Intelligent control method and system for floor radiation air conditioning system

Abstract

The invention provides an intelligent control method and system for a floor radiation air conditioning system, and the method comprises the steps: obtaining indoor personnel load estimation data and thermal comfort calculation data, and estimating the indoor personnel load; based on the indoor environment parameters and the thermal comfort calculation data, establishing a thermal feeling prediction model; based on the indoor and outdoor environment parameters, the equipment parameters and the air conditioning system operation parameters, an indoor environment and energy consumption prediction model is established, and the adjusted indoor environment and air conditioning system energy consumption of the air conditioning system are predicted; respectively constructing a personnel thermal comfort objective function and an energy consumption objective function according to the indoor and outdoor environment parameters, the indoor personnel load, the thermal sensation and the air conditioning system energy consumption, and determining a total objective function according to the weight of the personnel thermal comfort objective function and the weight of the energy consumption objective function; and an improved dung beetle optimization algorithm is applied to solve the total target function to obtain the optimal regulation and control parameters for controlling the floor radiation air-conditioning system, so that the reliability of controlling the floor radiation air-conditioning system is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of air conditioning system control, and in particular to an intelligent control method and system for a floor radiation air conditioning system. Background Art

[0002] With the rapid development of building intelligent technology, people's demand for building intelligence is getting higher and higher. Intelligent adjustment of air conditioning is an important part of building intelligence. Intelligent air conditioning system can provide users with a healthy and comfortable environment to meet the needs of users' work and life. Most of the current air conditioning systems control environmental comfort by setting a single temperature and humidity index, which cannot well reflect individual comfort needs, and are prone to "overcooling" and "overheating", resulting in energy waste.

[0003] On the other hand, the control strategy of traditional floor radiant air-conditioning systems uses temperature and condensation risk as indicators, ignoring the uncertainty of personnel flow. In addition, due to the inherent thermal inertia of radiant floors, the cooling capacity is slowly adjusted. When the indoor personnel load changes rapidly, the radiant air-conditioning system terminal has a certain lag effect on the adjustment of the indoor environment, resulting in a mismatch between supply and demand, which in turn leads to a deterioration in indoor environmental comfort and energy waste within a certain period of time, making the control reliability of floor radiant air-conditioning systems low.

[0004] In order to solve the problem of low reliability of control of floor radiation air conditioning system in the prior art, this solution is proposed. Summary of the invention

[0005] In order to solve the problems existing in the prior art, the present invention innovatively proposes an intelligent control method and system for a floor radiant air-conditioning system, which effectively solves the problem of low reliability of the control of the floor radiant air-conditioning system caused by the prior art, and effectively improves the reliability of the control of the floor radiant air-conditioning system.

[0006] A first aspect of the present invention provides an intelligent control method for a floor radiant air conditioning system, comprising:

[0007] Obtain indoor environmental parameters, outdoor environmental parameters, thermal imaging video streams, non-thermal imaging video streams, and air conditioning system operation data;

[0008] Use computer vision technology to process thermal imaging video streams and non-thermal imaging video streams, track indoor personnel, obtain indoor personnel load estimation data and thermal comfort calculation data, and estimate indoor personnel load based on indoor personnel load estimation data;

[0009] Based on indoor environmental parameters and thermal comfort calculation data, a thermal sensation prediction model is established to predict the thermal sensation of indoor occupants.

[0010] Based on indoor and outdoor environmental parameters, equipment parameters, and air-conditioning system operating parameters, an indoor environment and energy consumption prediction model is established to predict the indoor environment after adjustment by the air-conditioning system and the energy consumption of the air-conditioning system;

[0011] Determine the constraints, and construct the personnel thermal comfort objective function and energy consumption objective function based on indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air conditioning system energy consumption. Determine the overall objective function based on the weights of the personnel thermal comfort objective function and the energy consumption objective function.

[0012] The improved dung beetle optimization algorithm is used to solve the overall objective function and obtain the optimal control parameters of the floor radiant air conditioning system.

[0013] A second aspect of the present invention provides an intelligent control system for a floor radiation air conditioning system, comprising:

[0014] The first acquisition module acquires indoor and outdoor environmental parameters, thermal imaging video streams, non-thermal imaging video streams, air conditioning system operation data, and equipment parameters;

[0015] The second acquisition module uses computer vision technology to process thermal imaging video streams and non-thermal imaging video streams, track indoor personnel, obtain indoor personnel load estimation data and thermal comfort calculation data, and estimate indoor personnel load based on the indoor personnel load estimation data;

[0016] The first building module is to build a thermal sensation prediction model based on indoor environmental parameters and thermal comfort calculation data to predict the thermal sensation of indoor occupants;

[0017] The second establishment module establishes an indoor environment and energy consumption prediction model based on indoor and outdoor environmental parameters, equipment parameters, and air-conditioning system operating parameters to predict the indoor environment and air-conditioning system energy consumption after being adjusted by the air-conditioning system;

[0018] Determine the module, determine the constraint conditions, and construct the personnel thermal comfort objective function and energy consumption objective function respectively based on the indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air conditioning system energy consumption. Determine the overall objective function based on the weights of the personnel thermal comfort objective function and the energy consumption objective function.

[0019] The solution module applies the improved dung beetle optimization algorithm to solve the overall objective function and obtain the optimal control parameters for the floor radiation air conditioning system.

[0020] The technical solution adopted by the present invention includes the following technical effects:

[0021] 1. In the technical solution of the present invention, computer vision technology is used to process thermal imaging video streams and non-thermal imaging video streams, track indoor personnel, obtain indoor personnel load estimation data and thermal comfort calculation data, and estimate indoor personnel load according to indoor personnel load estimation data; a thermal sensation prediction model is established based on indoor environmental parameters and thermal comfort calculation data to predict indoor personnel thermal sensation; an indoor environment and energy consumption prediction model is established based on indoor and outdoor environmental parameters, equipment parameters, and air-conditioning system operation parameters to predict the indoor environment after air-conditioning system adjustment and the energy consumption of the air-conditioning system; constraint conditions are determined, and personnel thermal comfort objective function and energy consumption objective function are respectively constructed with indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air-conditioning system energy consumption, and the total objective function is determined according to the weights of the personnel thermal comfort objective function and the energy consumption objective function; an improved dung beetle optimization algorithm is applied to solve the total objective function to obtain the optimal control parameters of the floor radiation air-conditioning system control, and the radiation air-conditioning system parameters can be adjusted in real time according to the indoor personnel load and personnel thermal comfort, effectively solving the problem of low reliability of floor radiation air-conditioning system control caused by the prior art, and effectively improving the reliability of floor radiation air-conditioning system control.

[0022] 2. In the technical solution of the present invention, a personnel detection and tracking model is established based on computer vision technology to obtain the detected personnel position and number; the gender and age range of the personnel are obtained according to the human face recognition results; the recognized human body parts are continuously tracked, human body movements are identified, and the movement distance per unit time is obtained. According to the human body movements and the movement distance of human body parts per unit time, the human body activity status is identified, and the indoor personnel load is estimated. The indoor personnel load can be estimated according to the personnel type and activity status, thereby further improving the reliability of the floor radiant air-conditioning system control.

