Air conditioner control method based on humidity detection, electronic equipment and storage medium

Abstract

The invention relates to the technical field of air conditioners, particularly provides an air conditioner control method based on humidity detection, electronic equipment and a storage medium, and aims at solving the technical problem that in the prior art, due to the fact that humidity detection is high in cost and poor in precision, accurate and efficient environment adjustment is difficult to achieve. In order to achieve the purpose, the method comprises the steps that operation parameters and the set temperature of the air conditioner are obtained, and the operation parameters comprise the indoor temperature, the evaporator coil temperature, the initial compressor frequency and the initial fan rotating speed; inputting the operation parameters into the trained humidity detection model to obtain indoor relative humidity; and based on the indoor relative humidity and the first difference value between the indoor temperature and the set temperature, the operation mode and operation parameters of the air conditioner are controlled. Through the implementation mode, the indoor relative humidity can be obtained according to the multi-dimensional operation parameters and the humidity detection model, the operation mode and the operation parameters of the air conditioner are controlled in combination with the difference value between the indoor temperature and the set temperature, and accurate and efficient adjustment of the indoor environment is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of air conditioners, and particularly relates to an air conditioner control method based on humidity detection, an electronic device and a storage medium. BACKGROUND

[0002] An air conditioning system realizes optimization of an environment and meets the comfort needs of a user by sensing and adjusting indoor environmental parameters. Humidity is an important index for measuring the suitability of an indoor environment, and its state directly affects the user's sensory experience. In order to effectively manage humidity, various humidity detection technologies have been developed in the industry. These technologies collect parameters related to the environment to form a basis for judging humidity, and then provide a reference for the operation of the air conditioning system to ensure the adjustment effect on the indoor environment.

[0003] However, the existing humidity detection technologies have obvious limitations in application. On the one hand, the scheme relying on humidity sensors has high cost and poor precision; among them, the resistance type humidity sensor is easily affected by environmental factors such as dust and oil stains, and has large detection error; the capacitance type sensor has relatively high precision but is expensive, and is difficult to popularize in low-end air conditioner products. On the other hand, the humidity calculation scheme based on fitting algorithm has insufficient precision; among them, the traditional humidity fitting equation has a deviation of more than 30% in a 70%-95% relative humidity (Rh) environment; the multivariate first-order function regression algorithm has an average error of more than 15% in the extreme humidity (such as Rh<30% or Rh>70%), which leads to the inability to accurately obtain humidity information, affects the rationality of the operation control of the air conditioning system, and makes it difficult to realize precise and efficient environmental regulation.

[0004] Correspondingly, there is a need in the art for a new technical solution to solve the above problems. SUMMARY

[0005] In order to overcome the above defects, the present application is proposed to provide an air conditioner control method based on humidity detection, an electronic device and a storage medium, which solve or at least partially solve the technical problems in the prior art that the high cost and poor precision of humidity detection make it difficult to realize precise and efficient environmental regulation.

[0006] In a first aspect, the present application provides an air conditioner control method based on humidity detection, which comprises:

[0007] obtaining an operating parameter and a set temperature of an air conditioner; the operating parameter comprises an indoor temperature, an evaporator coil temperature, an initial compressor frequency and an initial fan speed;

[0008] inputting the operating parameter into a trained humidity detection model to obtain an indoor relative humidity;

[0009] control the operation mode and operation parameter of the air conditioner based on the indoor relative humidity, the indoor temperature and the first difference between the set temperature.

[0010] In one of the above technical solutions of the air conditioner control method based on humidity detection, the method further comprises:

[0011] obtaining position information of the air conditioner guide plate;

[0012] obtaining a wind volume attenuation coefficient based on the position information of the guide plate;

[0013] correcting the initial fan rotating speed based on the wind volume attenuation coefficient;

[0014] wherein the range of the wind volume attenuation coefficient is 75.7% to 100%.

[0015] In one of the above technical solutions of the air conditioner control method based on humidity detection, the control of the operation mode and operation parameter of the air conditioner based on the indoor relative humidity, the indoor temperature and the first difference between the set temperature comprises:

[0016] determining whether the air conditioner runs a dehumidification mode based on the indoor relative humidity, the indoor temperature and the first difference between the set temperature;

[0017] adjusting the operation parameter when the air conditioner runs the dehumidification mode.

[0018] In one of the above technical solutions of the air conditioner control method based on humidity detection, the determination of whether the air conditioner runs a dehumidification mode based on the indoor relative humidity, the indoor temperature and the first difference between the set temperature comprises:

[0019] controlling the air conditioner to run the dehumidification mode when the first difference is less than a preset temperature threshold and the indoor relative humidity is greater than or equal to a preset humidity threshold;

[0020] controlling the air conditioner to run a refrigeration mode when the first difference is greater than or equal to the preset temperature threshold.

[0021] In one of the above technical solutions of the air conditioner control method based on humidity detection, the adjustment of the operation parameter comprises:

[0022] adjusting the compressor frequency to the sum of the initial compressor frequency and a first preset value;

[0023] adjusting the fan rotating speed to the difference between the initial fan rotating speed and a second preset value;

[0024] obtaining a target relative humidity and a second difference between the indoor relative humidity and the target relative humidity;

[0025] adjust the compressor frequency and the fan speed based on the second difference.

