Intelligent control system and method for air supply additional guide plate of air conditioner

Abstract

The invention relates to an air conditioner air supply additional guide plate intelligent control system and method. The method comprises the following steps: S1, collecting information Qp of a three-dimensional space where a human body is located; s2, the information Qp of the three-dimensional space where the human body is located is input into the air conditioner air supply control model, and reasoning calculation is conducted to obtain the target opening size Si of each hole in the additional type flow guide plate and the target flow guide three-dimensional angle w of the additional type flow guide plate; the additional flow guide plate is mounted at the air outlet of the air conditioner and is provided with a plurality of holes of which the opening size can be independently controlled, the opening area of the holes is Si, and the included angle between the plane and the horizontal plane of the additional flow guide plate is a target flow guide solid angle w; and S3, controlling the additional guide plate according to the target opening size Si of each hole in the additional guide plate and the target guide solid angle w of the additional guide plate. Intelligent adjustment can be carried out according to indoor environment changes and user requirements, so that airflow distribution is optimized, the comfort degree is improved, and energy consumption is reduced.

Description

Technical Field

[0001] The invention relates to intelligent control of a guide plate, and in particular to an intelligent control system and method for an air-supply-attached guide plate for air conditioning. Background Art

[0002] With the improvement of people's quality of life and the development of technology, the demand for indoor comfort and energy-saving efficiency of air conditioners is increasing. In existing air conditioning systems, air supply guide plates usually adopt fixed or simple mechanical control methods, which makes it difficult to achieve precise air supply and personalized demand matching. Summary of the invention

[0003] The present invention aims to provide an intelligent control system and method for an air-conditioning air supply with an attached guide plate, which can be intelligently adjusted according to indoor environmental changes and user needs to optimize air flow distribution, improve comfort and reduce energy consumption, so as to solve the problems of the background technology.

[0004] By collecting indoor environmental data in real time and combining it with the user's usage habits, the angle and direction of the air supply guide plate of the air conditioner are automatically adjusted to accurately control the direction and speed of the air flow from the air conditioner, thereby achieving the best cooling / heating effect and uniform indoor temperature and humidity distribution.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows: An intelligent control system for an additional air guide plate for air supply of an air conditioner, characterized in that the additional air guide plate is rotatably mounted on the air outlet of the air conditioner and has a plurality of holes whose opening and closing sizes can be independently controlled; The additional deflector is connected to the first rotating shaft through a connecting rod, the first rotating shaft is fixed to the bracket, and the bracket is installed on the air conditioner housing, so that the additional deflector is installed at the air outlet of the air conditioner, and the angle w between the plane of the additional deflector and the horizontal plane is adjusted by rotating the first rotating shaft; Each hole on the additional guide plate can be covered by an independently controlled flip-over membrane. The area of ​​the membrane is slightly larger than the hole and is fixed to the back of the additional guide plate through a second rotating shaft. The opening and closing size Si of the hole can be controlled by different rotation angles. The system comprises: The electric drive device is used to control the angle w between the plane of the additional guide plate and the horizontal plane and the opening and closing size Si of the hole of the additional guide plate; The electric drive device includes a first motor for controlling the first rotating shaft and a second motor for controlling the second rotating shaft; Multi-dimensional sensor module, used to collect the three-dimensional spatial information Qp of the human body; The microprocessor controller is respectively connected to the electric drive device and the multi-dimensional sensor module, and is used to input the three-dimensional spatial information Qp of the human body into the air conditioning air supply control model in the intelligent algorithm module, and perform inference calculation to obtain the target opening and closing size Si' of each hole on the additional guide plate and the target guide solid angle w' of the additional guide plate; according to the target opening and closing size Si' of each hole on the additional guide plate and the target guide solid angle w' of the additional guide plate, the electric drive device is controlled to adjust the angle w between the plane of the additional guide plate and the horizontal plane and the opening and closing size Si of the holes of the additional guide plate.

[0006] Furthermore, the three-dimensional space information Qp of the human body includes: crowd characteristic information P, temperature setting information Ts, three-dimensional temperature field information Tr, three-dimensional humidity field information Rr, three-dimensional air quality information Ar, and regional location information Qr.

