Anti-condensation control method, air conditioning system and computer readable storage medium

Abstract

The invention discloses an anti-condensation control method, an air conditioning system and a computer readable storage medium, and relates to the technical field of air conditioners. After the server receives prediction request information from the target air conditioner, the air conditioner model, the current operation mode, the current evaporator temperature, the current indoor temperature, the current indoor fan speed and the current indoor humidity are input into the condensation prediction model, and a first prediction result is obtained. The first prediction result is used for representing whether condensation of the target air conditioner is about to occur or not. And when the first prediction result represents that the target air conditioner is about to generate condensation, the target air conditioner adjusts the rotating speed of a compressor so as to reduce the temperature of an evaporator of the target air conditioner, and therefore the risk of condensation of the air conditioner is reduced. Therefore, whether condensation of the air conditioner is about to occur or not can be predicted, the prediction accuracy is high, and when it is predicted that condensation of the air conditioner is about to occur, the rotating speed of the compressor of the air conditioner is adjusted in time, so that the risk of condensation of the air conditioner is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of air conditioners, in particular to a condensation control method, an air conditioning system and a computer readable storage medium. BACKGROUND

[0002] In the running process of an air conditioner, under the joint action of factors such as indoor temperature, evaporator temperature of the air conditioner, indoor humidity and specific mechanical structure of the air conditioner, condensation and dripping water may easily occur, such as water condensing on the surface of the structure of the air conditioner and dripping, or water droplets being blown out with circulating air during the running process, causing bad experience for users. In related technologies, the solution is usually to control the running of the air conditioner after detecting condensation and dripping water of the air conditioner. At present, there is an urgent need for a condensation control method capable of predicting condensation of the air conditioner. SUMMARY

[0003] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, the present application proposes a condensation control method, an air conditioning system and a computer readable storage medium, which can predict whether the air conditioner is about to condense, so as to timely adjust the compressor speed of the air conditioner, thereby reducing the risk of condensation of the air conditioner.

[0004] The condensation control method according to the first aspect of the present application is applied to an air conditioning system, the air conditioning system comprising a server and a plurality of air conditioners, the server being in communication connection with the plurality of air conditioners, and a condensation prediction model being deployed on the server and being pre-trained;

[0005] The method comprises:

[0006] The target air conditioner periodically acquires the air conditioner model, the current running mode, the current evaporator temperature, the current indoor temperature, the current indoor fan speed and the current indoor temperature of the target air conditioner; the target air conditioner being one of the plurality of air conditioners;

[0007] The target air conditioner generates prediction request information based on the air conditioner model, the current running mode, the current evaporator temperature, the current indoor temperature, the current indoor fan speed and the current indoor temperature;

[0008] The target air conditioner sends the prediction request information to the server;

[0009] The server receives the prediction request information sent by the target air conditioner, and inputs the air conditioner model, the current running mode, the current evaporator temperature, the current indoor temperature, the current indoor fan speed and the current indoor humidity into the condensation prediction model to obtain a first prediction result;

[0010] The server sends the first prediction result to the target air conditioner;

[0011] The target air conditioner receives the first prediction result sent by the server, and adjusts the compressor speed of the target air conditioner to reduce the temperature of the evaporator of the target air conditioner when it is detected that the first prediction result indicates that the target air conditioner is about to condense.

[0012] According to the condensation prevention control method, the server receives the prediction request information from the target air conditioner, inputs the air conditioner model, the current running mode, the current evaporator temperature, the current indoor temperature, the current indoor fan speed and the current indoor humidity into the condensation prediction model to obtain a first prediction result. The first prediction result is used to indicate whether the target air conditioner is about to condense. When the first prediction result indicates that the target air conditioner is about to condense, the target air conditioner adjusts the compressor speed to reduce the temperature of the evaporator of the target air conditioner, thereby reducing the risk of condensation of the air conditioner. Therefore, the present application can predict whether the air conditioner is about to condense, and the prediction accuracy is high. When it is predicted that the air conditioner is about to condense, the compressor speed of the air conditioner is adjusted in time, thereby reducing the risk of condensation of the air conditioner.

[0013] According to some embodiments of the first aspect of the present application, further comprising:

[0014] The target air conditioner acquires the pre-condensation evaporator temperature, the pre-condensation running mode, the pre-condensation indoor temperature, the pre-condensation indoor fan speed and the pre-condensation indoor humidity before a preset time period in response to detecting that the target air conditioner condenses;

[0015] The target air conditioner generates pre-condensation state information based on the air conditioner model, the pre-condensation running mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed and the pre-condensation indoor humidity;

[0016] The target air conditioner sends the pre-condensation state information to the server;

[0017] The server receives the pre-condensation state information sent by the target air conditioner, and inputs the air conditioner model, the pre-condensation running mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed and the pre-condensation indoor humidity into the condensation prediction model to obtain a second prediction result;

[0018] The server calculates a loss value based on the second prediction result and a loss function;

[0019] The server updates the condensation prediction model based on the loss value.

