affecting the cooling capacity of the air conditioner are deleted to obtain the remaining parameters. The remaining parameters are then cleaned using Kalman filtering to obtain the operating parameters that affect the cooling capacity of the air conditioner.

[0062] Due to the limitations of sensor and data acquisition equipment accuracy, data often exhibits significant disturbances. Therefore, in this embodiment, Kalman filtering is used to preprocess the collected operating parameters affecting air conditioning cooling capacity. This process cleans the key parameters returned by the sensors, such as temperature, humidity, and pressure, effectively removing noise and reducing the computational load of subsequent operations.

[0063] Figure 3 This is a flowchart of an embodiment of the air conditioning cooling capacity calculation method based on frequency domain analysis and deep neural networks according to an embodiment of the present invention, including:

[0064] Step 1: Collect key parameter signal data, including temperature and humidity data of the environment where the air conditioner is located, as well as air conditioner pressure data;

[0065] Step 2: Use the Kalman filter algorithm to preprocess the data and remove noise interference;

[0066] Step 3: Perform a Short Time Fourier Transform (STFT) on the preprocessed signal and simultaneously stitch the data together.

[0067] Step 4: Build a convolutional neural network;

[0068] Step 5: Train a feature extraction model based on a convolutional neural network, and use the feature extraction model to extract features from the concatenated data;

[0069] Step 6: Construct an air conditioning cooling capacity prediction model based on a recurrent neural network;

[0070] Step 7: Train the neural network to obtain the air conditioning cooling capacity prediction model;

[0071] Step 8: Apply neural networks to output the predicted value of the air conditioning cooling capacity based on the air conditioning cooling capacity prediction model.

[0072] Short-time Fourier Transform (SFT) can decompose a signal into several frequency domain components, facilitating subsequent processing and analysis. Deep neural networks, on the other hand, are powerful machine learning tools capable of efficient data processing and analysis in many fields. This embodiment combines SFT with deep neural networks to detect the cooling capacity of an air conditioning system. By analyzing the air conditioning operating characteristics from a frequency domain perspective, it can detect the user's cooling demand, thereby improving the efficiency and stability of the air conditioning system to a certain extent, and providing users with a better comfort experience and energy-saving effects.

[0073] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0074] Example 2

[0075] This embodiment also provides an air conditioning cooling capacity control device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0076] Figure 4 This is a structural block diagram of an air conditioning cooling capacity control device according to an embodiment of this application, such as... Figure 4 As shown, the device includes:

[0077] Module 40 is used to acquire operating parameters that affect the cooling capacity of the air conditioner;

[0078] Transformation module 41 is used to perform short-time Fourier transform on the operating parameters to obtain the first time-frequency data corresponding to the operating parameters;

[0079] Prediction module 42 is used to input the first time-frequency data into a pre-trained neural network model to obtain the predicted value of the air conditioning cooling capacity output by the neural network model;

[0080] The control module 43 is used to control the cooling capacity of the air conditioner based on the predicted value.

[0081] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0082] Example 3

[0083] Embodiments of this application also provide a storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

[0084] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0085] S1, obtain the operating parameters that affect the cooling capacity of the air conditioner;

[0086] S2, Perform a short-time Fourier transform on the operating parameters to obtain the first time-frequency data corresponding to the operating parameters;

[0087] S3, input the first time-frequency data into a pre-trained neural network model to obtain the predicted value of the air conditioning cooling capacity output by the neural network model;

[0088] S4, control the cooling capacity output of the air conditioner according to the predicted value.

[0089] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0090] Embodiments of this application also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0091] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0092] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0093] S1, obtain the operating parameters that affect the cooling capacity of the air conditioner;

[0094] S2, Perform a short-time Fourier transform on the operating parameters to obtain the first time-frequency data corresponding to the operating parameters;

[0095] S3, input the first time-frequency data into a pre-trained neural network model to obtain the predicted value of the air conditioning cooling capacity output by the neural network model;

[0096] S4, control the cooling capacity output of the air conditioner according to the predicted value.