[0007] Furthermore, the regional location information Qr includes the space type, indoor area and objects, and the three-dimensional model of the space, wherein: The types of space include sitting workspaces (such as study rooms and meeting rooms), human exercise and activity spaces (such as gyms and dance halls), resting spaces (such as bedrooms and rest rooms) and composite spaces (spaces that combine multiple functions); The indoor areas and items include work areas (areas where people mainly sit at tables and are relatively static), rest areas (areas where people mainly lie or half-lying on beds or sofas), and activity areas (areas where people stand, walk, exercise, etc. in dynamic ways); fixed furniture (such as cabinets, desks, and beds), and movable furniture (such as stools and chairs).

[0008] The three-dimensional spatial model includes the shape and length, width and height information of the indoor space, air-conditioning outlet information (including height from the ground, wall or ceiling to which it belongs, outlet width, etc.), indoor furniture placement area and length, width and height information, and length, width and height information of each area where indoor people are located.

[0009] Furthermore, the crowd characteristic information P includes gender, age, crowd composition, location (the distance between people and air conditioners, such as in the same small area in the same room or in different areas in the same building), number of people, and posture (mainly divided into three types of human postures: standing, sitting, and lying).

[0010] Furthermore, the posture is obtained by a human posture estimation method using a monocular image.

[0011] Furthermore, the human body image obtained by the camera is input into the pre-trained model of Lightweight Openpose to generate a human body posture skeleton framework diagram.

[0012] Furthermore, it also includes an energy storage and power replenishment module, which is electrically connected to the microprocessor controller, and the energy storage and power replenishment module includes a solar photovoltaic power generation device for generating electricity and an energy storage lithium battery pack for powering the system.

[0013] Furthermore, it also includes a timer, which is electrically connected to the microprocessor controller, and the timer is used for timing and time adjustment.

[0014] Furthermore, it also includes a voice interaction module, which is electrically connected to the microprocessor controller, and the voice interaction module is used for voice interaction, and the voice interaction module includes a microphone and a speaker.

[0015] Furthermore, it also includes a noise suppressor, which is electrically connected to the microprocessor controller. The noise suppressor is used to receive noise and then send out a reverse sound wave through a reverse sound wave noise reduction algorithm to suppress the noise. The noise suppressor is used to receive noise and then send out a reverse sound wave through a reverse sound wave noise reduction algorithm to suppress the noise. The noise suppressor includes a microphone, a speaker and an algorithm module.

[0016] Furthermore, it also includes a wireless transceiver device, which is electrically connected to the microprocessor controller, and the wireless transceiver device is used to communicate with an intelligent terminal, which includes a mobile phone, a remote control, a computer, etc.

[0017] A control method based on the above-mentioned air-conditioning air supply additional guide plate intelligent control system comprises the following steps: S1, collect the three-dimensional spatial information Qp of the human body through the multi-dimensional sensor module; S2, inputting the three-dimensional spatial information Qp of the human body into the air conditioning air supply control model in the intelligent algorithm module, and performing inference calculation to obtain the target opening and closing size Si' of each hole on the additional guide plate and the target guide solid angle w' of the additional guide plate; S3. According to the target opening and closing size Si' of each hole on the additional guide plate and the target guide solid angle w' of the additional guide plate, the electric drive device is controlled to adjust the angle w between the plane of the additional guide plate and the horizontal plane and the opening and closing size Si of the holes of the additional guide plate.

[0018] Furthermore, the air supply control model of the air conditioner adopts a neural network multi-classification model, and the training of the neural network multi-classification model includes the following steps: (1) Constructing the initial neural network multi-classification model: (2) The sample data set is used to train the initial neural network multi-classification model to obtain the trained neural network multi-classification model; the three-dimensional spatial information Qp of the human body is used as the input of the model, and the target opening and closing size Si of each hole on the additional guide plate and the target guide solid angle w of the additional guide plate are used as the output of the model; the network model trained by the sample data set should achieve the following objectives: The indoor target area temperature reaches the target as quickly as possible: According to the target area set temperature adjustment ±a℃, the target opening and closing size Si of each hole on the additional guide plate and the target diversion solid angle w of the additional guide plate are controlled. The average time to reach the target in the sample data set is b minutes. The opening and closing size of the guide plate hole matrix is ​​dynamically adjusted through the model algorithm, and the optimal diversion solid angle is calculated based on the target area; The optimal energy-saving target under the temperature balance state of the indoor target area; based on the current value of the detected target area temperature, the regional population characteristics P and the indoor area location information Qr are used as parameters, and the model algorithm is used to control the diversion solid angle and the opening and closing of the holes of the diverter plate. Under the condition of not changing the air supply and temperature of the air conditioner, the optimal energy-saving target is achieved by preferentially controlling the opening degree of the holes of the diverter plate. The average energy consumption of the sample data set is c kWh per hour.