[0020] According to some embodiments of the first aspect of the application, the condensation prediction model comprises a feature extraction module, a residual module, a long short-term memory module, and a classifier.

[0021] The inputting the air conditioner model, the pre-condensation operation mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed, and the pre-condensation indoor humidity into the condensation prediction model to obtain a second prediction result comprises:

[0022] The server constructs a first input vector based on the air conditioner model, the pre-condensation operation mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed, and the pre-condensation indoor humidity.

[0023] The server performs feature extraction processing on the first input vector through the feature extraction module to obtain a first input feature.

[0024] The server performs residual processing on the first input feature through the residual module to obtain a first residual feature.

[0025] The server inputs the first residual feature into the long short-term memory module to obtain a first updated feature.

[0026] The server inputs the first updated feature into the classifier to obtain the second prediction result.

[0027] According to some embodiments of the first aspect of the application, the adjusting the compressor speed of the target air conditioner comprises:

[0028] The target air conditioner determines a reference temperature based on the current indoor temperature and a preset temperature coefficient.

[0029] The target air conditioner obtains a current compressor speed of the target air conditioner, determines a target speed based on the current evaporator temperature, the reference temperature, and the current compressor speed.

[0030] The target air conditioner sets the compressor speed of the target air conditioner to the target speed.

[0031] According to some embodiments of the first aspect of the application, after the target air conditioner sets the compressor speed of the target air conditioner to the target speed, the method comprises:

[0032] In a case where it is detected that the target speed is greater than a preset threshold, the target air conditioner reduces the indoor fan speed of the target air conditioner.

[0033] The target air conditioner controls the air outlet direction of the target air conditioner to be upward air outlet.

[0034] According to some embodiments of the first aspect of the present application, the pre-training step of the condensation prediction model comprises:

[0035] The server obtains a test sample and a true label corresponding to the test sample, wherein the test sample comprises a test air conditioner model, a test running mode, a test evaporator temperature, a test indoor temperature, a test indoor fan speed, and a test indoor humidity.

[0036] The server inputs the test air conditioner model, the test running mode, the test evaporator temperature, the test indoor temperature, the test indoor fan speed, and the test indoor humidity into the initial condensation prediction model to obtain a training prediction result.

[0037] The server calculates a training loss value based on the training prediction result and the loss function.

[0038] The server iteratively updates the condensation prediction model based on the training loss value until the number of iterations reaches a preset iteration threshold to obtain the pre-trained condensation prediction model.

[0039] According to some embodiments of the first aspect of the present application, the server inputs the test air conditioner model, the test running mode, the test evaporator temperature, the test indoor temperature, the test indoor fan speed, and the test indoor humidity into the initial condensation prediction model to obtain a training prediction result, comprising:

[0040] The server constructs a second input vector based on the test air conditioner model, the test running mode, the test evaporator temperature, the test indoor temperature, the test indoor fan speed, and the test indoor humidity.

[0041] The server performs feature extraction processing on the second input vector through the feature extraction module to obtain a second input feature.

[0042] The server performs residual processing on the second input feature through the residual module to obtain a second residual feature.

[0043] The server inputs the second residual feature into the long short-term memory module to obtain a second updated feature.

[0044] The server inputs the second updated feature into the classifier to obtain the training prediction result.

[0045] According to some embodiments of the first aspect of the present application, the loss function is a cross-entropy function.

[0046] The second aspect embodiment of the present application provides an air conditioning system, the air conditioning system comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the anti-condensation control method of any one of the first aspect embodiments.

[0047] The third aspect embodiment of the present application provides a computer readable storage medium, the storage medium storing a computer program, and the computer program being executed by a processor to implement the anti-condensation control method of any one of the first aspect embodiments.

[0048] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0049] The present application will be further described below in conjunction with the accompanying drawings and embodiments, in which:

[0050] Figure 1 FIG. 1 is a structural schematic diagram of an air conditioning system according to an embodiment of the present application;

[0051] Figure 2 FIG. 2 is a step flow schematic diagram of an anti-condensation control method according to an embodiment of the present application;

[0052] Figure 3 FIG. 3 is another flow schematic diagram of an anti-condensation control method according to an embodiment of the present application;

[0053] Figure 4 FIG. 4 is a structural schematic diagram of a condensation prediction model according to an embodiment of the present application;

[0054] Figure 5 FIG. 5 is a pre-training step schematic diagram of a condensation prediction model according to an embodiment of the present application;

[0055] Figure 6 FIG. 6 is a specific flow schematic diagram of step S260 in FIG. 2 according to an embodiment of the present application; Figure 2

[0056] FIG. 7 is another specific flow schematic diagram after step S260 in FIG. 2 according to an embodiment of the present application; Figure 7 Figure 2

[0057] Figure 8 FIG. 8 is a hardware module block diagram of an air conditioning system according to an embodiment of the present application. DETAILED DESCRIPTION

[0058] ​​Embodiments of the present application are described below in the detailed description and illustrated in the accompanying drawings by various drawings for example. Identical or similar components or components having identical or similar functions are denoted by the same or similar reference numerals throughout the various drawings. The embodiments described below in the detailed description are exemplary only, and are not intended to limit the present application.

