Air conditioner dehumidification control method, device and system and air conditioner

Abstract

The invention discloses an air conditioner dehumidification control method, device and system and an air conditioner, and belongs to the field of air conditioner dehumidification. And when the air conditioner operates in a dehumidification or refrigeration mode, the predicted humidity and the target humidity after the specified duration are obtained, when the predicted humidity is smaller than the target humidity and the minimum predicted humidity is smaller than a preset humidity lower limit, the air conditioner is controlled to enter an early warning state, and when the air conditioner enters the early warning state, the dehumidification capacity of the air conditioner is adjusted according to the target humidity and the actual humidity. According to the scheme, the humidity after the specified duration is predicted and compared with the target humidity, when the predicted humidity is smaller than the target humidity and the minimum predicted humidity is smaller than the preset humidity lower limit, it is indicated that the excessive dehumidification phenomenon occurs after the specified duration, and therefore the dehumidification capacity of the air conditioner is adjusted in advance, it is guaranteed that excessive dehumidification cannot occur after the specified duration, and the dehumidification efficiency is improved. And the comfort and the experience of the user are improved.

Description

Technical Field

[0001] This application relates to the field of air conditioning dehumidification technology, and in particular, to an air conditioning dehumidification control method, device, system and air conditioner. Background Technology

[0002] Air conditioning humidity control is a core element in maintaining indoor environmental comfort and equipment energy efficiency. When air conditioning is in cooling mode or running dehumidification mode for extended periods, especially in enclosed environments without a fresh air system, a gradual imbalance in temperature and humidity can easily occur, resulting in over-dehumidification. When the air conditioner starts running, the compressor drives the refrigerant circulation, causing the evaporator surface temperature to drop rapidly. When humid air flows through the low-temperature evaporator, its temperature drops rapidly initially. Once the dew point temperature is reached, water vapor in the air begins to condense into water droplets and is discharged. During this stage, temperature and humidity decrease simultaneously, and the indoor environment gradually becomes cool and comfortable. However, as the running time increases, the indoor temperature approaches the set value, but the dehumidification process continues. The system continues to dehumidify, and the evaporator surface temperature further drops to 5-8°C. Although the dehumidification efficiency decreases due to the smaller temperature difference as the air dew point temperature decreases with humidity, the system continues to remove moisture from the air, causing the indoor relative humidity to drop continuously, ultimately leading to over-dehumidification and causing discomfort to the user. Summary of the Invention

[0003] In order to overcome the shortcomings of the prior art, this application provides an air conditioning dehumidification control method, device, system and air conditioner to solve the problem that the indoor relative humidity will continuously decrease during the cooling or dehumidification of existing air conditioners, eventually leading to excessive dehumidification and causing discomfort to users.

[0004] The technical solution adopted by this application to solve its technical problem is:

[0005] Firstly, an air conditioning humidity control method is provided, including:

[0006] When the air conditioner is in dehumidification or cooling mode, obtain the predicted humidity and target humidity after a specified period of time.

[0007] When the predicted humidity is less than the target humidity and the minimum predicted humidity is less than the preset humidity lower limit, the air conditioner is controlled to enter the warning state.

[0008] When the air conditioner enters the warning state, the dehumidification capacity of the air conditioner is adjusted according to the target humidity and the actual humidity.

[0009] As an optional implementation of this application, obtaining the predicted humidity after a specified time period includes:

[0010] Obtain the indoor humidity and exogenous variable parameters for the current period;

[0011] The indoor humidity and the exogenous variable parameters are input into the target time series model to obtain the preset humidity after a specified duration;

[0012] The exogenous variable parameters include at least one of the following:

[0013] Indoor temperature, set temperature, air conditioning mode, fan speed, and compressor frequency.

[0014] As an optional implementation of this application, the training steps of the target time series model include:

[0015] An initial time series model is obtained by modeling indoor temperature based on a time series model, wherein a lag operator and a seasonal term are introduced in the initial time series model;

[0016] Historical data is acquired, and the model parameters and seasonality coefficients of the initial time series model are adjusted based on the historical data to obtain the target time series model. The historical data includes historical humidity data and historical exogenous variable parameters.

[0017] As an optional implementation of this application, it also includes:

[0018] Acquire target data, which is the indoor humidity and exogenous variable parameters in the current period, or historical data;

[0019] Abnormal data is removed from the target data using a threshold method;

[0020] The ADF test method was used to obtain the statistics and p-values ​​of the target data after removing outliers.

[0021] Based on the statistics and p-value, determine whether the target data is stationary;

[0022] When the data is not stationary, it is differentially processed until it becomes stationary; when it is stationary, the stationary data is input into the target time series model.

[0023] As an optional implementation of this application, the step of determining whether the target data is stationary based on the statistic and the p-value includes:

[0024] Assuming the target data is stable, if the absolute value of the statistic is greater than the critical value, or if the P value is less than or equal to the preset value, the target data is determined to be unstable; if the absolute value of the statistic is less than or equal to the critical value, or if the P value is greater than the preset value, the target data is determined to be stable.

[0025] If the absolute value of the statistic is greater than the critical value, or if the P-value is less than or equal to the preset value, the target data is judged to be stable. If the absolute value of the statistic is less than or equal to the critical value, or if the P-value is greater than the preset value, the target data is judged to be non-stable.

[0026] As an optional implementation of this application, the step of performing differential processing on the data until it becomes stationary includes:

[0027] Perform a first-order difference on the data;

[0028] The statistical measures and p-values ​​of the data after first-order differencing were obtained based on the ADF test method;

[0029] Determine whether the data after first-order differencing is stationary based on statistics and p-values;

[0030] If the data is not stable, repeat the above steps until the data becomes stable.

