Electric power early warning method of air conditioning system, air conditioning system and cloud server

By using a three-dimensional convolutional neural network model, combining the location, time and weather information of the air conditioning system, the deviation problem caused by information compression in the power prediction of the air conditioning system is solved, and the accuracy of power prediction is improved.

CN119063201APending Publication Date: 2024-12-03QINGDAO HISENSE BOSCH AIR CONDITIONING SYSTEM CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411017833.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

When predicting the power load of air conditioning systems, the data stereoscopic distribution is damaged due to information compression, resulting in large deviations from the real value of the power prediction results and lack accuracy.

Method used

The three-dimensional convolutional neural network model is adopted to input the position information, time information and weather information of the air conditioning system, and combine the load value of the air conditioning system to predict the power, maintain the three-dimensional distribution of the data, and improve the accuracy of feature extraction.

Benefits of technology

It improves the accuracy of power prediction in the air conditioning system, reduces the deviation between the prediction results and the true value, and enhances the reliability of power prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119063201A_ABST
    Figure CN119063201A_ABST
Patent Text Reader

Abstract

The invention provides an electric power early warning method of an air conditioning system, the air conditioning system and a cloud server, particularly relates to the technical field of air conditioning systems, and is used for improving the accuracy of electric power prediction of the air conditioning system. The method comprises the steps that position information, time information, weather information and an air conditioning system load value of the air conditioning system are obtained; current environment information of the air conditioning system is determined based on the position information, the time information and the weather information, and the environment information comprises one or more of the average temperature value, the average humidity value and the airflow velocity value of the place where the air conditioning system is located; determining a predicted power value of the air conditioning system based on a preset three-dimensional convolutional neural network model, the environment information and the load value of the air conditioning system; and under the condition that the predicted power value is above the power threshold, outputting power early warning prompt information.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of air-conditioning systems, and in particular to a power early warning method for an air-conditioning system, an air-conditioning system and a cloud server. Background Art

[0002] As a device that can adjust and control the temperature, humidity, flow rate and other parameters of the ambient air in buildings or structures, the air conditioning system is increasingly widely used in life.

[0003] With global climate change and natural phenomena such as air flow, there are more and more cases of sudden temperature rise or fall in some local areas. Since the power load is greatly affected by temperature changes, sudden weather changes can cause the power grid load to rise sharply in a short period of time, resulting in power grid overload or even power outages. Related technologies use temperature changes and geographic location to predict power load changes during the use of air-conditioning systems, but sometimes the above method will destroy the original three-dimensional distribution of the data due to data compression, resulting in a large deviation between the power prediction results of the air-conditioning system and the actual value.

[0004] Therefore, how to improve the accuracy of power prediction for air-conditioning systems is an urgent problem to be solved. Summary of the invention

[0005] The embodiments of the present application provide a power early warning method for an air-conditioning system, an air-conditioning system, and a cloud server, which are used to improve the accuracy of power prediction of the air-conditioning system.

[0006] In order to achieve the above purpose, the embodiment of the present application adopts the following technical solution:

[0007] In a first aspect, a power early warning method for an air conditioning system is provided, the method comprising:

[0008] Obtaining the location information, time information, weather information and load value of the air conditioning system;

[0009] Based on the location information, time information and weather information, determine the current environmental information of the air conditioning system, where the environmental information includes one or more of an average temperature value, an average humidity value and an air flow velocity value of the location of the air conditioning system;

[0010] Determine the predicted power value of the air conditioning system based on a preset three-dimensional convolutional neural network model as well as environmental information and the load value of the air conditioning system;

[0011] When the predicted power value is above the power threshold, power warning prompt information is output.

[0012] The technical solution provided by the embodiment of the present application brings at least the following beneficial effects: the embodiment of the present application inputs environmental information and air-conditioning system load values ​​under different time information and spatial information into a preset three-dimensional convolutional neural network model, so that the input data maintains its original three-dimensional distribution without the need for compression, thereby improving the accuracy of feature extraction and thereby improving the accuracy of power prediction of the air-conditioning system.

[0013] In some embodiments, the above-mentioned preset three-dimensional convolutional neural network model is obtained by the following steps: obtaining historical environmental information of the air-conditioning system, historical air-conditioning system load values, and historical power values ​​corresponding to the historical environmental information, the historical environmental information including historical average temperature values, historical average humidity values, and historical air flow velocity values ​​at different locations in different time periods; using the historical environmental information and historical air-conditioning system load values ​​as training sample data, and using the historical power values ​​corresponding to the historical environmental information as training sample labels to construct a training sample set; training the original three-dimensional convolutional neural network model based on the training sample set to obtain the preset three-dimensional convolutional neural network model.

