An intelligent control method and system for an air conditioner blower

Abstract

The present invention relates to the technical field of blower regulation, and discloses an intelligent regulation method and system for an air conditioner blower. The method includes obtaining temperature parameters, humidity parameters, airflow parameters and indoor geometric features; performing parameter preprocessing to obtain an environmental data set; according to the environmental data set and the indoor geometric features, using a fluid dynamics model to calculate and simulate the motion state of indoor airflow to obtain a temperature prediction result; performing result analysis based on preset constraint conditions to obtain an initial parameter scheme; performing feedback processing on the parameter scheme to obtain real-time feedback data; based on a preset stable standard ratio, using an air outlet parameter control algorithm to calculate to obtain a corrected parameter scheme; performing equilibrium adjustment to obtain a final parameter scheme, and combining the correlation mechanism between indoor airflow motion and air outlet parameters to achieve dynamic response and precise control of the air supply state.

Description

Technical Field

[0001] The present invention relates to the technical field of air blower regulation, and particularly to an intelligent regulation method and system for an air conditioner air blower. Background Art

[0002] With the complication of building functions (such as commercial complexes, data centers, clean workshops, etc.), the demand for precise regulation of the indoor environment is increasing day by day. Users not only require uniform distribution of temperature, humidity, and air flow, but also need to consider energy efficiency, personnel comfort, and special requirements of specific scenarios (such as cleanliness in pharmaceutical workshops). The "one-size-fits-all" air supply mode of traditional air conditioning systems is difficult to meet the multi-region differential regulation requirements, and intelligent solutions are urgently needed.

[0003] In an existing technology, the system needs to collect environmental data of each region in real time and transmit these data to a central processor for analysis. The proportional-integral-derivative (PID) control algorithm is used, combined with the physical layout of fixed partitions, to regulate the air conditioner air blower. The system divides the building into several static regions (such as by floor and room), and each partition is provided with an independent temperature sensor and air outlet. The PID controller adjusts the air supply volume according to the temperature deviation of each partition to achieve local temperature control.

[0004] However, due to the large differences in environmental parameters between different regions, and the physical characteristics such as area, height, and layout of each region are different, it is difficult for the system to efficiently process complex multi-dimensional data, resulting in low regulation accuracy of the air conditioner air blower in a multi-region environment. Summary of the Invention

[0005] The present invention provides an intelligent regulation method and system for an air conditioner air blower to improve the regulation accuracy of the air conditioner air blower.

[0006] In a first aspect, to solve the above technical problems, the present invention provides an intelligent regulation method for an air conditioner air blower, including:

[0007] Obtain temperature parameters, humidity parameters, air flow parameters, and indoor geometric features;

[0008] According to the temperature parameters, the humidity parameters, and the air flow parameters, perform parameter preprocessing to obtain an environmental data set;

[0009] According to the environmental data set and the indoor geometric features, use a fluid dynamics model to calculate and simulate the motion state of indoor air flow to obtain a temperature prediction result;

[0010] According to the temperature prediction result, perform result analysis based on preset constraint conditions to obtain an initial parameter scheme;

[0011] According to the initial parameter scheme, the parameter scheme is subjected to feedback processing to obtain real-time feedback data;

[0012] According to the real-time feedback data, based on a preset stable standard ratio, air outlet parameter control operations are calculated to obtain a corrected parameter scheme;

[0013] According to the corrected parameter scheme and the temperature parameter, an equilibrium adjustment is performed to obtain a final parameter scheme, and in combination with the correlation mechanism between indoor air flow movement and air outlet parameters, dynamic response and precise control of the air supply state are achieved.

[0014] In an optional implementation manner, the parameter preprocessing is performed according to the temperature parameter, the humidity parameter, and the air flow parameter to obtain an environmental data set, including:

[0015] According to the temperature parameter, the humidity parameter, and the air flow parameter, based on sensor adaptability and a preset reliability index, outliers are removed to obtain regional environmental data;

[0016] According to the regional environmental data, interpolation operations are used to fill in missing values to obtain an environmental data sequence;

[0017] According to the environmental data sequence, standardization operations are performed to obtain a standardized data set;

[0018] According to the standardized data set, regression analysis operations are performed to obtain an environmental data set.

[0019] In an optional implementation manner, the movement state of indoor air flow is calculated and simulated according to the environmental data set and the indoor geometric characteristics to obtain a temperature prediction result, including:

[0020] According to the indoor geometric characteristics, boundary condition parameters are set to obtain an initial gas flow state;

[0021] According to the initial gas flow state, computational fluid dynamics simulation is performed to obtain gas flow dynamic data;

[0022] According to the gas flow dynamic data and the environmental data set, temperature field information is extracted to obtain a temperature prediction result;

[0023] Among them, the gas flow dynamic data is calculated through the following formula:

[0024]

[0025] Among them, is the fluid density, is the gas flow dynamic data, is the velocity field with respect to time The partial derivative of is the pressure gradient force, is the dynamic viscosity, is the Laplacian operator of the velocity field.

[0026] In an alternative embodiment, based on the temperature prediction result, performing result analysis based on preset constraint conditions to obtain an initial parameter scheme, including:

[0027] Performing data extraction according to the temperature prediction result to obtain regional feature data;

[0028] Using the preset wind speed adjustment range and airflow trajectory parameters as constraints, and performing optimization of the regional feature data using a particle swarm optimization algorithm to obtain initial parameters;

[0029] According to the initial parameters, determining whether the deviation between the initial parameters and the actual measured values exceeds a preset threshold. If so, adjusting the model parameter values and recalculating; if not, outputting the initial parameters as the initial parameter scheme;

[0030] Among them, the initial parameters are calculated by the following formula:

[0031]

[0032] Among them, is the initial parameter of the th region, , are acceleration constants, is the optimal position of the th region, is the position of the th region, , are random numbers in the range of [0, 1], is the global optimal position.