[0026] In one of the technical solutions of the air conditioner control method based on humidity detection, the humidity detection model comprises an input layer, a hidden layer and an output layer; the method further comprises training the humidity detection model based on the following steps:

[0027] obtaining a training data set and a test data set;

[0028] training the humidity detection model based on the training data set and optimizing parameters of the humidity detection model based on the test data set;

[0029] when the humidity detection model converges to a preset error, the training of the humidity detection model is completed.

[0030] In one of the technical solutions of the air conditioner control method based on humidity detection, the obtaining of the training data set and the test data set comprises:

[0031] setting the compressor frequency to a plurality of gears in a preset range, traversing a plurality of preset fan speeds, simulating a temperature rise and fall cycle in a preset temperature range to obtain sample data of indoor temperature, indoor humidity, compressor frequency, fan speed and evaporator coil temperature;

[0032] dividing the sample data into the training data set and the test data set according to a preset proportion.

[0033] In one of the technical solutions of the air conditioner control method based on humidity detection, the adjusting of the compressor frequency and the fan speed based on the second difference comprises:

[0034] adjusting the compressor frequency based on the second difference;

[0035] adjusting the fan speed based on the following formula:

[0036] Vr = INT((c*F+d) / 10)*10

[0037] wherein, Vr is the fan speed, INT is an integer function, c and d are preset coefficients, and F is the compressor frequency.

[0038] In a second aspect, the application provides an electronic device comprising a processor and a memory, the memory being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to execute the air conditioner control method based on humidity detection in any of the technical solutions of the air conditioner control method based on humidity detection.

[0039] In a third aspect, the present application provides a computer readable storage medium, which stores a plurality of program codes, the program codes being adapted to be loaded and run by a processor to execute the humidity detection based air conditioner control method of any one of the technical solutions of the above-mentioned humidity detection based air conditioner control method.

[0040] The one or more technical solutions of the present application have at least one or more of the following beneficial effects:

[0041] In the implementation of the technical solutions of the present application, firstly, the operating parameters and the set temperature of the air conditioner are acquired, the operating parameters including the indoor temperature, the evaporator coil temperature, the initial compressor frequency and the initial fan speed; then the operating parameters are input into the trained humidity detection model to obtain the indoor relative humidity; finally, the operating mode and the operating parameters of the air conditioner are controlled based on the indoor relative humidity, the first difference between the indoor temperature and the set temperature. Through the above-mentioned implementation, the indoor relative humidity can be obtained according to the multi-dimensional operating parameters of the air conditioner and the trained humidity detection model, and the operating mode and the operating parameters of the air conditioner are controlled in combination with the difference between the indoor relative humidity, the indoor temperature and the set temperature, thereby realizing accurate and efficient adjustment of the indoor environment, improving the comfort of the user, having higher accuracy than the traditional fitting algorithm, reducing the humidity detection deviation, making the air conditioner operating mode and parameter adjustment more reasonable, avoiding the problems of large sensor error and high cost, reducing the cost of the air conditioner system, and being suitable for various air conditioner products. BRIEF DESCRIPTION OF DRAWINGS

[0042] The disclosure of the present application will become more apparent with reference to the drawings. It is easily understood by those skilled in the art that the drawings are only for illustrative purposes, and are not intended to limit the scope of protection of the present application. Among them:

[0043] Figure 1 is a main step flow diagram of the humidity detection based air conditioner control method according to an embodiment of the present application;

[0044] Figure 2 is a main structure diagram of the humidity detection model according to an embodiment of the present application;

[0045] Figure 3 is a main step flow diagram of the training method of the humidity detection model according to an embodiment of the present application;

[0046] Figure 4 is a main step flow diagram of adjusting the operating parameters in the dehumidification mode according to an embodiment of the present application;

[0047] Figure 5 is a main structure diagram of an electronic device according to an embodiment of the present application.

[0048] List of reference signs:

[0049] 51: processor; 52: memory. DETAILED DESCRIPTION

[0050] Some embodiments of the present application will be described below with reference to the accompanying drawings. Those skilled in the art will understand that these embodiments are only used to explain the technical principles of the present application, and are not intended to limit the protection scope of the present application.

[0051] In the description of the present application, the "processor" can include hardware, software or a combination of both. The processor can be a central processor, a microprocessor, an image processor, a digital signal processor or any other suitable processor. The processor has data and / or signal processing functions. The processor can be implemented in software, hardware or a combination of both. The non-transitory computer readable storage medium includes any suitable medium that can store program codes, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, etc. The singular terms "a", "an" can also include the plural forms.

[0052] As described in the background, the existing humidity detection technology has obvious limitations in application. On the one hand, the scheme relying on humidity sensors has high cost and poor accuracy. Among them, the resistance type humidity sensor is easily affected by environmental factors such as dust and oil stains, and has large detection error; the capacitance type sensor has relatively high accuracy but high cost, which is difficult to popularize in low-end air conditioning products.

[0053] On the other hand, the humidity calculation scheme based on fitting algorithm has insufficient accuracy. Among them, the traditional humidity fitting equation deviates by more than 30% in the environment of 70%-95% Rh; the average error of the multivariate first-order function regression algorithm is more than 15% under the condition of extreme humidity (such as Rh<30% or Rh>70%), which leads to the inability to accurately obtain humidity information, affects the rationality of air conditioning system operation control, and is difficult to realize precise and efficient environmental regulation.