[0014] In some embodiments, the above-mentioned preset three-dimensional convolutional neural network model includes an input layer, a convolutional neural network layer, an activation layer, a pooling layer, a fully connected layer and an output layer; the input layer is used to input the training sample data into the preset three-dimensional convolutional neural network model, the convolutional neural network layer is used to extract features and generate feature vectors, the activation layer is used to perform nonlinear transformation processing on the feature vectors, the pooling layer is used to reduce the dimension of the feature vectors, the fully connected layer is used to learn the rules in the feature vectors to obtain predicted power values, and the output layer is used to output the predicted power values.

[0015] In some embodiments, after obtaining historical environmental information of the air-conditioning system, historical air-conditioning system load values, and historical power values ​​corresponding to the historical environmental information, the method also includes: performing z-score standardization processing on the historical environmental information and historical air-conditioning system load values ​​to remove abnormal values ​​in the historical environmental information and historical air-conditioning system load values.

[0016] In a second aspect, an embodiment of the present application provides an air conditioning system, the air conditioning system comprising:

[0017] Indoor unit;

[0018] Outdoor unit;

[0019] The controller is configured as:

[0020] Obtaining the location information, time information, weather information and load value of the air conditioning system;

[0021] Based on the location information, time information and weather information, determine the current environmental information of the air conditioning system, where the environmental information includes one or more of an average temperature value, an average humidity value and an air flow velocity value of the location of the air conditioning system;

[0022] Determine the predicted power value of the air conditioning system based on a preset three-dimensional convolutional neural network model as well as environmental information and the load value of the air conditioning system;

[0023] When the predicted power value is above the power threshold, power warning prompt information is output.

[0024] In a third aspect, an embodiment of the present application provides a cloud server, the cloud server comprising:

[0025] A communication device, used to establish a communication connection with the air conditioning system;

[0026] The processor is configured as:

[0027] Obtaining the location information, time information, weather information and load value of the air conditioning system;

[0028] Based on the location information, time information and weather information, determine the current environmental information of the air conditioning system, where the environmental information includes one or more of an average temperature value, an average humidity value and an air flow velocity value of the location of the air conditioning system;

[0029] Determine the predicted power value of the air conditioning system based on a preset three-dimensional convolutional neural network model as well as environmental information and the load value of the air conditioning system;

[0030] When the predicted power value is above the power threshold, power warning prompt information is output.

[0031] In a fourth aspect, an embodiment of the present application provides a controller comprising: one or more processors; one or more memories; wherein the one or more memories are used to store computer program codes, the computer program codes include computer instructions, and when the one or more processors execute the computer instructions, the controller executes the power warning method for the air-conditioning system provided in the first aspect.

[0032] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, which includes computer instructions. When the computer instructions are controlled on a computer, the computer executes the power warning method for the air-conditioning system provided in the first aspect and possible implementation methods.

[0033] In the sixth aspect, an embodiment of the present invention provides a computer program product, which can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program product can implement the power warning method for the air-conditioning system provided in the first aspect and possible implementation methods.

[0034] It should be noted that the above computer instructions may be stored in whole or in part on a computer-readable storage medium, wherein the computer-readable storage medium may be packaged together with the processor of the controller, or may be packaged separately from the processor of the controller, which is not limited in this application.

[0035] The beneficial effects described in the second to sixth aspects of the present application can be referred to the beneficial effect analysis of the first aspect and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0037] Figure 1 A schematic diagram of a multi-split air conditioning system provided in an embodiment of the present application Figure 1 ;

[0038] Figure 2 A schematic diagram of a multi-split air conditioning system provided in an embodiment of the present application Figure 2 ;

[0039] Figure 3 A schematic diagram of a multi-split air conditioning system provided in an embodiment of the present application Figure 3 ;

[0040] Figure 4 A schematic diagram of a multi-split air conditioning system provided in an embodiment of the present application Figure 4 ;

[0041] Figure 5 A schematic diagram of a multi-split air conditioning system provided in an embodiment of the present application Figure 5 ;

[0042] Figure 6 A schematic diagram of the hardware structure of a controller provided in an embodiment of the present application;

[0043] Figure 7 A schematic diagram of air conditioning data relationship provided in an embodiment of the present application;

[0044] Figure 8 A schematic diagram of an application scenario of an air conditioning system provided in an embodiment of the present application;

[0045] Fig. 9 A schematic diagram of another application scenario of an air conditioning system provided in an embodiment of the present application;

[0046] Fig.10 A schematic diagram of the structure of a cloud server provided in an embodiment of the present application;

[0047] Fig.11 A schematic flow chart of a power warning method for an air conditioning system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] In the description of the present invention, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0050] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0051] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0052] The terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0053] In addition, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0054] As the background technology, air conditioning systems are devices that can adjust and control parameters such as temperature, humidity, flow rate, etc. of ambient air in buildings or structures, and are increasingly widely used in life.

