Air conditioner control method and air conditioner control system based on multi-sensor fusion

Abstract

The invention relates to the technical field of air conditioner control, in particular to an air conditioner control method and system based on multi-sensor fusion, a first temperature sensor obtains the temperature of a single point, and a second temperature sensor obtains temperature array data; based on a frame difference filtering algorithm, the number of indoor people and human body coordinate positions are detected, disturbance of the human body temperature to the environment temperature is filtered, the temperature of the first temperature sensor and the temperature of the second temperature sensor are fused through a weighted average method, and the indoor average temperature is obtained; and controlling the power of the compressor and adjusting the angle of the air guide strip according to the temperature difference between the indoor average temperature and the set temperature. Errors caused by a traditional single temperature measurement mode are effectively avoided, the indoor environment temperature detection precision is improved, the number of people in a room and human body coordinate position information can be detected in real time, interference of human body temperature on environment temperature measurement can be removed, the intelligent sensing capacity of an air conditioner system is achieved, and the indoor environment temperature detection precision is improved. And the somatosensory comfort of the user is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of air conditioner control, in particular to an air conditioner control method based on multi-sensor fusion and an air conditioner control system. BACKGROUND

[0002] The variable frequency air conditioner can control the power of the compressor by controlling the power supply frequency of the compressor. The power of the compressor dynamically changes with the temperature difference between the indoor temperature and the preset temperature. When the temperature difference increases, the power of the compressor increases, and when the temperature difference decreases, the power of the compressor decreases. This adjustment method not only makes the room temperature quickly reach the preset temperature, improves the accuracy of temperature control, but also reduces the start-stop times of the compressor and reduces energy consumption. However, most of the existing room temperature measurement schemes use a method of installing a temperature sensor in the form of a thermal sensor device near the air return port of the air conditioner. Since the air conditioner is in a cooling state, the temperature in the room is not uniform, so this method has a large error in measuring the indoor temperature. SUMMARY

[0003] The present application aims to at least solve the technical problems existing in the prior art. To this end, the present application proposes an air conditioner control method based on multi-sensor fusion and an air conditioner control system, which improves the accuracy of indoor temperature measurement, and can detect the human body coordinate position in the room and control the direction of the air deflector according to the human body coordinate position information.

[0004] According to the air conditioner control method based on multi-sensor fusion according to some embodiments of the first aspect of the present application, the following steps are included:

[0005] S100, a first temperature sensor is installed near the air return port of the air conditioner for acquiring the temperature of a single point, and a second temperature sensor is installed on the indoor wall for acquiring temperature array data;

[0006] S200, based on the frame difference filtering algorithm, the number of people in the room and the human body coordinate position are detected, the disturbance of the human body temperature to the environment temperature is filtered, the temperatures of the first temperature sensor and the second temperature sensor are fused by the weighted average method to obtain the average indoor temperature;

[0007] S300, according to the temperature difference between the average indoor temperature and the set temperature, the power of the compressor is controlled by controlling the voltage frequency of the compressor, and the control of the angle of the air deflector is judged and executed according to the information of the indoor human center coordinate.

[0008] The air conditioner control method based on multi-sensor fusion according to some embodiments of the first aspect of the present application has at least the following beneficial effects:

[0009] The application obtains single-point temperature data by arranging a first temperature sensor near an air return outlet of an air conditioner, and arranges a second temperature sensor on an indoor wall to collect temperature array data at multiple positions, and combines a weighted average method to fuse the two, effectively avoiding errors caused by a traditional single temperature measurement method, improving the precision of indoor environment temperature detection, and using a frame difference-based filtering algorithm to analyze indoor heat source images, which can detect the number of people and the coordinate position information of the human body in real time, which not only helps to remove the interference of the human body temperature on the environment temperature measurement, but also provides basic data support for subsequent air guide control, realizes the intelligent sensing ability of the air conditioning system, and improves the user's body comfort.