[0054] In order to solve the above problems, the present application provides an air conditioner control method based on humidity detection, an electronic device and a storage medium.

[0055] Referring to the accompanying Figure 1 , Figure 1 is the main step flow diagram of the air conditioner control method based on humidity detection according to an embodiment of the present application. As shown in Figure 1 , the air conditioner control method based on humidity detection in the embodiment of the present application mainly includes the following steps S101 to S103.

[0056] Step S101: obtaining the running parameters and set temperature of the air conditioner;

[0057] wherein the operating parameters include indoor temperature, evaporator coil temperature, initial compressor frequency and initial fan speed; and the set temperature is a user-set target temperature.

[0058] Step S102: inputting the operating parameters into the trained humidity detection model to obtain the indoor relative humidity;

[0059] Step S103: controlling the operating mode and operating parameters of the air conditioner based on the indoor relative humidity, the first difference between the indoor temperature and the set temperature.

[0060] Based on the method described in steps S101 to S103, the indoor relative humidity can be obtained according to the multi-dimensional operating parameters of the air conditioner and the trained humidity detection model, and the operating mode and operating parameters of the air conditioner can be controlled based on the indoor relative humidity, the difference between the indoor temperature and the set temperature, which realizes accurate and efficient adjustment of the indoor environment, improves user comfort, has higher accuracy than traditional fitting algorithms, reduces humidity detection deviation, makes the air conditioner operating mode and parameter adjustment more reasonable, avoids the problems of large sensor error and high cost, reduces the cost of the air conditioning system, and is suitable for various air conditioning products.

[0061] The steps S101 to S103 are further described below.

[0062] In some embodiments of step S101, the operating parameters and the set temperature can be obtained when the air conditioner is running. The operating parameters mainly include indoor temperature, evaporator coil temperature, initial compressor frequency and initial fan speed, etc.

[0063] wherein the indoor temperature can be the actual environmental temperature of the space where the air conditioner is located, such as the indoor dry-bulb temperature, which is usually detected by an indoor temperature sensor; the evaporator coil temperature is the temperature of the surface of the evaporator of the indoor unit of the air conditioner, which reflects the heat exchange efficiency and the refrigeration / heating state; the initial compressor frequency is the current operating frequency of the compressor; and the initial fan speed is the current rotational speed of the fan of the indoor unit.

[0064] The set temperature refers to the target temperature (e.g. 26℃) input by the user through the control panel, remote controller, etc. of the air conditioner, which is the reference value for the air conditioner to adjust the indoor environment.

[0065] Further, in some embodiments, the initial fan speed can be corrected in combination with the influence of the position of the guide plate on the air volume to obtain more accurate operating parameters.

[0066] Specifically, the position information of the guide plate of the air conditioner can be obtained, the air volume attenuation coefficient can be obtained based on the position information of the guide plate, and the initial fan speed can be corrected based on the air volume attenuation coefficient.

[0067] The guide plate position information is the current swing angle or fixed position of the air conditioner guide plate, such as upward, downward, horizontal, or a certain inclination angle. The guide plate position information directly affects the direction and diffusion range of the air conditioner air outlet, and further changes the actual air volume sent into the room. For example, when the guide plate is excessively inclined, the airflow is blocked, which can make the actual air volume lower than the theoretical output air volume of the fan.

[0068] Therefore, the air volume attenuation coefficients under different guide plate positions can be obtained through experimental tests. Specifically, the air conditioner guide plate can be recorded at multiple specific positions in different directions, and the air volume values and air volume attenuation coefficients corresponding to different gear groups of high wind and medium wind can be distinguished.

[0069] For example, the up and down guide plate positions and air volume data of some air conditioners can be as shown in Table 1; the air volume attenuation coefficients corresponding to different guide plate positions and different gear groups in Table 1 can be as shown in Table 2. The left and right guide plate positions and air volume data of some air conditioners can be as shown in Table 3; the air volume attenuation coefficients corresponding to different guide plate positions and different gear groups in Table 3 can be as shown in Table 4.

[0070] Table 1

[0071] As shown in Table 1, different positions are included, such as up 1, up 2, middle, down 1, down 2, and up and down swing. And for high wind and medium wind gears, the air volume values corresponding to different guide plate positions are recorded. For example, the air volume at the up 1 position is 553, and the air volume at the up 2 position is 608.9 under the high wind gear.

[0072] Table 2 Guide vane position Up 1 Up 2 Mid Down 1 Down 2 Up-down wind High wind Mid 75.3％ 82.9％ 96.9％ 100.0％ 94.1％ 90.1％ Mid wind Mid 76.1％ 84.0％ 96.9％ 100.0％ 93.7％ 90.5％ Wind volume decay coefficient 75.7％ 83.5％ 96.9％ 100.0％ 93.9％ 90.3％

[0073] As shown in Table 2, the air volume attenuation coefficients corresponding to different guide plate positions and different gear combinations are given. For example, the air volume attenuation coefficient corresponding to high wind and up 1 position is 75.3%.