[0055] With global climate change and natural phenomena such as air flow, there are more and more cases of sudden temperature rise or fall in local areas. Since the power load is greatly affected by temperature changes, sudden changes in weather can cause the power grid load to rise sharply in a short period of time, resulting in power grid overload or even power outages. In related technologies, temperature changes and geographic location are used to predict the changes in power load during the use of air-conditioning systems, and the temperature changes and geographic location are input into a two-dimensional convolutional neural network model to predict the power value of the air conditioner. However, when the movement of the airflow changes greatly, due to the limited information carried by the two-dimensional convolutional neural network model, the above method will destroy the original three-dimensional distribution of the data due to data compression, resulting in a large deviation between the power prediction results of the air-conditioning system and the actual value.

[0056] Therefore, how to improve the accuracy of power prediction for air-conditioning systems is an urgent problem to be solved.

[0057] In view of this, the embodiment of the present application inputs environmental information and air-conditioning system load values ​​under different time information and spatial information into a preset three-dimensional convolutional neural network model, so that the input data maintains its original three-dimensional distribution without the need for compression, thereby improving the accuracy of feature extraction and further improving the accuracy of power prediction of the air-conditioning system.

[0058] Among them, the air-conditioning system provided in the embodiment of the present application can be a split wall-mounted air-conditioning system, a split cabinet air-conditioning system, a ceiling-mounted air-conditioning system, an embedded air-conditioning system, a central air-conditioning system or a multi-split air-conditioning system, and the embodiment of the present application does not impose any restrictions on this.

[0059] To further describe the technical solution of the embodiment of the present application, Figure 1 Shown is a structural diagram of an air conditioning system provided in an embodiment of the present application.

[0060] Reference Figure 1 The air conditioning system 1 includes: at least one outdoor unit 10 and at least one indoor unit 20.

[0061] The following is a detailed description of the configuration and functions of the various components of the outdoor unit 10.

[0062] In some embodiments, Figure 2 As shown, the outdoor unit 10 includes an outdoor heat exchanger 101. One end of the outdoor heat exchanger 101 is connected to the compressor through a four-way reversing valve, and the other end is connected to each indoor heat exchanger through a connecting pipe. The outdoor heat exchanger 101 is used to exchange heat between the refrigerant flowing in the heat transfer pipe of the outdoor heat exchanger 101 and the outdoor air.

[0063] In some embodiments, Figure 3 As shown, the outdoor unit 10 further includes a compressor 102. The compressor 102 is disposed between each indoor heat exchanger and the outdoor heat exchanger 101, and is used to provide power for the refrigerant circulation. Taking the refrigeration cycle as an example, the compressor 102 delivers the compressed refrigerant to the outdoor heat exchanger 101 via the four-way reversing valve 103.

[0064] In some embodiments, Figure 4 As shown, the outdoor unit 10 further includes a four-way reversing valve 103. The four ports of the four-way reversing valve 103 are respectively connected to the exhaust port of the compressor 102, the outdoor heat exchanger 101, the air intake port of the compressor 102, and each indoor heat exchanger. The four-way reversing valve 103 is used to achieve mutual conversion between the cooling mode and the heating mode by changing the flow direction of the refrigerant in the system pipeline.

[0065] In some embodiments, continuing as Figure 4 As shown, the outdoor unit 10 also includes an outdoor throttling device 104. The outdoor throttling device 104 is arranged between the outdoor heat exchanger 101 and each indoor heat exchanger, and has the effect of throttling the refrigerant flowing through the outdoor throttling device 104 to achieve a decompression effect, and is used to adjust the refrigerant flow rate of the refrigerant passage. Optionally, the outdoor throttling device 104 can be an electronic expansion valve. If the outdoor throttling device 104 reduces the opening, the flow resistance of the refrigerant passing through the outdoor throttling device 104 increases. If the outdoor throttling device 104 increases the opening, the flow resistance of the refrigerant passing through the outdoor throttling device 104 decreases. In this way, even if the states of other devices in the loop remain unchanged, when the opening of the outdoor throttling device 104 changes, the refrigerant flow rate flowing to the indoor heat exchanger 201 or the outdoor heat exchanger 101 will also change.

[0066] In some embodiments, continuing as Figure 4 As shown, the outdoor unit 10 further includes a gas-liquid separator 105. The gas-liquid separator 105 is connected to the air inlet of the compressor 102 and is used to contain the refrigerant of the liquid return portion in the refrigerant channel to prevent the compressor 102 from causing liquid hammer.

[0067] The following is a detailed description of the configuration and functions of the various components of the indoor unit 20.

[0068] In some embodiments, Figure 5 As shown, the indoor unit 20 includes an indoor heat exchanger 201. The indoor heat exchanger 201 is used to perform heat exchange between the refrigerant flowing in the heat transfer tube of the indoor heat exchanger 201 and the indoor air.