[0010] According to the air conditioner control method based on multi-sensor fusion according to some embodiments of the first aspect of the application, the S200 specifically comprises:

[0011] S210, band-pass filtering the infrared array data;

[0012] S220, performing frame difference operation on the band-pass filtered data, calculating the difference of the pixel values of two consecutive frames of images to detect the motion area, and generating a difference image;

[0013] S230, converting the difference image into a binary image by thresholding, separating the human body area and the background;

[0014] S240, marking adjacent pixels in the binary temperature matrix as the same label to distinguish different human body targets, and using a connected component labeling algorithm to identify independent connected regions;

[0015] S250, filtering noise according to the area of the connected domain, and merging adjacent regions;

[0016] S260, calculating the average value of the coordinates of the connected regions to obtain the center coordinates of the human body, and calculating the average temperature of each point after removing the human body temperature from the initial temperature to obtain the average temperature of the infrared array sensor;

[0017] S270, fusing the temperature of the first temperature sensor and the average temperature of the second temperature acquisition module by using a weighted average method to calculate the indoor average temperature.

[0018] According to the air conditioner control method based on multi-sensor fusion according to some embodiments of the first aspect of the application, the S210 specifically comprises: the temperature array sensor obtains an m*n temperature data matrix, and filters out data satisfying t>T1 and tT2 by band-pass filtering, and the filtered temperature is assigned as an array average temperature value, and the following can be obtained:

[0019]

[0020] According to the air conditioner control method based on multi-sensor fusion, the difference value image generated in S220 is calculated according to the following formula:

[0021] C(x,y) = |B t (x,y) - B t-1 (x,y) |;

[0022] Wherein, B t and B t-1 are temperature data of the current frame and the previous frame respectively.

[0023] According to the air conditioner control method based on multi-sensor fusion, S230 specifically includes:

[0024] The moving area is marked as white, i.e. value 1, and the background is black, i.e. value 0, and the formula for converting into a binary image is as follows:

[0025]

[0026] Wherein, T0 is a threshold value, which can be determined by experiment.

[0027] According to the air conditioner control method based on multi-sensor fusion, S240 specifically includes: traversing the pixels from left to right and from top to bottom, if the values are all foreground and there is a path connecting the two, it is judged as a connected region,

[0028] Dk = {i,j | C(i,j) = 1 and (i,j) is connected with other pixels in the region};

[0029] The set of all connected regions in the image is:

[0030] D = {D1, D2, …, Dk}.

[0031] According to the area of the connected domain, noise is filtered and adjacent regions are merged;

[0032] Area i ≥ K min , wherein Amin is the minimum effective area;

[0033] Then, adjacent regions are merged: the distance between the centers of two connected domains is calculated:

[0034]

[0035] When d ≤ dmax, the two are merged, and dmax is an adjustable parameter.

[0036] According to the air conditioner control method based on multi-sensor fusion, S260 specifically includes:

[0037] The average value of the connected region coordinates is calculated to obtain the human body center coordinate P(x, y);

[0038] After the human body temperature is removed from the initial temperature A(x, y), the average temperature of each point is obtained to obtain the average temperature T of the infrared array sensor array .

[0039] The indoor average temperature is calculated by fusing T r , the average temperature T array of the second temperature acquisition module, T array and T r by using a weighted average method, and the calculation formula is as follows:

[0040]

[0041] σ1 and σ2 are values taken according to the accuracy in the technical specifications of the first temperature sensor and the second temperature sensor.