[0019] Generally, a is 0.5, b is 5, and c is 0.7. a, b, and c can also be set as needed.

[0020] After the training is completed, the neural network multi-classification model is tested using a test data set. When the target success rate is higher than the first threshold, it can be used. Otherwise, the amount of data in the sample data set is increased to continue training until the target success rate is higher than the first threshold.

[0021] An electronic device, comprising: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the above method.

[0022] A computer-readable storage medium stores computer instructions, which implement the steps of the above method when executed by a processor.

[0023] The present invention has the following beneficial effects: 1) Solve the problem of air supply position and angle of air conditioner, achieve optimal control of air flow, reduce energy waste and improve the energy efficiency of air conditioner.

[0024] 2) The intelligent control system can automatically adjust the position and angle of the air supply guide plate according to factors such as indoor temperature, humidity and personnel activities, so as to achieve more uniform air distribution and a comfortable indoor environment.

[0025] 3) Automatically adjust the angle of the additional guide plate to reduce the frequent maintenance of air-conditioning equipment and reduce operation and maintenance costs. In addition, the intelligent control system can monitor the operating status of the air conditioner and improve the reliability and stability of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a schematic diagram of the structure of the system of the present invention; Figure 2 is a side structural schematic diagram of the system of the present invention; Figure 3 It is a schematic structural diagram of the diaphragm of the additional guide plate of the present invention; Figure 4 It is a schematic diagram of the transmission structure of the diaphragm of the additional guide plate of the present invention; Figure 5 It is another structural schematic diagram of the diaphragm of the additional guide plate of the present invention; Figure 6 is a flow chart of the method of the present invention; Among them, there are an additional guide plate 1, a hole 1-1, a first rotating shaft 1-2, a diaphragm 1-3, a rotating shaft 1-4, a microprocessor controller 2, a multi-dimensional sensor module 3, an energy storage and charging module 4, a timer 5, a voice interaction module 6, a noise suppressor 7, a wireless transceiver 8, an intelligent algorithm module 9, a worm gear A, and a worm B. DETAILED DESCRIPTION

[0027] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0028] like Figure 1 , an intelligent control system for an air-conditioning air supply additional deflector, comprising a microprocessor controller 2 and an additional deflector 1, wherein the microprocessor controller 2 controls an electric drive device, a multi-dimensional sensor module 3, an energy storage and charging module 4, a timer 5, a voice interaction module 6, a noise suppressor 7, a wireless transceiver 8 and an intelligent algorithm module 9; The additional deflector 1 is installed at the air outlet of the air conditioner and has a plurality of holes 1-1 whose opening and closing sizes can be independently controlled; like Figure 2 The additional guide plate 1 is connected to the first rotating shaft 1-2 through a connecting rod, the first rotating shaft 1-2 is fixed to the bracket, and the bracket is installed on the air conditioner casing, so that the additional guide plate 1 is installed at the air outlet of the air conditioner, and the angle w between the plane of the additional guide plate 1 and the horizontal plane is adjusted by rotating the first rotating shaft 1-2.

[0029] like Figure 3Each hole 1-1 on the additional guide plate 1 can be blocked by an independently controlled flip-over diaphragm 1-3. The area of ​​the diaphragm 1-3 is slightly larger than the hole 1-1. It is fixed to the back of the additional guide plate 1 by a second rotating shaft 1-4. The opening and closing size Si of the hole 1-1 is controlled by different rotation angles.