[0059] In the description of the present application, it should be understood that the orientation description, such as the orientation or position relationship indicated by up, down, front, back, left, right, etc. is based on the orientation or position relationship shown in the drawings, and is only for the purpose of facilitating the description of the present application and simplifying the description, and is not intended to indicate or imply that the device or component referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.

[0060] In the description of the present application, if the meaning of several is more than one, the meaning of multiple is more than two, greater than, less than, more than, etc. is understood as not including the number, above, below, etc. is understood as including the number. If it is described as first, second, it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or the order of indicated technical features.

[0061] In the description of the present application, unless otherwise explicitly limited, the words such as setting, installing, connecting, etc. should be broadly understood, and the person skilled in the art can reasonably determine the specific meaning of the above words in the present application in combination with the specific content of the technical solution.

[0062] In the description of the present application, the description of the terms "one embodiment", "some embodiments", "exemplary embodiment", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in combination with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the exemplary description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0063] In the running process of an air conditioner, under the joint action of factors such as indoor temperature, evaporator temperature of the air conditioner, indoor humidity, and specific mechanical structure of the air conditioner, the air conditioner is prone to condensation and water dripping, such as water condensation on the surface of the air conditioner structure and dripping, or water droplets blowing out with circulating air during the running process, causing adverse experience to the user. In the related technology, the solution is usually to control the running of the air conditioner after detecting the condensation and water dripping of the air conditioner. Moreover, since the environment of each air conditioner is different, the specific mechanical structure of different models of air conditioners also has slight differences, therefore, it is difficult to predict the condensation of different models of air conditioners and timely adjust the running of the air conditioner. At present, there is an urgent need for a control method that can prevent condensation of different models of air conditioners.

[0064] Based on this, the embodiment of the present application provides a condensation prevention control method, an air conditioning system and a computer readable storage medium. The condensation prevention prediction model is used to predict different models of air conditioners to predict whether the air conditioner will condense. When it is predicted that the air conditioner will condense, the compressor speed of the air conditioner is adjusted in time, so as to reduce the risk of condensation of the air conditioner. Moreover, during the running process of multiple air conditioners, when the air conditioner condenses, the server updates the condensation prediction model according to the condensation state information of the air conditioner before condensation. Thus, the condensation prediction model is constantly updated, which can constantly improve the prediction accuracy of the condensation prediction model.

[0065] Reference Figure 1 , Figure 1 is a structural schematic diagram of the air conditioning system of the embodiment of the present application. The air conditioning system includes a server and multiple air conditioners. The server can be a server or a central computer. The server is in communication connection with the multiple air conditioners. For example, an Internet module such as a wifi module can be arranged in the air conditioner, and the air conditioner is connected with the server through the Internet module. Each air conditioner periodically generates prediction request information, and then the air conditioner sends the prediction request information to the server. The server obtains a first prediction result through the condensation prediction model based on the prediction request information, and the first prediction result represents whether the air conditioner will condense. In the present application, the condensation prediction model is deployed in the server, that is, the prediction process of the model is executed in the server, and the complex calculation involved in the prediction process is performed in the server. One server serves multiple air conditioners, so that the air conditioner does not need to perform complex calculation and does not need to consume more computing resources, and the cost of the air conditioner can be reduced.

[0066] It should be noted that the server can be a server, and the server refers to a computer system capable of providing certain services to the air conditioner. Compared with ordinary terminals, servers have higher requirements in stability, security, performance, etc. The server can be a high-performance computer in a network platform, a cluster of multiple high-performance computers, a part of a high-performance computer (such as a virtual machine), a combination of a part of multiple high-performance computers (such as a virtual machine), etc.

[0067] The first aspect embodiment of the present application provides a condensation control method, which is applied to Figure 1 An air conditioning system is shown. Referring to Figure 2 , Figure 2 is a step flow diagram of the condensation control method of the embodiment of the present application. The condensation control method of the present application includes but is not limited to the following steps:

[0068] Step S210, the target air conditioner periodically acquires the air conditioner model, the current running mode, the current evaporator temperature, the current indoor temperature, the current indoor fan speed and the current indoor temperature of the target air conditioner; the target air conditioner is one of the plurality of air conditioners;

[0069] It should be noted that the target air conditioner is one of the plurality of air conditioners in communication connection with the server. In general, different air conditioners have different models, and different models of air conditioners have different mechanical structures. The present application takes the air conditioner model as the input of the condensation prediction model, which can improve the accuracy of the condensation prediction model. The current running mode refers to the current working mode of the target air conditioner; the current evaporator temperature refers to the current surface temperature of the evaporator of the target air conditioner; the current indoor temperature refers to the current temperature of the room where the target air conditioner is located; the current indoor fan speed refers to the speed of the indoor fan of the target air conditioner; and the current indoor humidity refers to the current humidity of the room where the target air conditioner is located.