[0031] As an optional implementation of this application, the step of adjusting the model parameters and seasonality coefficients of the initial time series model based on the historical data to obtain the target time series model includes:

[0032] Based on the analysis of autocorrelation function and partial autocorrelation function graphs, the model parameters and seasonality coefficients were initially determined, where the seasonality coefficients include the sampling period.

[0033] Select a humidity value within a sampling period and an exogenous variable parameter as input;

[0034] The parameters are optimized and fitted using the maximum likelihood estimation method;

[0035] The target time series model is obtained by determining the model parameters and seasonality coefficients based on the fitting residuals.

[0036] As an optional implementation of this application, obtaining the target humidity after a specified time period includes:

[0037] Get the current indoor ambient temperature and the rate of change of the current indoor ambient temperature;

[0038] The target humidity is determined based on the current indoor ambient temperature and the rate of change of the current indoor ambient temperature.

[0039] Among them, when the current indoor ambient temperature change rate is the same, the higher the current indoor ambient temperature, the greater the target humidity; when the current indoor ambient temperature is the same, the greater the current indoor ambient temperature change rate, the greater the target humidity.

[0040] As an optional implementation of this application, adjusting the dehumidification capacity of the air conditioner according to the target humidity and the actual humidity includes:

[0041] Calculate the humidity difference between the target humidity and the actual humidity, as well as the rate of change of the humidity difference;

[0042] The humidity difference and the rate of change of the humidity difference are used as inputs to the fuzzy controller to obtain the adjustment strategy of the air conditioner's dehumidification capacity.

[0043] The dehumidification capacity of the air conditioner is adjusted based on the aforementioned adjustment strategy.

[0044] Secondly, an air conditioning humidity control device is provided, comprising:

[0045] The parameter acquisition module is used to obtain the predicted humidity and target humidity after a specified period of time when the air conditioner is in dehumidification or cooling mode.

[0046] The early warning control module is used to control the air conditioner to enter an early warning state when the predicted humidity is less than the target humidity and the minimum predicted humidity is less than the preset humidity lower limit.

[0047] The dehumidification adjustment module is used to adjust the dehumidification capacity of the air conditioner according to the target humidity and the actual humidity when the air conditioner enters the warning state.

[0048] Thirdly, an air conditioning humidity control system is provided, comprising:

[0049] At least one processor and at least one memory;

[0050] The memory stores the executable instructions of the processor;

[0051] The processor is configured to perform the air conditioning humidity control method described in any of the preceding descriptions.

[0052] Fourthly, an air conditioner is provided that applies the air conditioning humidity control method described in any of the above-mentioned claims.

[0053] Beneficial effects:

[0054] This application provides an air conditioning dehumidification control method, device, system, and air conditioner. When the air conditioner is operating in dehumidification or cooling mode, the predicted humidity and target humidity after a specified time are obtained. When the predicted humidity is lower than the target humidity and the minimum predicted humidity is lower than a preset humidity lower limit, the air conditioner is controlled to enter a warning state. In the warning state, the air conditioner's dehumidification capacity is adjusted based on the target humidity and the actual humidity. This application's solution compares the predicted humidity after a specified time with the target humidity. When the predicted humidity is lower than the target humidity and the minimum predicted humidity is lower than the preset humidity lower limit, it indicates that excessive dehumidification will occur after the specified time. Therefore, the dehumidification capacity of the air conditioner is adjusted in advance to ensure that excessive dehumidification does not occur after the specified time, improving user comfort and experience. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a flowchart of an air conditioning humidity control method provided in an embodiment of this application;

[0057] Figure 2 This is a flowchart of a specific air conditioning humidity control method provided in an embodiment of this application;

[0058] Figure 3 This is a schematic diagram of fitting residual data provided in an embodiment of this application;

[0059] Figure 4 This is a schematic diagram of a model fitting effect provided in an embodiment of this application;

[0060] Figure 5 This is a schematic diagram of air conditioner humidity prediction provided in an embodiment of this application;

[0061] Figure 6 This is a schematic diagram of the structure of an air conditioning humidity control device provided in an embodiment of this application;

[0062] Figure 7 This is a schematic diagram of the structure of an air conditioning humidity control system provided in an embodiment of this application. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be described in detail below with reference to the accompanying drawings and embodiments. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0064] Regarding the problem of excessive dehumidification, due to the inherent coupling between temperature and humidity control during air conditioning operation, dehumidification is inevitably accompanied by the cooling process. Secondly, traditional control systems primarily respond to temperature signals, resulting in a lag in response to humidity changes. Furthermore, during air conditioning cooling regulation, the space is often enclosed, lacking a source of humidity replenishment, which accelerates the drying process. Traditional air conditioning systems often employ a fixed threshold dehumidification strategy, initiating dehumidification when the ambient humidity exceeds a preset threshold and stopping when it falls below. Alternatively, a temperature-humidity correlation function can be introduced to calculate a dynamic humidity threshold by real-time acquisition of environmental parameters (temperature, humidity, etc.), simultaneously increasing the humidity threshold as the temperature decreases. However, threshold calculations often use linear rules, such as humidity threshold = 65% - 0.2 × temperature deviation, which is insufficient to cover non-linear operating conditions and cannot adapt to dynamic loads such as seasonal changes and fluctuations in population density. This leads to excessive dehumidification, where the compressor continues to run even after the humidity rapidly drops to a safe range, resulting in a dry environment with humidity below 40%, causing discomfort to the human body.

[0065] To solve this problem, refer to Figure 1 This application provides an air conditioning humidity control method, including:

[0066] S11: When the air conditioner is in dehumidification or cooling mode, obtain the predicted humidity and target humidity after a specified period of time;

[0067] It should be noted that over-dehumidification only occurs when the air conditioner is in dehumidification or cooling mode. Therefore, in this embodiment, the determination of whether over-dehumidification exists is only performed when the air conditioner is in dehumidification or cooling mode; that is, the predicted humidity and target humidity are first obtained after a specified period of time.