[0023] 3. In the technical solution of the present invention, by real-time monitoring of indoor and outdoor environmental parameters and thermal imaging data, an artificial neural network algorithm is used to establish a thermal sensation prediction model based on indoor environmental parameters and thermal comfort calculation data to predict the thermal sensation of indoor occupants and accurately reflect the thermal sensation of users. This can realize personalized intelligent adjustment of the radiation air-conditioning system, reduce the user's tedious operations, and greatly improve the user's thermal comfort.

[0024] 4. The technical solution of the present invention uses computer vision to track and identify the number and activities of indoor people, respond to changes in indoor personnel load in a timely manner, quickly adjust air-conditioning parameters, effectively alleviate the lag effect in the control of the radiation air-conditioning system, and reduce the discomfort and energy waste caused by the imbalance between supply and demand of air-conditioning load.

[0025] 5. The technical solution of the present invention uses an artificial neural network algorithm to predict the control effect of the radiation air-conditioning system, and at the same time determines the constraint conditions, and constructs the personnel thermal comfort objective function and energy consumption objective function respectively according to the indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air-conditioning system energy consumption. According to the weights of the personnel thermal comfort objective function and the energy consumption objective function, the overall objective function is determined; the improved dung beetle optimization algorithm is applied to generate the optimal control parameters, thereby ensuring the thermal comfort of the personnel and reducing the energy consumption of the air-conditioning system.

[0026] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 A schematic diagram of a process of a method in Example 1 of the present invention;

[0029] Figure 2 Schematic diagram of the process of step S2 in the method of embodiment 1 of the present invention;

[0030] Figure 3 A schematic diagram of the personnel load corresponding to different activity states of different groups of people in the method of Example 1 of the present invention;

[0031] Figure 4 Schematic diagram of the process of step S3 in the method of embodiment 1 of the present invention;

[0032] Figure 5 This is a schematic diagram of collecting thermal sensation data in the method of Example 1 of the present invention;

[0033] Figure 6 Schematic diagram of the process of step S4 in the method of embodiment 1 of the present invention;

[0034] Figure 7 Schematic diagram of the process of step S5 in the method of embodiment 1 of the present invention;

[0035] Figure 8 It is a flow chart of the dung beetle optimization algorithm in the method of Example 1 in the scheme of the present invention;

[0036] Fig. 9 Another schematic diagram of the process of the method of Embodiment 1 in the scheme of the present invention;

[0037] Fig.10Schematic diagram of the implementation process of step S7 in the method of embodiment 1 of the present invention;

[0038] Fig.11 It is a schematic diagram of the structure of the system of Example 2 in the solution of the present invention. DETAILED DESCRIPTION

[0039] In order to clearly illustrate the technical features of the present solution, the present invention is described in detail below through specific implementation methods and in conjunction with the accompanying drawings. The disclosure below provides many different embodiments or examples for realizing different structures of the present invention. In order to simplify the disclosure of the present invention, the components and settings of specific examples are described below. In addition, the present invention may repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed. It should be noted that the components illustrated in the accompanying drawings are not necessarily drawn to scale. The present invention omits the description of known components and processing techniques and processes to avoid unnecessary limitations on the present invention.

[0040] Embodiment 1

[0041] like Figure 1 As shown, the present invention provides an intelligent control method for a floor radiation air conditioning system, comprising:

[0042] S1, obtain indoor environmental parameters, outdoor environmental parameters, thermal imaging video stream, non-thermal imaging video stream, and air conditioning system operation data;

[0043] S2, using computer vision technology to process thermal imaging video streams and non-thermal imaging video streams, track indoor personnel, obtain indoor personnel load estimation data and thermal comfort calculation data, and estimate indoor personnel load based on indoor personnel load estimation data;

[0044] S3, based on indoor environmental parameters and thermal comfort calculation data, a thermal sensation prediction model is established to predict the thermal sensation of indoor occupants;

[0045] S4, based on indoor and outdoor environmental parameters, equipment parameters, and air-conditioning system operating parameters, establish an indoor environment and energy consumption prediction model to predict the indoor environment after the air-conditioning system is adjusted and the energy consumption of the air-conditioning system;

[0046] S5, determine the constraint conditions, construct the personnel thermal comfort objective function and energy consumption objective function respectively based on the indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air conditioning system energy consumption, and determine the total objective function according to the weights of the personnel thermal comfort objective function and the energy consumption objective function;

[0047] S6, using the improved dung beetle optimization algorithm, the overall objective function is solved to obtain the optimal control parameters for the floor radiant air conditioning system.

[0048] Among them, in step S1, the air conditioning system operation data includes: fresh air temperature, fresh air speed, fresh air volume of fresh air fan, radiant floor surface temperature, radiant floor water supply temperature, radiant floor return water temperature; indoor environmental parameters include: indoor temperature, indoor humidity, wall temperature, and other surface temperatures except wall and floor surface; outdoor environmental parameters include: solar radiation, outdoor temperature, outdoor humidity; indoor personnel load estimation data include the number of personnel, personnel gender, age range, and human activity status; thermal comfort calculation data include human facial temperature, human hand temperature, indoor average radiation temperature, and operating temperature, and the operating temperature is the temperature of the comprehensive effect of indoor air temperature and indoor average radiation temperature on human body; sensors are used to obtain indoor and outdoor environmental parameters, thermal imaging video stream, ordinary video stream (non-thermal imaging video stream), and air conditioning system operation data, and thermal imaging real-time video is recorded by a thermal imager. Use a thermal imager to record the video in the room in real time; equipment parameters include: fresh air fan speed range, radiant floor water supply temperature range.

[0049] The applied radiant air conditioning system includes: fresh air fan, radiant floor, mixing water pump, temperature and humidity sensor, thermal imager and camera.

[0050] The acquired data are divided into two parts. One part is the acquired historical data, which is used to train the artificial neural network model; the other part is the real-time data, which is used for the real-time calculation of the intelligent control method and system of the floor radiation air-conditioning system based on computer vision to solve the optimal control parameters.

[0051] like Figure 2 As shown, step S2 specifically includes:

[0052] S21, establishing a personnel detection model, a personnel tracking model, and a human body recognition model based on computer vision technology, and inputting both the indoor thermal imaging video stream and the non-thermal imaging video stream into the trained personnel detection model, the personnel tracking model, and the human body recognition model;

[0053] S22, normalizing the indoor thermal imaging video stream and the non-thermal imaging video stream, using the trained personnel detection model and the personnel tracking model to identify and obtain the detected personnel positions and the number of personnel;

[0054] The personnel detection model can identify the human body in the thermal imaging video stream and the non-thermal imaging video stream, and the personnel tracking model can identify the movement of the human body in the thermal imaging video stream and the non-thermal imaging video stream. Here, it is a neural network based on deep learning (after labeling, training, testing, etc.), and the existing neural network model can also be used. As long as personnel detection and tracking can be achieved, the present invention is not limited here.

[0055] S23, inputting the person's location area into the trained human body recognition model, identifying the body parts, obtaining the facial temperature according to the temperature values ​​of different positions on the human face; obtaining the hand temperature according to the temperature values ​​of different positions on the human hand; and obtaining the gender and age range of the person according to the human face recognition result;

[0056] The location area of ​​the person is input into the human body recognition model, and the human body parts are identified. Multiple key points are taken for each part and the average value is calculated. Specifically, after facial recognition, the facial temperature is taken from the nose tip, left cheek, right cheek, and forehead, and the average value is calculated. The calculation formula is:

[0057]

[0058] Where, T m is the facial temperature, ℃; T mb is the nose tip temperature, °C; T mz is the left cheek temperature, ℃; T my is the right cheek temperature, ℃; T me is the forehead temperature, ℃.