[0070] Step S220, the target air conditioner generates prediction request information based on the air conditioner model, the current running mode, the current evaporator temperature, the current indoor temperature, the current indoor fan speed and the current indoor temperature;

[0071] Step S230, the target air conditioner sends the prediction request information to the server;

[0072] Step S240, the server receives the prediction request information sent by the target air conditioner, and inputs the air conditioner model, the current running mode, the current evaporator temperature, the current indoor temperature, the current indoor fan speed and the current indoor humidity into the condensation prediction model to obtain a first prediction result;

[0073] Step S250, the server sends the first prediction result to the target air conditioner;

[0074] Step S260, the target air conditioner receives the first prediction result sent by the server, and in a case where it is detected that the first prediction result represents that the target air conditioner is about to condense, the compressor speed of the target air conditioner is adjusted to reduce the temperature of the evaporator of the target air conditioner.

[0075] It is worth noting that according to the anti-condensation control method of the embodiment of the present application, through the above steps S210 to S260, after the server receives the prediction request information from the target air conditioner, the air conditioner model, the current running mode, the current evaporator temperature, the current indoor temperature, the current indoor fan speed and the current indoor humidity are input into the condensation prediction model to obtain the first prediction result. The first prediction result is used to represent whether the target air conditioner is about to condense. When the first prediction result represents that the target air conditioner is about to condense, the compressor speed of the target air conditioner is adjusted to reduce the temperature of the evaporator of the target air conditioner, thereby reducing the risk of condensation of the air conditioner. Therefore, the present application can predict whether the air conditioner is about to condense, and the prediction accuracy is relatively high. When it is predicted that the air conditioner is about to condense, the compressor speed of the air conditioner is adjusted in time, thereby reducing the risk of condensation of the air conditioner.

[0076] In some embodiments, with reference to Figure 3 , Figure 3 Another flowchart of the anti-condensation control method of the embodiment of the present application. Figure 3 The schematic flowchart includes steps S310 to S360.

[0077] Step S310, in response to detecting that the target air conditioner condenses, the target air conditioner obtains the condensation-preceding evaporator temperature, the condensation-preceding running mode, the condensation-preceding indoor temperature, the condensation-preceding indoor fan speed and the condensation-preceding indoor humidity before a preset time period;

[0078] In some embodiments, the target air conditioner is provided with a sensor for detecting whether the air outlet drips water, for example, a humidity sensor for detecting the humidity of the surface of the relevant structure of the air outlet. When the humidity sensor detects that the humidity is greater than a preset humidity threshold, it indicates that the air conditioner has condensation. The evaporator temperature before the condensation occurs is obtained as the evaporator temperature before condensation, the indoor temperature before the condensation occurs is obtained as the indoor temperature before condensation, the indoor fan speed before the condensation occurs is obtained as the indoor fan speed before condensation, the indoor humidity before the condensation occurs is obtained as the indoor humidity before condensation, and the operation mode before the condensation occurs is obtained as the operation mode before condensation. For example, the preset time period is 3 minutes, and the evaporator temperature before 3 minutes of the condensation occurs is obtained as the evaporator temperature before condensation, the indoor temperature before 3 minutes of the condensation occurs is obtained as the indoor temperature before condensation, the indoor fan speed before 3 minutes of the condensation occurs is obtained as the indoor fan speed before condensation, the indoor humidity before 3 minutes of the condensation occurs is obtained as the indoor humidity before condensation, and the operation mode before 3 minutes of the condensation occurs is obtained as the operation mode before condensation.

[0079] It should be noted that the preset time period is not limited in the embodiments of the present application, and the value of the preset time period can be set according to the actual situation by those skilled in the art.

[0080] In other embodiments, when the user finds that the target air conditioner has condensation and dripping water, the user operates the terminal connected to the target air conditioner. The terminal obtains the air conditioner model, the operation mode before condensation, the evaporator temperature before condensation, the indoor temperature before condensation, the indoor fan speed before condensation, and the indoor humidity before condensation from the target air conditioner in response to the operation instruction of the user, and then sends the state information before condensation including the air conditioner model, the operation mode before condensation, the evaporator temperature before condensation, the indoor temperature before condensation, the indoor fan speed before condensation, and the indoor humidity before condensation to the server. The terminal can be a mobile phone, a notebook computer, a tablet computer, a smart watch, or the like.

[0081] In step S320, the target air conditioner generates the state information before condensation based on the air conditioner model, the operation mode before condensation, the evaporator temperature before condensation, the indoor temperature before condensation, the indoor fan speed before condensation, and the indoor humidity before condensation.

[0082] In step S330, the target air conditioner sends the state information before condensation to the server.

