Variable air volume control method, device and equipment based on image recognition

Abstract

The invention provides a variable air volume control method, device and equipment based on image recognition. The method comprises the following steps: simulating turbulent flow for a target area based on a preset simulation condition to obtain temperature distribution of the target area; based on the temperature distribution of the target area, performing grid division of a predetermined size on the target area to obtain a plurality of grid areas; based on the fitting relation between the interface air volume and the air supply speed, the control temperature of each grid area and the number of people in each grid area, an area energy balance equation of each grid area is determined; and the air supply speed is controlled by minimizing the difference value between the control temperature and the design temperature of each grid area as an optimization target. The air supply speed of the air in the grid area can be dynamically controlled, then the interface air volume of the air in the grid area is controlled, the energy utilization efficiency is improved, the operation cost is reduced, the comfort requirement of a crowded area is guaranteed, and the green and low-carbon targets are achieved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and more specifically to a variable air volume control method, device and equipment based on image recognition. Background Art

[0002] Large-space buildings have significant energy consumption characteristics due to their large size, high floor height, and significant changes in population density. Building heating, ventilation, and air conditioning systems (i.e., HVAC systems) usually account for 40% to 60% of total energy consumption and are the core area of ​​energy consumption control. Stratification of hot and cold air, local overcooling or overheating are common in large spaces, and traditional air-conditioning systems mostly use constant air volume control, which is difficult to dynamically respond to the actual needs of different areas, not only increasing energy waste, but also reducing comfort in the space. With the development of smart buildings and the increase in energy-saving needs, the application of variable air volume control technology in large spaces has gradually become a research hotspot.

[0003] In the process of implementing the concept of the present invention, it was found that the existing air supply strategy is difficult to achieve precise control for large space areas with complex airflow distribution, and some areas still have low energy efficiency. In addition, the existing control system has a slow response speed and is difficult to quickly adapt to the rapid fluctuation of personnel density. Summary of the invention

[0004] In view of this, the present invention provides a variable air volume control method, device and equipment based on image recognition.

[0005] One aspect of the present invention provides a variable air volume control method based on image recognition, comprising: based on preset simulation conditions, simulating turbulent flow for a target area to obtain a temperature distribution of the target area; based on the temperature distribution of the target area, dividing the target area into grids of predetermined sizes to obtain multiple grid areas; based on the fitting relationship between interface air volume and air supply speed, the control temperature of each grid area and the number of personnel in each grid area, determining the regional energy balance equation of each grid area; and controlling the air supply speed with minimizing the difference between the control temperature and the design temperature of each grid area as an optimization target, wherein the number of personnel in each grid area is determined based on image recognition of the collected video data of the grid area.

[0006] According to an embodiment of the present invention, based on the fitting relationship between the interface air volume and the air supply speed, the control temperature of each grid area and the number of people in each grid area, the regional energy balance equation of each grid area is determined, including: determining the first heat for the air in the grid area based on the difference between the temperature of the area adjacent to the grid area and the temperature of the grid area, the air parameters of the grid area and the fitting relationship; determining the second heat for the air in the grid area based on the number of people in the grid area and the per capita heat dissipation; determining the third heat for the air in the grid area based on the difference between the air supply temperature of the grid area and the temperature of the grid area, the air supply port area of ​​the grid area, the air supply speed of the grid area and the air parameters of the grid area; determining the total heat based on the first heat, the second heat and the third heat; determining the change in internal energy of the air in the grid area based on the air parameters of the grid area, the volume of the grid area and the temperature of the grid area; and obtaining the regional energy balance equation based on the total heat being equal to the change in internal energy.

[0007] According to an embodiment of the present invention, the air supply speed is controlled with minimizing the difference between the control temperature and the design temperature of each grid area as an optimization goal, including: linear transformation based on the nonlinear term in the regional energy balance equation; determining the incremental form of the regional energy balance equation based on the transformed nonlinear term and the regional energy balance equation; converting the incremental form into a matrix form; discretizing the regional energy balance equation in matrix form by analytical method to obtain a state space equation with the increment of the control temperature of each grid area as output; determining the state space equation after a preset number of iteration steps based on the state space equation and a measurable disturbance condition; based on the state space equation after the preset number of iteration steps, converting the temperature increment and the air supply speed increment within the preset number of iteration steps into their respective corresponding matrix forms; determining a variable air volume prediction equation based on the matrix forms corresponding to the temperature increment and the air supply speed increment within the preset number of iteration steps; determining an objective function according to the optimization goal; obtaining a quadratic programming problem with the air supply speed as a variable according to the variable air volume prediction equation and the objective function; and solving the quadratic programming problem using an interior point penalty function method to control the air supply speed.

[0008] According to an embodiment of the present invention, an interior point penalty function method is used to solve a quadratic programming problem and control the feeding speed, including: converting the quadratic programming problem into a logarithmic interior point penalty function; updating variables using an adaptive learning rate algorithm, and gradually reducing the barrier factor of the logarithmic interior point penalty function, repeatedly updating the variables until a termination criterion is met, and obtaining updated variables; and completing the control of the interface speed when it is determined that a preset number of iteration steps meets an iteration threshold.

[0009] According to an embodiment of the present invention, the variable air volume control method based on image recognition further includes: in the case where it is determined that the respective real temperatures in the grid areas are collected successfully, determining the respective real temperatures in the grid areas as the control temperature.

[0010] According to an embodiment of the present invention, the variable air volume control method based on image recognition also includes: in the case where it is determined that the acquisition of the respective real temperatures within the grid areas fails but the acquisition of the respective real temperatures of some grid areas within the grid areas is successful, constructing an estimation model for estimating the temperature change within the target area based on the temperature state observer; using the estimation model and the respective real temperatures of some grid areas, predicting the respective real temperatures of other grid areas within the grid area except some grid areas to obtain their respective predicted temperatures; determining the respective real temperatures of some grid areas as the respective control temperatures of some grid areas; and determining the respective predicted temperatures of other grid areas as the respective control temperatures of other grid areas.

[0011] According to an embodiment of the present invention, based on the temperature distribution of the target area, the target area is divided into grids of predetermined sizes to obtain multiple grid areas, including: determining the temperature change in the target area according to the temperature distribution of the target area; when it is determined that the temperature change in the target area meets the design temperature change conditions, the target area is divided into multiple grid areas of a first predetermined size; when it is determined that the temperature change in the target area does not meet the design temperature change conditions, the target area is divided into multiple grid areas of a second predetermined size, wherein the first predetermined size is smaller than the second predetermined size.

[0012] According to an embodiment of the present invention, the variable air volume control method based on image recognition further includes: for each grid area: performing personnel contour detection on the collected video data and marking candidate frames; and determining the number of personnel based on the number of candidate frames.