[0069] In some embodiments, continuing as Figure 5 As shown, the indoor unit 20 also includes an indoor throttling device 202. The indoor throttling device 202 is connected to the indoor heat exchanger 201, and is used to throttle the refrigerant flowing through the indoor throttling device 202 to achieve a pressure reduction effect, and is used to adjust the refrigerant flow rate of the refrigerant passage. Optionally, the indoor throttling device 202 can be an electronic expansion valve.

[0070] The air conditioning system in the present application performs a refrigeration cycle of the air conditioning system by using a compressor 102, an outdoor heat exchanger 101, a throttling device 104, an indoor heat exchanger 201 and a four-way reversing valve 103 as a refrigerant circulation loop. The refrigeration cycle includes a series of processes involving compression, condensation, expansion and evaporation, and supplies refrigerant to the conditioned and heat-exchanged air.

[0071] The indoor heat exchanger 201 and the outdoor heat exchanger 101 are used as a condenser or an evaporator. When the indoor heat exchanger 201 is used as a condenser, the air conditioning system 1 is used as a heater in the heating mode, and when the indoor heat exchanger 201 is used as an evaporator, the air conditioning system 1 is used as a cooler in the cooling mode.

[0072] In some embodiments, the air conditioning system 1 further includes a controller 300. Figure 6 As shown, the controller 300 is electrically connected to the outdoor heat exchanger 101 , the compressor 102 , the four-way reversing valve 103 , the outdoor throttling device 104 , the gas-liquid separator 105 , the indoor heat exchanger 201 and the indoor throttling device 202 .

[0073] In some embodiments, the controller 300 can be used to obtain the location information, time information, weather information and air conditioning system load value of the air-conditioning system; based on the location information, time information and weather information, determine the current environmental information of the air-conditioning system, the environmental information including one or more of the average temperature value, average humidity value and air flow velocity value of the location of the air-conditioning system; based on a preset three-dimensional convolutional neural network model and the environmental information and air-conditioning system load value, determine the predicted power value of the air-conditioning system; when the predicted power value is above the power threshold, output power warning prompt information.

[0074] The embodiment of the present application inputs environmental information and air-conditioning system load values ​​under different time information and spatial information into a preset three-dimensional convolutional neural network model, so that the input data maintains its original three-dimensional distribution without the need for compression, thereby improving the accuracy of feature extraction and further improving the accuracy of power prediction of the air-conditioning system.

[0075] The location information may be the geographical area where the air conditioning system is located. For example, the geographical area where the air conditioning system is located is determined according to the longitude and latitude of the air conditioning system. The time information may be the date when the air conditioning system is working, so that the average temperature value, average humidity value and air flow velocity value of the location of the air conditioning system are determined according to the weather information of the geographical area where the air conditioning system is working on that day.

[0076] It can be understood that the average temperature value, average humidity value, air flow velocity value and load value of the air-conditioning system are important factors affecting the power of the air-conditioning system. Inputting the above environmental information and air-conditioning system load value into the preset three-dimensional convolutional neural network model can make the output power prediction value of the air-conditioning system closer to the actual power value of the air-conditioning system.

[0077] In some embodiments, when the predicted power value is above the power threshold, the controller 300 sends power warning information to the power grid cloud server that is communicatively connected to the air conditioning system 1 .

[0078] Optionally, the power warning prompt information includes predicted power value.

[0079] In some embodiments, the preset three-dimensional convolutional neural network model includes an input layer, a convolutional neural network layer, an activation layer, a pooling layer, a fully connected layer and an output layer; the input layer is used to input the training sample data into the preset three-dimensional convolutional neural network model, the convolutional neural network layer is used to extract features and generate feature vectors, the activation layer is used to perform nonlinear transformation processing on the feature vectors, the pooling layer is used to reduce the dimension of the feature vectors, the fully connected layer is used to learn the rules in the feature vectors to obtain predicted power values, and the output layer is used to output the predicted power values.

[0080] In other embodiments, the first layer of the preset three-dimensional convolution model in the embodiments of the present application includes 32 convolution kernels, the convolution kernel size is (3,3,3), and the activation function is ReLU; the second layer is 64 three-dimensional convolution kernels, and the activation function is ReLU; the third layer is a pooling layer, which is used to reduce 25% of the data; the fourth layer is a flattening layer, which is used to one-dimensionalize the output of the input multi-dimensional data; the fifth layer is a fully connected layer, and the activation function is a linear activation function.

[0081] As a possible implementation method, the three-dimensional convolutional neural network model in the embodiment of the present application can perform convolution operations from three dimensions, such as Figure 7 As shown, the three-dimensional convolutional neural network model includes a time dimension d1, a space dimension d2, and a feature change dimension d3. The following is constructed based on the time dimension, the space dimension, and the feature change dimension: Figure 7 Schematic diagram of air conditioning data relationship shown.