[0083] At step S340, the server receives the pre-condensation state information sent by the target air conditioner, inputs the air conditioner model, the pre-condensation operation mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed and the pre-condensation indoor humidity into the condensation prediction model, and obtains a second prediction result;

[0084] At step S350, the server calculates a loss value based on the second prediction result and a loss function.

[0085] At step S360, the server updates the condensation prediction model based on the loss value.

[0086] Notably, through the above steps S310 to S360, when the target air conditioner condenses, the target air conditioner sends the pre-condensation state information to the server, the server inputs the air conditioner model, the pre-condensation operation mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed and the pre-condensation indoor humidity into the condensation prediction model, and obtains a second prediction result; a loss value is calculated based on the second prediction result and a loss function; the condensation prediction model is updated based on the loss value. In this way, the condensation prediction model is updated, and the prediction accuracy of the condensation prediction model can be continuously improved. Therefore, the present application can predict whether the air conditioner will condense, and the prediction accuracy is high. When it is predicted that the air conditioner will condense, the compressor speed of the air conditioner is adjusted in time, thereby reducing the risk of condensation of the air conditioner.

[0087] In some embodiments, with reference to Figure 4 , Figure 4 is a structural schematic diagram of the condensation prediction model. The condensation prediction model includes a feature extraction module, a residual module, a long short-term memory module and a classifier; and step S340 specifically includes steps S410 to S450.

[0088] At step S410, the server constructs a first input vector based on the air conditioner model, the pre-condensation operation mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed and the pre-condensation indoor humidity.

[0089] Notably, since the air conditioner model, the pre-condensation operation mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed and the pre-condensation indoor humidity cannot be directly used as the input of the neural network model, the air conditioner model, the pre-condensation operation mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed and the pre-condensation indoor humidity need to be converted into a sequence vector, so as to construct the first input vector, and the first input vector is input into the condensation prediction model in the subsequent process.

[0090] At step S420, the service end performs feature extraction processing on the first input vector through a feature extraction module to obtain first input features;

[0091] It is worth noting that the feature extraction module can be a convolution block, and the first input vector is convoluted through the convolution block to achieve feature extraction processing and obtain the first input features.

[0092] At step S430, the service end performs residual processing on the first input features through a residual module to obtain first residual features;

[0093] In some embodiments, the residual module includes a plurality of residual blocks connected in sequence, and the residual processing is residual connection processing of the plurality of residual blocks in sequence. It should be noted that the residual block is mainly used to solve the gradient vanishing and degradation problem in deep neural network training. Its structure includes a convolution layer, batch normalization, an activation function, and a skip connection. The skip connection directly adds the input to the output to form a residual mapping, making it easier for the network to learn the identity mapping, thereby alleviating the gradient vanishing. When the input and output dimensions are the same, they are directly added; when the dimensions are different, a 1x1 convolution is used to adjust the input dimension to ensure matching. The activation function is usually applied after addition to enhance the non-linear expression capability. The residual block learns the difference between the input and output through residual learning, reducing the optimization difficulty, supporting the training of deeper networks, and improving performance. The number of residual blocks is not specifically limited in the present application, and those skilled in the art can set the number of residual blocks according to actual conditions.

[0094] At step S440, the service end inputs the first residual features to a long short-term memory module to obtain first updated features;

[0095] It should be noted that the Long Short-Term Memory (LSTM) is a special recurrent neural network (RNN) designed to address the long-term dependency problem encountered by RNN when processing long sequence data. LSTM is a time recurrent neural network that can remember values of indefinite length through its unique structure design, and effectively handle long-term dependencies in time series data. LSTM introduces three gating mechanisms (forget gate, input gate, and output gate) and a memory cell (also known as cell state) to control information storage and deletion. These gating mechanisms are composed of sigmoid and tanh functions, which calculate a real number vector between 0 and 1 to determine the degree of information passing. Through the design of gating mechanisms and cell state, LSTM effectively solves the gradient vanishing or explosion problem encountered by RNN when processing long sequence data, thereby capturing long-term dependencies in sequences. Although the first input vector in the embodiment of the present application is a non-time sequence, the first input vector in the embodiment of the present application includes a lot of information (air conditioner model, pre-condensation running mode, pre-condensation evaporator temperature, pre-condensation indoor temperature, pre-condensation indoor fan speed, and pre-condensation indoor humidity), and these information has context information and dependency relationship. The first input vector can be regarded as a long time sequence, so the to-be-extracted vector in the embodiment of the present application is suitable for regression prediction by LSTM, and the dependency relationship between the air conditioner model, the pre-condensation running mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed, and the pre-condensation indoor humidity can be captured by LSTM.

[0096] In step S450, the server inputs the first updated feature into the classifier to obtain a second prediction result.