[0042] According to the air conditioner control method based on multi-sensor fusion according to some embodiments of the first aspect of the application, the power of the compressor is controlled by controlling the voltage frequency of the compressor according to the temperature difference between the indoor average temperature and the set temperature, and the voltage frequency of the compressor is as follows:

[0043]

[0044] Where, Δt is the difference between the indoor average temperature T final and the preset temperature T set of the air conditioner, t1, t2, t3, t4 are temperature difference constants, the size of which is determined by experiments; f1, f2, f3, f3, f4, f5 are frequency constants of the air conditioner operation, the size of which is determined by experiments; a is a person number correction parameter, when the indoor person number is 0, a = 0.8; when the indoor person number is 1, a = 1; when the indoor person number is 2, a = 1.1; when the indoor person number is 3, a = 1.2; and when the indoor person number is greater than or equal to 4, a = 1.4.

[0045] According to the air conditioner control method based on multi-sensor fusion according to some embodiments of the first aspect of the application, the control of the angle of the air deflector strip is determined and executed according to the information of the indoor human center coordinate, and the control strategy of the human body coordinate and the air deflector strip of the air conditioner is as follows:

[0046] The angle of the air deflector strip is as follows:

[0047] Wherein, i is the gear number of the left and right swing of the air deflector, k is the gear number of the left and right swing of the air deflector,

[0048] Frame selection specific area, when any one human body center coordinate is in the preset coordinate area, the air deflector angle is switched to θ 11 , that is, the left and right angle of the air deflector is located at the leftmost, the up and down angle is located at the uppermost, any one human body center coordinate P(x,y) detected, X1≤x≤X2 and Y1≤y≤Y2, the air deflector angle θ is adjusted to θ 11 , wherein X1, X2, Y1, Y2 are preset coordinate range values.

[0049] According to the air conditioner control system based on multi-sensor fusion of some embodiments of the second aspect of the application, the air conditioner control method based on multi-sensor fusion of some embodiments of the first aspect is adopted, the air conditioner control system comprises a first temperature sensor, a second temperature sensor, an operation module, an air deflector control module and an outdoor compressor control module, the output end of the first temperature sensor and the output end of the second temperature sensor are connected with the input end of the operation module, the input end of the air deflector control module and the input end of the outdoor compressor control module are connected with the output end of the operation module.

[0050] According to the air conditioner control system based on multi-sensor fusion of some embodiments of the second aspect of the application, the beneficial effects of the air conditioner control system based on multi-sensor fusion of some embodiments of the first aspect have been described, which will not be repeated here.

[0051] Additional aspects and advantages of the application will be described in part below, some will become apparent from the following description, or will be understood by those skilled in the art through practice of the application. BRIEF DESCRIPTION OF DRAWINGS

[0052] The above and / or additional aspects and advantages of the application will become apparent and be readily understood from the following description, taken in connection with the accompanying drawings, in which:

[0053] Figure 1 The flow chart of the first aspect embodiment of the application.

[0054] Figure 2 The flow chart of step S200 of the first aspect embodiment of the application.

[0055] Figure 3 The principle block diagram of the second aspect embodiment of the application. DETAILED DESCRIPTION

[0056] Embodiments of the present application are described below in detail, examples of which are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only, for the purpose of explaining the present application, and should not be understood as a limitation of the present application.

[0057] In the description of the present application, it should be understood that the orientation description, such as the orientation or position relationship indicated by up, down, left, right, front, back, etc. is based on the orientation or position relationship shown in the drawings, which is only for the purpose of facilitating the description of the present application and simplifying the description, and does not indicate or imply that the modules or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application.

[0058] In the description of the present application, if the first, second, etc. are described, it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying the relative importance of the technical features indicated, or implying the number of technical features indicated, or implying the order of the technical features indicated.

[0059] In the description of the present application, unless otherwise explicitly limited, the words such as arrangement, installation, connection, etc. should be broadly understood, and the person skilled in the art can reasonably determine the specific meaning of the above words in the present application in combination with the specific content of the technical solution.

[0060] As shown in Figures 1-2 The first aspect of the present application provides a multi-sensor fusion-based air conditioner control method.