[0059] After hand temperature is identified, the left hand back, right hand back, left wrist, and right wrist temperatures are selected and averaged. The calculation formula is:

[0060]

[0061] Where, T s is the hand temperature, ℃; T sbz is the temperature of the left hand back, ℃; T sby is the temperature of the back of the right hand, ℃; T swz is the left wrist temperature, ℃; T swy is the right wrist temperature, ℃.

[0062] S24, continuously tracking the identified human body parts, identifying human body movements, obtaining the moving distance per unit time, identifying the human body activity state according to the human body movements and the moving distance per unit time of the human body parts, and estimating the indoor personnel load; wherein the indoor personnel load calculation formula is:

[0063] Among them, Q p is the personnel load; Q z is the estimated heat load of the zth group of people; n z is the number of the zth group of people; g is the total number of people; the people include male teenagers, male youths, male middle-aged people, male elders, female teenagers, female youths, female middle-aged people, and female elders;

[0064] More specifically, the human load is the heat load generated by each person in a specific environment, which is affected by many factors. Therefore, the present invention only makes a simple estimate here to assist in the rapid adjustment of the indoor environment. The human load standard is shown in Figure 3 shown.

[0065] S25, obtaining the pre-divided indoor floor surface temperature, indoor wall temperature, and indoor surface temperatures other than the floor surface and the wall surface from the thermal imaging video, and calculating the indoor average radiation temperature and the first calculated value of the operating temperature respectively according to the indoor floor surface temperature, the indoor wall temperature, and indoor surface temperatures other than the floor surface and the wall surface.

[0066] The calculation formula for the indoor average radiation temperature is:

[0067]

[0068] Among them, F j is the angle coefficient of the jth surface to the human body; T j is the absolute temperature of the jth surface; T r is the average indoor radiation temperature; k is the total number of surfaces; preferably, after the human body recognition algorithm completes the recognition, the human body pixels are removed, and then the average radiation temperature of the remaining part is calculated.

[0069] The calculation formula for the first calculated value of operating temperature (thermal comfort operating temperature) is:

[0070]

[0071] Among them, h c is the convective heat transfer coefficient; T a is the indoor air temperature; h r is the radiation heat transfer coefficient; T r is the mean radiation temperature; T OP is the first calculated value of the operating temperature.

[0072] Specifically, when installing the thermal imager, the image information is imported, the video information is corrected, the lens distortion is eliminated, and the noise is removed by using a filter. In the graphical user interface (GUI), the radiant floor area, the wall, and other indoor areas are pre-divided.

[0073] Operating temperature: Because the radiant floor in the radiant floor air conditioning system exchanges heat with the human body through radiation, the indoor environment cannot be measured only by indoor temperature and humidity, and then the operating temperature is quoted. The operating temperature is the temperature of the combined effect of indoor air temperature and average radiation temperature on the human body.

[0074] like Figure 4As shown, in step S3, a thermal sensation prediction model is established based on indoor environmental parameters and thermal comfort calculation data, and the prediction of indoor thermal sensation of people specifically includes:

[0075] S31, using indoor humidity historical data, indoor temperature historical data, facial temperature historical data, hand temperature historical data, indoor average radiation temperature historical data (which may also include operating temperature first calculated value historical data) as first input data, and using indoor personnel's thermal sensation historical data as first output data, to establish a first mapping database between first input data and corresponding first output data;

[0076] Specifically, a temperature and humidity recorder can be used in the laboratory to continuously measure the indoor thermal environment, and a thermal imager can be used to record the video, and the above step S2 can be repeated. The indoor temperature and humidity, facial temperature, hand temperature, average radiation temperature, and the first calculated value of the operating temperature are obtained. During the experiment, the indoor temperature and humidity, floor surface temperature, and wall temperature are adjusted at fixed intervals.

[0077] like Figure 5 As shown, 10 minutes after the environment is adjusted to the target environment, the thermal sensation of the subjects is collected through a questionnaire, including: very cold, cold, cool, slightly cool, neutral, slightly warm, warm, hot, and very hot; and finally a first mapping database of first input data and corresponding first output data is established.

[0078] S32, establishing and training a thermal sensation prediction model using an artificial neural network algorithm and a first mapping database;

[0079] Select input item: Face temperature T m , hand temperature T s , Indoor temperature T a , indoor humidity RH in , the first calculated value of the operating temperature T op , indoor average radiation temperature T r ; The output is thermal sensation.

[0080] Write artificial neural network algorithms, divide training sets and test sets, and normalize input and output data;

[0081] Determine the neural network structure, the number of neurons in the input layer is 6, try the number of neuron nodes in the hidden layer, and the number of neurons in the output layer is 1; input the hyperparameters of the model and start training; complete the thermal sensation prediction model training.

[0082] The test set is input into the thermal sensation prediction model to predict the thermal sensation, and the root mean square error (RMSE), mean absolute error (MAE) and determination coefficient: R2 are used to evaluate the model. If the model is trained based on the same data set, the smaller the RMSE and MAE values, and the closer the R2 is to 1, the higher the model accuracy.

[0083] It should be noted that the above-mentioned artificial neural network can be predicted based on algorithms such as recurrent neural networks, long short-term memory networks, etc., and the embodiments of the present application are not limited to this.

[0084] S33, input the real-time data of indoor temperature, indoor humidity, facial temperature, hand temperature, and indoor average radiation temperature (which may also include the real-time data of the first calculated value of the operating temperature) into the trained thermal sensation prediction model to predict the thermal sensation of the human body.

[0085] Specifically, cold, cool, slightly cool, neutral, slightly hot, hot and very hot are used as temperature adjustment indicators, representing temperatures 2°C below the comfort temperature, 1°C below the comfort temperature, 0.5°C below the comfort temperature, equal to the comfort temperature, 0.5°C above the comfort temperature, 1°C above the comfort temperature and 2°C below the comfort temperature respectively.

[0086] Furthermore, the temperature indexes may be divided according to actual conditions, and the present invention is not limited thereto.

[0087] like Figure 6 As shown, in step S4, based on indoor and outdoor environmental parameters, equipment parameters, and air conditioning system operating parameters, an indoor environment and energy consumption prediction model is established to predict the indoor environment after the air conditioning system is adjusted and the energy consumption of the air conditioning system, specifically including:

[0088] S41, using historical data of wall temperature, historical data of outdoor temperature, historical data of outdoor humidity, historical data of fresh air temperature, historical data of fresh air speed, historical data of floor surface temperature, historical data of radiant floor water supply temperature, and historical data of indoor personnel load as second input data, and using historical data of indoor average radiant temperature adjusted by the air-conditioning system, historical data of indoor condensation temperature difference adjusted by the air-conditioning system, historical data of energy consumption of the wind system, and historical data of energy consumption of the water system as second output data, to establish a second mapping database between the second input data and the corresponding second output data;

[0089] Specifically, the historical data obtained in S1 are sorted out, and the historical air conditioning system operation data includes: fresh air temperature, fresh air speed, radiant floor surface temperature, radiant floor water supply temperature, and radiant floor return water temperature; historical indoor environmental parameters include: indoor temperature, indoor humidity, wall temperature, and other surface temperatures except wall and floor surfaces; historical personnel activities include: number of personnel, personnel activities, and personnel load; historical outdoor environmental parameters include: solar radiation, outdoor temperature, and outdoor humidity. That is, historical data of wall temperature, historical data of outdoor temperature, historical data of outdoor humidity, historical data of fresh air temperature, historical data of fresh air speed, historical data of floor surface temperature, historical data of radiant floor water supply temperature, and historical data of indoor personnel load.