[0030] The electric drive device is used to control the angle w between the plane of the additional guide plate 1 and the horizontal plane and the opening and closing size Si of the hole 1-1 of the additional guide plate 1; The multi-dimensional sensor module 3 is used to collect the three-dimensional space information Qp where the human body is located; the three-dimensional space information Qp where the human body is located includes: crowd feature information P, temperature setting information Ts, three-dimensional temperature field information Tr, three-dimensional humidity field information Rr, three-dimensional air quality information Ar, and regional location information Qr; The energy storage and power replenishment module 4 includes a solar photovoltaic power generation device for generating electricity and an energy storage lithium battery pack for powering the system; Timer 5 is used for timing and time adjustment; The voice interaction module 6 is used for interaction via voice; The noise suppressor 7 is used to suppress the noise by sending out reverse sound waves through the reverse sound wave noise reduction algorithm after receiving the noise; The reverse sound wave noise reduction algorithm is based on the superposition principle of sound waves. When two sound waves with the same frequency and opposite phases meet, they will cancel each other out and form a silent vacuum state. This principle is the basis of the reverse sound wave noise reduction algorithm; Noise capture: First, capture the noise in the environment through microphones and other sound pickup devices; Signal processing: The captured noise signal is deeply analyzed by the algorithm to determine the key parameters of the noise, such as frequency and phase; Reverse sound wave generation: Based on the noise parameters obtained by analysis, the algorithm generates a reverse sound wave that is exactly symmetrical with the original noise; Sound wave superposition and cancellation: The generated reverse sound waves are played out through speakers and other equipment to meet and cancel out the original noise; In this embodiment, the Speex algorithm is used. Speex is a set of open source, free, and patent-free applications mainly for voice, including codecs, voice detection (VAD), discontinuous transmission (DTX), acoustic echo cancellation (AEC), denoising (NS) and other practical modules; Speex's denoising algorithm has good performance and adopts a complex algorithm flow including preprocessing, energy calculation, noise energy update, signal-to-noise ratio calculation, gain calculation and post-processing.

[0031] The intelligent algorithm module 9 is used to calculate the angle w between the plane of the additional guide plate and the horizontal plane and the opening and closing size Si of the hole according to the three-dimensional space information Qp where the human body is located; The wireless transceiver 8 is used to communicate with the intelligent terminal.

[0032] In this embodiment, the electric drive device includes a first motor for controlling the first rotating shaft 1-2 and a second motor for controlling the second rotating shaft 1-4. The shaft of the first motor is coaxially connected to the first rotating shaft 1-2. The second motor adopts a mini motor to reduce the volume and prevent interference between adjacent mini motors. Figure 4 The shaft of the second motor is installed with a worm B, and the shaft end of the second rotating shaft 1-4 is inserted into the shaft hole. The shaft hole is arranged on the back of the additional guide plate 1 and is located on both sides below the hole 1-1, so that the diaphragm 1-3 can cover the hole 1-1. The shaft portion of the second rotating shaft 1-4 is installed with a worm wheel A, and the transmission is performed through the engagement of the worm wheel A and the worm B. The number of the second motors is the same as the number of the holes 1-1, that is, each hole is provided with a diaphragm 1-3 that can be rotated by the second rotating shaft 1-4; in some embodiments, the transmission can also be connected and transmitted through transmission mechanisms such as gears, pulleys, universal joints, and magnetic couplings.

[0033] Similar, such as Figure 5 In some embodiments, the membrane 1-3 for shielding the hole 1-1 can also be opened and closed by rotating the second rotating shaft 1-4 installed in the middle thereof, thereby controlling the opening and closing size Si of the hole.

[0034] In some embodiments, the membrane 1 - 3 can also cover the hole 1 - 1 by sliding.

[0035] like Figure 6 , an intelligent control method for an air-conditioning air supply additional guide plate, comprising the following steps: S1, collect the three-dimensional space information Qp of the human body; S2. Input the three-dimensional space information Qp of the human body into the air supply control model of the air conditioner, and perform inference calculation to obtain the target opening and closing size Si of each hole on the additional deflector and the target deflection solid angle w of the additional deflector; the additional deflector is installed at the air outlet of the air conditioner and has a number of holes whose opening and closing sizes can be independently controlled. The area of ​​the holes opened is Si, and the angle between the plane of the additional deflector and the horizontal plane is the target deflection solid angle w; Since each hole has its corresponding open area value, Si is a vector, and each hole has its own position number, which makes it convenient to control the opening and closing size of each hole; By adjusting the target opening and closing size Si and the target diversion solid angle w, the air volume, wind speed and temperature cooling rate in each direction can be controlled; S3. Controlling the additional guide plate according to the target opening and closing size Si of each hole on the additional guide plate and the target guide solid angle w of the additional guide plate.

[0036] In some embodiments, a remote control function is used, and the user can adjust the control parameters of the additional guide plate anytime and anywhere through a mobile phone or other smart device to flexibly meet personal needs.