[0061] A multi-sensor fusion-based air conditioner control method, comprising the following steps:

[0062] S100, a first temperature sensor is installed near an air conditioner return air inlet for acquiring a single-point temperature, and a second temperature sensor is installed on an indoor wall for acquiring temperature array data, and the sampling frequency of the temperature sensor data is h;

[0063] S200, based on a frame difference filtering algorithm, detecting the number of people in the room, the human body coordinate position, filtering the disturbance of human body temperature on the environment temperature, and fusing the temperatures of the first temperature sensor and the second temperature sensor by a weighted average method to obtain the indoor average temperature;

[0064] S300, according to the temperature difference between the indoor average temperature and the set temperature, controlling the power of the compressor by controlling the voltage frequency of the compressor, and judging and executing the control of the air deflector angle according to the information of the indoor human center coordinate.

[0065] The application obtains single-point temperature data by arranging a first temperature sensor near an air return outlet of an air conditioner, and arranges a second temperature sensor on an indoor wall to collect temperature array data of multiple positions, and combines and processes the two by using a weighted average method, effectively avoiding errors caused by a traditional single temperature measurement method, improving the precision of indoor environment temperature detection, and using a frame difference-based filtering algorithm to analyze an indoor heat source image, which can detect the number of people and the coordinate position information of the human body in real time, which not only helps to remove the interference of the human body temperature on the environment temperature measurement, but also provides basic data support for subsequent air guide control, realizes the intelligent sensing ability of the air conditioning system, and improves the user's body comfort.

[0066] The air conditioner control method based on multi-sensor fusion described in the embodiment specifically includes:

[0067] S210, band-pass filtering the infrared array data;

[0068] S220, performing frame difference operation on the band-pass filtered data, calculating the difference of the pixel values of two continuous frames of images to detect the motion area, and generating a difference value image;

[0069] S230, converting the difference value image into a binary image by thresholding, separating the human body area and the background;

[0070] S240, marking adjacent pixels in the binary temperature matrix as the same label to distinguish different human body targets, and using a connected component labeling algorithm to identify independent connected regions;

[0071] S250, filtering noise according to the area of the connected domain, and merging adjacent regions;

[0072] S260, calculating the average value of the coordinates of the connected regions to obtain the center coordinates of the human body, and calculating the average temperature of each point after removing the human body temperature from the initial temperature to obtain the average temperature of the infrared array sensor;

[0073] S270, fusing the temperature of the first temperature sensor and the average temperature of the second temperature acquisition module by using a weighted average method to calculate the indoor average temperature.

[0074] Specifically, the complete image processing process including band-pass filtering, frame difference operation, binary processing, connected component labeling, region merging and center calculation can effectively identify the number of people and the position of the human body, so as to remove the interference of the human body heat source on the environment temperature measurement, improve the temperature measurement precision, and provide reliable human positioning basis for subsequent intelligent air guide control.

[0075] The air conditioning control method based on multi-sensor fusion described in this embodiment includes step S210, which specifically includes: acquiring an m×n temperature data matrix from a temperature array sensor; filtering out data where t≥T1 and t≤T2 through bandpass filtering; and assigning the filtered-out temperature value as the array average temperature value. The result is:

[0076]

[0077] Specifically, it effectively eliminates the influence of environmental noise and unsteady heat sources, ensuring the stability and reliability of subsequent temperature data processing.

[0078] In the air conditioning control method based on multi-sensor fusion described in this embodiment, the formula for the generated difference image in step S220 is as follows:

[0079] C(x,y)=∣B t (x,y)-B t-1 (x,y)∣;

[0080] Among them, B t and B t-1 These are the temperature data for the current frame and the previous frame, respectively.

[0081] Specifically, by generating a difference image through frame difference operation, the system highlights the changing area between two consecutive frames, thereby accurately identifying the area where moving objects are located. This provides a key image foundation for subsequent human detection and localization, and enhances the system's adaptability to dynamic scenes.