[0068] Traditional methods for determining over-dehumidification rely on the current humidity level and a set threshold. However, this approach indicates that over-dehumidification has already occurred or is about to occur. Adjusting the air conditioner's dehumidification capacity at this point results in a poor user experience. Therefore, this application uses predicted humidity after a specified time period to determine if over-dehumidification is occurring. This allows for proactive adjustment of the air conditioner's dehumidification capacity, preventing over-dehumidification.

[0069] As a preferred implementation of this application, the indoor humidity and exogenous variable parameters within the current period are obtained;

[0070] The indoor humidity and the exogenous variable parameters are input into the target time series model to obtain the preset humidity after a specified duration;

[0071] The exogenous variable parameters include at least one of the following:

[0072] Indoor temperature, set temperature, air conditioning mode, fan speed, and compressor frequency.

[0073] The training steps for the target time series model include:

[0074] An initial time series model is obtained by modeling indoor temperature based on a time series model, wherein a lag operator and a seasonal term are introduced in the initial time series model;

[0075] Historical data is acquired, and the model parameters and seasonality coefficients of the initial time series model are adjusted based on the historical data to obtain the target time series model. The historical data includes historical humidity data and historical exogenous variable parameters.

[0076] Preferably, the step of adjusting the model parameters and seasonality coefficients of the initial time series model based on the historical data to obtain the target time series model includes:

[0077] Based on the analysis of autocorrelation function and partial autocorrelation function graphs, the model parameters and seasonality coefficients were initially determined, where the seasonality coefficients include the sampling period.

[0078] Select a humidity value within a sampling period and an exogenous variable parameter as input;

[0079] The parameters are optimized and fitted using the maximum likelihood estimation method;

[0080] The target time series model is obtained by determining the model parameters and seasonality coefficients based on the fitting residuals.

[0081] In this process, both historical data and model input data need to undergo stabilization processing and evaluation. Specifically:

[0082] Acquire target data, which is the indoor humidity and exogenous variable parameters in the current period, or historical data;

[0083] Abnormal data is removed from the target data using a threshold method; for example, data exceeding or falling below a threshold is identified as abnormal data and then removed.

[0084] The ADF test method was used to obtain the statistics and p-values ​​of the target data after removing outliers.

[0085] Based on the statistics and p-value, determine whether the target data is stationary;

[0086] When the data is not stationary, it is differentially processed until it becomes stationary; when it is stationary, the stationary data is input into the target time series model.

[0087] Furthermore, determining whether the target data is stationary based on the statistic and the p-value includes:

[0088] Assuming the target data is stable, if the absolute value of the statistic is greater than the critical value, or if the P value is less than or equal to the preset value, the target data is determined to be unstable; if the absolute value of the statistic is less than or equal to the critical value, or if the P value is greater than the preset value, the target data is determined to be stable.

[0089] If the absolute value of the statistic is greater than the critical value, or if the P-value is less than or equal to the preset value, the target data is judged to be stable. If the absolute value of the statistic is less than or equal to the critical value, or if the P-value is greater than the preset value, the target data is judged to be non-stable.

[0090] Furthermore, the differential processing of the data until it stabilizes includes:

[0091] Perform a first-order difference on the data;

[0092] The statistical measures and p-values ​​of the data after first-order differencing were obtained based on the ADF test method;

[0093] Determine whether the data after first-order differencing is stationary based on statistics and p-values;

[0094] If the data is not stable, repeat the above steps until the data becomes stable.

[0095] This application uses a time series model for humidity prediction. In practice, prediction can also be based on historical data. Historical data prediction involves obtaining current parameters, such as indoor humidity, outdoor humidity, current operating conditions, indoor temperature, and outdoor humidity. When the current parameters are the same as the historical parameters, and the trend of each parameter's change is the same as the trend of historical data change, the humidity after a specified period of historical data is used as the predicted humidity.

[0096] As a preferred implementation of this application, obtaining the target humidity after a specified time period includes:

[0097] Get the current indoor ambient temperature and the rate of change of the current indoor ambient temperature;

[0098] The target humidity is determined based on the current indoor ambient temperature and the rate of change of the current indoor ambient temperature.

[0099] Among them, when the current indoor ambient temperature change rate is the same, the higher the current indoor ambient temperature, the greater the target humidity; when the current indoor ambient temperature is the same, the greater the current indoor ambient temperature change rate, the greater the target humidity.

[0100] In another embodiment, the target humidity after a specified time period can also be determined based on a pre-set table or correspondence. For example, each set of indoor and outdoor ambient temperatures in the table corresponds to a target humidity.

[0101] S12: When the predicted humidity is less than the target humidity and the minimum predicted humidity is less than the preset humidity lower limit, control the air conditioner to enter the warning state;

[0102] It is understood that the predicted humidity obtained using a time series model includes humidity values ​​from multiple time points, with the lowest predicted humidity value being the minimum predicted humidity. When the predicted humidity is lower than the target humidity and the minimum predicted humidity is lower than a preset humidity lower limit, it indicates that the air conditioner will experience excessive dehumidification after a specified period. Therefore, a warning state is activated.

[0103] S13: When the air conditioner enters the warning state, adjust the dehumidification capacity of the air conditioner according to the target humidity and the actual humidity.

[0104] In one embodiment, the difference between the target humidity and the actual humidity is calculated, and the dehumidification capacity of the air conditioner is adjusted based on the sign and absolute value of the difference between the target humidity and the actual humidity.