[0013] Another aspect of the present invention provides a variable air volume control device based on image recognition, comprising: a simulation module, used to simulate turbulent flow in a target area based on preset simulation conditions to obtain the temperature distribution of the target area; a division module, used to divide the target area into grids of predetermined sizes based on the temperature distribution of the target area to obtain multiple grid areas; a determination module, used to determine the regional energy balance equation of each grid area based on the fitting relationship between interface air volume and air supply speed, the control temperature of each grid area and the number of personnel in each grid area; and a control module, used to control the air supply speed with minimizing the difference between the control temperature and the design temperature of each grid area as the optimization target, wherein the number of personnel in each grid area is determined based on image recognition of the collected video data of the grid area.

[0014] Another aspect of the present invention provides an electronic device, comprising: one or more processors; a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0015] According to the embodiments of the present invention, due to the simulation of turbulent flow, the temperature distribution in the spatial area with complex airflow distribution can be determined, and refined management can be achieved by combining grid division. Then, the regional energy balance equation of each grid area constructed by the number of personnel, air supply speed, and temperature is analyzed, and the difference between the control temperature and the design temperature is gradually minimized. The air supply speed of the air in the grid area is dynamically optimized and controlled, and then the interface air volume of the air in the grid area is controlled, so as to improve energy utilization efficiency, reduce operating costs, and ensure the comfort requirements of densely populated areas, which will help the construction industry achieve green and low-carbon goals. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0017] Figure 1 A flow chart of a variable air volume control method based on image recognition according to an embodiment of the present invention is shown;

[0018] Figure 2 A schematic diagram of grid division based on temperature distribution according to an embodiment of the present invention is shown;

[0019] Figure 3 A schematic diagram showing detection of a person's outline based on a deep learning target detection algorithm model according to an embodiment of the present invention is shown;

[0020] Figure 4 A schematic diagram of feature value selection according to an embodiment of the present invention is shown;

[0021] Figure 5 A schematic diagram of a Lumberg observer control structure according to an embodiment of the present invention is shown;

[0022] Figure 6 A flow chart for variable air volume control according to an embodiment of the present invention is shown;

[0023] Figure 7 A block diagram of a variable air volume control device based on image recognition according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0024] Below, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of concepts of the present invention.

[0025] The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the existence of features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0026] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0027] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0028] In the process of realizing the concept of the present invention, it was found that the variable air volume control system can adjust the air supply volume according to real-time parameters such as temperature, humidity, and carbon dioxide concentration to adapt to actual needs and improve the energy efficiency of the air in the grid area. Although it can have advantages in reducing energy consumption, for large-space buildings such as subway stations, airport terminals, stadiums, and shopping centers, due to the complex airflow distribution in large spaces, the existing air supply strategy is difficult to achieve precise control, and some areas still have problems with low energy efficiency. In addition, the existing control system has a slow response speed and is difficult to quickly adapt to the rapid fluctuations in population density. In response to these problems, intelligent control and optimization should be further studied, such as the introduction of artificial intelligence algorithms in the present invention to improve the response and prediction capabilities of the controller.

[0029] Based on this, an embodiment of the present invention provides a variable air volume control method, device and equipment based on image recognition. The method includes: based on preset simulation conditions, simulating turbulent flow for a target area to obtain the temperature distribution of the target area; based on the temperature distribution of the target area, dividing the target area into grids of predetermined sizes to obtain multiple grid areas; based on the fitting relationship between the interface air volume and the air supply speed, the control temperature of each grid area and the number of personnel in each grid area, determining the regional energy balance equation of each grid area; and controlling the air supply speed with minimizing the difference between the control temperature and the design temperature of each grid area as the optimization target, wherein the number of personnel in each grid area is determined based on image recognition of the collected video data of the grid area.

[0030] The following will be passed Figure 1 to Figure 6 The variable air volume control method based on image recognition according to an embodiment of the present invention is described in detail.

[0031] Figure 1 A flow chart of a variable air volume control method based on image recognition according to an embodiment of the present invention is shown.

[0032] like Figure 1 As shown, the variable air volume control method based on image recognition includes operations S110 to S140.

[0033] In operation S110 , based on preset simulation conditions, turbulent flow is simulated for a target area to obtain a temperature distribution of the target area.

[0034] In operation S120 , the target area is divided into grids of a predetermined size based on the temperature distribution of the target area to obtain a plurality of grid areas.

[0035] In operation S130, a regional energy balance equation of each grid area is determined based on a fitting relationship between the interface air volume and the air supply speed, a control temperature of each grid area, and the number of personnel in each grid area.

[0036] In operation S140, the air supply speed is controlled with minimizing the difference between the control temperature and the design temperature of each grid area as an optimization target.

[0037] According to an embodiment of the present invention, the target area may include multiple air supply vents and / or multiple air return vents, the air supply vents are used to transfer air from outside the target area to inside the target area, and the air return vents are used to transfer air from inside the target area to outside the target area, and the air supply vents and the air return vents may have the same air supply speed when transferring air. The target area may include, for example, but is not limited to, large space building areas such as subway stations, exhibition halls, and airports.

[0038] According to an embodiment of the present invention, a geometric model can be established to divide the target area into tetrahedral grids. Based on preset simulation conditions, the k-ε turbulence model of computational fluid dynamics (CFD) software can be used to simulate turbulent flow to obtain the temperature distribution of the target area.

[0039] According to an embodiment of the present invention, the preset simulation conditions can be determined according to the simulation software. For example, for computational fluid dynamics (CFD) software, the preset simulation conditions can include but are not limited to: boundary conditions, air outlets are set as velocity inlets, the air supply speed and air supply temperature of each air supply outlet are the same, the air supply speed and air supply temperature of each air supply outlet are steady-state calculated values ​​under the design conditions, the return air outlet is set as a pressure outlet, all boundaries except the air outlet are set as non-slip walls, the initial indoor temperature distribution, the outdoor meteorological parameters of a typical meteorological day, setting the solver and defining the convergence criteria, etc. Outdoor meteorological parameters such as outdoor air temperature, relative humidity, wind speed, solar radiation, etc. The initial indoor temperature distribution can be set according to actual conditions.

[0040] According to an embodiment of the present invention, the predetermined size can be determined according to the regional temperature change situation. The regional temperature change situation is inversely proportional to the predetermined size, for example, a region with a large temperature change trend is divided into a small size, and a region with a small temperature change trend is divided into a large size.

[0041] According to an embodiment of the present invention, the convective heat exchange between the wall and the air can be ignored and regarded as an unmeasurable disturbance in the variable air volume control. The fitting relationship between the interface air volume and the air supply speed, the control temperature of each grid area, and the number of people in each grid area are regarded as measurable disturbances in the variable air volume control, and the regional energy balance equation of each grid area is constructed based on the conservation of energy.