[0082] Among them, the time dimension represents the time interval for power prediction and the time interval for air-conditioning system data collection. The time interval for power prediction and the time interval for air-conditioning system data collection can be set by the developer at the factory, or by the user according to actual needs. For example, the time interval for power prediction can be 1 day, 2 days, 1 week, etc.; the time interval for air-conditioning system data collection can be 1 week, 1 month, or collected according to the season, which is not limited in this embodiment of the present application. Taking the example of a power prediction time interval of 1 day and a time step of 1 hour, the length of the time dimension d1 is 24 hours. The time step is the time interval between each data point and the previous data point.

[0083] The spatial dimension represents the geographical location information. For example, 1 square kilometer in the location information can be used as a unit grid unit, and the length of the spatial dimension d2 can be 24 grid units.

[0084] The feature change dimension represents information about variables that affect power consumption. For example, the variables that affect power consumption may include one or more of the average temperature value, average humidity value, air flow velocity value, load value of the air conditioning system, and operating power of the air conditioning system in the unit grid.

[0085] In some embodiments, the controller 300 can also be used to obtain historical environmental information of the air-conditioning system, historical air-conditioning system load values, and historical power values ​​corresponding to the historical environmental information, where the historical environmental information includes historical average temperature values, historical average humidity values, and historical air flow velocity values ​​at different locations in different time periods; the historical environmental information and historical air-conditioning system load values ​​are used as training sample data, and the historical power values ​​corresponding to the historical environmental information are used as training sample labels to construct a training sample set; the original three-dimensional convolutional neural network model is trained based on the training sample set to obtain a preset three-dimensional convolutional neural network model.

[0086] Optionally, the memory of the air-conditioning system in the present application stores historical environmental information of the air-conditioning system, historical air-conditioning system load values, historical power values ​​corresponding to the historical environmental information, as well as historical average temperature values, historical average humidity values ​​and historical air flow velocity values ​​at different locations in different time periods.

[0087] As a possible implementation method, in the embodiment of the present application, training the original three-dimensional convolutional neural network model based on the training sample set includes the following steps S101-S105:

[0088] S101. Input the historical environmental information and historical air-conditioning system load values ​​in the training sample set into the original three-dimensional convolutional neural network model to obtain the prediction results (i.e., predicted power values) of the power values ​​corresponding to the historical environmental information and historical air-conditioning load values ​​in the training sample set.

[0089] S102: Determine the loss value according to the prediction result of the power value corresponding to the historical environmental information and the historical air conditioning system load value in the training sample set and the actual power value corresponding to the historical environmental information and the historical air conditioning system load value.

[0090] Optionally, the mean square error between the predicted result of the power value corresponding to the historical environmental information and the historical air-conditioning system load value and the actual power value corresponding to the historical environmental information and the historical air-conditioning system load value is used as the loss value.

[0091] S103. Determine whether the three-dimensional convolutional neural network model has converged according to the loss value of the training sample set.

[0092] S104. If not, update the weight parameters in the original three-dimensional convolutional neural network model according to the loss value of the training sample set, and continue to execute step S101 to input the historical environmental information and historical air-conditioning system load values ​​in the training sample set into the original three-dimensional convolutional neural network model to obtain the prediction results of the power values ​​corresponding to the historical environmental information and historical air-conditioning load values ​​in the training sample set.

[0093] Optionally, the Adam optimizer is used to determine the weight parameters when the model accuracy reaches the accuracy threshold.

[0094] S105: If yes, determine the current three-dimensional convolutional neural network model as a preset three-dimensional convolutional neural network model.

[0095] In some embodiments, the controller 300 may also be used to perform z-score normalization processing on the historical environmental information and the historical air conditioning system load values ​​to remove abnormal values ​​in the historical environmental information and the historical air conditioning system load values.

[0096] As a possible implementation method, the historical environmental information and historical air conditioning system load values ​​can be z-score standardized using the following formula:

[0097]

[0098] Wherein, x is the historical environmental information or the historical air conditioning system load value, x' is the historical environmental information after standardization or the historical air conditioning system load value after standardization, and σ is the standard deviation.

[0099] The controller 300 is a device that can generate an operation control signal according to the instruction operation code and the timing signal to instruct the air conditioning system 1 to execute the control instruction. Exemplarily, the controller 300 can be a central processing unit (CPU), a general-purpose processor network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD) or any combination thereof. The controller 300 can also be other devices with processing functions, such as circuits, devices or software modules, and the embodiments of the present application do not impose any restrictions on this.

[0100] In some embodiments, the controller 300 may be a microcontroller unit (MCU). MCU, also known as a single chip microcomputer or single chip microcomputer, is a computer that appropriately reduces the frequency and specifications of a central processing unit, and integrates peripheral interfaces such as memory, timer, USB, A / D conversion, UART, PLC, DMA, and even LCD driver circuits on a single chip to form a chip-level computer that performs different combination controls for different application scenarios.