[0105] For example, when the difference between the target humidity and the actual humidity is greater than 0, the dehumidification capacity of the air conditioner is reduced. The greater the difference between the target humidity and the actual humidity, the greater the reduction in the dehumidification capacity. For example, adjusting the dehumidification capacity of the air conditioner can be done by changing the evaporator temperature or adjusting the contact time between the air and the evaporator (e.g., changing the speed of the indoor fan). Reducing the dehumidification capacity means increasing the evaporator temperature or increasing the indoor fan speed.

[0106] When the difference between the target humidity and the actual humidity is less than 0, the dehumidification capacity of the air conditioner is increased. The greater the difference between the target humidity and the actual humidity, the greater the increase in the dehumidification capacity of the air conditioner.

[0107] As a preferred implementation of this application, adjusting the dehumidification capacity of the air conditioner according to the target humidity and the actual humidity includes:

[0108] Calculate the humidity difference between the target humidity and the actual humidity, as well as the rate of change of the humidity difference;

[0109] The humidity difference and the rate of change of the humidity difference are input into the fuzzy controller as input quantities to obtain the adjustment strategy of the air conditioner's dehumidification capacity.

[0110] For example, the fuzzy controller takes the current humidity error e = RH_target - RH_now and the humidity change rate Δe (i.e., the difference between RH_now and the previous RH) as input variables, and normalizes the values ​​using methods such as Z-score or Min-Max, standardizing the value range to [-1, +1] for fuzzification operation.

[0111] The normalized input variables e and Δe are divided into multiple fuzzy language sets, where e includes seven levels: Nmax, Nmid, Nmin, Z0, Pmin, Pmid, and Pmax. Δe is divided into three levels: N (negative change), Z (no change), and P (positive change), as shown in Table 1 (output control mode ΔU).

[0112] Table 1

[0113]

[0114] The control changes include "enhanced" (significantly reducing dehumidification intensity), "maintaining" (keeping the current control state unchanged), and "strong enhancement" (significantly increasing dehumidification capacity). The system performs combined reasoning on the above inputs based on a predefined rule base. For example, when e is Nmax and Δe is N (negative change), the output control quantity ΔU is "strong reduction," indicating that the dehumidification intensity needs to be significantly reduced; when e is Z0 and Δe is Z (no change), ΔU is "maintain," indicating that the current humidity is stable and no adjustment is needed. The system sets a minimum humidity protection threshold (e.g., RH_min = 38%) to prevent excessively low humidity due to erroneous control. The SARIMAX model parameters are periodically retrained to adapt to different seasons and usage environments, achieving closed-loop system control.

[0115] It should be noted that any process or method description in the flowchart or otherwise described herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order according to the functions involved, as should be understood by those skilled in the art to which the embodiments of this application pertain.

[0116] Furthermore, in the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0117] The air conditioning humidity control method provided in this application obtains the predicted humidity and target humidity after a specified period when the air conditioner is running in dehumidification or cooling mode. When the predicted humidity is less than the target humidity and the minimum predicted humidity is less than a preset humidity lower limit, the air conditioner is controlled to enter a warning state. While in the warning state, the air conditioner's dehumidification capacity is adjusted based on the target humidity and the actual humidity. This solution compares the predicted humidity after a specified period with the target humidity. When the predicted humidity is less than the target humidity and the minimum predicted humidity is less than the preset humidity lower limit, it indicates that excessive dehumidification will occur after the specified period. Therefore, the dehumidification capacity of the air conditioner is adjusted in advance to ensure that excessive dehumidification does not occur after the specified period, improving user comfort and experience.

[0118] To more clearly illustrate the solution of this application, a specific method for controlling air conditioning humidity is provided below, such as... Figure 2 As shown:

[0119] First, the temperature and humidity sensors deployed in the indoor unit of the air conditioner collect environmental variables in real time during the operation of the air conditioning system, including indoor relative humidity (RH_now), indoor ambient temperature (T_now), user-set temperature (T_set), and target relative humidity (RH_target). These are then coupled with the temperature sensor to determine the following:

[0120]

[0121] Where RH_base is the preset base humidity, T air The current indoor ambient temperature is used, and α and γ are fixed coefficients (which vary depending on the air conditioner and the environment, and need to be determined based on historical data).

[0122] The parameters are sampled every 2 minutes. Indoor humidity sequences are modeled using a time-series SARIMAX model, and combined with exogenous variables, humidity trend predictions are made for a future period. The prediction period is set to 30-60 minutes, and the model expression for the lag of the target humidity sequence is given:

[0123] Φ P (B s )φ p (B)(1-B) d (1-B s ) D Y t =Θ Q (B s )θ q (B)ε(t)+β T X t

[0124] Here, B is the lag operator. The delay operator is similar to a time pointer; multiplying the current sequence value by a delay operator is equivalent to moving the time of the current sequence value back one moment. In particular, (1-B)X t =x t -x t-1 Indicates x t Perform the first-order difference, and so on. Indicates x t Perform a d-order difference.

[0125] B s The seasonal delay operator is equivalent to turning back the time of the current sequence value by one cycle; (1-B) s )X t =x t -x t-s Represents x t A seasonal difference with a period of s was performed, and so on. Indicates x t Perform seasonal differences D times with a period of s. Here, P, D, and Q are the orders, as detailed in the following formula.

[0126] Y t Let B be the current target humidity value, and B be the hysteresis operator. Then BY... t =Y t-1 d is the difference order, D is the seasonal difference order, and s is the sampling period. p For AR autoregression coefficients:

[0127] Y t =1Y t-1 +2Y t-2 +…+ p Y t-p +ε(t)

[0128] p (B) = 1 - 1B - 2B - ... - p B

[0129] θ q The moving average (MA) coefficient:

[0130] θ q (B)=1+θ1B+θ2B 2 +…+θ q B q

[0131] Θ Q Seasonal SMA coefficient:

[0132] Θ Q (B s )=1+θ1B+θ2B2s +…+θ Q B Qs

[0133] Φ P Seasonal SAR coefficient:

[0134] Φ P (B s )=1-1B s -2B s -…- P B Qs

[0135] ε(t) represents the error term due to white noise disturbance or unmodeled effects, β represents the exogenous regression coefficient, and X represents the error term due to these disturbances. t The vector of exogenous variables is:

[0136] β T X t =β0+β1X1, t +β2X2、 t +…+β n X n , t

[0137] Note: X t It is the vector of exogenous variables at time point t, where n represents the exogenous variable selected at the nth time point t.