[0082] The air conditioning control method based on multi-sensor fusion described in this embodiment, specifically includes step S230:

[0083] The moving area is marked as white (value 1), and the background is black (value 0). The formula for converting it to a binary image is as follows:

[0084]

[0085] T0 is the threshold value, which can be determined experimentally.

[0086] Specifically, a set threshold is used to binarize the difference image, which clearly separates the moving area (human body) from the background, simplifies the image structure, and facilitates subsequent rapid recognition and analysis.

[0087] The air conditioning control method based on multi-sensor fusion described in this embodiment includes step S240, which specifically involves traversing pixels from left to right and from top to bottom. If all values ​​are foreground and there is a path connecting the two, then the region is determined to be a connected region.

[0088] Dk = {i,j | C(i,j) = 1 and (i,j) is connected to other pixels in the region};

[0089] The set of all connected regions in the image is:

[0090] D={D1, D2, …, Dk}.

[0091] The S250 specifically includes:

[0092] Filter noise according to the area of the connected domain, and merge adjacent regions.

[0093] Area i ≥K min Where Amin is the minimum effective area.

[0094] Then, merge adjacent regions: calculate the distance between the centers of two connected domains:

[0095]

[0096] When d≤dmax, merge, and dmax is an adjustable parameter.

[0097] Specifically, the independent human target region is identified by a connected component labeling algorithm, noise is filtered according to the area size, adjacent regions are merged, the accuracy and robustness of human recognition are further improved, misjudgment or missed detection phenomena are avoided, and the stability of the system in a complex scene is enhanced.

[0098] The S260 specifically includes:

[0099] The average value of the coordinates of the connected regions is calculated to obtain the human center coordinates P(x, y).

[0100] After removing the human temperature from the initial temperature A(x, y), the average temperature of each point is taken to obtain the average temperature T of the infrared array sensor array .

[0101] The S270 specifically includes:

[0102] The indoor average temperature T is calculated r , the average temperature T of the second temperature acquisition module is calculated array The weighted average method is used for fusion to fuse T array , T r , and the indoor average temperature is calculated, and the calculation formula is as follows:

[0103]

[0104] σ1, σ2 are values according to the accuracy in the technical specifications of the first temperature sensor and the second temperature sensor.

[0105] Specifically, the above setting improves the accuracy and reliability of the overall environment temperature detection.

[0106] The air conditioner control method based on multi-sensor fusion described in the embodiment specifically includes: controlling the power of the compressor according to the temperature difference between the indoor average temperature and the set temperature by controlling the voltage frequency of the compressor. The voltage frequency of the compressor is as follows:

[0107]

[0108] Where, Δt is the difference between the indoor average temperature T final and the air conditioner preset temperature T set , t1, t2, t3, t4 are temperature difference constants, the size of which is determined by experiment; f1, f2, f3, f3, f4, f5 are frequency constants of air conditioner operation, the size of which is determined by experiment; a is a person number correction parameter, when the indoor person number is 0, a = 0.8; when the indoor person number is 1, a = 1; when the indoor person number is 2, a = 1.1; when the indoor person number is 3, a = 1.2; when the indoor person number is greater than or equal to 4, a = 1.4. Specifically, the more the indoor person number, the slower the air conditioner operation reaches the expected temperature, so the air conditioner compressor needs higher power operation to ensure that the indoor temperature reaches the expected temperature quickly.

[0109] Specifically, the compressor frequency is dynamically adjusted according to the temperature difference between the indoor average temperature and the set temperature, and a person number correction parameter is introduced, so that the compressor power control is more refined, which can meet the load demand under different person numbers, and can also avoid excessive refrigeration / heat, and improve the system energy saving performance and operation efficiency.