[0074] Table 3

[0075] As shown in Table 3, the positions include left 1, left 2, middle, right 1, right 2, and left and right swing. Similarly, high wind and medium wind gears are distinguished, and the air volume values corresponding to different guide plate positions are recorded. For example, the air volume at the left 1 position is 636.1 under the high wind gear. Guide vane position Left 1 Left 2 Mid Right 1 Right 2 Left-right wind High wind Down 1 86.7％ 97.8％ 100.0％ 93.9％ 80.6％ 92.6％ Mid wind Down 1 85.1％ 96.2％ 100.0％ 92.9％ 79.7％ 92.0％ High wind Mid 88.6％ 99.3％ 100.0％ 93.3％ 80.5％ 92.9％ Wind volume decay coefficient 86.8％ 97.7％ 100.0％ 93.4％ 80.3％ 92.5％

[0076] As shown in Table 4, the air volume attenuation coefficients corresponding to different guide plate positions and different gear combinations are given. For example, the air volume attenuation coefficient corresponding to high wind and left 1 position is 86.7%.

[0077] Further, through the above Tables 1 to 4, the air volume attenuation coefficients corresponding to the positions of the guide plates can be obtained, as shown in the following Table 5.

[0078] Table 5 Guide vane position Up 1 Up 2 Mid Down 1 Down 2 Up-down wind Wind volume decay coefficient 75.7％ 83.5％ 96.9％ 100.0％ 93.9％ 90.3％ Guide vane position Left 1 Left 2 Mid Right 1 Right 2 Left-right wind Wind volume decay coefficient 86.8％ 97.7％ 100.0％ 93.4％ 80.3％ 92.5％

[0079] As can be seen from Table 5, the range of the air volume attenuation coefficients corresponding to the positions of the guide plates is 75.7% to 100%. The closer the coefficient is to 100%, the smaller the air volume loss is. The lower the coefficient is, the more obvious the air volume attenuation caused by the position of the guide plate is.

[0080] It should be noted that only the correspondence between some positions of the guide plates and the air volume attenuation coefficients is shown in the above Table 5. In actual application, due to factors such as air conditioner models and specific use environments, there are guide plate positions that are not covered in the table. When a guide plate position that is not explicitly shown in the table appears, the attenuation coefficient of the adjacent or similar position can be referred to for preliminary estimation. To ensure more accurate air volume attenuation coefficients, experimental tests, simulation analysis and other means can be used to further determine the accurate air volume attenuation coefficients corresponding to the positions of the guide plates in the actual application scenarios of the products, so as to ensure the accuracy and stability of the air conditioner operation control.

[0081] Further, after obtaining the air volume attenuation coefficient, the initial fan speed is multiplied by the air volume attenuation coefficient to obtain the corrected actual effective speed.

[0082] For example, if the initial fan speed is 1000 rpm and the attenuation coefficient of the corresponding position is 80%, the corrected equivalent effect of 800 rpm is used for subsequent humidity prediction and control logic.

[0083] The above is a further description of step S101, and the following further describes step S102.

[0084] In some embodiments of the above step S102, the humidity detection model can be first constructed and trained, and then the operating parameters are input into the trained humidity detection model to obtain the indoor relative humidity.

[0085] Specifically, based on the heat and mass transfer theory, mathematical models can be established by using principles such as mass conservation, water conservation and energy conservation, and then the condensate mass calculation formula and the air heat release calculation formula are derived to form a physical model framework.

[0086] The mass conservation law is the following formula (1):

[0087] m a1 =m a2 (1)

[0088] In the formula, m aindicates the supply air volume, subscript 1 indicates the inlet, and 2 indicates the outlet.

[0089] The water conservation law is the following formula (2):

[0090] m a1 d1 = m a2 d2 + m w (2)

[0091] In the formula, d indicates the moisture content, m w indicates the condensate mass. The condensate mass is calculated by the following formula (3):

[0092]

[0093] In the formula, a d is the mass transfer coefficient, A is the heat exchange area, and s indicates the evaporator surface air state.

[0094] The energy conservation law is the following formula (4):

[0095] m a1 h1 = m a2 h2 + q t (4)

[0096] In the formula, h indicates the enthalpy, q t indicates the total heat released by the air. The total heat released by the air is calculated by the following formula (5):

[0097]

[0098]

[0099] In the formula, h fg indicates the latent heat of vaporization of water, a is the heat transfer coefficient, and T indicates the temperature.

[0100] In the above formula (2) and formula (4), the supply air volume m a depends on the supply fan speed, the inlet moisture content d1, the outlet moisture content d2, the inlet temperature T1, and the outlet temperature T2 depend on the inlet and outlet air states; the mass transfer coefficient a d and the heat transfer coefficient a depend on the compressor frequency and the fan speed, the moisture content d s of the evaporator surface air state, and the evaporator surface temperature T s depend on the evaporator surface air state.

[0101] As can be seen, in formula (2) and formula (4), there are 6 unknown variables (the outlet air state and the evaporator surface air state are considered as saturated air), and 2 equations and 4 known variables can be used to solve 2 unknown variables.

[0102] Therefore, a test scheme can be designed to adjust the composite ratio of indoor load output, traverse the compressor frequency and the fan rotating speed, and output the ambient temperature and humidity test curve.