[0033] In an alternative manner, based on the initial parameter scheme, performing feedback processing on the parameter scheme to obtain real-time feedback data, including:

[0034] According to the initial parameter scheme, using a sliding window algorithm to calculate the temperature change trend of each region to obtain a temperature change curve;

[0035] Determining whether the deviation between the temperature change curve and a preset stable standard value is less than a preset threshold. If so, determining that the temperature has reached a stable state, and outputting the initial parameter scheme to obtain real-time feedback data; if not, using the K-means clustering algorithm to classify the regions that have not reached the stable state, and recalculating the temperature change trend of each region.

[0036] In an alternative approach, based on the real-time feedback data and a preset stable standard ratio, a correction parameter scheme is calculated using an air outlet parameter control algorithm, including:

[0037] Extract data from the real-time feedback data to obtain regional temperature values;

[0038] Based on the regional temperature values, calculate the wind speed value and the step value using an air outlet parameter control algorithm;

[0039] Based on the wind speed value and the step value, evaluate using an air flow movement simulation model to obtain an evaluation value;

[0040] Determine whether the evaluation value exceeds a preset expected threshold. If so, re-extract data to obtain new regional temperature values, re-determine the wind speed value and the step value, and perform air flow simulation again; if not, output the regional temperature values to obtain a correction parameter scheme.

[0041] In an alternative approach, based on the correction parameter scheme and the temperature parameter, perform balanced adjustment to obtain a final parameter scheme, including:

[0042] Perform time rolling update based on the temperature parameter to obtain real-time temperature data;

[0043] Analyze the temperature distribution of the correction parameter scheme to obtain temperature distribution characteristics;

[0044] Combined with the temperature distribution characteristics, determine whether the real-time temperature data exceeds a preset balance threshold. If so, re-adjust the parameters; if not, output the correction parameter scheme to obtain a final parameter scheme.

[0045] In a second aspect, the present invention provides an intelligent control system for an air conditioner blower, including:

[0046] A data acquisition module for acquiring temperature parameters, humidity parameters, air flow parameters, and indoor geometric features;

[0047] A parameter processing module for performing parameter preprocessing based on the temperature parameters, the humidity parameters, and the air flow parameters to obtain an environmental data set;

[0048] A temperature prediction module for calculating and simulating the movement state of indoor air flow using a fluid dynamics model based on the environmental data set and the indoor geometric features to obtain a temperature prediction result;

[0049] An initial scheme module for performing result analysis based on the temperature prediction result and preset constraint conditions to obtain an initial parameter scheme;

[0050] A real-time data module, configured to perform feedback processing on a parameter scheme according to the initial parameter scheme to obtain real-time feedback data;

[0051] A correction scheme module, configured to calculate a corrected parameter scheme based on the real-time feedback data by using an air outlet parameter control algorithm based on a preset stable standard ratio;

[0052] A result output module, configured to perform equilibrium adjustment according to the corrected parameter scheme and the temperature parameter to obtain a final parameter scheme, and realize dynamic response and precise control of the air supply state by combining the correlation mechanism between indoor air flow movement and air outlet parameters.

[0053] In a third aspect, the present invention further provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the intelligent regulation method of the air conditioner blower described in any one of the above is implemented.

[0054] In a fourth aspect, the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program. When the computer program runs, the device where the computer-readable storage medium is located is controlled to execute the intelligent regulation method of the air conditioner blower described in any one of the above.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] (1) By integrating temperature, humidity, air flow parameters, and indoor geometric features (such as area, height, layout), the present invention breaks through the limitations of traditional single-temperature regulation and accurately identifies dynamic changes in the environment. Preprocessing technologies (such as interpolation filling and principal component analysis) are used to eliminate sensor noise and generate an environmental data set, avoiding regulation deviations caused by misjudgment.

[0057] (2) By using a computational fluid dynamics (CFD) model and combining real-time data to simulate indoor air flow movement, the present invention predicts the temperature field distribution under different air supply parameters, reducing the trial-and-error cost of actual adjustment. According to real-time environmental data (such as door and window opening and closing, and personnel density), the CFD model parameters are updated to ensure that the simulation results are highly consistent with the actual scenario and improve the feasibility of the air supply scheme.

[0058] (3) Through real-time feedback from sensors and in combination with a preset stability standard, the present invention dynamically adjusts parameters such as the air outlet wind speed and trajectory, shortening the temperature equilibrium time. The particle swarm optimization algorithm is used to continuously optimize the regulation strategy based on historical data and real-time feedback, gradually improving the system's adaptive ability. Description of the Drawings

[0059] Figure 1It is a schematic flowchart of the intelligent regulation method of the air conditioner blower provided by the first embodiment of the present invention;

[0060] Figure 2 It is a schematic structural diagram of the intelligent regulation system of the air conditioner blower provided by the second embodiment of the present invention. Specific embodiments

[0061] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0062] Refer to Figure 1 , the first embodiment of the present invention provides an intelligent regulation method for an air conditioner blower, including the following steps:

[0063] S11, obtaining temperature parameters, humidity parameters, airflow parameters and indoor geometric features;

[0064] S12, performing parameter preprocessing according to the temperature parameters, the humidity parameters and the airflow parameters to obtain an environmental data set;

[0065] S13, calculating and simulating the motion state of indoor airflow by using a fluid dynamics model according to the environmental data set and the indoor geometric features to obtain a temperature prediction result;

[0066] S14, performing result analysis based on preset constraint conditions according to the temperature prediction result to obtain an initial parameter scheme;

[0067] S15, performing feedback processing on the parameter scheme according to the initial parameter scheme to obtain real-time feedback data;

[0068] S16, calculating by using an air outlet parameter control algorithm according to the real-time feedback data based on a preset stability standard ratio to obtain a corrected parameter scheme;

[0069] S17, performing balanced adjustment according to the corrected parameter scheme and the temperature parameters to obtain a final parameter scheme, and realizing dynamic response and precise control of the air supply state in combination with the correlation mechanism between indoor airflow movement and air outlet parameters.