[0042] According to an embodiment of the present invention, the design temperature may be a design value, which may be determined by a field specification or standard. The control temperature may include a temperature actually collected by a sensor.

[0043] According to the embodiments of the present invention, due to the simulation of turbulent flow, the temperature distribution in the spatial area with complex airflow distribution can be determined, and refined management can be achieved by combining grid division. Then, the regional energy balance equation of each grid area constructed by the number of personnel, air supply speed, and temperature is analyzed, and the difference between the control temperature and the design temperature is gradually minimized. The air supply speed of the air in the grid area is dynamically optimized and controlled, and then the interface air volume of the air in the grid area is controlled, so as to improve energy utilization efficiency, reduce operating costs, and ensure the comfort requirements of densely populated areas, which will help the construction industry achieve green and low-carbon goals.

[0044] According to the embodiments of the present invention, the temperature distribution is determined by CFD simulation, the air supply strategy is optimized, and refined management is performed in combination with the grid area requirements, which is conducive to effectively coping with the complex loads of large spaces. The variable air volume control method provided by the present invention is conducive to the gradual development of variable air volume control technology towards intelligence and low carbonization.

[0045] According to an embodiment of the present invention, for the above Figure 1 In operation S120, based on the temperature distribution of the target area, dividing the target area into a grid of a predetermined size to obtain a plurality of grid areas may include the following operations: determining the temperature change in the target area according to the temperature distribution of the target area; if it is determined that the temperature change in the target area meets the preset temperature change condition, dividing the target area into a plurality of grid areas of a first predetermined size; if it is determined that the temperature change in the target area does not meet the preset temperature change condition, dividing the target area into a plurality of grid areas of a second predetermined size. The first predetermined size is smaller than the second predetermined size.

[0046] According to an embodiment of the present invention, the preset temperature change condition can be determined according to actual conditions, and is used to indicate a situation where the temperature change trend reaches a preset trend value.

[0047] Figure 2 A schematic diagram of grid division based on temperature distribution according to an embodiment of the present invention is shown.

[0048] like Figure 2 As shown, taking a certain target area as an example, the blank part represents the wall column in the target area, and the other part represents the open area of ​​the target area. For the open area, the temperature gradually increases from green to yellow and then to red. The black box can represent the divided grid area. The size of the grid area divided by the area with drastic temperature changes is smaller than the size of the grid area divided by the area with gentle temperature changes. The blue dots represent the air outlets set in the target area. It should be noted that the air supply speed of each air outlet is the same, and the air outlet is set according to the area of ​​the actual air supply area.

[0049] According to an embodiment of the present invention, a small grid is used in an area where the temperature changes dramatically, so that the temperature gradient can be captured more accurately and the calculation error can be reduced. A large grid is used in an area where the temperature changes slowly to reduce the amount of calculation and improve the simulation efficiency. Since eddy currents are usually accompanied by local strong coupling of momentum and heat, the influence on heat exchange and momentum exchange is significant, such as near a heat source, a cold source or a flow separation area. Therefore, by refining the grid based on the temperature distribution of the present invention, sufficient resolution can be provided to more accurately capture the local phenomenon caused by eddy currents near the interface, avoid the eddy currents being smoothed by numerical diffusion, and make the eddy current shape closer to the actual situation, thereby improving the physical rationality of the overall flow field. Through a reasonable grid division strategy, the credibility of the numerical simulation can be greatly improved, the applicability and numerical convergence of the model can be improved, and the optimal balance point between calculation efficiency and accuracy can be found at the same time. It can at least partially solve the problem of ignoring heat exchange due to the small net air volume due to the presence of eddy currents on the interface of some non-grid boundaries.

[0050] According to another embodiment of the present invention, the variable air volume control method based on image recognition may include the following steps: Figure 1 In addition to the operations S110 to S140 shown, the following operations may also be included: for each grid area: performing personnel contour detection on the collected video data and marking candidate frames; and determining the number of personnel according to the number of candidate frames.

[0051] According to an embodiment of the present invention, a real-time visual application system can be developed by combining a programming language with a computer vision and machine learning software library (OpenCV), and a deep learning target detection algorithm (FASTER R-CNN) is used to perform dynamic crowd detection on the video data of the real-time camera shooting picture in the target area. The real-time visual application system accesses the video stream of the real-time camera shooting picture through an interface, and uses a cross-platform software development kit (such as SDK) built on an open source multimedia framework (such as LibVLC) to obtain the video stream through a predetermined format transmission protocol (RTSP). The real-time frame is captured from the video stream through the OpenCV class function cv2.VideoCapture and converted into video data in a Mat format.

[0052] The improved FASTER R-CNN algorithm model can be used to detect the contours of people in the collected video data and frame candidate frames. The number of people can be determined based on the number of candidate frames.

[0053] The improved FASTER R-CNN algorithm model may include a convolutional layer, a region proposal network (RPN) layer, a region of interest pooling layer, a classification layer, and a bounding box regression layer. The convolutional layer can extract features from video data to obtain a feature map. The RPN layer can mark the region with head features based on the feature map to obtain a candidate box. The region of interest pooling layer can scale the candidate box and feature map obtained by the RPN layer to a fixed size to obtain a feature map of a fixed size containing the candidate box. The classification layer can determine whether the candidate box contains a person by detecting the classification probability. The bounding box regression layer can adjust the position and size of the candidate box by detecting the bounding box regression so that it surrounds the person more accurately, thereby achieving more accurate person recognition and person counting.

[0054] Figure 3 A schematic diagram of detecting a person's outline based on a deep learning target detection algorithm according to an embodiment of the present invention is shown.

[0055] like Figure 3 As shown, the video data can be input into the convolution layer, the feature map is output, the feature map is input into the RPN layer to obtain the candidate box, the candidate box and the feature map are input into the region of interest pooling layer, the fixed-size feature map containing the candidate box is output, the fixed-size feature map containing the candidate box is input into the classification layer, the detection classification probability of whether the candidate box contains a person is output, and whether the candidate box contains a person is determined based on the detection classification probability. In addition, before the fixed-size feature map containing the candidate box is input into the classification layer, the fixed-size feature map containing the candidate box can also be input into the bounding box regression layer, the adjusted feature map containing the candidate box is output, and then input into the classification layer.

[0056] In determining the number of people, for example, after selecting a specific area through the camera screen, the video data within these 30 frames can be processed in a cycle of 30 frames. In each frame, the improved FASTER R-CNN detects the people in the image and marks the candidate boxes. At the same time, based on the correlation filter algorithm (KCF), the dynamic tracking of the flow of people in each grid area is continuously performed in each cycle. In every 30-frame cycle in the video stream, the system counts the number of people detected in each frame and calculates the average of the detected number. Since the average value can smooth out short-term fluctuations caused by detection errors, target overlap or inaccurate tracking, it can provide a more stable statistical result.