[0097] In an embodiment, a Softmax function is used as the classifier. The Softmax function can convert the original output into a probability distribution, so that the output value of each class is between 0 and 1, and the sum of the probabilities of all classes is 1. Compared with other normalization methods such as simple maximum normalization, the Softmax function is more stable in numerical value. When the input value is large or small, the Softmax function can avoid the problem of numerical overflow or underflow, thereby ensuring the stability and accuracy of the model. The calculation of the Softmax function is relatively simple and can be efficiently calculated through vectorization. This makes it possible to reduce the calculation time and resource consumption when training large-scale data sets.

[0098] In some embodiments, the loss function uses a cross-entropy loss function.

[0099] Correspondingly, in step S360, the second prediction result and the real label used to represent that the air conditioner is about to condense are input into a cross-entropy loss function to obtain a loss value, and the condensation prediction model is updated based on the loss value.

[0100] In some embodiments, with reference to Figure 5 , Figure 5 A pre-training step diagram of the condensation prediction model of the embodiments of the present application. The pre-training step of the condensation prediction model comprises:

[0101] In step S510, the server obtains a test sample and a real label corresponding to the test sample. The test sample includes a test air conditioner model, a test running mode, a test evaporator temperature, a test indoor temperature, a test indoor fan speed, and a test indoor temperature.

[0102] In step S520, the server inputs the test air conditioner model, the test running mode, the test evaporator temperature, the test indoor temperature, the test indoor fan speed, and the test indoor temperature into the initial condensation prediction model to obtain a training prediction result.

[0103] In step S530, the server calculates a training loss value based on the training prediction result and a loss function.

[0104] In step S540, the server iteratively updates the condensation prediction model based on the training loss value until the number of iterations reaches a preset iteration threshold, obtaining a pre-trained condensation prediction model.

[0105] It is worth noting that the initial condensation prediction model is pre-trained based on the test sample and the real label corresponding to the test sample. The test sample can be obtained by relevant personnel executing different running instructions on different air conditioners, and the real label is used to represent that the air conditioner is about to condense or that the air conditioner will not condense. The test sample includes an air conditioner model, a running mode, an evaporator temperature, an indoor temperature, an indoor fan speed, and an indoor humidity. The test sample is input into the condensation prediction model to obtain a training prediction result. The training prediction result and the real label corresponding to the test data are input into a loss function to obtain a training loss value, and the condensation prediction model is updated based on the training loss value. In this way, the parameter set of the condensation prediction model is iteratively updated until the number of updates reaches a preset iteration threshold, and the obtained condensation prediction model is a pre-trained condensation prediction model.

[0106] In some embodiments, step S520 specifically comprises steps S521 to S525.

[0107] In step S521, the server constructs a second input vector based on the test air conditioner model, the test running mode, the test evaporator temperature, the test indoor temperature, the test indoor fan speed, and the test indoor humidity.

[0108] It is worth noting that since the test air conditioner model, the test running mode, the test evaporator temperature, the test indoor temperature, the test indoor fan speed and the test indoor humidity cannot be directly taken as the input of the neural network model, it is necessary to convert the test air conditioner model, the test running mode, the test evaporator temperature, the test indoor temperature, the test indoor fan speed and the test indoor humidity into a sequence vector, so as to obtain the second input vector, and the subsequent process inputs the second input vector into the condensation prediction model.

[0109] In step S522, the server performs feature extraction processing on the second input vector through the feature extraction module to obtain a second input feature;

[0110] In step S523, the server performs residual processing on the second input feature through the residual module to obtain a second residual feature;

[0111] In step S524, the server inputs the second residual feature into the long short-term memory module to obtain a second updated feature;

[0112] In step S525, the server inputs the second updated feature into the classifier to obtain a training prediction result.

[0113] In some embodiments, with reference to Figure 6 , Figure 6 For Figure 2 a specific flowchart of step S260. The adjustment of the compressor speed of the target air conditioner in step S26 includes steps S610 to S630.

[0114] In step S610, the target air conditioner determines a reference temperature based on the current indoor temperature and a preset temperature coefficient;

[0115] In step S620, the target air conditioner obtains the current compressor speed of the target air conditioner, and determines a target speed based on the current evaporator temperature, the reference temperature and the current compressor speed;

[0116] In step S630, the target air conditioner sets the speed of the compressor of the target air conditioner to the target speed.

[0117] Specifically, the reference temperature is DCTUYU, and if the current evaporator temperature < DCTUYU, then:

[0118] f1 = f0 - fx;

[0119] If the current evaporator temperature < (DCTUYU + TUYUDC1), and TUYUDC1 is a first preset coefficient, then:

[0120] f1 = f0;

[0121] If (DCTUYU+TUYUDC2)>(current evaporator temperature)>(DCTUYU+TUYUDC1), TUYUDC2 is a second preset coefficient, then there is:

[0122] f1=f0+fx;

[0123] If (current evaporator temperature)>(DCTUYU+TUYUDC2), then there is:

[0124] f1=120;

[0125] f1 is a target rotating speed, f0 is a current compressor rotating speed, and fx is a preset value. The calculation of the reference temperature is as follows:

[0126] DCTUYU=ATUYU+BTUYU*TR;

[0127] wherein ATUYU is a temperature constant, BTUYU is a temperature coefficient, and TR is a current indoor temperature.