[0070] In step S11, temperature parameters, humidity parameters, airflow parameters and indoor geometric features are obtained.

[0071] It should be noted that high-precision temperature sensors are arranged at different key positions indoors, such as at the four corners of the room, areas near windows and doors, and positions where there are heat sources (such as near electrical equipment) or cold sources (such as near the air-conditioning outlet). These sensors can monitor and record the temperature data at the corresponding positions in real time, forming a temperature monitoring network. The type of sensor can be selected according to specific requirements and accuracy requirements. In this embodiment, thermocouple sensors and thermistor sensors are used. According to the stability of the indoor environment and the accuracy requirements for temperature control, the acquisition frequency is set between once per minute and once per 10 minutes. For example, for an ordinary indoor environment that is relatively stable and does not have extremely high requirements for temperature accuracy, the temperature data can be set to be acquired once every 5 minutes; while for places with extremely high requirements for temperature control and rapid environmental changes, such as laboratories and data rooms, it can be set to be acquired once per minute or even at a higher frequency.

[0072] The humidity parameter is measured using humidity sensors, such as capacitive humidity sensors and resistive humidity sensors. Its working principle is based on the change in the capacitance or resistance value of the sensor caused by humidity changes, thereby obtaining humidity data. For example, in a laboratory environment, the humidity sensor continuously monitors the indoor humidity.

[0073] Multiple anemometers and wind vanes are installed indoors to measure the air flow velocity and direction at different positions. The accuracy of the anemometer and wind vane should be selected according to actual needs. For a general indoor environment, an instrument with an accuracy of about ±0.1 m / s can meet the basic needs; while for places with strict requirements for air flow control, such as clean rooms and wind tunnel laboratories, instruments with higher accuracy (such as ±0.05 m / s or even higher) are required. In addition to directly measuring the air flow parameters, air flow visualization techniques, such as the smoke method and the silk thread method, can also be used to visually observe the flow pattern and main path of the indoor air flow.

[0074] The indoor space is scanned and modeled using three-dimensional laser scanning technology or photogrammetry technology to obtain accurate geometric dimensions and shape information of the indoor space. These technologies can quickly generate a three-dimensional model of the indoor space, including the length, width, and height of the room, the position and size of doors and windows, and the distribution and shape of furniture and other obstacles.

[0075] In step S12, according to the temperature parameter, the humidity parameter, and the air flow parameter, parameter preprocessing is performed to obtain an environmental data set, including:

[0076] According to the temperature parameter, the humidity parameter, and the air flow parameter, based on sensor adaptability and a preset reliability index, outliers are removed to obtain regional environmental data;

[0077] Based on the regional environmental data, an interpolation algorithm is used to fill in the missing values to obtain an environmental data sequence;

[0078] Based on the environmental data sequence, a standardization algorithm is used to obtain a standardized data set;

[0079] Based on the standardized data set, a regression analysis method is used to obtain an environmental data set.

[0080] It should be noted that it is necessary to determine the normal working range of the sensor under different temperature, humidity and air flow conditions and the corresponding reliability indicators. For example, a certain temperature sensor is considered reliable when the measurement error is within ±0.5 degrees Celsius in the range of 0 - 50 degrees Celsius. When the collected temperature data exceeds this range, it is marked as an outlier. The same judgment criteria apply to humidity and air flow parameters. Then, these outliers are removed from the original collected data, and the remaining data is the regional environmental data. During the actual data collection process, due to sensor failures or other reasons, data is missing at some moments. The interpolation algorithm can estimate the missing values based on known adjacent data points. For example, when using linear interpolation, if the temperature value at time t1 is T1, the temperature value at time t3 is T3, and the data at time t2 is missing, then the estimated temperature value T2 at time t2 = (t2 - t1)×(T3 - T1) / (t3 - t1)+T1, and finally a complete environmental data sequence is obtained. The standardization algorithm is to convert the data into a distribution with a mean of 0 and a variance of 1. Standardization processing is performed separately for each parameter (temperature, humidity, air flow) in the environmental data sequence. Suppose the data sequence of a certain environmental parameter is x1, x2,..., x n , whose mean is μ and the standard deviation is σ, then the standardized value y i =(x i -μ) / σ. By performing such conversions on all data points of each parameter, a standardized data set is obtained. Regression analysis is used to establish the relationship between variables. The parameters of the regression model are estimated through the known standardized data set to obtain the fitted model, and then this model is used to predict or analyze the environmental data, and finally an environmental data set is obtained. A multiple linear regression model is used (where , ,..., are other relevant environmental parameters, , ,..., are regression coefficients, is the error term). The parameters of the regression model are estimated through the known standardized data set to obtain the fitted model, and then this model is used to predict and analyze the environmental data, and finally an environmental data set is obtained.

[0081] In a specific embodiment, the temperature sensor data suddenly jumps to -40 degrees Celsius, which is clearly not in line with the actual situation and needs to be excluded. Due to condensation, the humidity sensor has short-term data loss. At this time, the average value of adjacent time points can be used for filling. When a person passes by, the airflow sensor generates instantaneous fluctuations, and the moving average method needs to be used for smoothing. The processed data needs to be interpolated to ensure continuity. If temperature data is missing in the production operation area, the cubic spline interpolation method can be used to fill the missing data using the temperature data before and after the missing point. For humidity data, the linear interpolation method is used to calculate the value of the missing point. For airflow data, the nearest neighbor interpolation can be used to maintain the step characteristics of the data. Suppose the environmental data sequence in a certain area is [40, 45, 50, 55, 60], and its mean μ = (40 + 45 + 50 + 55 + 60) / 5 = 50, and the standard deviation σ ≈ 7.91. Then the standardized data is as follows:

[0082] y1 = (40 - 50) / 7.91 ≈ -1.26

[0083] y2 = (45 - 50) / 7.91 ≈ -0.63

[0084] y3 = (50 - 50) / 7.91 = 0

[0085] y4 = (55 - 50) / 7.91 ≈ 0.63

[0086] y5 = (60 - 50) / 7.91 ≈ 1.26

[0087] The standardized data set is [-1.26, -0.63, 0, 0.63, 1.26]. Finally, the environmental data set is obtained through the linear regression model of the above linear regression analysis.