[0057] According to an embodiment of the present invention, a camera can be used to continuously collect images of crowd flow in a grid area within a preset period, and crowd flow images can be detected and identified based on an improved Faster R-CNN algorithm to achieve real-time and accurate online statistics of the number of people in the grid area, which can be used as a measurable disturbance to control the air supply speed and further control the air supply volume.

[0058] According to an embodiment of the present invention, for the above Figure 1 In operation S130, based on the fitting relationship between the interface air volume and the air supply speed, the control temperature of each grid area and the number of people in each grid area, the regional energy balance equation of each grid area is determined, which may include the following operations: determining a first amount of heat for the air in the grid area based on the difference between the temperature of the area adjacent to the grid area and the temperature of the grid area, the air parameters of the grid area and the fitting relationship; determining a second amount of heat for the air in the grid area based on the number of people in the grid area and the per capita heat dissipation; determining a third amount of heat for the air in the grid area based on the difference between the air supply temperature of the grid area and the temperature of the grid area, the air supply port area of ​​the grid area, the air supply speed of the grid area and the air parameters of the grid area; determining a total amount of heat based on the first amount of heat, the second amount of heat and the third amount of heat; determining a change in the internal energy of the air in the grid area based on the air parameters of the grid area, the volume of the grid area and the temperature of the grid area; and obtaining a regional energy balance equation based on the total amount of heat being equal to the change in the internal energy.

[0059] According to an embodiment of the present invention, the air parameters of the grid area may include the air density of the grid area and the specific heat capacity of the air of the grid area. The volume of the grid area may be determined by multiplying the net height of the grid area by the bottom area of ​​the grid area.

[0060] According to an embodiment of the present invention, the interface air volume and air supply speed The fitting relationship can be , and are the coefficients of the first-order term and the constant term of the fitting relationship respectively. The convective heat transfer between the wall and the air can be ignored and regarded as an unmeasurable disturbance in the variable air volume control. Each grid area in the target area can be mapped into a two-dimensional area from the same direction, and the center of each grid area is represented by the x-axis and y-axis, and the grid area is identified by the coordinate point of the center of each grid area. For example, any grid area ( ), i represents the x-axis coordinate of the center of the grid area in the two-dimensional area, j represents the y-axis coordinate of the center of the grid area in the two-dimensional area, and the regional energy balance equation of each grid area can be expressed as follows (1):

[0061] (1)

[0062] in, is the air density in the grid area, in kg / m 3 ; is the specific heat capacity of the air in the grid area, in J / (kg·K); is the grid area ( )’s clear height, in meters; is the grid area ( )’s bottom area, in m 2 ; is the grid area ( ) at the time of calculation The control temperature at time is in °C; the unit is in s; , They are the grid areas ( ) The linear coefficient and constant term of the fitting relationship between the interface air volume and air supply speed on the interface m; as mentioned above Figure 2 Each grid shown in contains four interfaces, top, bottom, left, and right, and m is each interface; is the grid area ( ) at the time of calculation The air supply speed at the time is in m / s; is the area with the grid ( ) of the interface m adjacent area at the time of calculation The control temperature at the time is in °C; is the heat dissipation per capita, in W / person; is the grid area ( ) Intrinsic calculation time The number of personnel at the time; is the air outlet area of ​​the grid area, in m 2 ; is the air supply temperature of the grid area, in degrees Celsius. The term on the left side of the formula (1) can represent the change in the internal energy of the air in the grid area. The term on the right side of the formula (1) is the sum of three terms, namely the total heat, which can represent the first heat, the second heat and the third heat for the air in the grid area from left to right. The per capita heat dissipation can represent the heat dissipated by the human body to the surrounding environment in different ways. In the present invention, the per capita heat dissipation can be determined based on empirical values.

[0063] According to an embodiment of the present invention, for the above Figure 1In operation S140, the air supply speed is controlled with minimizing the difference between the control temperature and the design temperature of each grid area as the optimization goal, which may include the following operations: linear transformation based on the nonlinear terms in the regional energy balance equation; determining the incremental form of the regional energy balance equation based on the transformed nonlinear terms and the regional energy balance equation; converting the incremental form into a matrix form; discretizing the regional energy balance equation in matrix form by analytical method to obtain a state space equation with the control temperature increment of each grid area as the output; determining the state space equation after a preset number of iteration steps based on the state space equation and a measurable disturbance condition; converting the temperature increment and the air supply speed increment within the preset number of iteration steps into their respective corresponding matrix forms based on the state space equation after the preset number of iteration steps; determining the variable air volume prediction equation based on the matrix forms corresponding to the temperature increment and the air supply speed increment within the preset number of iteration steps; determining the objective function according to the optimization goal; obtaining a quadratic programming problem with the air supply speed as a variable according to the variable air volume prediction equation and the objective function; and solving the quadratic programming problem using the interior point penalty function method to control the air supply speed.

[0064] According to an embodiment of the present invention, the nonlinear term in the regional energy balance equation may include the product of the temperature of the grid area and the air supply speed. For example, the nonlinear term in formula (1) , can be linearized using the first-order Taylor expansion. , , Then it is directly written in incremental form, as shown in the following formula (2):

[0065] (2)

[0066] in, , , The initial values ​​of the three variables, control temperature, air supply speed and number of personnel, corresponding to the grid area, can be the steady-state calculated values ​​under the design conditions; , , Corresponding to the calculation time The increments of the three variables of controlled temperature, air supply speed and number of people in the grid area.

[0067] Formula (2) can be substituted into formula (1), and then subtracted from the initial form of formula (1) to obtain the incremental form of the regional energy balance equation as shown in the following formula (3):

[0068] (3)

[0069] in, is the grid area ( ) at the time of calculation The temperature increment at is the area with the grid ( ) of the interface m adjacent area at the time of calculation The temperature increment at is the grid area ( ) at the time of calculation Increase in staff at that time; is the area with the grid ( ) is the initial value of the control temperature of the region adjacent to the interface m; is the grid area ( ) at the time of calculation The air supply speed increment at . The above formula (3) can be arranged into a matrix form as shown in the following formula (4):

[0070] (4)

[0071] in, Indicates the calculation time The temperature increment matrix at time , the dimension is n × 1; n is the number of grid areas, The coefficient matrix representing the temperature increment of n grid regions has a dimension of n×n; The coefficient matrix representing the input parameter air supply speed has a matrix dimension of n×1; Indicates the calculation time The increment of air supply speed at the time is a numerical value; The coefficient matrix representing the change in the number of people in each grid area of ​​the measurable disturbance is n×n. Since each grid area only contains the measurable disturbance in its own area, The matrix is ​​diagonal; Indicates the calculation time The personnel increment matrix at the time has a dimension of n×1.