[0128] In some embodiments, if the current indoor temperature is greater than 27 degrees Celsius, TR is fixed at 27.

[0129] In an embodiment, TUYUDC1=0, TUYUDC2=2, and fx=3. A person skilled in the art can set the values of TUYUDC1, TUYUDC2, fx, ATUYU, and BTUYU according to actual needs.

[0130] In some embodiments, the reference temperature is calculated according to the following formula: Figure 7 , Figure 7 is Figure 2 a specific flowchart after step S260 in FIG. 8. After the target air conditioner sets the rotating speed of the compressor of the target air conditioner to the target rotating speed, steps S710 and S720 are included.

[0131] Step S710: In the case where the target rotating speed is greater than a preset threshold, the target air conditioner reduces the rotating speed of the indoor fan of the target air conditioner.

[0132] Step S720: The target air conditioner controls the air outlet direction of the target air conditioner to be upward air outlet.

[0133] For example, in the cooling mode, since the target rotating speed is greater than the preset threshold, it indicates that the current air conditioner has strong cooling capacity. At this time, the cold air blown by the air conditioner may cause human body discomfort, so the rotating speed of the indoor fan of the air conditioner is reduced, and the air outlet direction of the air conditioner is controlled to be upward air outlet, thereby avoiding the discomfort of the cold air to the human body.

[0134] The second aspect embodiment of the present application provides an air conditioning system, the air conditioning system comprising a memory and a processor, the memory storing a computer program, and the processor implementing the anti-condensation control method of the above embodiments when executing the computer program.

[0135] In an embodiment, referring to Figure 8 , Figure 8 The hardware module block diagram of the air conditioning system of the embodiment of the present application is illustrated, and the air conditioner comprises:

[0136] The processor 801 can be implemented in the form of a general-purpose CPU (Central Processing Unit, central processor), a microprocessor, an ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), or one or more integrated circuits, etc., for executing related programs to implement the technical solutions provided by the embodiments of the present application;

[0137] The memory 802 can be implemented in the form of a ROM (ReadOnly Memory, read-only memory), a static storage device, a dynamic storage device, or a RAM (Random Access Memory, random access memory), etc. The memory 802 can store an operating system and other application programs, and when the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are saved in the memory 802 and called and executed by the processor 801 to implement the anti-condensation control method of the embodiments of the present application;

[0138] The input / output interface 803 is used to realize information input and output;

[0139] The communication interface 804 is used to realize the communication interaction between the device and other devices, which can realize communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0140] The bus 805 transmits information between various components (such as the processor 801, the memory 802, the input / output interface 803, and the communication interface 804) of the device;

[0141] The processor 801, the memory 802, the input / output interface 803, and the communication interface 804 are connected to each other through the bus 805 for communication within the device.

[0142] The third aspect embodiment of the present application is a computer readable storage medium, which stores a computer program, and the computer program is executed by the processor to implement the anti-condensation control method of the first aspect embodiment.

[0143] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include a high-speed random access memory and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory that is remotely disposed relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0144] The embodiments described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0145] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and can include more or fewer steps than shown in the figures, or combine certain steps or different steps.

[0146] The device embodiments described above are only schematic, and units described as separate components can or can not be physically separate, i.e., can be located in one place or distributed over multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0147] Those skilled in the art can understand that all or some of the steps in the above disclosed method, the functional modules / units in the system and the device can be implemented as software, firmware, hardware and their appropriate combinations.

[0148] The terms "first", "second", "third", "fourth" and the like used in the description of the present application and the above drawings (if any) are used to distinguish similar objects, and do not necessarily have to describe a particular order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0149] It should be understood that, in the application, "at least one" refers to one or more, and "multiple" refers to two or more. "And / or" is used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, "A and / or B" can represent three cases of only A, only B, and A and B existing at the same time, wherein A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can represent a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, and c can be single or multiple.

[0150] In several embodiments provided in the application, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiments described above are only illustrative, for example, the division of the above units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0151] The units described above as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment scheme.

[0152] In addition, the functional units in each embodiment of the application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0153] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.

[0154] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, and are not limited to the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A condensation-preventing control method characterized by, The application is applied to an air conditioning system, the air conditioning system comprises a server and a plurality of air conditioners, the server is in communication connection with the plurality of air conditioners, and a pre-trained condensation prediction model is deployed on the server; The method comprises: The target air conditioner periodically acquires an air conditioner model, a current operation mode, a current evaporator temperature, a current indoor temperature, a current indoor fan speed and a current indoor temperature of the target air conditioner; the target air conditioner is one of the plurality of air conditioners; The target air conditioner generates prediction request information based on the air conditioner model, the current operation mode, the current evaporator temperature, the current indoor temperature, the current indoor fan speed and the current indoor temperature; The target air conditioner sends the prediction request information to the server; The server receives the prediction request information sent by the target air conditioner, and inputs the air conditioner model, the current operation mode, the current evaporator temperature, the current indoor temperature, the current indoor fan speed and the current indoor humidity into the condensation prediction model to obtain a first prediction result; The server sends the first prediction result to the target air conditioner; The target air conditioner receives the first prediction result sent by the server, and adjusts the compressor speed of the target air conditioner to reduce the temperature of the evaporator of the target air conditioner when detecting that the first prediction result represents that the target air conditioner will soon condense.