[0110] The air conditioner control method based on multi-sensor fusion described in the embodiment specifically includes: controlling the power of the compressor according to the temperature difference between the indoor average temperature and the set temperature by controlling the voltage frequency of the compressor. The voltage frequency of the compressor is as follows:

[0111] The angle of the air deflector is as follows:

[0112] Where, i is the gear number of left and right swing of the air deflector, k is the gear number of left and right swing of the air deflector,

[0113] When any person center coordinate is in the preset coordinate area, the air deflector angle is switched to θ 11, that is, the left and right angle of the air guide bar is located at the leftmost, the up and down angle is located at the topmost, when any human body center coordinate P(x, y) is detected, X1≤x≤X2 and Y1≤y≤Y2, the air guide bar angle θ is adjusted to θ 11 , wherein X1, X2, Y1, Y2 are preset coordinate range values.

[0114] Specifically, by comparing the human body center coordinate with the preset area, the air guide bar angle is dynamically adjusted, so that the cold air is not directly blown to the human body, the user's comfort is improved, the energy waste caused by invalid air supply is reduced, and the intelligent level of the air conditioning system is enhanced.

[0115] The following is a specific embodiment:

[0116] The first temperature sensor adopts a thermistor and is installed near the air return port of the air conditioner to obtain a single-point temperature. The second temperature sensor is installed on the indoor wall and adopts an infrared array sensor or a thermoelectric pile infrared array sensor to obtain temperature array data.

[0117] The thermoelectric pile infrared array sensor in this embodiment has a resolution of 8*12 and a sampling frequency of 1 time / second.

[0118] The sampling starts at the current time, at t1, the temperature obtained by the first temperature sensor is T r1 = 25.5℃, and the temperature value obtained by the second temperature sensor is

[0119]

[0120] At t2, the temperature obtained by the thermistor of the first temperature acquisition module is T r2 = 25.5℃, and the temperature value obtained by the thermoelectric pile infrared array sensor is

[0121]

[0122] (1) The infrared array data is subjected to band-pass filtering processing.

[0123] According to the formula,

[0124] Let T1=5℃ and T2=45℃, so after filtering, B1=A1 and B2=A2

[0125] (2) Frame difference operation is performed on the band-pass filtered data.

[0126] According to the formula,

[0127]

[0128] (3) Binaryzation processing

[0129] The difference image is converted to a binary image by thresholding, separating the human body region and the background. The moving region is marked as white (1) and the background as black (0).

[0130] According to the formula,

[0131] Let T0=1.2℃, then

[0132] (4) Connected component analysis

[0133] According to the formula, D={D1}, so there is only one connected region in C1.

[0134] (5) Human body identification and filtering

[0135] Filter noise according to the area of the connected component, and merge adjacent regions;

[0136] Area i ≥K min ;

[0137] Where Amin is the minimum effective area. In this embodiment, let kmin=3

[0138] According to the formula, Area i satisfies the determination condition Area i ≥K min , so D1 can be identified as the connected region of the human body.

[0139] (6) Calculate and output the human body center coordinates and average temperature.

[0140] According to the coordinates of the non-zero elements of D1 (5, 3), (6, 3), (7, 3), (6, 4), (7, 4), (6, 5), the horizontal coordinate of the human body center position is calculated as:

[0141] P x1 = [(5+6+7+6+7+6) / 6]=6

[0142] P y2 = [(3+3+3+4+4+5) / 6]=4

[0143] Therefore, the center coordinates of the human body are P=(6, 4).

[0144] For the temperature matrix A2, after removing the human body temperature points, the temperature matrix is:

[0145]

[0146] The average value is calculated as:

[0147] T array =∑A′2 / (12*8-6)=26.3

[0148] The indoor average temperature is calculated using the weighted average method. For the thermistor and thermopile infrared array sensor, the characteristics can be taken as σ1 = 0.6 and σ2 = 0.4.

[0149] According to the following formula,

[0150]

[0151] Based on the temperature difference between the average indoor temperature and the set temperature, the compressor power is controlled by adjusting the compressor's voltage frequency. Taking a 1.5 HP inverter air conditioner with a cooling capacity of 3500W as an example, when the array sensor detects that there is one person in the room, the relationship between the average indoor temperature Δt and the set temperature and the inverter air conditioner's power supply frequency is as follows.