[0097] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0098] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0099] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0100] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0101] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0102] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0103] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0104] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for controlling the cooling capacity of an air conditioner, characterized in that, The method includes: Obtain operating parameters that affect the cooling capacity of an air conditioner. The cooling capacity is the total amount of heat removed from a closed space, room, or area per unit time when an air conditioner or other refrigeration unit is running. The operating parameters include air conditioner pressure data. Perform a short-time Fourier transform on the operating parameters to obtain the first time-frequency data corresponding to the operating parameters; The first time-frequency data is input into a pre-trained neural network model to obtain the predicted value of the air conditioning cooling capacity output by the neural network model. The cooling capacity output of the air conditioner is controlled based on the predicted value; The operating parameters include temperature and humidity data of the environment where the air conditioner is located. Performing a short-time Fourier transform on the operating parameters yields the following first time-frequency data corresponding to the operating parameters: Short-time Fourier transforms are performed on the temperature data, humidity data, and air conditioning pressure data respectively to obtain second time-frequency data corresponding to the temperature data, third time-frequency data corresponding to the humidity data, and fourth time-frequency domain data corresponding to the air conditioning pressure data. The second time-frequency data, the third time-frequency data, and the fourth time-frequency data are concatenated to obtain the first time-frequency data; Inputting the first time-frequency data into a pre-trained neural network model to obtain the predicted value of the air conditioning cooling capacity output by the neural network model includes: The first time-frequency data is input into the feature extraction model to obtain the time-frequency features output by the feature extraction model, wherein the first time-frequency data is a time-frequency data graph with time as the horizontal axis and frequency as the vertical axis; The time-frequency features are input into the cooling capacity prediction model to obtain the predicted value of the air conditioner cooling capacity output by the cooling capacity prediction model. The neural network model includes the feature extraction model and the cooling capacity prediction model.

2. The method according to claim 1, characterized in that, Before inputting the first time-frequency data into a pre-trained neural network model, the method further includes: Acquire time-frequency data training samples, and use the time-frequency data training samples to train a convolutional neural network to obtain a feature extraction model; The time-frequency feature training samples output by the feature extraction model are obtained, and the recurrent neural network is trained using the time-frequency feature training samples to obtain the cooling capacity prediction model. The neural network model includes the feature extraction model and the cooling capacity prediction model.

3. The method according to claim 1, characterized in that, Performing a short-time Fourier transform on the operating parameters to obtain the first time-frequency data corresponding to the operating parameters includes: Obtain the window function of the short-time Fourier transform, wherein the time window corresponding to the window function is fixed; The running parameters are extracted into multiple running sub-parameters according to the time window; The frequency domain characteristics of each operating sub-parameter are obtained by segment-by-segment analysis. The frequency domain characteristics of all running sub-parameters are used as the first time-frequency data.

4. The method according to claim 1, characterized in that, Controlling the air conditioning cooling capacity based on the predicted value includes: Obtain the actual cooling capacity output by the air conditioner based on the aforementioned operating parameters; Calculate the difference between the predicted value and the actual cooling capacity; Based on the difference, the actual cooling capacity output by the air conditioner is adjusted so that the adjusted actual cooling capacity is the same as the predicted value.

5. The method according to claim 1, characterized in that, The operating parameters that affect the cooling capacity of an air conditioner include: Collect the operating parameters of the air conditioner; Remove all interfering parameters from the operating parameters except those that affect the air conditioning cooling capacity to obtain the remaining parameters; The remaining parameters are cleaned using Kalman filtering to obtain the operating parameters.

6. A device for controlling the cooling capacity of an air conditioner, characterized in that, include: The acquisition module is used to acquire operating parameters that affect the cooling capacity of the air conditioner. The cooling capacity is the total amount of heat removed from a closed space, room or area per unit time when the air conditioner or other refrigeration unit is running. The operating parameters include air conditioner pressure data. The transformation module is used to perform a short-time Fourier transform on the operating parameters to obtain the first time-frequency data corresponding to the operating parameters; The prediction module is used to input the first time-frequency data into a pre-trained neural network model to obtain the predicted value of the air conditioning cooling capacity output by the neural network model. The control module is used to control the cooling capacity of the air conditioner based on the predicted value; The operating parameters include temperature and humidity data of the environment where the air conditioner is located. Performing a short-time Fourier transform on the operating parameters yields the following first time-frequency data corresponding to the operating parameters: Short-time Fourier transforms are performed on the temperature data, humidity data, and air conditioning pressure data respectively to obtain second time-frequency data corresponding to the temperature data, third time-frequency data corresponding to the humidity data, and fourth time-frequency domain data corresponding to the air conditioning pressure data. The second time-frequency data, the third time-frequency data, and the fourth time-frequency data are concatenated to obtain the first time-frequency data; Inputting the first time-frequency data into a pre-trained neural network model to obtain the predicted value of the air conditioning cooling capacity output by the neural network model includes: The first time-frequency data is input into the feature extraction model to obtain the time-frequency features output by the feature extraction model, wherein the first time-frequency data is a time-frequency data graph with time as the horizontal axis and frequency as the vertical axis; The time-frequency features are input into the cooling capacity prediction model to obtain the predicted value of the air conditioner cooling capacity output by the cooling capacity prediction model. The neural network model includes the feature extraction model and the cooling capacity prediction model.

7. An air conditioner, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, communication interface, and memory communicate with each other through the communication bus; wherein: Memory, used to store computer programs; A processor for executing the method steps of any one of claims 1 to 5 by running a program stored in memory.

8. A storage medium, characterized in that, The storage medium includes a stored program, wherein the program, when executed, performs the method steps of any one of claims 1 to 5.

Images