[0090] The second output data is the historical data of the indoor average radiation temperature after the air conditioning system is adjusted, the historical data of the indoor condensation temperature difference after the air conditioning system is adjusted, the historical data of the energy consumption of the wind system, and the historical data of the energy consumption of the water system. The calculation formula of the condensation temperature difference is:

[0091] ΔT l =T d -T ld

[0092] Where, T d is the floor surface temperature, °C; T ld is the dew point temperature of indoor air, ℃; ΔT l is the condensation temperature difference, ℃.

[0093] The energy consumption calculation formula of the wind system is:

[0094] ΔE x =V×ρ s ×(C pa ×T o +w o (C pw ×T o +R w ×T o )-C pa ×T f +w f (C pw ×T f +R w ×T f )),

[0095] Where V is the air volume of the air system, m 3 / h;ρ s is the water density, kg / m3; C pa is the specific heat capacity of dry air, kJ / kg·K; T o is the outdoor air temperature, ℃; w o is the humidity content of outdoor air, kgH2 O / kgDryAir; C pw is the specific heat capacity of water vapor, kJ / kg·K; R W is the gas constant of water vapor, kJ / kg·K; T f is the air temperature at the outlet of the fresh air blower, ℃; w f is the humidity content of the air at the outlet of the fresh air fan, kgH 2 O / kgDryAir;ΔE x is the energy consumption of the wind system per hour, kW / h.

[0096] The energy consumption calculation formula of water system is:

[0097] ΔE s =Q r ×ρ s ×C×ΔT

[0098] In the formula, ΔE s is the energy dissipated by the water system per hour, kW / h; Q r is the water flow rate, m 3 / h;ρ s is the water density, kg / m3; C is the specific heat capacity of water, about 4.18 kJ / (kg·K); ΔT r The supply and return water temperature difference of the radiant floor, ℃.

[0099] S42, using an artificial neural network algorithm and a second mapping database to establish and train an indoor environment and energy consumption prediction model;

[0100] Select input items: wall temperature, outdoor temperature, outdoor humidity, fresh air temperature, fresh air speed, floor surface temperature, radiant floor water supply temperature, and personnel load; output items: historical data of indoor average radiant temperature after adjustment by the air-conditioning system, historical data of indoor condensation temperature difference after adjustment by the air-conditioning system, historical data of wind system energy consumption, and historical data of water system energy consumption.

[0101] Write artificial neural network algorithms; divide training sets and test sets, and normalize input and output data;

[0102] Determine the neural network structure, the number of neurons in the input layer is 8, try to find the number of neuron nodes in the hidden layer, and the number of neurons in the output layer is 4;

[0103] Enter the model's hyperparameters and start training; complete the indoor environment and energy consumption prediction model training.

[0104] The test set is input into the indoor environment and energy consumption prediction model to predict the indoor environment and energy consumption, and the root mean square error (RMSE), mean absolute error (MAE) and determination coefficient: R2 are used to evaluate the model. If the model is trained based on the same data set, the smaller the RMSE and MAE values ​​are, and the closer the R2 is to 1, the higher the model accuracy is.

[0105] It should be noted that the above-mentioned artificial neural network algorithm can be based on algorithms such as recurrent neural networks, long short-term memory networks, etc. for prediction, and the embodiments of the present application are not limited to this.

[0106] S43, input the real-time data of wall temperature, outdoor temperature, outdoor humidity, fresh air temperature, fresh air speed, floor surface temperature, radiant floor water supply temperature, and indoor personnel load into the trained indoor environment and energy consumption prediction model, and predict the real-time data of the indoor average radiation temperature after adjustment by the air-conditioning system, the real-time data of the indoor condensation temperature difference after adjustment by the air-conditioning system, the real-time data of the wind system energy consumption, and the real-time data of the water system energy consumption.

[0107] In step S5, the constraints include air supply volume constraint, water supply pump state constraint and floor water supply temperature constraint; wherein the air supply volume constraint is:

[0108]

[0109] in, It is the minimum air supply volume of the fresh air system; The maximum air supply volume of the fresh air system; To regulate the air supply volume of the fresh air system;

[0110] The water supply pump state constraints are:

[0111] 0≤K b ≤1,

[0112] Among them, 0 is off, 1 is on, K b Pump status;

[0113] The floor water supply temperature constraint is:

[0114]

[0115] in, Provides the minimum temperature for floor water supply; Provides the maximum water temperature for the floor; To regulate the floor water supply pump temperature;

[0116] like Figure 7As shown in the figure, the personnel thermal comfort objective function and energy consumption objective function are constructed based on the indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air conditioning system energy consumption. According to the weights of the personnel thermal comfort objective function and the energy consumption objective function, the overall objective function is determined, including:

[0117] S51, outdoor temperature, outdoor humidity, wall temperature, floor surface temperature, indoor temperature, indoor humidity, operating temperature, and personnel load are used as environmental independent variables, and fresh air volume of the fresh air fan, radiant floor water supply temperature, and radiant floor water supply pump status are used as control parameter independent variables;

[0118] Specifically, the real-time data set described in S1 is exported, including: wall temperature, outdoor temperature, outdoor humidity, fresh air temperature, fresh air speed, floor surface temperature, radiant floor water supply temperature, and the personnel load and operating temperature first calculated value obtained in S2 are exported.

[0119] The outdoor temperature, outdoor humidity, wall temperature, floor surface temperature, indoor temperature, indoor humidity, the first calculated value of operating temperature, and personnel load are taken as the environmental data set and as part of the independent variables, respectively as X 1 , X 2 , X 3 , X 4 , X 5 , X 6 , X 7 , X 8 .

[0120] The control parameters are taken as part of the independent variables, namely, the fresh air volume of the fresh air fan, the radiant floor water supply temperature, and the radiant floor water supply pump status, which are X 9 , X 10 , X 11 That is, the control parameter independent variable is combined with the above-mentioned environmental parameter independent variable as the independent variable of the optimization algorithm.