[0072] The time step for calculating the moment can be , ,from to , the above matrix can be discretized by analytical method to obtain the following formula (5):

[0073] (5)

[0074] Assuming that the air supply speed and the measurable disturbance are step functions, to The air supply speed and the measurable disturbance remain unchanged respectively. and , then the above formula (5) can be transformed into the following formula (6):

[0075] (6)

[0076] Integrate the function in equation (6) First move left , and then make a symmetric transformation, the above equation (6) is transformed into a state space equation with the increment of the control temperature of each grid area as the output, as shown in the following equation (7):

[0077] (7)

[0078] in, Represents the temperature increment matrix at the kth time step, with dimension n×1; The coefficient matrix representing the state variables (temperature increments) of n grid regions describes the evolution of the system from the kth time step to the k+1th time step without input, and the matrix dimension is n×n; The coefficient matrix representing the input parameter air supply speed represents the degree of influence of the input on the system state change, and the matrix dimension is n×1; It represents the increment of air supply speed at the kth time step, which is a numerical value; The coefficient matrix representing the change in the number of people in each grid area of ​​the measurable disturbance represents the degree of influence of the measurable disturbance on the change of the system state. The matrix dimension is n×n; The incremental matrix representing the number of personnel at the kth time step has a dimension of n×1; represents the output variable, which is the temperature increment at the kth time step. In the present invention, the dimension is N×1, where N is the number of grid areas where the temperature can be measured; Represents the output matrix, which describes the contribution of state variables to the output, that is, the state How to map to the output of the system , in the present invention, the dimension is N×n; represents the influence matrix of the input variables on the output variables, which is zero in the present invention; represents the influence matrix of the measurable disturbance on the output variable, which is zero in the present invention. The temperature at the k+1th time step is the temperature at the kth time step plus the temperature increment at the k+1th time step, that is, = + According to another embodiment of the present invention, the variable air volume control method based on image recognition is Figure 1 In addition to the operations S110 to S140 shown, the method may further include: in the case where the real temperatures of the respective grid areas are successfully collected, determining the real temperatures of the respective grid areas as the control temperatures.

[0079] In the process of implementing the embodiments of the present invention, it is found that when the space of the target area is large, the cost, quantity and accuracy of installing sensors will be limited. If temperature measurement points can only be arranged in a limited area, the actual temperature measurement value obtained can only reflect the temperature information of a part of the area, and cannot directly provide the complete state of the entire space. In this case, if the control is directly dependent on the measurement data, it will cause the system response to lag or be inaccurate.

[0080] Based on this, another embodiment of the present invention is a variable air volume control method based on image recognition. Figure 1 In addition to the operations S110 to S140 shown, the operation may also include: when it is determined that the acquisition of the respective true temperatures in the grid areas fails but the acquisition of the respective true temperatures of some grid areas in the grid area succeeds, constructing an estimation model for estimating the temperature change in the target area based on the temperature state observer; and using the estimation model and the respective true temperatures of some grid areas, predicting the respective true temperatures of other grid areas in the grid area except some grid areas to obtain their respective predicted temperatures; determining the respective true temperatures of some grid areas as the respective control temperatures of some grid areas; and determining the respective predicted temperatures of other grid areas as the respective control temperatures of other grid areas.

[0081] According to an embodiment of the present invention, in order to ensure that the state estimator can accurately estimate the temperature of all regions through the measurable regional temperature, the matrix pair It is observable, and the basis for judging observability is the matrix The row is full rank, and the output matrix The number of rows should be as small as possible to achieve the minimum number of measurement points to estimate the temperature of all areas. Output matrix A screening matrix with dimension N×n, where N is the number of measurable temperature regions and n is the number of grid regions. As shown in the following formula (8):

[0082] (8)

[0083] A temperature state observer, such as the Luenberger observer, can be used to establish an estimation model for estimating the temperature change in the target area. The discretized standard form is shown in the following equation (9):

[0084] (9)

[0085] in, represents the estimated temperature increment matrix at the k+1th time step; represents the estimated temperature increment matrix at the kth time step; represents the gain matrix; represents the output calculated by the estimated state variables at the kth time step.

[0086] The estimated temperature at the k+1th time step is the output calculated by the estimated state variables at the k+1th time step plus the estimated temperature at the kth time step, that is, = + .

[0087] The second formula in formula (9) can be substituted into the first formula in formula (9) to obtain the following formula (10):

[0088] (10)

[0089] The first formula in formula (7) can be subtracted from formula (10), and the second formula in formula (7) can be substituted into the formula (11) to obtain:

[0090] (11)

[0091] in, is the error of the estimated model at the kth time step , we can get the following formula (12):

[0092] (12)

[0093] is the error of the estimated model at the k+1th time step.

[0094] Figure 4 A schematic diagram of feature value selection according to an embodiment of the present invention is shown.

[0095] Since the design estimation model can ensure the stability of variable air volume control, the discrete system requires the matrix All eigenvalues ​​of must satisfy a modulus less than 1 (located within the unit circle in the complex plane) to ensure the asymptotic stability of the system. The dynamics of the corresponding estimation model is determined by the error, so the matrix The eigenvalues ​​of must also satisfy the modulus less than 1 and be consistent with the matrix No common eigenvalues.

[0096] All matrices The eigenvalues ​​are configured as Figure 4 The area is a sector with a radius less than 1. The area is composed of two lines that radiate from the origin and have an angle of The larger the angle, the greater the overshoot. The eigenvalues ​​of are configured at a certain point or concentrated in a small area, which usually results in slow response and large execution signal amplitude. The eigenvalues ​​are evenly distributed in Figure 4 It would be better to be on a circle with a radius of r in the sector area shown in . The larger the radius of the circle, the faster the response speed. The present invention divides the sector arc symmetrical with the real axis into n-1 segments equally, and takes each node coordinate to obtain n / 2 pairs of conjugate complex eigenvalues, such as Figure 4 shown.

[0097] A reasonable gain matrix can be calculated using the Lyapunov equation , so that the matrix The eigenvalue of is the selected conjugate complex eigenvalue, and the matrix pair is obtained by the duality theorem. Controllable, build an observable matrix pair , the matrix F is a modal matrix constructed from n / 2 pairs of conjugate complex eigenvalues, and the real part of the eigenvalue of the matrix F is At the main diagonal position, the imaginary part On the off-diagonal positions, the dimensions are n×n, and the matrix The dimension is N×n, and each block of the corresponding matrix F has at least one column that is not all zero. The matrix F is shown in the following formula (13):

[0098] (13)

[0099] Solve the Lyapunov equation as follows (14). If the matrix G is singular, replace it with a new matrix And solve again, if the matrix G is non-singular, then the gain matrix is ​​calculated by the following formula (15): , so that the matrix The same as the eigenvalues ​​of the matrix F are the expected n / 2 pairs of conjugate complex eigenvalues, completing the establishment of the estimation model for estimating the temperature change in the target area.