[0037] The three-dimensional space information Qp of the human body includes: crowd characteristic information P, temperature setting information Ts, three-dimensional temperature field information Tr, three-dimensional humidity field information Rr, three-dimensional air quality information Ar, and regional location information Qr.

[0038] The temperature setting information Ts is the target temperature information input by a person through a remote control or voice.

[0039] The three-dimensional temperature field information Tr is obtained by arranging infrared thermal imaging temperature detectors on the surface of the additional guide plate facing the indoor space and point temperature detectors with wireless transmission function distributed in the indoor activity area.

[0040] The three-dimensional humidity field information Rr is obtained by arranging humidity detectors on the surface of the indoor space with additional guide plates and point humidity detectors with wireless transmission function distributed in the indoor activity area.

[0041] The three-dimensional air quality information Ar is detected by air quality sensors arranged on the indoor space surface through additional guide plates and distributed air quality sensors with wireless transmission function arranged in the indoor activity area to detect PM2.5, CO 2 The above sensor model is Sensirion - SHT85 +SPS30.

[0042] The crowd characteristic information P includes gender, age, crowd composition, location (the distance between people and air conditioners, such as in the same small area in the same room or in different areas in the same building), number of people, and posture (mainly divided into three types of human postures: standing, sitting, and lying).

[0043] Gender and age are obtained by taking images with a camera and using the ResNet + AgeNet / GenderNet multi-task learning model. Position and number of people are obtained by placing activity sensors on the surface of the indoor space with additional guide plates and distributed activity sensors in the indoor activity area with wireless transmission functions. The sensor model used is Senion Indoor Positioning and People Counting System.

[0044] The posture is obtained by a human posture estimation method of a monocular image, specifically a fully connected neural network model, the model includes an input layer, a hidden layer, and an output layer. The input layer corresponds to a human skeleton framework image of n×m pixels, and the output layer corresponds to the results of three types of human posture recognition models: 0, 1, and 2, where 0 represents lying / half-lying, 1 represents sitting, and 2 represents standing; in this embodiment, n×m is 128×128; For the heat map Hi of joint point i with a size of D×H×W, the space where the human body is located is discretized into a discrete space of D×H×W. Each element Hi(x,y,z) of the volume heat map represents the confidence that the position of joint point i is at (x,y,z). During the network training phase, the pseudo 3D coordinates (x truth ,y truth ,z truth ), the corresponding volume heat map Hi can be obtained by a Gaussian distribution with a fixed σ: Hi(x,y,z)=(1 / (2πσ 2 )×(e^(-((xx truth ) 2 +(yy truth ) 2 +(zz truth ) 2 ) / (2πσ 2 ))); Using volume heatmaps instead of 3D coordinate points to supervise network training converts highly nonlinear problems such as 3D coordinate regression into predictions of discrete space 3D matrices, which can better play the advantages of neural networks in capturing spatial features. In the test reasoning stage, after the neural network outputs the volume heatmap of the joint point, the pseudo 3D coordinates (x pre ,y pre ,z pre ) is the coordinate index of the largest element in the volume heat map. (x pre ,y pre ,z pre )=arg max(Hi(x,y,z)); The human body image obtained by the camera is input into the pre-trained model of Lightweight Openpose to generate a human body posture skeleton framework diagram.

[0045] Pre-trained models for Lightweight Openpose are available from Daniil-Osokin on github.

[0046] Specifically, data preprocessing is first performed. Before the collected images are input into the model, the images are preprocessed, the images are scaled to a size of 224×224, and the image pixel values ​​are normalized to the interval [-1, 1]. Random rotation, translation, flipping and other operations can also be added to improve the generalization ability of the model.

[0047] Then determine the input and output, the input is a 224 × 224 RGB image. The output is that we want to identify 17 key points (the number of common human key points), and the output will be 17 × 2 (each key point has two coordinates x and y).

[0048] The input layer then receives an RGB image of size 224×224 and flattens the 224×224×3 three-dimensional image data into a one-dimensional vector with a length of 150528.

[0049] Next, the first hidden layer contains 1024 neurons and the input is a 150528-dimensional input vector. Each neuron has a weight connected to the input vector, so the size of the weight matrix is ​​(150528, 1024). Then a linear transformation is performed to calculate the weighted sum of each neuron. The result of the linear transformation is passed through the activation function and output to the next layer.