[0121] S52, with personnel thermal comfort, personnel load, condensation risk, wind system energy consumption and water system energy consumption as optimization targets respectively;

[0122] f 1 =min|T OPS (X i )-T OP |,

[0123] f 1' =min|T in (X i )-T sd |,

[0124] f 2 =-min|ΔT l (X i )|,

[0125] f 3 =minE f (X i ),

[0126] f 4 =minE s (X i ),

[0127] f 5 =min|Q p -|E f -E fs ||,

[0128] Among them, f 1 is the thermal comfort objective function; f 1' Set the temperature objective function for the user; f 2 is the condensation temperature difference objective function; f 3 is the objective function of the wind system; f 4 is the objective function of the water system; f 5 is the personnel load objective function; X i is the ith independent variable; T OPS The second calculated value of the indoor operating temperature calculated from the indoor average radiation temperature predicted by the indoor environment and energy consumption prediction model, ℃; T OP is the first calculated value of the operating temperature, °C; T in is the indoor temperature predicted by the indoor environment and energy consumption prediction model, ℃; ΔT l is the condensation temperature difference predicted by the indoor environment and energy consumption prediction model, ℃; T sd Set the temperature for the user, ℃; E f The wind system energy consumption predicted by the indoor environment and energy consumption prediction model, kw·h; E s The energy consumption of the water system predicted by the indoor environment and energy consumption prediction model, kw·h; Q p is the indoor personnel load, w; E fs is the energy consumption of the wind system in the previous period, kw·h;

[0129] Taking outdoor temperature, outdoor humidity, cooling load, wet load, fresh air volume of fresh air fan, radiant floor water supply temperature and radiant floor water supply pump status as variables, the indoor air temperature is set, and based on the difference between the indoor air temperature and the user-set value, the indoor temperature objective function (i.e., the user-set temperature objective function) is constructed. 1' ;

[0130] The personnel thermal comfort objective function f is constructed with outdoor temperature, outdoor humidity, wall temperature, floor surface temperature, indoor temperature, indoor humidity, operating temperature, personnel load, fresh air volume of fresh air fan, radiant floor water supply temperature, and radiant floor water supply pump status as variables. 1 ;

[0131] The condensation temperature difference objective function f is constructed with outdoor temperature, outdoor humidity, wall temperature, floor surface temperature, indoor temperature, indoor humidity, operating temperature, personnel load, fresh air volume of fresh air fan, radiant floor water supply temperature, and radiant floor water supply pump status as variables. 2 ;

[0132] The wind system energy consumption objective function f is constructed with outdoor temperature, outdoor humidity, wall temperature, floor surface temperature, indoor temperature, indoor humidity, operating temperature, personnel load, fresh air volume of fresh air fan, radiant floor water supply temperature, and radiant floor water supply pump status as variables. 3 ;

[0133] The energy consumption objective function f of the water system is constructed with outdoor temperature, outdoor humidity, wall temperature, floor surface temperature, indoor temperature, indoor humidity, operating temperature, personnel load, fresh air volume of the fresh air fan, radiant floor water supply temperature, and radiant floor water supply pump status as variables. 4 ;

[0134] The energy consumption objective function f of the water system is constructed by taking the indoor personnel load, indoor environment, wind system energy consumption predicted by the energy consumption prediction model, and wind system energy consumption in the previous period as variables. 5 .

[0135] Specifically, the objective function of the optimization algorithm is set. The present invention takes personnel thermal comfort, personnel load, condensation risk, energy consumption, etc. as optimization targets. Energy consumption is divided into wind system energy consumption and water system energy consumption. It is worth noting that when the number of indoor personnel changes, the thermal balance of the indoor environment is broken, and the air conditioning system control parameters need to be changed quickly to cope with the change in personnel load. Due to the thermal inertia of the radiant floor, it is difficult to handle instantaneous load changes, so the short-term load changes are handled by the wind system and deactivated after a period of time.

[0136] S53, according to the weight of each objective function, determine the total objective function f:

[0137] f=α 1 f 1 +α 2 f 2 +α 3 f 3 +α 4 f 4 +α 5 f 5 +α 6 f1' ,

[0138] Among them, α 1 , α 2 , α 3 , α 4 , α 5 , α 6 The weight of each goal.

[0139] Specifically, in order to reduce the complexity of the algorithm and simplify the multi-objective optimization problem, the above-mentioned indoor thermal and humidity environment, condensation risk, energy consumption function, etc. are weighted to form the thermal, humidity, condensation, and energy consumption objective function f. The weight of each objective function can be adjusted according to the actual needs of the user. 5 It is not 0 only when there is movement of people indoors.

[0140] Among them, Figure 8 As shown in the figure, the improved dung beetle optimization algorithm is used to solve the overall objective function, and the optimal control parameters of the floor radiation air conditioning system are obtained, including:

[0141] The environmental independent variables and control parameter independent variables corresponding to the total objective function are taken as a dung beetle, and the dung beetle population is initialized using Bernoulli mapping;

[0142] Specifically, the dung beetle optimization algorithm includes five behavioral parts: rolling, dancing, reproduction, foraging, and stealing. The Bernoulli mapping is used to initialize the dung beetle population, increase population diversity, and enhance the speed of its algorithm traversing the global environment, thereby improving the optimization efficiency and convergence speed. The calculation formula is:

[0143]

[0144] In the formula, Z n is the position of the nth dung beetle (the current value of the nth chaotic sequence generated), Z n+1 is the position of the n+1th dung beetle (the current value of the n+1th chaotic sequence generated). ρ is a mapping parameter, and its chaotic orbit state value range is (0, 1).

[0145] Calculating the fitness value of the dung beetle population, wherein the fitness value is the overall objective function;

[0146] Update the current position of the dung beetle, and calculate the current fitness value for each updated dung beetle;

[0147] Specifically, updating the current dung beetle position specifically includes:

[0148] When there is no obstacle in the rolling process, when λ<γ, it is in the obstacle-free state, otherwise it is in the obstacle state, where λ is a random number, λ∈[0,1]; γ is the probability value, γ=0.9. At this time, the position of the dung beetle is updated as:

[0149]

[0150] Where t is the current iteration number; represents the position of the i-th dung beetle at the t-th iteration; α is the natural coefficient, which takes the values ​​of 1 and -1; k is the deflection coefficient constant, which takes the value range of (0, 0.2]; b is a constant between (0, 1); for the position of the worst dung beetle in the population;

[0151] When encountering obstacles during the rolling process, the dung beetle will re-determine the rolling direction θ by dancing. The rolling direction θ is between (0, π). When the rolling direction is re-determined, the dung beetle will continue to roll the ball. At this time, the dung beetle position update formula is as follows:

[0152]

[0153] Since tanθ is 0 or does not exist when θ=0, π / 2, π, the position of the dung beetle is not updated at this time.

[0154] Dung beetles roll dung balls to safe and suitable areas for laying eggs and hide. The egg-laying area is simulated by the boundary selection strategy:

[0155]

[0156] Where: Lb* and Ub* represent the lower and upper limits of the spawning area, respectively. is the current local optimal position, R = 1-t / t max is the linear convergence factor, t max is the maximum number of iterations, Lb and Ub are the lower and upper limits of the problem to be optimized respectively;

[0157] When the egg-laying area is determined, the breeding dung beetles begin to lay eggs, and only one egg is laid in each iteration, and the position of the egg is also dynamically updated. At this time, the formula for updating the position of the dung beetle egg is:

[0158]

[0159] in, is the position of the sth egg at the tth iteration, b 1 and b 2 They are all independent random vectors of 1×D, where D represents the independent variable of the control parameter; that is, it represents the dimension of the optimization problem, specifically: the fresh air volume of the fresh air fan, the start and stop status of the radiant floor water supply pump, and the radiant floor water supply temperature.