[0100] (14)

[0101] (15)

[0102] Since the present invention and is zero, so the control structure diagram of the Lumberg observer can be as follows Figure 5 As shown, it can be based on and As the input of equations (7) and (9), the estimated model (9) at the kth time step is fitted to the real system (7) at the kth time step, and then the error of the estimated model is determined. The gain matrix is ​​calculated according to equation (12): , so that the matrix The eigenvalues ​​of the matrix F are the same as the expected n / 2 pairs of conjugate complex eigenvalues. By updating the feedback, the estimated model can completely fit the real system.

[0103] According to an embodiment of the present invention, a state estimator is introduced to estimate all values ​​of temperature measuring points in some areas based on their actual temperatures, that is, the estimation model is corrected using the deviation between the actual temperature of the measurable area temperature in the target area and the estimated value. This can solve the problem of insufficient temperature measuring points in the target area and reduce the cost of sensors. Especially when the temperature in the target area changes dynamically rapidly, the global state can be inferred or estimated based on these limited measurement data, which can supplement state variables that cannot be directly measured, so that the control system can use the estimated global state to perform optimized control and avoid errors in the control strategy due to lack of comprehensive information.

[0104] According to an embodiment of the present invention, in a variable air volume control system of an actual target area, it is assumed that the prediction time domain and the control time domain of the variable air volume constraint control are both to , the measurable disturbances before and after the kth time step are known, while the measurable disturbances after the kth time step are unknown. Assuming that the measurable disturbances after the kth time step remain unchanged, we have , thus we can get the following formula (16):

[0105] (16)

[0106] The temperature increment of all grid regions is estimated by the estimation model and based on the state estimate at the kth time step And predicted temperature , the k+lth time step of each grid area in the prediction time domain l can be derived from formula (7) and As shown in the following formula (17), Indicates that the k+lth time step is calculated from the kth time step:

[0107] (17)

[0108] The prediction time domain to The predicted temperature vector within and input variables (air supply speed increment) is written in matrix form as shown in equation (18) and Matrix, each predicted temperature vector The dimensions of are all state variable dimensions n×1, so the matrix composed of predicted temperature vectors It is an n×l column vector, that is, nl×1.

[0109] (18)

[0110] Based on equations (17) and (18), the variable air volume prediction equation in the prediction time domain can be obtained as shown in (19), where the coefficient matrix corresponding to temperature increment, temperature, and personnel increment is , , Each element in is an n×n square matrix. In particular, Each element in is an n×n unit matrix, Each element in is a normal n×n square matrix, and the coefficient matrix corresponding to the air supply speed increment is is an l×1 lower triangular matrix whose elements are n×1 column vectors.

[0111] (19)

[0112] The optimization goal can be to make the temperature of each grid area in the target area in all prediction time domains equal to the design temperature. The control temperature is the actual temperature or the predicted temperature. The objective function is shown in the following formula (20):

[0113] (20)

[0114] in, For the prediction time domain to The weight coefficient of the nth grid area within, is the weight coefficient matrix of each grid area in the target area in the prediction time domain, which is a diagonal matrix of nl×nl, and the diagonal elements are the weight coefficients of each prediction error in the objective function at different times; To predict the design temperature of the nth grid area in the time domain, To predict the design temperature matrix of each grid area in the target area in the time domain, it is a column vector of nl, which allows different design values ​​for each output at different times; , They are respectively the air supply speed constraint column vectors with dimension l, which are determined based on the variation range of air volume in large space; , are the air supply speed increment constraint column vectors with a dimension of l, which avoids wind pressure fluctuations caused by large adjustments to the air supply speed.

[0115] Substituting the variable air volume prediction equation (19) into the objective function (20) and removing the constant term that is irrelevant to the control variable, it can be organized into a quadratic programming form with the air supply speed increment as the control variable, as shown in the following equation (21):

[0116] (twenty one)

[0117] The constraints of air supply speed and its increment can be summarized as shown in the following formula (22), where both the I matrix and the O matrix are dimensions of the control time domain to The I matrix is ​​the identity matrix, and the O matrix is ​​a lower triangular matrix with elements of 1. The optimal value of the air supply speed calculated for the k-1th time step is a known value at the kth time step.

[0118] (twenty two)

[0119] The objective function of the quadratic programming problem is a quadratic function, and the constraints are linear inequalities, which are solved using the interior point penalty function method. Based on equations (21) and (22), the quadratic programming problem with air supply speed as a variable is shown in equation (23).

[0120] (twenty three)

[0121] in, is a quadratic function.

[0122] According to an embodiment of the present invention, solving a quadratic programming problem using an interior point penalty function method to control the air supply volume may include the following operations: converting the quadratic programming problem into a logarithmic interior point penalty function; updating variables using an adaptive learning rate algorithm, and gradually reducing the barrier factor of the logarithmic interior point penalty function, repeatedly updating the variables until a termination criterion is met to obtain updated variables; and completing the control of the interface air volume when it is determined that a preset number of iteration steps meets an iteration threshold.

[0123] According to an embodiment of the present invention, the interior point penalty function method can substitute the constraint as a penalty term into the objective function, thereby transforming the constrained optimization problem into an unconstrained optimization problem. The interior point penalty function method is applicable to solving inequality constraint problems. The so-called interior point refers to the assumed initial point within the constraint range. The above formula (23) is transformed into a logarithmic interior point penalty function form as shown in the following formula (24):

[0124] (twenty four)

[0125] in, is the interior point penalty function, is the obstacle factor; is a row vector of dimension 4l, whose elements are all 1.

[0126] The solution principle of the interior point penalty function is to assume that the initial optimization control variables are within the constraints. , through iterative update The penalty function is made to be infinitesimal. When the optimization variable approaches the constraint boundary, the penalty function logarithmic term increases rapidly to avoid exceeding the boundary. The barrier factor is gradually reduced, and the optimal solution under the current barrier factor is used as the starting point for the next optimization until the termination criterion is met:

[0127] (25)

[0128] in, is a constant used to determine whether the optimization has converged and can be a small constant.