[0103] In some embodiments, the compressor frequency can be set to multiple gears in a preset range, multiple preset fan rotating speeds are traversed, a temperature rise and fall cycle in a preset temperature range is simulated, and sample data of indoor temperature, indoor humidity, compressor frequency, fan rotating speed, and evaporator coil temperature are obtained.

[0104] Specifically, a room where the indoor unit is located is recorded as room A, and a room where the outdoor unit is located is recorded as room B. If there is no special designation, the fan is the indoor fan by default.

[0105] Experimental scheme: fixing the compressor frequency and the indoor fan rotating speed, changing the temperature and humidity.

[0106] The experiment includes the following steps:

[0107] (1) Using the load generator, controlling the temperature and humidity of room A to be 35℃ / 90% or using the upper limit of the ambient temperature and humidity;

[0108] (2) maintaining the temperature of room B at 35℃, and allowing the outdoor fan to run freely;

[0109] (3) turning on the air conditioner to be tested, fixing the compressor frequency at 79Hz, and allowing the outdoor fan to run freely;

[0110] (4) changing the opening degree of the load generator to gradually make the indoor temperature and humidity of room A tend to 16℃ / 30% or the lower limit of the ambient temperature and humidity;

[0111] (5) using sensors to record the changes of indoor temperature and humidity, compressor frequency, fan rotating speed, and evaporator coil temperature, and ensuring that the sampling frequency is as small as possible;

[0112] (6) after the indoor temperature and humidity of room A reach 16℃ / 30% or the lower limit of the ambient temperature and humidity, still fixing the compressor frequency at 79Hz, and adjusting the indoor fan rotating speed to 6 gears;

[0113] (7) changing the opening degree of the load generator to gradually make the indoor temperature and humidity of room A tend to 35℃ / 90% or the upper limit of the ambient temperature and humidity;

[0114] (8) after the indoor temperature and humidity of room A reach 16℃ / 30% or the lower limit of the ambient temperature and humidity, still fixing the compressor frequency at 79Hz, and adjusting the indoor fan rotating speed to 5 gears;

[0115] (9) repeating the above temperature and humidity cycle until all fan rotating speeds are traversed, which is regarded as a group;

[0116] (10) repeating the above steps (1)-(9) except changing the compressor frequency in the process; wherein the compressor frequency is changed by 5 Hz for each step, and the compressor frequency is 79, 74, 69,..., 9 Hz, a total of 15 combinations.

[0117] wherein the above fan speed is the fan speed corrected based on the air volume attenuation coefficient corresponding to the air guide position, and the corresponding relationship between the guide position and the air volume attenuation coefficient is described in detail in the above Table 5, which will not be described here.

[0118] Through the above steps (1) to (10), the temperature and humidity cycle of 16-35°C can be simulated, so that the sample data such as temperature and humidity change curve, indoor temperature and humidity, compressor frequency, fan speed, evaporator coil temperature, etc. can be recorded. Then, the sample data can be divided into training data set and test data set according to the preset proportion. For example, 70% is randomly divided as the training data set, and 30% is randomly divided as the test data set.

[0119] In some embodiments of the above step S102, a neural network model with a 16-64-1 structure (including an input layer, a hidden layer and an output layer) can be constructed. The input layer includes 16 input nodes, i.e. the neural network model needs to input 16 feature parameters; the hidden layer includes 64 hidden nodes, which is the core calculation layer of the model, responsible for nonlinear conversion and feature extraction of the input feature parameters; the output layer includes 1 output node, used to output the final prediction result.

[0120] Further, the hidden layer nodes of the neural network model can be optimized, specifically by comparing the model errors corresponding to different node numbers to select the node configuration with the highest prediction accuracy. Wherein, the Mean Absolute Error (MAE) can be used as an evaluation index, the smaller the MAE value, the smaller the deviation between the model prediction value and the true value, and the higher the accuracy. Through testing, when the number of hidden layer nodes is 64, the MAE is 2.09%, indicating that the prediction error of the model is smaller under this node number, and the performance is better, so the setting of 64 hidden nodes is retained.

[0121] In addition, the input layer of the neural network model can also be simplified from the initial 16 input features to 4 features, which are indoor temperature, evaporator coil temperature, initial compressor frequency and initial fan speed, respectively. The parameters most closely related to humidity are retained, which reduces the model complexity while ensuring accuracy.

[0122] By processing the above neural network model, the humidity detection model of the present application can be obtained. Referring to FIG. 8, the humidity detection model of the present application is shown. Figure 2 Figure 2 is the main structure diagram of the humidity detection model according to an embodiment of the present application.​

[0123] As shown in Figure 2 , the input layer includes 4 nodes, which are indoor temperature, evaporator coil temperature, initial compressor frequency and initial fan speed; the hidden layer still uses 64 nodes; the output layer is 1 node, and the output is the predicted indoor relative humidity.

[0124] Further, the constructed humidity detection model can be trained.

[0125] Referring to the accompanying Figure 3 , Figure 3 is the main step flow schematic diagram of the training method of the humidity detection model according to an embodiment of the present application. As shown in Figure 3 , it mainly includes the following steps S301 to S303.