[0088] In step S13, according to the environmental data set and the indoor geometric characteristics, a fluid dynamics model is used to calculate and simulate the movement state of the indoor airflow, and a temperature prediction result is obtained, including:

[0089] According to the indoor geometric characteristics, boundary condition parameters are set to obtain the initial gas flow state;

[0090] According to the initial gas flow state, computational fluid dynamics simulation is performed to obtain the airflow dynamic data;

[0091] According to the airflow dynamic data and the environmental data set, temperature field information is extracted to obtain the temperature prediction result;

[0092] Among them, the airflow dynamic data is calculated by the following formula:

[0093]

[0094] wherein, is the fluid density, is the dynamic data of the air flow, is the velocity field partial derivative with respect to time of, is the pressure gradient force, is the dynamic viscosity, is the Laplacian operator of the velocity field.

[0095] It should be noted that according to the geometric characteristics of the room (such as the shape, size, positions of windows and doors, etc.), the boundary condition parameters of the fluid dynamics model are set to determine the initial state of the air flow pattern. Different sets of air supply volume parameters are set in the initial air flow pattern, and the computational fluid dynamics simulation is run to obtain the air flow motion data in the indoor area. Combining the simulated air flow dynamic data and the environmental data set, and using relevant physical laws such as the energy conservation equation, information about the temperature field is extracted from the simulation results, and then the temperature prediction results at different positions in the room are obtained. The energy conservation equation indicates that the total amount of energy remains unchanged during the process of transfer and conversion. In the indoor environment, the flow of air is accompanied by the transfer of energy, such as heat conduction, convective heat transfer, etc. By establishing an energy balance equation, for example, in a tiny control volume, the incoming energy (including the energy carried by the air flow, the energy introduced by solar radiation, etc.) minus the outgoing energy (the energy carried away by the air flow, the energy dissipated through the walls, etc.) is equal to the rate of change of energy in this control volume. According to this equation, the heat distribution at different positions can be calculated, and thus the temperature field information can be obtained.

[0096] In a specific embodiment, there is a cuboid room with a length of 5 m, a width of 4 m, and a height of 3 m. Inside the room, there is a table with a size of 1 m × 1 m located in the center of the room. When setting the boundary conditions, the velocity at the walls of the room is set to 0 (no-slip condition). For the pressure boundary condition, it can be assumed that a constant pressure value (such as 101325 Pa, i.e., the standard atmospheric pressure) is given at a certain ventilation opening to obtain the initial gas flow state, that is, the approximate distribution and flow state of the gas in the room at the initial moment. Based on the above room model, through simulation calculations using CFD (Computational Fluid Dynamics) software, after a certain time step (such as after 10 seconds with a time step of 0.1 second), the velocity vectors of the gas at different positions in the room (such as the velocity at a certain point is (0.2, 0.1, 0) m / s), the pressure values (such as the pressure at a certain point is 101200 Pa), and other gas flow dynamic data can be obtained. According to the law of conservation of energy, the temperature in the area close to the air-conditioning outlet and far from the window and the computer is 20 °C; the temperature in the area close to the computer and far from the air-conditioning outlet is 28 °C; the temperature in the area close to the window and far from the air-conditioning and the computer is 29 °C, etc. The office space can be divided into multiple small grids, and each grid corresponds to a temperature prediction value, thus forming a complete temperature field distribution, intuitively showing the temperature conditions at different positions indoors. The power of the computer is 200 W and it continuously dissipates heat within 30 minutes. According to the law of conservation of energy, the heat dissipated by the computer will increase the temperature of the surrounding air. Taking a certain table as the center, a small control volume is divided around it, and it is assumed that the volume of this control volume is 1 m³. The heat Q dissipated by the computer within 30 minutes (1800 s) is Q = 200 W × 1800 s = 360000 J. According to the specific heat capacity of air c = 1005 J / (kg·K) and the air density ρ = 1.2 kg / m³, the temperature increase value ΔT of the air in this control volume after absorbing heat is ΔT = Q / (ρVc) = 360000 J / (1.2 kg / m³ × 1 m³ × 1005 J / (kg·K)) ≈ 300 K. Combining with the initial temperature of 25 °C, the theoretical temperature of this control volume will rise to approximately 28 °C, but due to the air flow carrying away heat, the actual temperature will be lower than this value.

[0097] In step S14, according to the temperature prediction result, based on the preset constraint conditions, result analysis is performed to obtain an initial parameter scheme, including:

[0098] According to the temperature prediction result, data extraction is performed to obtain regional feature data;

[0099] Based on the preset wind speed adjustment range and air flow trajectory parameters as constraints, and optimizing the regional feature data using the particle swarm optimization algorithm to obtain the initial parameters;

[0100] Based on the initial parameters, determine whether the deviation between the initial parameters and the actual measured values exceeds a preset threshold. If so, adjust the model parameter values and recalculate; if not, output the initial parameters as the initial parameter solution.

[0101] Among them, the initial parameters are calculated by the following formula:

[0102]

[0103] Among them, is the initial parameter of the th region, and are acceleration constants, is the optimal position of the th region, is the position of the th region, and are random numbers in the interval [0, 1], is the global optimal position.