[0129] For a certain obstacle factor, an adaptive learning rate algorithm (Adam) is used to iteratively update the control variable The calculation formula of the first-order moment and the second-order moment of the Adam algorithm and the updating method of the model coefficients to be calculated are expressed as shown in the following formula (26):

[0130] (26)

[0131] in, They are the first-order moment and second-order moment of the coefficient gradient to be calculated in the Adam algorithm; They are the decay rate factors of the first-order moment and the second-order moment, generally taken as 0.9 and 0.99; is the initial learning rate of the coefficient to be determined, which is 0.001; Update the smoothing control parameter for the coefficient to be determined, and take 10 -6 ; is the gradient of the coefficient to be determined; are the coefficients to be determined, including weight coefficients and bias.

[0132] The derivative of the logarithmic interior point penalty function with respect to the control variable is shown in equation (27):

[0133] (27)

[0134] in, is a column vector and column vector of control variables The Jacobian matrix of the matrix has the dimension of 4l×l. The general formula of the elements is shown in formula (28); is a column vector With column vector The Jacobian matrix has a dimension of 4l×4l and is a diagonal matrix. The general formula of the elements on the diagonal is shown in the following formula (29).

[0135] (28)

[0136] (29)

[0137] in, For the matrix The element in the i-th row and j-th column of ; For the matrix The i-th element of the diagonal of ; are all elements in the i-th row of matrix W; is the i-th element of the column vector Z; is the column vector of control variables The j-th element of .

[0138] According to an embodiment of the present invention, the difference between the temperature of each grid area in the target area and the design temperature is determined as the objective function, constraints are set for the air supply volume and air supply speed, the variable air volume control optimization problem based on the state estimator is converted into a standard quadratic programming form, and the interior point penalty function method is used to solve the quadratic programming problem in real time, and variable air volume adjustment is performed to realize on-demand air supply, which effectively avoids the energy consumption problem of one-size-fits-all air supply in the entire space of the target area.

[0139] Figure 6 A flow chart for variable air volume control according to an embodiment of the present invention is shown.

[0140] like Figure 6 As shown, the method for variable air volume control in this embodiment includes operations S601 to S614.

[0141] In operation S601 , a linear term coefficient and a constant term of a fitting relationship between an interface air volume and an air supply speed are input.

[0142] In operation S602, the control time domain and time step are initialized, and the initial values ​​and initial increments of the air supply speed, the number of personnel, and the control temperature in each grid area are assumed.

[0143] In operation S603, the coefficient matrix of the state space equation is calculated , , .

[0144] In operation S604, a gain matrix L is calculated.

[0145] In operation S605, the temperature variable at the kth time step is predicted by the estimation model. .

[0146] In operation S606 , a quadratic programming problem is constructed based on the temperature variable at the kth time step.

[0147] In operation S607 , the barrier factor μ0 and the control variable ΔV(k)0 are initialized.

[0148] In operation S608, the Adam algorithm is used to update ΔV(k)0 to obtain an updated control variable ΔV(k).

[0149] In operation S609, it is determined whether f(ΔV(k), μ0)≤ε. If it is determined to be yes, operation S610 is performed. If it is determined to be no, operation S608 is repeatedly performed.

[0150] Operation S610, determine whether μ0Iln(WΔV(k)-Z)≤ε. If it is determined to be yes, perform operation S612 to output the control variable Act on the air in the grid area. If it is determined to be no, perform operation S611, set μ=0.5μ0 and then repeat operation S608.

[0151] In operation S613, it is determined whether k=k off If it is determined to be yes, the calculation ends. off = k+1, if it is determined to be negative, perform operation S614, set k′=k+1 and then repeat operation S605.

[0152] According to the embodiment of the present invention, the variable air volume control method based on image recognition proposed by the present invention can solve the core problems in environmental control and energy management of large space buildings (such as subway stations, exhibition halls, airports, etc.). The number of people is obtained through real-time image recognition technology, and the fitting relationship between grid temperature, interface air volume and air supply speed is combined to dynamically optimize the operating parameters of the air in the grid area, realize on-demand energy supply and precise control, significantly improve energy utilization efficiency, reduce operating costs, and ensure the comfort requirements of densely populated areas at the same time, which is expected to help the construction industry achieve green and low-carbon goals. Taking the subway station as an example, the variable air volume control method based on image recognition proposed by the present invention can dynamically adjust the air supply volume of the station hall according to peak and non-peak periods, optimize the airflow organization, improve the comfort of passengers, and reduce unnecessary energy consumption. Compared with traditional feedback control, the present invention can realize forward-looking regulation by predicting temperature changes, optimize the operating parameters of the air in the grid area in advance, reduce the response delay of the system, and reduce the energy waste caused by frequent adjustments.

[0153] Figure 7 A block diagram of a variable air volume control device based on image recognition according to an embodiment of the present invention is shown.

[0154] like Figure 7 As shown, the variable air volume control device 700 based on image recognition includes a simulation module 710 , a division module 720 , a determination module 730 and a control module 740 .

[0155] The simulation module 710 is used to simulate turbulent flow in the target area based on preset simulation conditions to obtain the temperature distribution of the target area. The division module 720 is used to divide the target area into grids of predetermined sizes based on the temperature distribution of the target area to obtain multiple grid areas. The determination module 730 is used to determine the regional energy balance equation of each grid area based on the fitting relationship between the interface air volume and the air supply speed, the control temperature of each grid area, and the number of personnel in each grid area. The control module 740 is used to control the air supply speed with the optimization goal of minimizing the difference between the control temperature of each grid area and the design temperature control temperature, wherein the number of personnel in each grid area is determined based on image recognition of the collected video data of the grid area.

[0156] According to an embodiment of the present invention, the variable air volume control device 700 based on image recognition further includes a first temperature determination module. The first temperature determination module is used to determine the respective real temperatures in the grid area as the control temperature when the respective real temperatures in the grid area are successfully determined and collected.

[0157] According to an embodiment of the present invention, the variable air volume control device 700 based on image recognition further includes: a construction module, a prediction module, a second temperature determination module and a third temperature determination module. The construction module is used to construct an estimation model for estimating the temperature change in the target area based on the temperature state observer when the determination of collecting the respective real temperatures in the grid area fails and the collection of the respective real temperatures of some grid areas in the grid area succeeds. The prediction module is used to predict the respective real temperatures of other grid areas in the grid area except some grid areas by using the estimation model and the respective real temperatures of some grid areas to obtain the respective predicted temperatures. The second temperature determination module is used to determine the respective real temperatures of some grid areas as the respective control temperatures of some grid areas. The third temperature determination module is used to determine the respective predicted temperatures of other grid areas as the respective control temperatures of other grid areas.

[0158] According to an embodiment of the present invention, the variable air volume control device 700 based on image recognition further includes: a detection module and a counting module. The detection module is used to detect the outline of people in the collected video data for each grid area and mark the candidate frame. The counting module is used to determine the number of people according to the number of candidate frames.