[0126] Step S301: obtaining a training data set and a test data set;

[0127] That is, the above is divided into a training data set and a test data set according to a preset ratio.

[0128] Among them, the training data set contains a large number of sample data related to air conditioner operation, which is used to let the model learn the mapping relationship between the input features (indoor temperature, compressor frequency, fan speed and evaporator coil temperature) and humidity. The test data set is used to evaluate the generalization ability of the model on unseen data, avoiding model overfitting (i.e. only remembering training data and unable to accurately predict new data).

[0129] Step S302: training the humidity detection model based on the training data set, and optimizing the parameters of the humidity detection model based on the test data set;

[0130] Specifically, step S302 can include a training phase and a parameter optimization phase.

[0131] Among them, the training phase is to input the training data set into the humidity detection model, the model outputs the predicted humidity through forward calculation, and then compares the error between the predicted value and the true humidity, adjusts the parameters such as weights and biases in the network through the back propagation algorithm, gradually reduces the error, and makes the model learn to predict humidity according to the input features.

[0132] In the parameter optimization phase, the test data set needs to be used to verify the model performance. If the test set error is too large, it means that the model may have overfitting or unreasonable parameter setting problem, and the model structure or training strategy needs to be further adjusted until the test set error is stable in a reasonable range, ensuring the universality of the model.

[0133] Step S303: when the humidity detection model converges to a preset error, the training of the humidity detection model is completed.

[0134] The convergence refers to a state that the error (such as MAE) gradually decreases and tends to be stable in the training process of the model; and the preset error is a preset accuracy threshold, when the model error reaches or is lower than the threshold, it indicates that the prediction accuracy of the model has met the demand, and the training process is terminated.

[0135] Through the method described in steps S301 to S303, a trained humidity detection model can be obtained, which can accurately output the indoor relative humidity based on the input air conditioner operating parameters, providing a reliable basis for the operation control of the air conditioner.

[0136] The inventors applied the above humidity detection model for humidity detection at user side in different regions, and evaluated the chip resources, and found that the MAE of the user side was less than or equal to 7.25%, the overall accuracy of the humidity model met the requirements, and the existing chip could support the algorithm to calculate once per second, which could guarantee the model operation calculation.

[0137] The above is a further description of step S102, and the following will continue to further describe step S103.

[0138] In some embodiments of the above step S103, whether the air conditioner runs a dehumidification mode can be determined based on the indoor relative humidity, and a first difference between the indoor temperature and the set temperature, and the operating parameters are adjusted when the air conditioner runs the dehumidification mode.

[0139] Specifically, when the first difference is less than a preset temperature threshold, and the indoor relative humidity is greater than or equal to a preset humidity threshold, the air conditioner can be controlled to run in the dehumidification mode; and when the first difference is greater than or equal to the preset temperature threshold, the air conditioner can be controlled to run in the cooling mode.

[0140] That is, when the indoor temperature (Room Temperature, Tr) and the set temperature (Set Temperature, Ts) satisfy Tr-Ts≥A (such as 2℃≤A≤4℃), the current running cooling mode is maintained. Since the indoor temperature is significantly higher than the user set temperature at this time, the temperature difference reaches or exceeds the threshold A, which indicates that the indoor is in a hot state, and the cooling demand is prioritized over humidity adjustment, so the cooling mode can be continued to run to quickly reduce the indoor temperature, so that the indoor temperature approaches the set temperature, and the core demand of the user for temperature is prioritized.

[0141] When Tr-Ts<A and Rh≥Rh0 (such as Rh0≥65%), the air conditioner is controlled to switch to the dehumidification mode. Specifically, when the temperature difference is less than A, it indicates that the indoor temperature has approached the set temperature, and the cooling demand is weakened. If the indoor relative humidity reaches or exceeds the threshold Rh0 at this time, high humidity will cause the user to feel hot and humid, and may cause mold growth and other problems. At this time, the dehumidification mode is converted, which can reduce the humidity while maintaining the temperature basically stable, and improve the overall comfort.

[0142] Further, in some embodiments of the step S103, when the air conditioner operates in the dehumidification mode, the operating parameters can be adjusted.

[0143] Referring to the accompanying Figure 4 , Figure 4 is a main flowchart of adjusting operating parameters in the dehumidification mode according to an embodiment of the present application. As shown in the figure, it mainly includes the following steps S401 to S404. Figure 4

[0144] Step S401: adjusting the compressor frequency to the sum of the initial compressor frequency and a first preset value;

[0145] When operating in the dehumidification mode, appropriately increasing the compressor frequency can enhance the refrigerating capacity of the evaporator, reduce the temperature of the coil, and make the water vapor in the air more likely to condense into water on the surface of the evaporator, thereby improving the dehumidification efficiency. Therefore, the current compressor frequency F' can be increased to F' = F + a (1 Hz≤a≤5 Hz), where F is the initial compressor frequency.

[0146] Step S402: adjusting the fan speed to the difference between the initial fan speed and a second preset value;

[0147] When operating in the dehumidification mode, reducing the fan speed can prolong the contact time of air with the evaporator, allowing more water vapor to condense, while reducing the sudden drop in indoor temperature caused by rapid air supply, balancing the relationship between dehumidification and temperature control. Therefore, the current fan speed Vr' can be reduced to Vr' = Vr - b (30 rpm≤b≤80 rpm), where Vr is the initial fan speed.