[0138] The humidity time series data acquired and processed by the sensor is subjected to stationarization processing to confirm whether the acquisition is stationary. If it is not stationary, first-order / second-order difference processing is applied.

[0139] The stationarity processing here refers to the process of removing outliers from the collected data using a threshold method. Then, the stationarity of the standard data is quantified using the ADF test. The ADF test is a hypothesis test that examines the null hypothesis (H0): the time series is non-stationary (has a unit root), and the alternative hypothesis (H1): the time series is stationary. The test result mainly considers two values: ADF Statistic: a negative value. The more negative the value (i.e., the larger the absolute value), the more likely it is to reject the null hypothesis (i.e., the more likely it is to consider the series to be stationary). p-value: this is the key basis for decision-making. If the p-value ≤ the significance level (usually taken as 0.05), then we have sufficient evidence to reject the null hypothesis (H0) and consider the series to be stationary. If the p-value > 0.05, then we cannot reject the null hypothesis (H0) and consider the series to be non-stationary. If the data is not stationary after stationarity is determined, a first difference is performed, and the stationarity is judged again based on the first difference result. If it is still not stationary, a second difference is performed, and so on, until the data is stationary.

[0140] The model order (p, d, q) and seasonal terms (P, D, Q, s) are initially determined through the analysis of the autocorrelation function (ACF) and partial autocorrelation function (PACF) plots. Here, s is the sampling period. The modeling data window selects the humidity values within the recent s hours (i.e., 30×s points), and the indoor temperature, set temperature, air-conditioning mode, wind speed gear, and compressor frequency are used as the exogenous variable matrix input. The parameters are optimized and fitted by the maximum likelihood estimation method. As Figure 3 and Figure 4 shown, the reliability of the prediction is tested using statistical indicators such as the autocorrelation, normality, and skewness of the fitting residuals to determine the model order (p, d, q) and seasonal terms (P, D, Q, s). The SARIMAX model is updated and run every 5 minutes for a rolling prediction of the next 30 - 60 minutes, and the predicted humidity values RH_pred(t) at each future moment are output. The prediction results are as Figure 5 shown. The prediction result sequence is output, and RH_pred < RH_target is judged as a prerequisite for entering the dehumidification warning control. If there is an interval where RH_pred < RH_target in the prediction sequence, and the predicted minimum value RH_min_pred is lower than the lower limit of the safe humidity (e.g., 42%RH), the system enters the "over-dehumidification trend warning" state. In this solution, the following calculation example is given. In the example, the model order (p, d, q) and seasonal term (P, D, Q, s) parameters are determined by giving simulated data. The error distribution is selected as the Gaussian distribution, and the prediction results and fitting effects are given for the simulated data in the case.

[0141] When the warning state occurs, the system automatically calls the fuzzy controller module for flexible adjustment. The fuzzy controller takes the current humidity error e = RH_target - RH_now and the humidity change rate Δe (i.e., the difference between RH_now and the previous RH) as input variables, and normalizes the values through methods such as Z-score or Min-Max, standardizing the value range to [-1, +1] for fuzzy operation.

[0142] The normalized input variables e and Δe are respectively divided into multiple fuzzy language sets. Among them, e includes 7 levels such as Nmax, Nmid, Nmin, Z0, Pmin, Pmid, and Pmax. Δe is divided into three levels: N (negative change), Z (no change), and P (positive change). The fuzzy rule table is shown in Table 1 (output control mode ΔU):

[0143] Table 1

[0144]

[0145]

[0146] The control changes include "enhanced" (significantly reducing dehumidification intensity), "maintaining" (keeping the current control state unchanged), and "strong enhancement" (significantly increasing dehumidification capacity). The system performs combined reasoning on the above inputs based on a predefined rule base. For example, when e is Nmax and Δe is N (negative change), the output control quantity ΔU is "strong reduction," indicating that the dehumidification intensity needs to be significantly reduced; when e is Z0 and Δe is Z (no change), ΔU is "maintain," indicating that the current humidity is stable and no adjustment is needed. The system sets a minimum humidity protection threshold (e.g., RH_min = 38%) to prevent excessively low humidity due to erroneous control. The SARIMAX model parameters are periodically retrained to adapt to different seasons and usage environments, achieving closed-loop system control.

[0147] The specific air conditioning dehumidification control method provided in this application embodiment is based on the linkage of time series prediction and fuzzy control. By collecting temperature and humidity sensor data, a time series model is introduced to predict and judge the future trend of indoor humidity. The humidity control target value is confirmed by temperature change data, and a dehumidification warning interval is set. When the warning of excessive dehumidification is issued, flexible control intervention is automatically performed to avoid the occurrence of excessively low humidity. This improves the level of intelligence and comfort, and reduces the discomfort caused by excessive dehumidification to the human body and the environment.

[0148] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the air conditioning humidity control method provided in any of the above embodiments.