[0159] According to an embodiment of the present invention, any multiple modules of the simulation module 710, the partition module 720, the determination module 730 and the control module 740 can be combined in one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the simulation module 710, the partition module 720, the determination module 730 and the control module 740 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the simulation module 710, the partition module 720, the determination module 730 and the control module 740 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be executed.

[0160] It should be noted that the variable air volume control device part based on image recognition in the embodiment of the present invention corresponds to the variable air volume control method part based on image recognition in the embodiment of the present invention. The description of the variable air volume control device part based on image recognition specifically refers to the variable air volume control method part based on image recognition, which will not be repeated here.

[0161] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present invention may be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, the features described in the various embodiments of the present invention may be combined and / or combined in various ways without departing from the spirit and teachings of the present invention. All of these combinations and / or combinations fall within the scope of the present invention.

[0162] The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although each embodiment is described above, it does not mean that the measures in each embodiment cannot be used in combination. The scope of the present invention is defined by the attached claims and their equivalents. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A variable air volume control method based on image recognition, characterized in that: The variable air volume control method comprises: Based on preset simulation conditions, simulating turbulent flow in a target area to obtain a temperature distribution in the target area; Based on the temperature distribution of the target area, dividing the target area into grids of a predetermined size to obtain a plurality of grid areas; Determining a regional energy balance equation for each of the grid areas based on a fitting relationship between the interface air volume and the air supply speed, the control temperature of each of the grid areas, and the number of personnel in each of the grid areas; and The air supply speed is controlled with the optimization goal of minimizing the difference between the control temperature and the design temperature of each grid area, wherein the number of people in each grid area is determined based on image recognition of the video data collected from the grid area.

2. The variable air volume control method according to claim 1, characterized in that: The regional energy balance equation of each grid area is determined based on the fitting relationship between the interface air volume and the air supply speed, the control temperature of each grid area, and the number of personnel in each grid area, including: Determine a first heat quantity for the air in the grid area based on a difference between a temperature of an area adjacent to the grid area and a temperature of the grid area, an air parameter of the grid area, and the fitting relationship; Determining a second heat quantity for the air in the grid area based on the number of people in the grid area and the average heat dissipation per person; Determine a third heat amount for the air in the grid area based on a difference between the air supply temperature of the grid area and the temperature of the grid area, an air supply port area of ​​the grid area, an air supply speed of the grid area, and an air parameter of the grid area; determining a total amount of heat based on the first amount of heat, the second amount of heat, and the third amount of heat; Determining a change in the internal energy of the air in the grid area based on the air parameters of the grid area, the volume of the grid area, and the temperature of the grid area; and Based on the total heat being equal to the change in internal energy, the regional energy balance equation is obtained.

3. The variable air volume control method according to claim 1, characterized in that: The control of the air supply speed with minimizing the difference between the control temperature and the design temperature of each grid area as an optimization goal comprises: Performing linear transformation based on nonlinear terms in the regional energy balance equation; Determining an incremental form of the regional energy balance equation based on the transformed nonlinear term and the regional energy balance equation; converting the incremental form into a matrix form; Discretizing the regional energy balance equation in matrix form by analytical method to obtain a state space equation with the increment of the control temperature of each grid area as output; Based on the state-space equation and the measurable disturbance condition, determining the state-space equation after iterating a preset number of steps; Based on the state space equation after the preset number of iteration steps, the temperature increment and the air supply speed increment within the preset number of iteration steps are converted into respective corresponding matrix forms; Determine a variable air volume prediction equation based on the matrix forms corresponding to the temperature increment and the air supply speed increment within the preset number of iteration steps; According to the optimization goal, determining the objective function; According to the variable air volume prediction equation and the objective function, a quadratic programming problem with the air supply speed as a variable is obtained; and The quadratic programming problem is solved by using an interior point penalty function method to control the air supply speed.

4. The variable air volume control method according to claim 3, characterized in that: The method of solving the quadratic programming problem by using the interior point penalty function method to control the air supply speed includes: Converting the quadratic programming problem into a logarithmic interior point penalty function; Using an adaptive learning rate algorithm to update the variable, gradually reducing the barrier factor of the logarithmic interior point penalty function, and repeatedly updating the variable until a termination criterion is met, thereby obtaining an updated variable; and When it is determined that the preset number of iteration steps meets the iteration threshold, the control of the air supply speed is completed.

5. The variable air volume control method according to claim 1, characterized in that: The variable air volume control method further includes: in a case where it is determined that the real temperatures of each grid area are collected successfully, determining the real temperatures of each grid area as the control temperature.

6. The method according to claim 1, characterized in that The method further comprises: In the case where it is determined that the acquisition of the respective real temperatures within the grid area fails, but the acquisition of the respective real temperatures of some grid areas within the grid area succeeds, constructing an estimation model for estimating the temperature change within the target area based on a temperature state observer; Using the estimation model and the respective true temperatures of the partial grid areas, predicting the respective true temperatures of the other grid areas within the grid area except the partial grid areas to obtain respective predicted temperatures; determining the respective real temperatures of the partial grid areas as the respective control temperatures of the partial grid areas; and The predicted temperature of each of the other grid areas is determined as the control temperature of each of the other grid areas.

7. The variable air volume control method according to any one of claims 1 to 6, characterized in that: The step of dividing the target area into grids of a predetermined size based on the temperature distribution of the target area to obtain a plurality of grid areas includes: Determining temperature changes within the target area according to the temperature distribution of the target area; When it is determined that the temperature change in the target area meets the preset temperature change condition, the target area is divided into a plurality of grid areas of a first predetermined size; When it is determined that the temperature change in the target area does not meet the preset temperature change condition, the target area is divided into a plurality of grid areas of a second predetermined size, wherein the first predetermined size is smaller than the second predetermined size.

8. The variable air volume control method according to any one of claims 1 to 6, characterized in that: The variable air volume control method further comprises: For each of the grid regions: Performing person contour detection on the collected video data and marking candidate frames; and The number of personnel is determined according to the number of the candidate boxes.

9. A variable air volume control device based on image recognition, characterized in that: The variable air volume control device comprises: A simulation module, used to simulate turbulent flow in a target area based on preset simulation conditions to obtain a temperature distribution in the target area; A division module, used for dividing the target area into grids of predetermined sizes based on the temperature distribution of the target area to obtain a plurality of grid areas; a determination module, configured to determine a regional energy balance equation for each of the grid areas based on a fitting relationship between the interface air volume and the air supply speed, a control temperature of each of the grid areas, and the number of personnel in each of the grid areas; and A control module is used to control the air supply speed with the optimization goal of minimizing the difference between the control temperature and the design temperature of each grid area, wherein the number of people in each grid area is determined based on image recognition of the video data collected from the grid area.

10. An electronic device, comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the variable air volume control method according to any one of claims 1 to 8.

Images