[0148] Step S403: obtaining the target relative humidity and the second difference between the indoor relative humidity and the target relative humidity;

[0149] Specifically, if the user sets a target humidity, the user-set value is taken as the target relative humidity (Relative Humidity of set target, Rh S ); if the user does not set a target humidity, Rh S can be defaulted to 50%≤Rh S ≤60%, which is set based on human comfort and mold prevention needs, and indoor relative humidity below 50% can cause dry air, and above 60% can breed mold.

[0150] Further, the second difference between the indoor relative humidity and the target relative humidity can be calculated.

[0151] Step S404: adjusting the compressor frequency and the fan speed based on the second difference. ​

[0152] In some embodiments, step S404 can include steps S4041-S4042.

[0153] Step S4041: Adjust the compressor frequency based on the second difference value.

[0154] Specifically, the running frequency can be controlled by proportional integral derivative (PID) control or fuzzy control with the second difference value as the target. The PID control is to calculate a suitable control amount according to the deviation between the set value and the actual value, so that the controlled object is stabilized around the target value. The fuzzy control is an intelligent control method based on fuzzy logic, which does not rely on accurate mathematical formulas, but converts expert experience or operation rules into "fuzzy language" (such as high temperature, moderate humidity, large wind speed, etc.), and then processes these uncertain information through fuzzy reasoning to output specific control amount.

[0155] For example, if Rh>>Rh S (humidity is too high), the compressor frequency is increased to enhance the dehumidification capacity; if Rh≈Rh S (near the target), the compressor frequency is reduced to maintain stability and avoid excessive dehumidification.

[0156] The dynamic adjustment mode of PID control or fuzzy control of the running frequency with the second difference value as the target can ensure accurate and stable dehumidification process, and avoid large humidity fluctuations.

[0157] Step S4041: Adjust the fan speed based on the following formula (6):

[0158] Vr = INT((c*F+d) / 10)*10 (6)

[0159] Where Vr is the fan speed, INT is the integer function, c and d are preset coefficients which can be determined by experiments, and F is the compressor frequency.

[0160] Through the above formula (6), the fan speed can be matched with the compressor frequency, that is, when the compressor frequency increases, the fan speed also increases accordingly, and vice versa. This ensures that the air circulation amount and the condensation efficiency remain balanced under different dehumidification intensities, which not only guarantees the dehumidification effect, but also avoids energy waste or temperature fluctuations.

[0161] The above is a further description of steps S101-S104.

[0162] The air conditioning control method based on humidity detection provided in this application reduces air conditioning costs by avoiding the use of humidity sensors and reduces the average absolute error of humidity detection to within 7.25%, which is significantly more accurate than traditional methods (error > 15%). At the same time, it maintains good performance under extreme humidity conditions, is highly adaptable, and can operate efficiently on existing air conditioning chips without hardware upgrades, making it highly practical. It also comprehensively considers the influence of multiple factors such as compressor frequency, fan speed, and guide plate position, achieving precise and efficient adjustment of the indoor environment and improving user comfort.

[0163] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effect of this application, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of this application.

[0164] Those skilled in the art will understand that all or part of the processes in the method of the above-described embodiment can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0165] Furthermore, this application also provides an electronic device. (See appendix) Figure 5 , Figure 5 This is a schematic diagram of the main structure of an electronic device according to an embodiment of this application. Figure 5 As shown, the electronic device in this embodiment mainly includes a processor 51 and a memory 52. ​​The memory 52 can be configured to store a program for executing the air conditioning control method based on humidity detection in the above-described method embodiments. The processor 51 can be configured to execute the program in the memory 52, which includes, but is not limited to, the program for executing the air conditioning control method based on humidity detection in the above-described method embodiments. For ease of explanation, only the parts related to the embodiments of this application are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of this application.

[0166] In some possible implementation of the present application, the electronic device can include a plurality of processors 51 and a plurality of memories 52. The program for implementing the air conditioner control method based on humidity detection of the above-mentioned method embodiments can be divided into a plurality of sub-programs, each of which can be loaded and run by the processor 51 to perform different steps of the air conditioner control method based on humidity detection of the above-mentioned method embodiments. Specifically, each sub-program can be stored in a different memory 52, and each processor 51 can be configured to execute the program in one or more memories 52 to jointly implement the air conditioner control method based on humidity detection of the above-mentioned method embodiments, i.e., each processor 51 performs different steps of the air conditioner control method based on humidity detection of the above-mentioned method embodiments to jointly implement the air conditioner control method based on humidity detection of the above-mentioned method embodiments.

[0167] The plurality of processors 51 mentioned above can be processors deployed on the same device, for example, the electronic device mentioned above can be a high-performance device composed of a plurality of processors, and the plurality of processors 51 mentioned above can be processors configured on the high-performance device. In addition, the plurality of processors 51 mentioned above can also be processors deployed on different devices, for example, the electronic device mentioned above can be a server cluster, and the plurality of processors 51 mentioned above can be processors on different servers in the server cluster, or the computer device mentioned above can be an air conditioner device cluster, and the plurality of processors 901 mentioned above can be processors on different driving devices in the air conditioner device cluster.