[0149] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0150] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0151] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0152] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0153] The computer-readable storage medium provided in this application embodiment stores a computer program. When executed by a processor, the computer program implements the steps of the air conditioning control method provided in any of the above embodiments. Thus, when the air conditioner is operating in dehumidification or cooling mode, it obtains the predicted humidity and target humidity after a specified period. When the predicted humidity is less than the target humidity and the minimum predicted humidity is less than a preset humidity lower limit, the air conditioner is controlled to enter a warning state. While the air conditioner is in the warning state, its dehumidification capacity is adjusted according to the target humidity and the actual humidity. This application solution can compare the predicted humidity after a specified period with the target humidity. If the predicted humidity is less than the target humidity and the minimum predicted humidity is less than the preset humidity lower limit, it indicates that excessive dehumidification will occur after the specified period. Therefore, the dehumidification capacity of the air conditioner is adjusted in advance to ensure that excessive dehumidification does not occur after the specified period, improving user comfort and experience.

[0154] Based on the same inventive concept, such as Figure 6 As shown, this application also provides an air conditioning humidity control device 60, including:

[0155] The parameter acquisition module 61 is used to acquire the predicted humidity and target humidity after a specified period of time when the air conditioner is in dehumidification or cooling mode.

[0156] It should be noted that over-dehumidification only occurs when the air conditioner is in dehumidification or cooling mode. Therefore, in this embodiment, the determination of whether over-dehumidification exists is only performed when the air conditioner is in dehumidification or cooling mode; that is, the predicted humidity and target humidity are first obtained after a specified period of time.

[0157] Traditional methods for determining over-dehumidification rely on the current humidity level and a set threshold. However, this approach indicates that over-dehumidification has already occurred or is about to occur. Adjusting the air conditioner's dehumidification capacity at this point results in a poor user experience. Therefore, this application uses predicted humidity after a specified time period to determine if over-dehumidification is occurring. This allows for proactive adjustment of the air conditioner's dehumidification capacity, preventing over-dehumidification.

[0158] As a preferred implementation of this application, the indoor humidity and exogenous variable parameters within the current period are obtained;

[0159] The indoor humidity and the exogenous variable parameters are input into the target time series model to obtain the preset humidity after a specified duration;

[0160] The exogenous variable parameters include at least one of the following:

[0161] Indoor temperature, set temperature, air conditioning mode, fan speed, and compressor frequency.

[0162] The training steps for the target time series model include:

[0163] An initial time series model is obtained by modeling indoor temperature based on a time series model, wherein a lag operator and a seasonal term are introduced in the initial time series model;

[0164] Historical data is acquired, and the model parameters and seasonality coefficients of the initial time series model are adjusted based on the historical data to obtain the target time series model. The historical data includes historical humidity data and historical exogenous variable parameters.

[0165] Preferably, the step of adjusting the model parameters and seasonality coefficients of the initial time series model based on the historical data to obtain the target time series model includes:

[0166] Based on the analysis of autocorrelation function and partial autocorrelation function graphs, the model parameters and seasonality coefficients were initially determined, where the seasonality coefficients include the sampling period.

[0167] Select a humidity value within a sampling period and an exogenous variable parameter as input;

[0168] The parameters are optimized and fitted using the maximum likelihood estimation method;

[0169] The target time series model is obtained by determining the model parameters and seasonality coefficients based on the fitting residuals.

[0170] In this process, both historical data and model input data need to undergo stabilization processing and evaluation. Specifically:

[0171] Acquire target data, which is the indoor humidity and exogenous variable parameters in the current period, or historical data;

[0172] Abnormal data is removed from the target data using a threshold method; for example, data exceeding or falling below a threshold is identified as abnormal data and then removed.

[0173] The ADF test method was used to obtain the statistics and p-values ​​of the target data after removing outliers.

[0174] Based on the statistics and p-value, determine whether the target data is stationary;

[0175] When the data is not stationary, it is differentially processed until it becomes stationary; when it is stationary, the stationary data is input into the target time series model.

[0176] Furthermore, determining whether the target data is stationary based on the statistic and the p-value includes:

[0177] Assuming the target data is stable, if the absolute value of the statistic is greater than the critical value, or if the P value is less than or equal to the preset value, the target data is determined to be unstable; if the absolute value of the statistic is less than or equal to the critical value, or if the P value is greater than the preset value, the target data is determined to be stable.

[0178] If the absolute value of the statistic is greater than the critical value, or if the P-value is less than or equal to the preset value, the target data is judged to be stable. If the absolute value of the statistic is less than or equal to the critical value, or if the P-value is greater than the preset value, the target data is judged to be non-stable.

[0179] Furthermore, the differential processing of the data until it stabilizes includes:

[0180] Perform a first-order difference on the data;

[0181] The statistical measures and p-values ​​of the data after first-order differencing were obtained based on the ADF test method;

[0182] Determine whether the data after first-order differencing is stationary based on statistics and p-values;

[0183] If the data is not stable, repeat the above steps until the data becomes stable.

[0184] This application uses a time series model for humidity prediction. In practice, prediction can also be based on historical data. Historical data prediction involves obtaining current parameters, such as indoor humidity, outdoor humidity, current operating conditions, indoor temperature, and outdoor humidity. When the current parameters are the same as the historical parameters, and the trend of each parameter's change is the same as the trend of historical data change, the humidity after a specified period of historical data is used as the predicted humidity.

[0185] As a preferred implementation of this application, obtaining the target humidity after a specified time period includes:

[0186] Get the current indoor ambient temperature and the rate of change of the current indoor ambient temperature;

[0187] The target humidity is determined based on the current indoor ambient temperature and the rate of change of the current indoor ambient temperature.

[0188] Among them, when the current indoor ambient temperature change rate is the same, the higher the current indoor ambient temperature, the greater the target humidity; when the current indoor ambient temperature is the same, the greater the current indoor ambient temperature change rate, the greater the target humidity.

[0189] In another embodiment, the target humidity after a specified time period can also be determined based on a pre-set table or correspondence. For example, each set of indoor and outdoor ambient temperatures in the table corresponds to a target humidity.