[0050] The second hidden layer contains 512 neurons, and the input is the output of the first layer, which is 1024 in size, so the size of the weight matrix is ​​(1024, 512). Then a linear transformation is performed to calculate the weighted sum of each neuron. Then, through the activation function, it is output to the next layer.

[0051] The third hidden layer contains 256 neurons, and the input is the output of the second layer, which has a size of 512, so the size of the weight matrix is ​​(512, 256). Then a linear transformation is performed to calculate the weighted sum of each neuron. Then, through the activation function, it is output to the next layer.

[0052] The output layer has 34 output nodes, each corresponding to the x and y coordinates of a keypoint. The size of the output vector is 34. The size of the weight matrix is ​​(256, 34).

[0053] The input of each hidden layer is processed by weighted summation and activation function. The output layer maps the output of the third layer to the final 34 coordinate outputs.

[0054] The indoor area location information Qr is the space venue type setting, the indoor area item setting, and the three-dimensional indoor construction information model, where: Space types include seated workspaces (such as study rooms and meeting rooms), human exercise and activity spaces (such as gyms and dance halls), resting spaces (such as bedrooms and rest rooms), and composite spaces (spaces that combine multiple functions) Indoor areas and items, including work areas (relatively static areas where people mainly sit at tables), rest areas (areas where people mainly lie or half-lying on beds or sofas), and activity areas (dynamic areas where people stand, walk, exercise, etc.); fixed furniture (such as cabinets, desks, and beds), and movable furniture (such as stools and chairs).

[0055] Three-dimensional indoor construction information, including the shape and length, width and height information of the indoor space, air-conditioning outlet information (including height from the ground, wall or ceiling, outlet width, etc.), indoor furniture placement area and length, width and height information, and length, width and height information of each area where indoor people are located.

[0056] The air supply control model of the air conditioner adopts a neural network multi-classification model. The training of the neural network multi-classification model includes the following steps: (1) Constructing the initial neural network multi-classification model: (2) The sample data set is used to train the initial neural network multi-classification model to obtain the trained neural network multi-classification model; the three-dimensional spatial information Qp of the human body is used as the input of the model, and the target opening and closing size Si of each hole on the additional guide plate and the target guide solid angle w of the additional guide plate are used as the output of the model; the network model trained by the sample data set should achieve the following goals: The indoor target area temperature reaches the target as quickly as possible: According to the target area set temperature, the target opening and closing size Si of each hole on the additional guide plate and the target guide solid angle w of the additional guide plate are adjusted by ±0.5℃. The average time to reach the target in the sample data set is 5 minutes. The opening and closing size of the guide plate hole matrix is ​​dynamically adjusted through the model algorithm, and the optimal guide solid angle is calculated based on the target area; The optimal energy-saving target under the temperature balance state of the indoor target area; based on the current value of the detected target area temperature, the regional population characteristics P and the indoor area location information Qr are used as parameters, and the model algorithm is used to control the diversion solid angle and the opening and closing of the holes of the diverter plate. Under the condition of not changing the air supply and temperature of the air conditioner, the optimal energy-saving target is achieved by preferentially controlling the opening degree of the holes of the diverter plate. The average energy consumption of the sample data set is 0.7 kWh per hour.

[0057] After the training is completed, the neural network multi-classification model is tested using a test data set. When the target success rate is higher than 90%, it can be used. Otherwise, the amount of data in the sample data set is increased to continue training until the target success rate is higher than 90%.

[0058] In this embodiment, the first threshold is 90%, which can also be set according to needs.

[0059] An electronic device, comprising: one or more processors; A memory for storing one or more programs; When one or more programs are executed by one or more processors, the one or more processors implement the above method.

[0060] In the embodiments provided in the present application, it should be understood that the disclosed method and system can also be implemented in other ways. The method and system embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the method and system, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a module, a program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0061] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0062] On the other hand, a computer-readable storage medium stores computer instructions, which implement the steps of the above method when executed by a processor. The computer program implements the method as described in any one of the first aspects above when executed by a processor. If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or part of the technical solution that contributes to the prior art or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory 101 (ROM, Read-Only Memory), a random access memory 101 (RAM, Random Access Memory), a disk or an optical disk, and other media that can store program codes.