2. The anti-condensation control method according to claim 1, characterized by, Further comprising: The target air conditioner acquires a pre-condensation evaporator temperature, a pre-condensation operation mode, a pre-condensation indoor temperature, a pre-condensation indoor fan speed and a pre-condensation indoor humidity before a preset time period in response to detecting that the target air conditioner condenses; The target air conditioner generates pre-condensation state information based on the air conditioner model, the pre-condensation operation mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed and the pre-condensation indoor humidity; The target air conditioner sends the pre-condensation state information to the server; The server receives the pre-condensation state information sent by the target air conditioner, and inputs the air conditioner model, the pre-condensation operation mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed and the pre-condensation indoor humidity into the condensation prediction model to obtain a second prediction result; The server calculates a loss value based on the second prediction result and a loss function; The server updates the condensation prediction model based on the loss value.

3. The anti-condensation control method according to claim 2, characterized by, The condensation prediction model comprises a feature extraction module, a residual module, a long short-term memory module and a classifier; The inputting of the air conditioner model, the pre-condensation operation mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed and the pre-condensation indoor humidity into the condensation prediction model to obtain the second prediction result comprises: The server constructs a first input vector based on the air conditioner model, the pre-condensation operation mode, the pre-condensation evaporator temperature, the pre-condensation indoor temperature, the pre-condensation indoor fan speed, and the pre-condensation indoor humidity. The server performs feature extraction processing on the first input vector through the feature extraction module to obtain first input features. The server performs residual processing on the first input features through the residual module to obtain first residual features. The server inputs the first residual features into the long short-term memory module to obtain first updated features. The server inputs the first updated features into the classifier to obtain the second prediction result.

4. The anti-condensation control method according to claim 1, characterized by, The adjustment of the compressor speed of the target air conditioner includes: The target air conditioner determines a reference temperature based on the current indoor temperature and a preset temperature coefficient; The target air conditioner obtains the current compressor speed of the target air conditioner, and determines a target speed based on the current evaporator temperature, the reference temperature, and the current compressor speed; The target air conditioner sets the compressor speed of the target air conditioner to the target speed.

5. The anti-condensation control method according to claim 4, characterized by, After the target air conditioner sets the compressor speed of the target air conditioner to the target speed, it includes: In the case where the target speed is greater than a preset threshold, the target air conditioner reduces the speed of the indoor fan of the target air conditioner; The target air conditioner controls the air outlet direction of the target air conditioner to be upward air outlet.

6. The anti-condensation control method according to claim 3, characterized by, The pre-training step of the condensation prediction model includes: The server obtains test samples and real labels corresponding to the test samples, the test samples including test air conditioner models, test operation modes, test evaporator temperatures, test indoor temperatures, test indoor fan speeds, and test indoor temperatures; The server inputs the test air conditioner models, the test operation modes, the test evaporator temperatures, the test indoor temperatures, the test indoor fan speeds, and the test indoor temperatures into the initial condensation prediction model to obtain training prediction results; The server calculates a training loss value based on the training prediction results and the loss function; The server iteratively updates the condensation prediction model based on the training loss value until the number of iterations reaches a preset iteration threshold to obtain the pre-trained condensation prediction model.

7. The anti-condensation control method according to claim 6, characterized by, The server inputs the test air conditioner models, the test operation modes, the test evaporator temperatures, the test indoor temperatures, the test indoor fan speeds, and the test indoor temperatures into the initial condensation prediction model to obtain training prediction results, including: The server constructs a second input vector based on the test air conditioner model, the test operation mode, the test evaporator temperature, the test indoor temperature, the test indoor fan speed, and the test indoor humidity. The server performs feature extraction processing on the second input vector through the feature extraction module to obtain second input features. The server performs residual processing on the second input feature through the residual module to obtain a second residual feature; The server inputs the second residual feature into the long short-term memory module to obtain a second updated feature; The server inputs the second updated feature into the classifier to obtain the training prediction result.

8. The anti-condensation control method according to claim 3, characterized by, The loss function is a cross-entropy function.

9. An air conditioning system, characterised in that, The air conditioning system comprises a memory and a processor, the memory stores a computer program, and the processor implements the anti-condensation control method of any one of claims 1-8 when executing the computer program.

10. A computer readable storage medium, the storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the anti-condensation control method of any one of claims 1-8.

Images