[0101] In addition, the controller 300 can be used to control the operation of various components in the air-conditioning system 1 , so that the various components of the air-conditioning system 1 operate to achieve various predetermined functions of the air-conditioning system 1 .

[0102] It is to be understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the air conditioning system. In other embodiments of the present application, the air conditioning system may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0103] Figure 8 This is a schematic diagram of an application scenario of an air conditioning system provided in this application. Figure 8 As shown, the application scenario includes an air conditioning system 100 and an electric power cloud server 200 .

[0104] There is a communication connection between the power cloud server 200 and the air conditioning system 100 .

[0105] In some embodiments, the air conditioning system 100 is a device that regulates and controls parameters such as temperature, humidity, and flow rate of ambient air in a building or structure.

[0106] In some embodiments, the power cloud server 200 can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, big data servers, etc. This application does not impose any special restrictions on the specific form of the power cloud server 200.

[0107] In some embodiments, the air conditioning system 100 can send its own location information, time information and air conditioning system load value to the power cloud server 200, in which a preset three-dimensional convolutional neural network model is deployed. The power cloud server 200 determines the current environmental information of the air conditioning system 100 based on the location information, time information and weather information of the air conditioning system 100, thereby inputting the current environmental information and air conditioning system load value of the air conditioning system 100 into the power cloud server 200 to obtain the predicted power value of the air conditioning system 100.

[0108] Fig. 9 This is another application scenario diagram of an air conditioning system provided in this application. Fig. 9 As shown, the application scenario includes an air conditioning system 400 , a cloud server 500 , and a power cloud server 600 .

[0109] Among them, there is a communication connection between the air conditioning system 400 and the cloud server 500, the cloud server 500 and the power cloud server 600.

[0110] In some embodiments, the air conditioning system 400 is a device that adjusts and controls parameters such as temperature, humidity, and flow rate of the ambient air in a building or structure.

[0111] In some embodiments, the cloud server 500 can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, big data servers, etc. This application does not impose any special restrictions on the specific form of the cloud server 500.

[0112] Optionally, a preset three-dimensional convolutional neural network model is deployed in the cloud server 500.

[0113] In some embodiments, the electric power cloud server 600 may be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data servers. This application does not impose any special restrictions on the specific form of the electric power cloud server 600. Optionally, the electric power cloud server 600 stores power configuration information and power configuration strategies, and after the electric power cloud server 600 receives power warning information, it adjusts the power configuration strategy according to the power configuration information.

[0114] In some embodiments, the air conditioning system 400 can send its own location information, time information and air conditioning system load value to the cloud server 500, in which a preset three-dimensional convolutional neural network model is deployed. The cloud server 500 determines the current environmental information of the air conditioning system 400 based on the location information, time information and weather information of the air conditioning system 400, and then inputs the current environmental information and air conditioning system load value of the air conditioning system 400 into the cloud server 500 to obtain the predicted power value of the air conditioning system 400. Therefore, when the predicted power value is above the power threshold, power warning information is sent to the power cloud server 600.

[0115] Fig.10 The figure shows a schematic diagram of the structure of a cloud server provided by the present application. Fig.10 As shown, the cloud server 500 may include a communication device 501 , a memory 502 and a processor 503 .

[0116] In some embodiments, the communication device 501 is used to establish a communication connection with the air-conditioning system. Through the communication device 501, the cloud server 500 can obtain the location information, time information and load value of the air-conditioning system.

[0117] In other embodiments, the communication device 501 is also used to establish a connection with the power grid cloud server. Through the communication device 501, the cloud server 500 can send the predicted power value and power warning prompt information of the air-conditioning system to the power grid cloud platform.

[0118] The communication device 501 may include a radio frequency (RF) module, a cellular module, a wireless fidelity (WIFI) module, and a GPS module. Taking the RF module as an example, the RF module can be used to receive and send signals, in particular, send the received information to the processor 503 for processing; in addition, send the signal generated by the processor 503. Generally, the RF circuit may include but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, etc.

[0119] In some embodiments, the memory 502 can be used to store software programs and data. The processor 503 executes various functions and data processing of the cloud server 200 by running the software programs or data stored in the memory 502. The memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. The memory 502 stores an operating system that enables the processor 503 to run. In the present application, the memory 502 can store an operating system and various application programs, and can also store code for executing the air conditioning system power early warning method provided in the embodiment of the present application.

[0120] In some embodiments, the processor 503 is used to obtain the location information, time information, weather information and air conditioning system load value of the air conditioning system; based on the location information, time information and weather information, determine the current environmental information of the air conditioning system, the environmental information including one or more of the average temperature value, average humidity value and air flow velocity value of the location of the air conditioning system; based on a preset three-dimensional convolutional neural network model and the environmental information and the air conditioning system load value, determine the predicted power value of the air conditioning system; when the predicted power value is above the power threshold, output power warning prompt information.