[0160] When the larvae break out of the eggs and grow into small dung beetles, they start looking for food. At this time, the formula for updating the foraging position of the small dung beetles is:

[0161]

[0162] Among them, Lb l and Ub l are the lower and upper limits of the dung beetle's foraging range. is the current global optimal position;

[0163] Adaptive T-distribution disturbance is introduced during the foraging stage of the dung beetle. t(iter) is a T-distribution variation disturbance with the number of iterations iter as the degree of freedom parameter, which is used to perturb the foraging behavior of the dung beetle. At this time, the position update formula of the dung beetle is as follows:

[0164]

[0165] Among them, t(iter) is the T-distributed variation disturbance with the number of iterations iter as the degree of freedom parameter;

[0166] There is a behavior of stealing dung balls in the dung beetle population. At this time, the position update formula of the stealing dung beetle is:

[0167]

[0168] Where S is a constant and g is a random vector that follows a normal distribution.

[0169] In the population, the ratio of rolling dung beetles, breeding dung beetles, foraging dung beetles and stealing dung beetles can be 6:6:8:10, and can also be adjusted according to actual conditions. The boundary of each updated dung beetle is determined, and the current fitness value and the optimal value are updated and calculated.

[0170] It is determined whether a preset stop condition is met, wherein the preset stop condition includes reaching a preset maximum number of iterations.

[0171] like Fig. 9 As shown, the technical solution of the present invention provides an intelligent control system for a floor radiation air conditioning system, which also includes:

[0172] S7, regulating the floor radiant air conditioning system based on the optimal control parameters of the floor radiant air conditioning system and the indoor environmental parameters.

[0173] Among them, Fig.10 As shown, step S7 specifically includes:

[0174] Determine whether the difference between the floor surface temperature and the dew point temperature is greater than a preset difference threshold (e.g., 1°C); if not, adjust the fresh air volume of the fresh air fan to the highest level;

[0175] If it is greater, determine whether the fresh air volume of the fresh air fan is not less than the minimum fresh air volume required by indoor personnel. If it is not less than, regulate the floor radiant air-conditioning system based on the optimal control parameters of the floor radiant air-conditioning system control; if it is less than, change the constraint conditions, reapply the improved dung beetle optimization algorithm, and solve the optimal control parameters until the fresh air volume of the fresh air fan is not less than the minimum fresh air volume required by indoor personnel.

[0176] When solving the optimal control parameters, anti-condensation and minimum fresh air volume requirements are required. Specifically, the control logic of the air conditioning system's anti-condensation and pre-dehumidification is that before turning on the anti-condensation radiant cooling equipment, when the indoor condensation temperature difference is less than 1°C, there is a risk of condensation on the radiant floor surface, and the fresh air volume of the fresh air fan is adjusted to the highest level, effectively reducing the humidity of the indoor air, reducing the risk of condensation, and avoiding condensation problems.

[0177] Furthermore, the minimum fresh air volume, in step S2, the formula for calculating the minimum fresh air volume Q required by indoor personnel according to the number of people N active indoors is as follows: Q = q × N;

[0178] Q=q×N

[0179] Among them, q is the minimum fresh air volume required per person; N is the number of people in the room; Q is the minimum fresh air volume required by the indoor personnel;

[0180] Specifically, for an office, q is set to 30m 3 / (h·person), for the conference room, q is 11~14m 3 / (h·person), for classroom, q is 22~28m 3 / (h·person).

[0181] When the air-conditioning system is running, first obtain indoor and outdoor environmental parameters, thermal imaging image data, and ordinary image data; use computer vision technology to process the image to obtain the number of people, personnel load, facial temperature, hand temperature, average radiation temperature, operating temperature, and floor surface temperature; then judge the condensation risk, that is, whether the floor surface temperature is higher than the dew point temperature by 1°C; if not, adjust the fresh air volume of the fresh air fan to the highest level to quickly dehumidify the indoor air, and complete the current air-conditioning system control process; if so, use the improved dung beetle optimization algorithm to solve the optimal control parameters; then judge whether the fresh air volume of the fresh air fan is greater than or equal to the minimum fresh air volume required by indoor personnel; if not, change the constraint conditions to meet the minimum fresh air volume required by indoor personnel, use the improved dung beetle optimization algorithm to solve the optimal control parameters and control the air-conditioning system according to the optimal control parameters to complete the current air-conditioning system control process; if so, control the air-conditioning system according to the optimal control parameters to complete the current air-conditioning system control process.

[0182] In the technical solution of the present invention, computer vision technology is used to process thermal imaging video streams and non-thermal imaging video streams, to track indoor personnel, to obtain indoor personnel load estimation data and thermal comfort calculation data, and to estimate the indoor personnel load according to the indoor personnel load estimation data; a thermal sensation prediction model is established based on indoor environmental parameters and thermal comfort calculation data to predict the thermal sensation of indoor personnel; an indoor environment and energy consumption prediction model is established based on indoor and outdoor environmental parameters, equipment parameters, and air-conditioning system operation parameters to predict the indoor environment after adjustment by the air-conditioning system and the energy consumption of the air-conditioning system; constraint conditions are determined, and a personnel thermal comfort objective function and an energy consumption objective function are respectively constructed based on indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air-conditioning system energy consumption, and a total objective function is determined based on the weights of the personnel thermal comfort objective function and the energy consumption objective function; an improved dung beetle optimization algorithm is applied to solve the total objective function to obtain the optimal control parameters of the floor radiation air-conditioning system control, and the radiation air-conditioning system parameters can be adjusted in real time according to the indoor personnel load and the thermal comfort of the personnel, effectively solving the problem of low reliability of the floor radiation air-conditioning system control caused by the prior art, and effectively improving the reliability of the floor radiation air-conditioning system control.

[0183] In the technical solution of the present invention, a personnel detection and tracking model is established based on computer vision technology to obtain the detected personnel position and number; the gender and age range of the personnel are obtained according to the human face recognition results; the recognized human body parts are continuously tracked, human body movements are identified, and the movement distance per unit time is obtained. According to the human body movements and the movement distance per unit time of human body parts, the human body activity status is identified, and the indoor personnel load is estimated. The indoor personnel load can be estimated according to the personnel type and activity status, thereby further improving the reliability of the control of the floor radiant air-conditioning system.

[0184] In the technical solution of the present invention, by real-time monitoring of indoor and outdoor environmental parameters and thermal imaging data, an artificial neural network algorithm is used to establish a thermal sensation prediction model based on indoor environmental parameters and thermal comfort calculation data, so as to predict the thermal sensation of indoor occupants and accurately reflect the thermal sensation of users. This can realize personalized intelligent adjustment of the radiation air-conditioning system, reduce the user's tedious operations, and greatly improve the user's thermal comfort.

[0185] The technical solution of the present invention uses computer vision to track and identify the number and activities of indoor personnel, promptly responds to changes in indoor personnel load, quickly adjusts air-conditioning parameters, effectively alleviates the lag effect in the control of the radiant air-conditioning system, and reduces discomfort and energy waste caused by the imbalance between supply and demand of air-conditioning load.

[0186] The technical solution of the present invention uses an artificial neural network algorithm to predict the control effect of the radiation air-conditioning system, and at the same time determines the constraint conditions, and constructs the personnel thermal comfort objective function and the energy consumption objective function respectively according to the indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air-conditioning system energy consumption, and determines the overall objective function according to the weights of the personnel thermal comfort objective function and the energy consumption objective function; applies the improved dung beetle optimization algorithm to generate the optimal control parameters, thereby ensuring the thermal comfort of the personnel and reducing the energy consumption of the air-conditioning system.