[0104] It should be noted that the average temperature, maximum temperature, minimum temperature, temperature change rate, etc. of each region are calculated, and these processed data are used as regional characteristic data. The wind speed adjustment range and air flow trajectory parameters are preset as constraint conditions. The wind speed adjustment range is determined according to the actual performance of the air blower and the requirements of the air conditioning system. For example, the wind speed must be between 2 m / s and 8 m / s. The air flow trajectory parameters can be determined according to the layout and ventilation requirements of the shopping mall. For example, the air flow should evenly diffuse from the entrance of the shopping mall to each region. The Particle Swarm Optimization (PSO) algorithm regards each possible solution as a particle in the search space, and each particle has its own position and velocity. At the beginning of the algorithm, the positions and velocities of a group of particles are randomly initialized. Then, the regional characteristic data are input into the objective function, which is to minimize the difference between the actual temperature and the set temperature of each region. The particles continuously "fly" in the search space and update their velocities and positions according to their own historical optimal positions and the historical optimal positions of the group until the optimal solution is found. The initial parameters obtained by the PSO algorithm are compared with the actual measured values, and the deviation between the two is calculated. If the deviation exceeds the preset threshold, it means that the initial parameters deviate greatly from the actual situation, and relevant parameters in the PSO need to be adjusted, such as the acceleration constants and inertia weights in the PSO algorithm, or the constraint conditions need to be reconsidered, and then the PSO algorithm is run again to find new initial parameters. If the deviation does not exceed the preset threshold, the currently obtained initial parameters are output as the final initial parameter solution.

[0105] In a specific embodiment, assuming that the temperature prediction result is 25°C, the system needs to adjust the wind speed and air flow direction of the air conditioner. Extract the regional characteristic data at this temperature from the historical data, for example, the heat load distribution in different regions. Set the wind speed adjustment range from 20% to 100%, and the air flow trajectory parameter from 0° to 360°. Input the regional characteristic data into the objective function, which evaluates the energy consumption and comfort at different wind speeds and air flow directions. Run the particle swarm optimization algorithm to find the optimal combination of wind speed and air flow direction. Assume that the obtained initial parameters are a wind speed of 60% and an air flow direction of 180°. Compare the parameters with the actual measured values (for example, the actual wind speed is 58% and the air flow direction is 175°). If the deviation exceeds the preset threshold (for example, the wind speed deviation exceeds 5% and the air flow direction deviation exceeds 15°), then adjust the acceleration constant parameter value and recalculate. If the deviation is within the acceptable range, output the initial parameters as the initial parameter scheme.

[0106] In step S15, according to the initial parameter scheme, perform feedback processing on the parameter scheme to obtain real-time feedback data, including:

[0107] According to the initial parameter scheme, use the sliding window algorithm to calculate the temperature change trend of each region to obtain a temperature change curve;

[0108] Judge whether the deviation between the temperature change curve and the preset stable standard value is less than the preset threshold. If so, determine that the temperature has reached a stable state, and output the initial parameter scheme to obtain real-time feedback data; if not, use the K-means clustering algorithm to classify the regions that have not reached the stable state, and recalculate the temperature change trend of each region.

[0109] It should be noted that the sliding window algorithm is used to calculate the temperature change trend of each region and generate a temperature change curve. The size of the sliding window refers to the number of consecutive data points considered when calculating the temperature change trend. The choice of window size will affect the accuracy and sensitivity of the calculation results. Generally speaking, a larger window can smooth the data and reduce the influence of noise, but it will mask some short-term temperature changes; a smaller window can reflect the temperature changes more promptly, but it will be affected by noise. In the example of the shopping mall, we can choose every 5 minutes as a window, that is, each window contains 5 temperature data points. Starting from the first data point, continuously select data points of the window size in sequence, and calculate information such as the change rate of temperature within the window. The calculation indicators include the average temperature within the window, the temperature change rate (such as the temperature difference between adjacent data points), etc. After the calculation is completed, slide the window backward by one data point and continue the next calculation until all data points are traversed. Corresponding the temperature change indicators (such as average temperature, temperature change rate) calculated for each window with the central time point of the window, and draw a temperature change curve. This curve intuitively shows the temperature change trend of each region over time. Extract the preset stable standard value and compare it with the temperature change curve. If the deviation between the temperature change curve and the stable standard value is less than the preset threshold, it is judged that the regional temperature has reached a stable state. If the deviation between the temperature change curve and the stable standard value is greater than the preset threshold, the K-means clustering algorithm is used to classify the regions that have not reached the stable state. For different categories of regions, recalculate the regional temperature change trend and repeat the above steps until the regional temperatures all reach the stable state.

[0110] In a specific embodiment, in the management of the air supply parameter scheme, the acquisition of initial data needs to be combined with the layout of multiple area sensors. In a large shopping mall, a temperature sensor network is installed in each floor area to collect temperature data in real time. In a certain shopping mall case, there are twenty temperature sensors in the dining area on the basement floor and thirty temperature sensors in the shopping area on the first floor, which are evenly distributed to ensure the representativeness of data collection. When the sliding window algorithm is applied to the analysis of the temperature change trend, an appropriate time window can be selected, such as every five minutes as a window unit. The temperature data obtained through continuous sampling can reflect the change of the regional temperature over time. For example, during the peak dining period in the dining area, the temperature will rise rapidly, and at this time, more intensive data sampling is required to accurately grasp the temperature change trend. The temperature stability judgment standard can be set from multiple dimensions. For example, a certain shopping mall controls the temperature fluctuation range within plus or minus 0.5 degrees Celsius, and if it lasts for more than fifteen minutes, it is considered to reach a stable state. The K-means clustering algorithm is used for the classification analysis of the regional temperature, and the unstable regions can be divided into different categories. For example, the region is divided into three categories: the temperature continuously rising area, the temperature fluctuating area, and the temperature slowly decreasing area. In a certain shopping mall case, through cluster analysis, it is found that the area near the door is vulnerable to the external environment and forms a temperature fluctuating area, while the internal area is relatively stable. The air supply parameter adjustment strategy needs to take different measures for different category areas. For the area where the temperature continuously rises, the air supply speed can be increased, and the air flow direction can be adjusted to avoid heat accumulation.