[0063] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An intelligent control system for an air-conditioning air supply with an additional guide plate, characterized in that: The additional deflector is rotatably mounted on the air outlet of the air conditioner and has a plurality of holes whose opening and closing sizes can be independently controlled; the system comprises: An electric drive device, used to control the angle w between the plane of the additional guide plate and the horizontal plane and the opening and closing size Si of the hole of the additional guide plate; Multi-dimensional sensor module, used to collect the three-dimensional spatial information Qp of the human body; The microprocessor controller is respectively connected to the electric drive device and the multi-dimensional sensor module, and is used to input the three-dimensional spatial information Qp of the human body into the air conditioning air supply control model in the intelligent algorithm module, and perform inference calculation to obtain the target opening and closing size Si' of each hole on the additional guide plate and the target guide solid angle w' of the additional guide plate; according to the target opening and closing size Si' of each hole on the additional guide plate and the target guide solid angle w' of the additional guide plate, the electric drive device is controlled to adjust the angle w between the plane of the additional guide plate and the horizontal plane and the opening and closing size Si of the holes of the additional guide plate.

2. The intelligent control system for air-conditioning air supply with attached guide plate according to claim 1, characterized in that: The three-dimensional space information Qp of the human body includes: crowd feature information P, temperature setting information Ts, three-dimensional temperature field information Tr, three-dimensional humidity field information Rr, three-dimensional air quality information Ar, and regional location information Qr.

3. The intelligent control system for air-conditioning air supply with attached guide plate according to claim 2, characterized in that: The regional location information Qr includes the space type, indoor area and objects, and the three-dimensional model of the space.

4. The intelligent control system for air-conditioning air supply with attached guide plate according to claim 2, characterized in that: The crowd characteristic information P includes gender, age, crowd composition, location, number of people, and posture.

5. The intelligent control system for air-conditioning air supply with attached guide plate according to claim 4, characterized in that: The posture is obtained by a human posture estimation method using a monocular image.

6. The intelligent control system for air-conditioning air supply with attached guide plate according to claim 5, characterized in that: The human body image obtained by the camera is input into the pre-trained model of Lightweight Openpose to generate a human body posture skeleton framework diagram.

7. A control method for the intelligent control system of the air-conditioning air supply additional guide plate according to claim 1, characterized in that: The steps include: S1, collect the three-dimensional spatial information Qp of the human body through the multi-dimensional sensor module; S2, inputting the three-dimensional spatial information Qp of the human body into the air conditioning air supply control model in the intelligent algorithm module, and performing inference calculation to obtain the target opening and closing size Si' of each hole on the additional guide plate and the target guide solid angle w' of the additional guide plate; S3. According to the target opening and closing size Si' of each hole on the additional guide plate and the target guide solid angle w' of the additional guide plate, the electric drive device is controlled to adjust the angle w between the plane of the additional guide plate and the horizontal plane and the opening and closing size Si of the holes of the additional guide plate.

8. The method according to claim 7, characterized in that The air supply control model of the air conditioner adopts a neural network multi-classification model. The training of the neural network multi-classification model includes the following steps: (1) Constructing the initial neural network multi-classification model: (2) Using a sample data set to train an initial neural network multi-classification model to obtain a trained neural network multi-classification model, the sample data set includes the three-dimensional spatial information Qp where the human body is located, the target opening and closing size Si of each hole on the additional guide plate, and the target guide solid angle w of the additional guide plate; the three-dimensional spatial information Qp where the human body is located is used as the input of the model, and the target opening and closing size Si of each hole on the additional guide plate and the target guide solid angle w of the additional guide plate are used as the output of the model; the network model trained by the sample data set should achieve the following objectives: According to the target area set temperature adjustment ±a℃, the target opening and closing size Si of each hole on the additional guide plate and the target guide solid angle w of the additional guide plate are controlled. The average time to achieve the target in the sample data set is b minutes; Based on the current temperature value of the detected target area, with the regional population characteristics P and regional location information Qr as parameters, without changing the air supply and temperature of the air conditioner, the average energy consumption of the sample data set is c kWh per hour; The neural network multi-classification model is tested using a test data set. When the target success rate is higher than a first threshold, it can be used. Otherwise, the amount of data in the sample data set is increased to continue training until the target success rate is higher than the first threshold.

9. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 7 to 8.

10. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by the processor, the steps of the method as described in any one of claims 7 to 8 are implemented.

Images