[0187] Embodiment 2

[0188] like Fig.11 As shown, the technical solution of the present invention also provides an intelligent control system for a floor radiation air conditioning system, comprising:

[0189] The first acquisition module 101 acquires indoor and outdoor environmental parameters, thermal imaging video streams, non-thermal imaging video streams, air conditioning system operation data, and equipment parameters;

[0190] The second acquisition module 102 uses computer vision technology to process the thermal imaging video stream and the non-thermal imaging video stream, tracks indoor personnel, obtains indoor personnel load estimation data and thermal comfort calculation data, and estimates the indoor personnel load based on the indoor personnel load estimation data;

[0191] The first building module 103 builds a thermal sensation prediction model based on indoor environmental parameters and thermal comfort calculation data to predict the thermal sensation of indoor personnel;

[0192] The second establishment module 104 establishes an indoor environment and energy consumption prediction model based on indoor and outdoor environmental parameters, equipment parameters, and air conditioning system operation parameters, and predicts the indoor environment after the air conditioning system is adjusted and the energy consumption of the air conditioning system;

[0193] Determining module 105, determining constraint conditions, constructing personnel thermal comfort objective function and energy consumption objective function respectively based on indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air conditioning system energy consumption, and determining the overall objective function according to the weights of the personnel thermal comfort objective function and the energy consumption objective function;

[0194] The solution module 106 uses the improved dung beetle optimization algorithm to solve the overall objective function and obtain the optimal control parameters for the floor radiation air conditioning system.

[0195] It should be noted that the implementation processes of the first acquisition module 101, the second acquisition module 102, the first establishment module 103, the second establishment module 104, the determination module 105, and the solution module 106 in this embodiment correspond to the method steps in Example 1, and are not repeated in this embodiment.

[0196] In the technical solution of the present invention, computer vision technology is used to process thermal imaging video streams and non-thermal imaging video streams, to track indoor personnel, to obtain indoor personnel load estimation data and thermal comfort calculation data, and to estimate the indoor personnel load according to the indoor personnel load estimation data; a thermal sensation prediction model is established based on indoor environmental parameters and thermal comfort calculation data to predict the thermal sensation of indoor personnel; an indoor environment and energy consumption prediction model is established based on indoor and outdoor environmental parameters, equipment parameters, and air-conditioning system operation parameters to predict the indoor environment after adjustment by the air-conditioning system and the energy consumption of the air-conditioning system; constraint conditions are determined, and a personnel thermal comfort objective function and an energy consumption objective function are respectively constructed based on indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air-conditioning system energy consumption, and a total objective function is determined based on the weights of the personnel thermal comfort objective function and the energy consumption objective function; an improved dung beetle optimization algorithm is applied to solve the total objective function to obtain the optimal control parameters of the floor radiation air-conditioning system control, and the radiation air-conditioning system parameters can be adjusted in real time according to the indoor personnel load and the thermal comfort of the personnel, effectively solving the problem of low reliability of the floor radiation air-conditioning system control caused by the prior art, and effectively improving the reliability of the floor radiation air-conditioning system control.

[0197] In the technical solution of the present invention, a personnel detection and tracking model is established based on computer vision technology to obtain the detected personnel position and number; the gender and age range of the personnel are obtained according to the human face recognition results; the recognized human body parts are continuously tracked, human body movements are identified, and the movement distance per unit time is obtained. According to the human body movements and the movement distance per unit time of human body parts, the human body activity status is identified, and the indoor personnel load is estimated. The indoor personnel load can be estimated according to the personnel type and activity status, thereby further improving the reliability of the control of the floor radiant air-conditioning system.

[0198] In the technical solution of the present invention, by real-time monitoring of indoor and outdoor environmental parameters and thermal imaging data, an artificial neural network algorithm is used to establish a thermal sensation prediction model based on indoor environmental parameters and thermal comfort calculation data, so as to predict the thermal sensation of indoor occupants and accurately reflect the thermal sensation of users. This can realize personalized intelligent adjustment of the radiation air-conditioning system, reduce the user's tedious operations, and greatly improve the user's thermal comfort.

[0199] The technical solution of the present invention uses computer vision to track and identify the number and activities of indoor personnel, promptly responds to changes in indoor personnel load, quickly adjusts air-conditioning parameters, effectively alleviates the lag effect in the control of the radiant air-conditioning system, and reduces discomfort and energy waste caused by the imbalance between supply and demand of air-conditioning load.

[0200] The technical solution of the present invention uses an artificial neural network algorithm to predict the control effect of the radiation air-conditioning system, and at the same time determines the constraint conditions, and constructs the personnel thermal comfort objective function and the energy consumption objective function respectively according to the indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air-conditioning system energy consumption, and determines the overall objective function according to the weights of the personnel thermal comfort objective function and the energy consumption objective function; applies the improved dung beetle optimization algorithm to generate the optimal control parameters, thereby ensuring the thermal comfort of the personnel and reducing the energy consumption of the air-conditioning system.

[0201] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. An intelligent control method for a floor radiant air conditioning system, characterized in that: include: Obtain indoor environmental parameters, outdoor environmental parameters, thermal imaging video streams, non-thermal imaging video streams, and air conditioning system operation data; Use computer vision technology to process thermal imaging video streams and non-thermal imaging video streams, track indoor personnel, obtain indoor personnel load estimation data and thermal comfort calculation data, and estimate indoor personnel load based on indoor personnel load estimation data; Based on indoor environmental parameters and thermal comfort calculation data, a thermal sensation prediction model is established to predict the thermal sensation of indoor occupants. Based on indoor and outdoor environmental parameters, equipment parameters, and air-conditioning system operating parameters, an indoor environment and energy consumption prediction model is established to predict the indoor environment after adjustment by the air-conditioning system and the energy consumption of the air-conditioning system; Determine the constraints, and construct the personnel thermal comfort objective function and energy consumption objective function based on indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air conditioning system energy consumption. Determine the overall objective function based on the weights of the personnel thermal comfort objective function and the energy consumption objective function. The improved dung beetle optimization algorithm is used to solve the overall objective function and obtain the optimal control parameters of the floor radiant air conditioning system.

2. The intelligent control method of a floor radiant air conditioning system according to claim 1, characterized in that: The air-conditioning system operation data include: fresh air temperature, fresh air speed, fresh air fan air volume, fresh air fan fresh air volume, radiant floor surface temperature, radiant floor water supply temperature, radiant floor return water temperature; indoor environmental parameters include: indoor temperature, indoor humidity, wall temperature, and other surface temperatures except wall and floor surfaces; outdoor environmental parameters include: solar radiation, outdoor temperature, and outdoor humidity; indoor personnel load estimation data include the number of personnel, gender, age range, and human activity status; thermal comfort calculation data include human facial temperature, human hand temperature, indoor average radiation temperature, and operating temperature, where the operating temperature is the temperature of the combined effect of indoor air temperature and indoor average radiation temperature on the human body.