[0111] In step S16, according to the real-time feedback data, based on a preset stable standard ratio, a tuyere parameter control algorithm is used for calculation to obtain a modified parameter scheme, including:

[0112] Extract data from the real-time feedback data to obtain the regional temperature value;

[0113] According to the regional temperature value, a tuyere parameter control algorithm is used for calculation to obtain the wind speed value and the step size value;

[0114] Based on the air flow movement simulation model, evaluate according to the wind speed value and the step size value to obtain an evaluation value;

[0115] Judge whether the evaluation value exceeds a preset expected threshold. If so, re-extract data to obtain a new regional temperature value, re-determine the wind speed value and the step size value, and perform air flow simulation again; if not, output the regional temperature value to obtain a modified parameter scheme.

[0116] It should be noted that numerical information related to the regional temperature is identified and extracted. For example, if the real-time feedback data is an array containing multiple parameters such as temperature and pressure collected by a series of sensors, the value of the temperature parameter is found through indexing. If the format of the data array collected by the sensor is fixed, that is, the position of the temperature parameter in the array is fixed. For example, if the array format is [temperature, pressure, humidity,...], then the regional temperature value can be directly extracted through a fixed index position (such as index 0). The wind speed value calculation formula is , and the step value calculation formula is: , where and are the initial wind speed and initial step, and are the wind speed and step adjustment coefficients, is the preset target temperature, is the actual temperature. The wind speed and the step are input into the airflow movement simulation model to calculate the evaluation value E, and the formula is: , where is the number of regional monitoring points, is the th actual wind speed of the monitoring point, is the regional average wind speed. The obtained evaluation value is compared with the preset expected threshold. If the evaluation value exceeds the threshold, the wind speed and step values are readjusted (adjust the wind speed adjustment coefficient and step adjustment coefficient), and the airflow simulation is performed again; if the evaluation value does not exceed the threshold, the regional temperature value is output as the correction parameter solution. For example, if the threshold is set to 0.9, if the evaluation value 0.8 is less than 0.9, the regional temperature value is output; if the evaluation value is greater than 0.9, the data extraction is performed again to obtain a new regional temperature value, and the wind speed and step values are re-determined according to the adjustment strategy (such as increasing the wind speed by 10% and decreasing the step value by 20%, etc.), and then the airflow simulation is performed again. According to the re-determined wind speed value and step value, the airflow trajectory value is updated, and the airflow movement simulation is performed again. The final evaluation value is obtained, and it is judged whether the evaluation value meets the threshold requirement to complete the adjustment process.

[0117] Specifically, high-precision temperature sensing points are set inside the shopping mall, and several temperature acquisition points are arranged in each area to obtain temperature data from different positions. The preset stability standard is that the temperatures in multiple areas inside the shopping mall are maintained between 23 and 25 degrees, and the temperature fluctuation range does not exceed 0.5 degrees. The controller automatically calculates the appropriate airspeed adjustment amount according to the temperature deviation value. The temperature in a certain area is 27 degrees, exceeding the set value by 4 degrees. The controller will calculate that the airspeed needs to be adjusted to 3 meters per second according to the temperature deviation value, and the step value is set to be adjusted once every ten minutes. The generation of the air flow trajectory plan needs to consider the distribution of obstacles in the area. Taking the atrium of the shopping mall as an example, by reasonably arranging the outlet orientation angle and position, an ideal air flow organization is formed. The air flow movement simulation uses a computational fluid dynamics model, which can simulate the movement trajectory and temperature field distribution of the air flow under different air supply parameters and calculate the evaluation value. Finally, it is judged whether the evaluation value exceeds the preset expected threshold. If so, the airspeed value and step value are re-determined, and the air flow simulation is carried out again; if not, the real-time feedback data is output to obtain the corrected parameter plan.

[0118] In step S17, according to the corrected parameter plan and the temperature parameters, an equilibrium adjustment is performed to obtain the final parameter plan, including:

[0119] According to the temperature parameters, a time rolling update is performed to obtain real-time temperature data;

[0120] Perform a temperature distribution analysis on the corrected parameter plan to obtain temperature distribution characteristics;

[0121] Combined with the temperature distribution characteristics, it is judged whether the real-time temperature data exceeds the preset equilibrium threshold. If so, the parameters are readjusted; if not, the corrected parameter plan is output to obtain the final parameter plan.

[0122] It should be noted that according to the temperature parameters, the system executes a time rolling update mechanism to obtain the latest real-time temperature data. Combining with the temperature distribution characteristic curve, if the real-time temperature data and the curve exceed the deviation threshold, that is, the preset equilibrium threshold, the outlet parameters are adjusted. According to the adjusted outlet parameters, the real-time temperature data of the area sensor is re-obtained, and it is judged whether the temperature change trend approaches the preset value. If the temperature change trend does not approach the preset value, the corresponding relationship between the outlet parameters and the temperature change is further analyzed, and a new adjustment value of the outlet parameters is calculated. Using the new adjustment value of the outlet parameters, the real-time temperature data of the area sensor is obtained again, and it is judged whether the real-time temperature data reaches the preset equilibrium state. If the temperature reaches the preset equilibrium state, a mathematical model of the relationship between the outlet parameters and the temperature change is established according to the temperature change curve to obtain the final parameter plan.

[0123] In a specific embodiment, there is a temperature control system for an office building. The office building has 5 floors, and there are multiple temperature sensors distributed in different areas on each floor. The goal of the system is to maintain the temperature on each floor between 22 and 24 degrees Celsius. The system collects data from the temperature sensors on each floor every 10 minutes. This data is transmitted to the central control system via a wireless network. The central control system performs a time rolling update on the collected data to have the latest real-time temperature data. The system uses a correction parameter scheme to analyze the collected temperature data and identify the characteristics of the temperature distribution, such as temperature peaks, valleys, and change trends. The analysis results show that the temperature in the entrance area of the office building fluctuates greatly due to frequent door openings and closings, while the internal area is relatively stable. The preset equilibrium threshold of the system is ±0.5 degrees Celsius. The central control system compares the real-time temperature data with the preset threshold. It is found that in the entrance area, the real-time temperature data exceeds the equilibrium threshold. The system automatically adjusts the parameters of the air conditioning system in this area, such as increasing the wind speed or adjusting the air outlet angle.