[0168] Further, the present application also provides a computer readable storage medium. In one computer readable storage medium embodiment according to the present application, the computer readable storage medium can be configured to store the program for implementing the air conditioner control method based on humidity detection of the above-mentioned method embodiments, which can be loaded and run by the processor to implement the above-mentioned air conditioner control method based on humidity detection. For ease of illustration, only the part related to the embodiments of the present application is shown, and the specific technical details not disclosed are referred to the method part of the embodiments of the present application. The computer readable storage medium can be a memory device formed by various electronic devices, and optionally, the computer readable storage medium in the embodiments of the present application is a non-transitory computer readable storage medium.

[0169] It should be noted that the related user personal information involved in the embodiments of the present application is strictly in accordance with the requirements of laws and regulations, and follows the principles of legality, legitimacy and necessity, and based on the reasonable purpose of business scene, handles the personal information provided by the user in the process of using the product / service or generated due to the use of the product / service, and authorized by the user.

[0170] The user personal information processed by the present application may vary according to specific product / service scenarios, and shall be subject to the specific scenarios in which the user uses the product / service. The user personal information may involve the user's account information, device information, running information, or other related information. The present application will treat the user's personal information and its processing with a high degree of diligence.

[0171] The present application attaches great importance to the security of user personal information. Reasonable and feasible security protection measures in line with industry standards have been taken to protect the user's information and prevent unauthorized access, public disclosure, use, modification, damage, or loss of personal information.

[0172] So far, the technical solutions of the present application have been described in conjunction with one embodiment shown in the accompanying drawings, but those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical solutions after these changes or replacements will fall within the protection scope of the present application.

Claims

1. An air conditioning control method based on humidity detection, characterized in that, The method includes: Obtain the operating parameters and set temperature of the air conditioner; the operating parameters include indoor temperature, evaporator coil temperature, initial compressor frequency, and initial fan speed; The operating parameters are input into the trained humidity detection model to obtain the indoor relative humidity; The operating mode and operating parameters of the air conditioner are controlled based on the indoor relative humidity, the first difference between the indoor temperature and the set temperature.

2. The air conditioning control method based on humidity detection according to claim 1, characterized in that, The method further includes: Obtain the position information of the air conditioner guide plate; The airflow attenuation coefficient is obtained based on the position information of the guide plate. The initial fan speed is corrected based on the air volume attenuation coefficient; The air volume attenuation coefficient ranges from 75.7% to 100%.

3. The air conditioning control method based on humidity detection according to claim 1, characterized in that, The method of controlling the operating mode and operating parameters of the air conditioner based on the first difference between the indoor relative humidity, the indoor temperature, and the set temperature includes: Based on the indoor relative humidity, the first difference between the indoor temperature and the set temperature, it is determined whether the air conditioner is in dehumidification mode. When the air conditioner is operating in the dehumidification mode, adjust the operating parameters.

4. The air conditioning control method based on humidity detection according to claim 3, characterized in that, The step of determining whether the air conditioner is in dehumidification mode based on the first difference between the indoor relative humidity, the indoor temperature, and the set temperature includes: When the first difference is less than a preset temperature threshold and the indoor relative humidity is greater than or equal to a preset humidity threshold, the air conditioner is controlled to operate the dehumidification mode. When the first difference is greater than or equal to the preset temperature threshold, the air conditioner is controlled to operate in cooling mode.

5. The air conditioning control method based on humidity detection according to claim 3, characterized in that, The adjustment of the operating parameters includes: Adjust the compressor frequency to the sum of the initial compressor frequency and the first preset value; Adjust the fan speed to the difference between the initial fan speed and the second preset value; Obtain the target relative humidity, and a second difference between the indoor relative humidity and the target relative humidity; The compressor frequency and the fan speed are adjusted based on the second difference.

6. The air conditioning control method based on humidity detection according to claim 1, characterized in that, The humidity detection model includes an input layer, a hidden layer, and an output layer; the method further includes training the humidity detection model based on the following steps: Obtain the training and test datasets; The humidity detection model is trained based on the training dataset, and the parameters of the humidity detection model are optimized based on the test dataset. The training of the humidity detection model is complete when the humidity detection model converges to a preset error.

7. The air conditioning control method based on humidity detection according to claim 6, characterized in that, The acquisition of the training dataset and the test dataset includes: The compressor frequency is set to multiple levels within a preset range, and multiple preset fan speeds are traversed to simulate the heating and cooling cycle within a preset temperature range in order to obtain sample data of indoor temperature, indoor humidity, compressor frequency, fan speed and evaporator coil temperature. The sample data is divided into the training dataset and the test dataset according to a preset ratio.

8. The air conditioning control method based on humidity detection according to claim 5, characterized in that, The step of adjusting the compressor frequency and the fan speed based on the second difference includes: The compressor frequency is adjusted based on the second difference; The fan speed is adjusted based on the following formula: Vr = INT((c*F+d) / 10)*10 Where Vr is the fan speed, INT is the rounding function, c and d are preset coefficients, and F is the compressor frequency.

9. An electronic device comprising a processor and a memory, the memory being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to perform the air conditioning control method based on humidity detection as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the air conditioning control method based on humidity detection as described in any one of claims 1 to 8.

Images