[0152]

[0153] When the air conditioner's set temperature Tset is 23℃, Δt = 3.1℃, the compressor's power supply frequency is 70Hz, and the compressor's operating power is approximately 62% of its full-load operating power.

[0154] The angle of the air guide vanes is controlled based on the coordinates of the center of the person inside the room.

[0155] At this point, with the preset values ​​X1 = 3, X2 = 8, Y1 = 2, and Y2 = 9, and the coordinates of the human body's center position P = (6, 4),...

[0156] The judgment condition is met. Therefore, the system automatically adjusts the air guide vane angle to θ. 11 That is, the cold wind blows towards the top and leftmost point, not towards people.

[0157] like Figure 3 As shown, a second aspect of the present invention provides an air conditioning control system based on multi-sensor fusion.

[0158] An air conditioning control system based on multi-sensor fusion is disclosed, employing an air conditioning control method based on multi-sensor fusion according to some embodiments of the first aspect. The air conditioning control system includes a first temperature sensor, a second temperature sensor, a computing module, an air guide vane control module, and an outdoor compressor control module. The output terminals of the first temperature sensor and the second temperature sensor are both connected to the input terminal of the computing module, and the input terminals of the air guide vane control module and the outdoor compressor control module are both connected to the output terminal of the computing module.

[0159] While embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely divergences of the principles and application of the present application and that numerous modifications, changes, substitutions, and alterations can be made thereto without departing from the spirit and scope of the present application, which is defined by the following claims and their equivalents.

Claims

1. A multi-sensor fusion-based air conditioner control method, characterized by, Includes the following steps: S100. Install the first temperature sensor near the air conditioner return air vent to obtain the temperature at a single point, and install the second temperature sensor on the indoor wall to obtain temperature array data. S200 uses a frame difference-based filtering algorithm to detect the number of people and their coordinates indoors, filters out the disturbance of human body temperature to ambient temperature, and fuses the temperatures from the first and second temperature sensors using a weighted average method to obtain the average indoor temperature. S300: Based on the temperature difference between the average indoor temperature and the set temperature, the compressor power is controlled by controlling the compressor voltage frequency, and the air guide vane angle is controlled based on the indoor center coordinate information.

2. The multi-sensor fusion based air conditioner control method according to claim 1, characterized in that, Specifically, S200 includes: S210. Perform bandpass filtering on the infrared array data; S220. Perform frame difference operation on the bandpass filtered data, calculate the difference in pixel values ​​between two consecutive frames to detect motion regions, and generate a difference image. S230. Convert the difference image into a binary image by using a threshold to separate the human body region and the background; S240. Mark adjacent pixels in the binarized temperature matrix as the same label to distinguish different human targets, and use the connected component labeling algorithm to identify independent connected regions. S250. Filter noise based on the area of ​​connected components and merge adjacent regions; S260. By calculating the average value of the coordinates of the connected regions, the coordinates of the human body center can be obtained. After removing the human body temperature from the initial temperature, the average temperature of each point is taken to obtain the average temperature of the infrared array sensor. S270. The temperature of the first temperature sensor and the average temperature of the second temperature acquisition module are fused using a weighted average method to calculate the indoor average temperature.

3. The multi-sensor fusion based air conditioner control method according to claim 2, characterized in that, S210 specifically includes: the temperature array sensor acquires an m×n temperature data matrix, and through bandpass filtering, data with t≥T1 and t≤T2 are filtered out. The filtered-out temperatures are assigned as the array average temperature value, thus obtaining: 。 4. The multi-sensor fusion based air conditioner control method according to claim 3, characterized in that, In step S220, the formula for generating the difference image is as follows: ； wherein, and Tcurr and Tprev are temperature data of the current frame and the previous frame, respectively.