[0124] After adjustment, the system collects real-time temperature data again and makes an equilibrium threshold judgment. If the new real-time temperature data does not exceed the equilibrium threshold, the current correction parameter scheme is output as the final parameter scheme.

[0125] The working process of the present invention is described below by taking a relatively common scenario as an example.

[0126] This embodiment is applied to a large commercial shopping center with five floors, and the area of each floor is about 10,000 square meters. The goal is to maintain the temperature on each floor between 22 and 24 degrees Celsius to provide a comfortable shopping environment. 20 temperature sensors are arranged on each floor, distributed in corridors, entrances, atriums, and shops. 5 humidity sensors, anemometers, and wind direction sensors are placed in key areas. Three-dimensional laser scanning technology is used to obtain the indoor geometric features. Data collection frequency: once every 5 minutes. The collected data is preprocessed by a central processor, including removing outliers, filling in missing values, standardization processing, and regression analysis, to generate an accurate environmental data set. Then, the system uses a computational fluid dynamics model, combines the environmental data set and the indoor geometric features, simulates the movement state of the indoor air flow, and predicts the temperature distribution in different areas. Based on the predicted temperature distribution, the system generates an initial parameter scheme, including the settings of wind speed and air flow direction, and these parameters are calculated by a particle swarm optimization algorithm to find the best air supply strategy. The system also monitors the temperature changes in each area in real time, uses a sliding window algorithm to analyze the temperature change trend, and adjusts the air outlet parameters according to the feedback data. In addition, the system performs an equilibrium adjustment based on the correction parameter scheme and the real-time temperature data to obtain the final parameter scheme, so as to achieve real-time rolling optimization of the control scheme and improve the control accuracy.

[0127] In summary, the present invention discloses an intelligent control method for an air conditioner blower, including obtaining temperature parameters, humidity parameters, air flow parameters, and indoor geometric features; performing parameter preprocessing according to the temperature parameters, the humidity parameters, and the air flow parameters to obtain an environmental data set; calculating and simulating the motion state of indoor air flow using a fluid dynamics model according to the environmental data set and the indoor geometric features to obtain a temperature prediction result; performing result analysis based on preset constraint conditions according to the temperature prediction result to obtain an initial parameter scheme; inputting the parameter scheme into a central processing unit according to the initial parameter scheme to obtain real-time feedback data; calculating according to the real-time feedback data based on a preset stability standard ratio using an air outlet parameter control algorithm to obtain a corrected parameter scheme; performing balanced adjustment according to the corrected parameter scheme and the temperature parameters to obtain a final parameter scheme, and combining the correlation mechanism between indoor air flow motion and air outlet parameters to achieve dynamic response and precise control of the air supply state. The present invention improves the accuracy of blower control through an efficient control method for processing complex multi-dimensional data.

[0128] Referring to Figure 2 , the second embodiment of the present invention provides an intelligent control system for an air conditioner blower, including:

[0129] A data acquisition module for obtaining temperature parameters, humidity parameters, air flow parameters, and indoor geometric features;

[0130] A parameter processing module for performing parameter preprocessing according to the temperature parameters, the humidity parameters, and the air flow parameters to obtain an environmental data set;

[0131] A temperature prediction module for calculating and simulating the motion state of indoor air flow using a fluid dynamics model according to the environmental data set and the indoor geometric features to obtain a temperature prediction result;

[0132] An initial scheme module for performing result analysis based on preset constraint conditions according to the temperature prediction result to obtain an initial parameter scheme;

[0133] A real-time data module for performing feedback processing on the parameter scheme according to the initial parameter scheme to obtain real-time feedback data;

[0134] A correction scheme module for calculating according to the real-time feedback data based on a preset stability standard ratio using an air outlet parameter control algorithm to obtain a corrected parameter scheme;

[0135] A result output module for performing balanced adjustment according to the corrected parameter scheme and the temperature parameters to obtain a final parameter scheme, and combining the correlation mechanism between indoor air flow motion and air outlet parameters to achieve dynamic response and precise control of the air supply state.

[0136] It should be noted that the intelligent control system for an air conditioner blower provided in the embodiments of the present invention is used to execute all the process steps of the intelligent control method for an air conditioner blower in the above embodiments. The working principles and beneficial effects of the two correspond one by one, so they will not be elaborated here.

[0137] The embodiments of the present invention also provide an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a data acquisition program. When the processor executes the computer program, it implements the steps in the above embodiments of the intelligent control method for each air conditioner blower, such as Figure 1 the step S11 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above device embodiments, such as the data acquisition module.

[0138] Exemplarily, the computer program can be divided into one or more modules / units. The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the electronic device.

[0139] The electronic device can be a computing device such as a desktop computer, a notebook, a palm computer, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples of the electronic device and do not constitute a limitation on the electronic device. It may include more or fewer components than the above, or combine some components, or different components. For example, the electronic device may further include input / output devices, network access devices, a bus, etc.

[0140] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the electronic device and connects various parts of the entire electronic device through various interfaces and lines.

[0141] The memory can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory, and invoking the data stored in the memory, the processor realizes various functions of the electronic device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0142] Wherein, if the modules / units integrated in the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above method embodiments of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above method embodiments can be realized. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0143] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided by the present invention, the connection relationships between the modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement without creative efforts.