[0190] The early warning control module 62 is used to control the air conditioner to enter an early warning state when the predicted humidity is less than the target humidity and the minimum predicted humidity is less than the preset humidity lower limit.

[0191] It is understood that the predicted humidity obtained using a time series model includes humidity values ​​from multiple time points, with the lowest predicted humidity value being the minimum predicted humidity. When the predicted humidity is lower than the target humidity and the minimum predicted humidity is lower than a preset humidity lower limit, it indicates that the air conditioner will experience excessive dehumidification after a specified period. Therefore, a warning state is activated.

[0192] The dehumidification adjustment module 63 is used to adjust the dehumidification capacity of the air conditioner according to the target humidity and the actual humidity when the air conditioner enters the warning state.

[0193] In one embodiment, the difference between the target humidity and the actual humidity is calculated, and the dehumidification capacity of the air conditioner is adjusted based on the sign and absolute value of the difference between the target humidity and the actual humidity.

[0194] For example, when the difference between the target humidity and the actual humidity is greater than 0, the dehumidification capacity of the air conditioner is reduced. The greater the difference between the target humidity and the actual humidity, the greater the reduction in the dehumidification capacity. For example, adjusting the dehumidification capacity of the air conditioner can be done by changing the evaporator temperature or adjusting the contact time between the air and the evaporator (e.g., changing the speed of the indoor fan). Reducing the dehumidification capacity means increasing the evaporator temperature or increasing the indoor fan speed.

[0195] When the difference between the target humidity and the actual humidity is less than 0, the dehumidification capacity of the air conditioner is increased. The greater the difference between the target humidity and the actual humidity, the greater the increase in the dehumidification capacity of the air conditioner.

[0196] As a preferred implementation of this application, adjusting the dehumidification capacity of the air conditioner according to the target humidity and the actual humidity includes:

[0197] Calculate the humidity difference between the target humidity and the actual humidity, as well as the rate of change of the humidity difference;

[0198] The humidity difference and the rate of change of the humidity difference are input into the fuzzy controller as input quantities to obtain the adjustment strategy of the air conditioner's dehumidification capacity.

[0199] For example, the fuzzy controller takes the current humidity error e = RH_target - RH_now and the humidity change rate Δe (i.e., the difference between RH_now and the previous RH) as input variables, and normalizes the values ​​using methods such as Z-score or Min-Max, standardizing the value range to [-1, +1] for fuzzification operation.

[0200] The normalized input variables e and Δe are divided into multiple fuzzy language sets, where e includes seven levels: Nmax, Nmid, Nmin, Z0, Pmin, Pmid, and Pmax. Δe is divided into three levels: N (negative change), Z (no change), and P (positive change), as shown in Table 1 (output control mode ΔU).

[0201] The control changes include "enhanced" (significantly reducing dehumidification intensity), "maintaining" (keeping the current control state unchanged), and "strong enhancement" (significantly increasing dehumidification capacity). The system performs combined reasoning on the above inputs based on a predefined rule base. For example, when e is Nmax and Δe is N (negative change), the output control quantity ΔU is "strong reduction," indicating that the dehumidification intensity needs to be significantly reduced; when e is Z0 and Δe is Z (no change), ΔU is "maintain," indicating that the current humidity is stable and no adjustment is needed. The system sets a minimum humidity protection threshold (e.g., RH_min = 38%) to prevent excessively low humidity due to erroneous control. The SARIMAX model parameters are periodically retrained to adapt to different seasons and usage environments, achieving closed-loop system control.

[0202] The air conditioning humidity control device provided in this application, when the air conditioner is operating in dehumidification or cooling mode, acquires the predicted humidity and target humidity after a specified period of time. When the predicted humidity is lower than the target humidity and the minimum predicted humidity is lower than a preset humidity lower limit, the air conditioner is controlled to enter a warning state. In the warning state, the air conditioner's dehumidification capacity is adjusted based on the target humidity and the actual humidity. This solution compares the predicted humidity after a specified period of time with the target humidity. When the predicted humidity is lower than the target humidity and the minimum predicted humidity is lower than the preset humidity lower limit, it indicates that excessive dehumidification will occur after the specified period of time. Therefore, the dehumidification capacity of the air conditioner is adjusted in advance to ensure that excessive dehumidification does not occur after the specified period of time, improving user comfort and experience.

[0203] Based on the same inventive concept, such as Figure 7 As shown, this application also provides an air conditioning humidity control system 70, comprising:

[0204] At least one processor 71 and at least one memory 72;

[0205] The memory stores the executable instructions of the processor;

[0206] The processor is configured to execute the air conditioning humidity control method provided in the above embodiments.

[0207] The air conditioning humidity control system provided in this application stores executable instructions of the processor in a memory. When these executable instructions are executed, the processor can obtain the predicted humidity and target humidity after a specified period of time when the air conditioner is running in dehumidification or cooling mode. When the predicted humidity is less than the target humidity and the minimum predicted humidity is less than a preset lower humidity limit, the air conditioner is controlled to enter a warning state. In the warning state, the air conditioner's dehumidification capacity is adjusted according to the target humidity and the actual humidity. This application's solution can compare the predicted humidity after a specified period of time with the target humidity. When the predicted humidity is less than the target humidity and the minimum predicted humidity is less than the preset lower humidity limit, it indicates that excessive dehumidification will occur after the specified period of time. Therefore, the dehumidification capacity of the air conditioner is adjusted in advance to ensure that excessive dehumidification does not occur after the specified period of time, thereby improving user comfort and experience.

[0208] Based on the same inventive concept, this application also provides an air conditioner that applies the air conditioning humidity control method provided in any of the above embodiments.