5. The multi-sensor fusion based air conditioner control method according to claim 4, wherein Specifically, S230 includes: The moving area is marked as white (value 1), and the background is black (value 0). The formula for converting it to a binary image is as follows: wherein is a threshold value, which can be determined experimentally.

6. The multi-sensor fusion based air conditioner control method according to claim 5, wherein, S240 specifically includes: traversing pixels from left to right and from top to bottom; if both values ​​are foreground and there is a path connecting them, then it is determined to be a connected region. Dk={i,j|C(i,j)=1 and (i,j) is connected to other pixels in the region}; The set of all connected regions in the image is: D = {D1, D2, ..., Dk}. Specifically, S250 includes: Noise is filtered based on the area of ​​the connected components, and adjacent regions are merged. where Amin is the minimum effective area; Then, merge neighboring regions: calculate the distance between the centers of two connected regions: ； When d ≤ dmax, merge; dmax is an adjustable parameter.

7. The multi-sensor fusion based air conditioner control method according to claim 6, wherein, Specifically, S260 includes: The average of the connected region coordinates is calculated to obtain the body center coordinates ; For the initial temperature After removing the human body temperature from the initial temperature , the average temperature of each point is taken to obtain the average temperature of the infrared array sensor Specifically, S270 includes: The temperature of the first temperature sensor is calculated as the average indoor temperature The average temperature of the second temperature acquisition module The fusion is performed by using the weighted average method 、 The fusion is performed, and the average indoor temperature is calculated according to the following formula: ； ； is valued according to the precision in the technical specifications of the first temperature sensor and of the second temperature sensor.

8. The multi-sensor fusion based air conditioner control method according to claim 1, wherein, The method of controlling the compressor power by controlling the compressor voltage frequency based on the temperature difference between the average indoor temperature and the set temperature specifically includes: controlling the compressor power by controlling the compressor voltage frequency based on the temperature difference between the average indoor temperature and the set temperature, wherein the compressor voltage frequency is as follows: Wherein, Δt is the indoor average temperature T final The difference between the air conditioning preset temperature T set t1, t2, t3, t4, is the temperature difference constant, the size is determined by experiment; f1, f2, f3, f3, f4, f5 is the frequency constant of air conditioning operation, the size is determined by experiment; a is the number of people correction parameter, when the indoor number is 0, a = 0.8; the indoor number is 1, a = 1; the indoor number is 2, a = 1.1; the indoor number is 3, a = 1.2; the indoor number is greater than or equal to 4, a = 1.

4.

9. The multi-sensor fusion based air conditioner control method according to claim 1, wherein, The information of the indoor human-centered coordinate is used to determine and execute the control of the angle of the air deflector, which includes the following steps: the coordinate of the human body is linked with the air deflector of the air conditioner, and a signal for controlling the direction of the air deflector of the air conditioner is sent, so that the cold air is not directly blown to the human body. The control strategy of the coordinate of the human body and the air deflector of the air conditioner is as follows: The angle of the air deflector bar is as follows: Wherein, i is the gear number of left and right swing of the air deflector, k is the gear number of left and right swing of the air deflector, The specific area is framed, and when any human body center coordinate is in a preset coordinate area, the air guide strip angle is switched to , that is, the left and right angles of the air guide strip are located at the leftmost, the up and down angles are located at the uppermost, and when any human body center coordinate P(x, y) detected is X1≤x≤X2 and Y1≤y≤Y2, the air guide strip angle is , wherein X1, X2, Y1, and Y2 are preset coordinate range values.

10. A multi-sensor fusion based air conditioning control system, characterized by, The air conditioner control system comprises a first temperature sensor, a second temperature sensor, an operation module, an air deflector control module and an outdoor compressor control module. The output end of the first temperature sensor and the output end of the second temperature sensor are connected with the input end of the operation module. The input end of the air deflector control module and the input end of the outdoor compressor control module are connected with the output end of the operation module.

Images