[0144] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. In particular, for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent control method for an air conditioner blower, characterized in that, Including: Obtaining temperature parameters, humidity parameters, air flow parameters, and indoor geometric features; Performing parameter preprocessing based on the temperature parameters, the humidity parameters, and the air flow parameters to obtain an environmental data set; Calculating and simulating the motion state of indoor air flow using a fluid dynamics model based on the environmental data set and the indoor geometric features to obtain a temperature prediction result; Performing result analysis based on preset constraint conditions according to the temperature prediction result to obtain an initial parameter scheme; Performing feedback processing on the parameter scheme according to the initial parameter scheme to obtain real-time feedback data; Performing an air outlet parameter control operation based on a preset stability standard ratio according to the real-time feedback data to obtain a corrected parameter scheme; Performing balanced adjustment according to the corrected parameter scheme and the temperature parameters to obtain a final parameter scheme, and combining the correlation mechanism between indoor air flow motion and air outlet parameters to achieve dynamic response and precise control of the air supply state; Among them, the performing result analysis based on preset constraint conditions according to the temperature prediction result to obtain an initial parameter scheme includes: Performing data extraction according to the temperature prediction result to obtain regional feature data; Using a preset wind speed adjustment range and air flow trajectory parameters as constraints, and optimizing the regional feature data using a particle swarm optimization algorithm to obtain initial parameters; Judging whether the deviation between the initial parameters and the actual measured values exceeds a preset threshold according to the initial parameters. If so, adjusting the model parameter values and recalculating; if not, outputting the initial parameters as the initial parameter scheme; Among them, the initial parameters are calculated by the following formula: ； Among them, is the initial parameter of the th region, , is the acceleration constant, is the optimal position of the th region, is the position of the th region, , are random numbers within the interval [0, 1], is the global optimal position; Among them, the performing an air outlet parameter control algorithm calculation based on a preset stability standard ratio according to the real-time feedback data to obtain a corrected parameter scheme includes: Performing data extraction on the real-time feedback data to obtain regional temperature values; Calculating a wind speed value and a step value using an air outlet parameter control algorithm according to the regional temperature values; Evaluating based on an air flow motion simulation model according to the wind speed value and the step value to obtain an evaluation value; Judging whether the evaluation value exceeds a preset expected threshold. If so, re-performing data extraction to obtain new regional temperature values, re-determining the wind speed value and the step value, and performing air flow simulation again; if not, outputting the regional temperature values to obtain a corrected parameter scheme; Among them, the air outlet parameters include a wind speed value and a step value; Among them, the calculation formula for the wind speed value is , and the calculation formula for the step value is: , where 、 are the initial wind speed and the initial step, 、 are the wind speed and step adjustment coefficients, is the preset target temperature, is the actual temperature; Among them, the performing balanced adjustment according to the corrected parameter scheme and the temperature parameters to obtain a final parameter scheme includes: Performing time rolling update according to the temperature parameters to obtain real-time temperature data; Performing temperature distribution analysis on the corrected parameter scheme to obtain temperature distribution characteristics; Combining the temperature distribution characteristics to judge whether the real-time temperature data exceeds a preset balance threshold. If so, readjusting the parameters; if not, outputting the corrected parameter scheme to obtain a final parameter scheme.

2. The intelligent regulation method of the air conditioner blower according to claim 1, characterized in that, The performing parameter preprocessing based on the temperature parameters, the humidity parameters, and the air flow parameters to obtain an environmental data set includes: Based on the temperature parameter, the humidity parameter, and the air flow parameter, outliers are removed according to sensor adaptability and a preset reliability index to obtain regional environmental data; Based on the regional environmental data, interpolation operations are used to fill in missing values to obtain an environmental data sequence; Based on the environmental data sequence, standardization operations are performed to obtain a standardized data set; Based on the standardized data set, regression analysis operations are performed to obtain an environmental data set.

3. The intelligent regulation method of the air conditioner blower according to claim 1, characterized in that, Based on the environmental data set and the indoor geometric characteristics, the hydrodynamic model is used to calculate and simulate the motion state of the indoor air flow to obtain a temperature prediction result, including: Based on the indoor geometric characteristics, boundary condition parameters are set to obtain an initial gas flow state; Based on the initial gas flow state, computational fluid dynamics simulation is performed to obtain gas flow dynamic data; Based on the gas flow dynamic data and the environmental data set, temperature field information is extracted to obtain a temperature prediction result; Among them, the gas flow dynamic data is calculated through the following formula: ； wherein, is the fluid density, is the dynamic data of the air flow, is the velocity field with respect to time partial derivative, is the pressure gradient force, is the dynamic viscosity, is the Laplace operator of the velocity field.

4. The intelligent control method of the air conditioner blower according to claim 1, characterized in that, Based on the initial parameter scheme, the parameter scheme is subjected to feedback processing to obtain real-time feedback data, including: Based on the initial parameter scheme, the sliding window algorithm is used to calculate the temperature change trend of each region to obtain a temperature change curve; It is judged whether the deviation between the temperature change curve and the preset stable standard value is less than the preset threshold. If so, it is determined that the temperature reaches a stable state, and the initial parameter scheme is output to obtain real-time feedback data; if not, the K-means clustering algorithm is used to classify the regions that have not reached the stable state, and the temperature change trend of each region is recalculated.

5. An intelligent control system for an air conditioner blower, characterized in that, For implementing the intelligent control method of the air conditioner blower as described in any one of claims 1 to 4, including: A data acquisition module for acquiring temperature parameters, humidity parameters, air flow parameters, and indoor geometric characteristics; A parameter processing module for performing parameter preprocessing based on the temperature parameter, the humidity parameter, and the air flow parameter to obtain an environmental data set; A temperature prediction module for calculating and simulating the motion state of the indoor air flow based on the environmental data set and the indoor geometric characteristics to obtain a temperature prediction result; An initial scheme module for performing result analysis based on preset constraint conditions according to the temperature prediction result to obtain an initial parameter scheme; A real-time data module for performing feedback processing on the parameter scheme based on the initial parameter scheme to obtain real-time feedback data; A correction scheme module for calculating based on the real-time feedback data using the air outlet parameter control algorithm based on a preset stable standard ratio to obtain a corrected parameter scheme; A result output module for performing balanced adjustment based on the corrected parameter scheme and the temperature parameter to obtain a final parameter scheme, and combining the correlation mechanism between the indoor air flow motion and the air outlet parameters to achieve dynamic response and precise control of the air supply state.

6. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the intelligent control method of the air conditioner blower as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the intelligent regulation method of the air conditioner blower according to any one of claims 1 to 4.

Images