[0121] The specific steps and beneficial effects of the processor 503 executing the power warning method for the air-conditioning system in the present application can refer to the steps and beneficial effects of the controller 300 executing the power warning method for the air-conditioning system in the present application, which will not be repeated here.

[0122] In some embodiments, when the predicted power value is above the power threshold, the processor 503 sends power warning prompt information to the power cloud server.

[0123] Optionally, the power warning prompt information includes predicted power value.

[0124] In some embodiments, the processor 503 can be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present disclosure, such as: one or more digital signal processors (DSP), or one or more field programmable gate arrays (FPGA).

[0125] Those skilled in the art will understand that Fig.10The hardware structure shown in the figure does not constitute a limitation on the cloud server. The cloud server may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0126] The following is a detailed introduction to the embodiments of the present application in conjunction with the accompanying drawings.

[0127] like Fig.11 As shown, an embodiment of the present application provides a power early warning method for an air conditioning system, which is applied to a controller of the air conditioning system. The method includes the following steps:

[0128] S1. Obtaining location information, time information, weather information and load value of the air conditioning system.

[0129] S2. Determine current environmental information of the air conditioning system based on location information, time information and weather information.

[0130] The environmental information includes one or more of an average temperature value, an average humidity value, and an air flow velocity value at the location of the air conditioning system.

[0131] S3. Determine the predicted power value of the air-conditioning system based on a preset three-dimensional convolutional neural network model, environmental information, and air-conditioning system load value.

[0132] In some embodiments, the preset three-dimensional convolutional neural network model includes an input layer, a convolutional neural network layer, an activation layer, a pooling layer, a fully connected layer and an output layer; the input layer is used to input the training sample data into the preset three-dimensional convolutional neural network model, the convolutional neural network layer is used to extract features and generate feature vectors, the activation layer is used to perform nonlinear transformation processing on the feature vectors, the pooling layer is used to reduce the dimension of the feature vectors, the fully connected layer is used to learn the rules in the feature vectors to obtain predicted power values, and the output layer is used to output the predicted power values.

[0133] S4. When the predicted power value is above the power threshold, output power warning prompt information.

[0134] Fig.11 The illustrated embodiment brings at least the following beneficial effects: the embodiment of the present application inputs environmental information and air-conditioning system load values ​​under different time information and spatial information into a preset three-dimensional convolutional neural network model, so that the input data maintains its original three-dimensional distribution without the need for compression, thereby improving the accuracy of feature extraction and thereby improving the accuracy of power prediction for the air-conditioning system.

[0135] In some embodiments, after obtaining the location information, time information, weather information and air-conditioning system load value of the air-conditioning system, the power warning method for the air-conditioning system provided in the present application may also include z-score standardization processing of historical environmental information and historical air-conditioning system load values ​​to remove abnormal values ​​in the historical environmental information and historical air-conditioning system load values.

[0136] It can be seen that the above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. To achieve the above functions, the embodiment of the present application provides a hardware structure and / or software module corresponding to each function. Those skilled in the art should easily appreciate that, in combination with the modules and algorithm steps of each example described in the embodiment disclosed herein, the embodiment of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware 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 to exceed the scope of the present invention.

[0137] The embodiment of the present application can divide the controller into functional modules according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. Optionally, the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0138] An embodiment of the present application also provides a computer-readable storage medium, including computer-executable instructions, which, when executed on a computer, enable the computer to execute any one of the power warning methods for an air-conditioning system provided in the above embodiments.

[0139] An embodiment of the present application also provides a computer program product including computer executable instructions, which, when executed on a computer, enables the computer to execute any one of the power warning methods for air-conditioning systems provided in the above embodiments.

[0140] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer-executable instructions. When the computer-executable instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer-executable instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer-executable instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more servers that can be integrated with the medium. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0141] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other changes to the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in a claim. Certain measures are recorded in mutually different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0142] Although the present application is described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0143] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A power early warning method for an air conditioning system, characterized in that: include: Obtaining location information, time information, weather information and air conditioning system load value of the air conditioning system; Based on the location information, the time information and the weather information, determine the current environmental information of the air conditioning system, the environmental information including one or more of an average temperature value, an average humidity value and an air flow velocity value of the location of the air conditioning system; Determine a predicted power value of the air conditioning system based on a preset three-dimensional convolutional neural network model, the environmental information, and the load value of the air conditioning system; When the predicted power value is above the power threshold, power warning prompt information is output.