[0209] The air conditioner provided in this application, by applying the air conditioning humidity control method provided in any of the above embodiments, can obtain the predicted humidity and target humidity after a specified period when the air conditioner is running in dehumidification or cooling mode. When the predicted humidity is less than the target humidity and the minimum predicted humidity is less than a preset humidity lower limit, the air conditioner is controlled to enter a warning state. When the air conditioner enters the warning state, the dehumidification capacity of the air conditioner is adjusted according to the target humidity and the actual humidity. This application's solution can compare the predicted humidity after a specified period with the target humidity. When the predicted humidity is less than the target humidity and the minimum predicted humidity is less than the preset humidity lower limit, it indicates that excessive dehumidification will occur after the specified period. Therefore, the dehumidification capacity of the air conditioner is adjusted in advance to ensure that excessive dehumidification will not occur after the specified period, thereby improving user comfort and experience.

[0210] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0211] It should be noted that in the description of this application, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "a plurality of" means at least two.

[0212] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. An air conditioning humidity control method, characterized in that, include: When the air conditioner is in dehumidification or cooling mode, obtain the predicted humidity and target humidity after a specified period of time. When the predicted humidity is less than the target humidity and the minimum predicted humidity is less than the preset humidity lower limit, the air conditioner is controlled to enter the warning state. When the air conditioner enters the warning state, the dehumidification capacity of the air conditioner is adjusted according to the target humidity and the actual humidity.

2. The method according to claim 1, characterized in that: The process of obtaining the predicted humidity after a specified duration includes: Obtain the indoor humidity and exogenous variable parameters for the current period; The indoor humidity and the exogenous variable parameters are input into the target time series model to obtain the preset humidity after a specified duration; The exogenous variable parameters include at least one of the following: Indoor temperature, set temperature, air conditioning mode, fan speed, and compressor frequency.

3. The method according to claim 2, characterized in that: The training steps for the target time series model include: An initial time series model is obtained by modeling indoor temperature based on a time series model, wherein a lag operator and a seasonal term are introduced in the initial time series model; Historical data is acquired, and the model parameters and seasonality coefficients of the initial time series model are adjusted based on the historical data to obtain the target time series model. The historical data includes historical humidity data and historical exogenous variable parameters.

4. The method according to claim 3, characterized in that, Also includes: Acquire target data, which is the indoor humidity and exogenous variable parameters in the current period, or historical data; Abnormal data is removed from the target data using a threshold method; The ADF test method was used to obtain the statistics and p-values ​​of the target data after removing outliers. Based on the statistics and p-value, determine whether the target data is stationary; When the data is not stationary, it is differentially processed until it becomes stationary; when it is stationary, the stationary data is input into the target time series model.

5. The method according to claim 4, characterized in that: The step of determining whether the target data is stationary based on the statistic and p-value includes: Assuming the target data is stable, if the absolute value of the statistic is greater than the critical value, or if the P value is less than or equal to the preset value, the target data is determined to be unstable; if the absolute value of the statistic is less than or equal to the critical value, or if the P value is greater than the preset value, the target data is determined to be stable. If the absolute value of the statistic is greater than the critical value, or if the P-value is less than or equal to the preset value, the target data is judged to be stable. If the absolute value of the statistic is less than or equal to the critical value, or if the P-value is greater than the preset value, the target data is judged to be non-stable.

6. The method according to claim 4, characterized in that: The step of performing differential processing on the data until it stabilizes includes: Perform a first-order difference on the data; The statistical measures and p-values ​​of the data after first-order differencing were obtained based on the ADF test method; Determine whether the data after first-order differencing is stationary based on statistics and p-values; If the data is not stable, repeat the above steps until the data becomes stable.

7. The method according to claim 3, characterized in that: The process of adjusting the model parameters and seasonality coefficients of the initial time series model based on the historical data to obtain the target time series model includes: Based on the analysis of autocorrelation function and partial autocorrelation function graphs, the model parameters and seasonality coefficients were initially determined, where the seasonality coefficients include the sampling period. Select a humidity value within a sampling period and an exogenous variable parameter as input; The parameters are optimized and fitted using the maximum likelihood estimation method; The target time series model is obtained by determining the model parameters and seasonality coefficients based on the fitting residuals.

8. The method according to claim 1, characterized in that: The target humidity obtained after a specified duration includes: Get the current indoor ambient temperature and the rate of change of the current indoor ambient temperature; The target humidity is determined based on the current indoor ambient temperature and the rate of change of the current indoor ambient temperature. Among them, when the current indoor ambient temperature change rate is the same, the higher the current indoor ambient temperature, the greater the target humidity; when the current indoor ambient temperature is the same, the greater the current indoor ambient temperature change rate, the greater the target humidity.

9. The method according to claim 1, characterized in that: The step of adjusting the dehumidification capacity of the air conditioner based on the target humidity and the actual humidity includes: Calculate the humidity difference between the target humidity and the actual humidity, as well as the rate of change of the humidity difference; The humidity difference and the rate of change of the humidity difference are used as inputs to the fuzzy controller to obtain the adjustment strategy of the air conditioner's dehumidification capacity. The dehumidification capacity of the air conditioner is adjusted based on the aforementioned adjustment strategy.

10. An air conditioning humidity control device, characterized in that, include: The parameter acquisition module is used to obtain the predicted humidity and target humidity after a specified period of time when the air conditioner is in dehumidification or cooling mode. The early warning control module is used to control the air conditioner to enter an early warning state when the predicted humidity is less than the target humidity and the minimum predicted humidity is less than the preset humidity lower limit. The dehumidification adjustment module is used to adjust the dehumidification capacity of the air conditioner according to the target humidity and the actual humidity when the air conditioner enters the warning state.

11. An air conditioning humidity control system, characterized in that, include: At least one processor and at least one memory; The memory stores the executable instructions of the processor; The processor is configured to perform the method according to any one of claims 1-9.

12. An air conditioner, characterized in that, The method described in any one of claims 1-9.

Images