2. The method according to claim 1, characterized in that The preset three-dimensional convolutional neural network model is obtained by the following steps: Acquire historical environmental information of the air conditioning system, historical air conditioning system load values, and historical power values ​​corresponding to the historical environmental information, wherein the historical environmental information includes historical average temperature values, historical average humidity values, and historical air flow velocity values ​​at different locations in different time periods; The historical environmental information and the historical air conditioning system load values ​​are used as training sample data, and the historical power values ​​corresponding to the historical environmental information are used as training sample labels to construct a training sample set; The original three-dimensional convolutional neural network model is trained based on the training sample set to obtain the preset three-dimensional convolutional neural network model.

3. The method according to claim 2, characterized in that The preset three-dimensional convolutional neural network model includes an input layer, a convolutional neural network layer, an activation layer, a pooling layer, a fully connected layer and an output layer; The input layer is used to input the training sample data into the preset three-dimensional convolutional neural network model, the convolutional neural network layer is used to extract features and generate feature vectors, the activation layer is used to perform nonlinear transformation processing on the feature vectors, the pooling layer is used to reduce the dimension of the feature vectors, the fully connected layer is used to learn the rules in the feature vectors to obtain predicted power values, and the output layer is used to output the predicted power values.

4. The method according to claim 2, characterized in that: After acquiring the historical environmental information of the air conditioning system, the historical air conditioning system load value, and the historical power value corresponding to the historical environmental information, the method further includes: The historical environmental information and the historical air conditioning system load values ​​are subjected to z-score standardization processing to remove abnormal values ​​in the historical environmental information and the historical air conditioning system load values.

5. An air conditioning system, characterized in that: include: Indoor unit; Outdoor unit; The controller is configured as: Obtaining location information, time information, weather information and air conditioning system load value of the air conditioning system; Based on the location information, the time information and the weather information, determine the current environmental information of the air conditioning system, the environmental information including one or more of an average temperature value, an average humidity value and an air flow velocity value of the location of the air conditioning system; Determine a predicted power value of the air conditioning system based on a preset three-dimensional convolutional neural network model, the environmental information, and the load value of the air conditioning system; When the predicted power value is above the power threshold, power warning prompt information is output.

6. The air conditioning system according to claim 5, characterized in that: The preset three-dimensional convolutional neural network model is obtained by the controller executing the following steps: Acquire historical environmental information of the air conditioning system, historical air conditioning system load values, and historical power values ​​corresponding to the historical environmental information, wherein the historical environmental information includes historical average temperature values, historical average humidity values, and historical air flow velocity values ​​at different locations in different time periods; The historical environmental information and the historical air conditioning system load values ​​are used as training sample data, and the historical power values ​​corresponding to the historical environmental information are used as training sample labels to construct a training sample set; The original three-dimensional convolutional neural network model is trained based on the training sample set to obtain the preset three-dimensional convolutional neural network model.

7. The air conditioning system according to claim 6, characterized in that: The preset three-dimensional convolutional neural network model includes an input layer, a convolutional neural network layer, an activation layer, a pooling layer, a fully connected layer and an output layer; The input layer is used to input the training sample data into the preset three-dimensional convolutional neural network model, the convolutional neural network layer is used to extract features and generate feature vectors, the activation layer is used to perform nonlinear transformation processing on the feature vectors, the pooling layer is used to reduce the dimension of the feature vectors, the fully connected layer is used to learn the rules in the feature vectors to obtain predicted power values, and the output layer is used to output the predicted power values.

8. The air conditioning system according to claim 6, characterized in that: After acquiring the historical environment information of the air conditioning system, the historical air conditioning system load value, and the historical power value corresponding to the historical environment information, the controller is further configured to: The historical environmental information and the historical air conditioning system load values ​​are subjected to z-score standardization processing to remove abnormal values ​​in the historical environmental information and the historical air conditioning system load values.

9. A cloud server, characterized in that: include: A communication device, used to establish a communication connection with the air conditioning system; The processor is configured as: Obtaining location information, time information, weather information and air conditioning system load value of the air conditioning system; Based on the location information, the time information and the weather information, determine the current environmental information of the air conditioning system, the environmental information including one or more of an average temperature value, an average humidity value and an air flow velocity value of the location of the air conditioning system; Determine a predicted power value of the air conditioning system based on a preset three-dimensional convolutional neural network model, the environmental information, and the load value of the air conditioning system; When the predicted power value is above the power threshold, power warning prompt information is output.

10. The cloud server according to claim 9, characterized in that: The preset three-dimensional convolutional neural network model is obtained by the following steps: Acquire historical environmental information of the air conditioning system, historical air conditioning system load values, and historical power values ​​corresponding to the historical environmental information, wherein the historical environmental information includes historical average temperature values, historical average humidity values, and historical air flow velocity values ​​at different locations in different time periods; The historical environmental information and the historical air conditioning system load values ​​are used as training sample data, and the historical power values ​​corresponding to the historical environmental information are used as training sample labels to construct a training sample set; The original three-dimensional convolutional neural network model is trained based on the training sample set to obtain the preset three-dimensional convolutional neural network model.