3. The intelligent control method of a floor radiant air conditioning system according to claim 2, characterized in that: Computer vision technology is used to process thermal imaging video streams and non-thermal imaging video streams, track indoor personnel, obtain indoor personnel load calculation data and thermal comfort calculation data, and estimate indoor personnel load based on indoor personnel load estimation data, including: Based on computer vision technology, a personnel detection model, a personnel tracking model, and a human body recognition model are established, and both the indoor thermal imaging video stream and the non-thermal imaging video stream are input into the trained personnel detection model, the personnel tracking model, and the human body recognition model; Normalize the indoor thermal imaging video stream and non-thermal imaging video stream, use the trained personnel detection model and personnel tracking model to identify and obtain the detected personnel positions and number; Input the person's location area into the trained human body recognition model to identify the body parts. According to the temperature values ​​of different positions on the face of the human body, the facial temperature is obtained; according to the temperature values ​​of different positions on the hand of the human body, the hand temperature is obtained; according to the facial recognition results, the gender and age range of the person are obtained; The identified human body parts are continuously tracked, human body movements are identified, and the moving distance per unit time is obtained. Based on the human body movements and the moving distance per unit time of human body parts, the human body activity status is identified and the indoor personnel load is estimated. The indoor personnel load calculation formula is: Among them, Q p is the personnel load; Q z is the estimated heat load of the zth group of people; n z is the number of the zth group of people; g is the total number of people; the people include male teenagers, male youths, male middle-aged, male elders, female teenagers, female youths, female middle-aged, and female elders; The pre-divided indoor floor surface temperature, indoor wall temperature, and other indoor surface temperatures are obtained from the thermal imaging video, and the indoor average radiation temperature and the first calculated value of the operating temperature are calculated respectively according to the indoor floor surface temperature, the indoor wall temperature, and the indoor surface temperatures other than the floor surface and the wall surface.

4. The intelligent control method of a floor radiant air conditioning system according to claim 3 is characterized in that: The calculation formula for the indoor average radiation temperature is: Among them, F j is the angle coefficient of the jth surface to the human body; T j is the absolute temperature of the jth surface; T r is the average indoor radiation temperature; k is the total number of surfaces; The calculation formula for the first calculated value of the operating temperature is: Among them, h c is the convective heat transfer coefficient; T a Indoor air temperature; h r is the radiation heat transfer coefficient; T r is the mean radiation temperature; T OP is the first calculated value of the operating temperature.

5. The intelligent control method of a floor radiant air conditioning system according to claim 3 is characterized in that: Based on indoor environmental parameters and thermal comfort calculation data, a thermal sensation prediction model is established to predict the thermal sensation of indoor personnel, including: Taking indoor humidity historical data, indoor temperature historical data, facial temperature historical data, hand temperature historical data, and indoor average radiation temperature historical data as first input data, and taking indoor personnel's thermal sensation historical data as first output data, a first mapping database between first input data and corresponding first output data is established; Using artificial neural network algorithm and the first mapping database, a thermal sensation prediction model is established and trained; The real-time data of indoor temperature, indoor humidity, facial temperature, hand temperature and indoor average radiation temperature are input into the trained thermal sensation prediction model to predict the thermal sensation of the human body.

6. The intelligent control method of floor radiant air conditioning system according to claim 3 is characterized in that: Based on indoor and outdoor environmental parameters, equipment parameters, and air conditioning system operating parameters, an indoor environment and energy consumption prediction model is established to predict the indoor environment after the air conditioning system is adjusted and the energy consumption of the air conditioning system, including: Taking the historical data of wall temperature, the historical data of outdoor temperature, the historical data of outdoor humidity, the historical data of fresh air temperature, the historical data of fresh air speed, the historical data of floor surface temperature, the historical data of radiant floor water supply temperature, and the historical data of indoor personnel load as the second input data, and taking the historical data of indoor average radiant temperature adjusted by the air-conditioning system, the historical data of indoor condensation temperature difference adjusted by the air-conditioning system, the historical data of wind system energy consumption, and the historical data of water system energy consumption as the second output data, a second mapping database between the second input data and the corresponding second output data is established; Using artificial neural network algorithm and second mapping database, establish and train indoor environment and energy consumption prediction model; The real-time data of wall temperature, outdoor temperature, outdoor humidity, fresh air temperature, fresh air speed, floor surface temperature, radiant floor water supply temperature and indoor personnel load are input into the trained indoor environment and energy consumption prediction model to predict the real-time data of indoor average radiation temperature after adjustment by the air-conditioning system, the real-time data of indoor condensation temperature difference after adjustment by the air-conditioning system, the real-time data of wind system energy consumption and the real-time data of water system energy consumption.

7. The intelligent control method of floor radiant air conditioning system according to claim 6, characterized in that: The constraints include air supply volume constraint, water supply pump status constraint and floor water supply temperature constraint; among them, the air supply volume constraint is: in, It is the minimum air supply volume of the fresh air system; The maximum air supply volume of the fresh air system; To regulate the air supply volume of the fresh air system; The water supply pump state constraints are: 0≤K b ≤1， Among them, 0 is off, 1 is on, K b Pump status; The floor water supply temperature constraint is: in, Provides the minimum temperature for floor water supply; Provides the maximum water temperature for the floor; To regulate the floor water supply pump temperature; The personnel thermal comfort objective function and energy consumption objective function are constructed based on the indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air conditioning system energy consumption. According to the weights of the personnel thermal comfort objective function and energy consumption objective function, the overall objective function is determined, including: The outdoor temperature, outdoor humidity, wall temperature, floor surface temperature, indoor temperature, indoor humidity, operating temperature, and personnel load are used as environmental independent variables, and the fresh air volume of the fresh air fan, the radiant floor water supply temperature, and the radiant floor water supply pump status are used as control parameter independent variables; Taking personnel thermal comfort, personnel load, condensation risk, wind system energy consumption and water system energy consumption as optimization targets respectively; f1=min|T OPS X i -T OP |, f 1′ =min|T in X i -T sd |, f2=-min|ΔT l X i |, f3=minE f X i , f4=minE s X i , f5=min|Q p -|E f -E fs ||, Among them, f1 is the thermal comfort objective function; f 1′ f2 is the condensation temperature difference objective function; f3 is the wind system objective function; f4 is the water system objective function; f5 is the personnel load objective function; X i is the ith independent variable; T OPS is a second calculated value of the indoor operating temperature calculated based on the indoor average radiation temperature predicted by the indoor environment and energy consumption prediction model; T OP The first calculated value of operating temperature; T in is the indoor temperature predicted by the indoor environment and energy consumption prediction model; ΔT l is the condensation temperature difference predicted by the indoor environment and energy consumption prediction model; T sd Set the temperature for the user; E f Wind system energy consumption predicted by indoor environment and energy consumption prediction model; E s The water system energy consumption predicted by the indoor environment and energy consumption prediction model; Q p is the indoor personnel load; E fs is the energy consumption of the wind system in the previous period; According to the weight of each objective function, the total objective function f is determined: f=α1f1+α2f2+α3f3+α4f4+α5f5+α6f 1′ , Among them, α1, α2, α3, α4, α5, and α6 are the weights of each target.

8. The intelligent control method of a floor radiant air conditioning system according to claim 2, characterized in that: The improved dung beetle optimization algorithm is used to solve the overall objective function, and the optimal control parameters of the floor radiation air conditioning system are obtained, including: The environmental independent variables and control parameter independent variables corresponding to the total objective function are taken as a dung beetle, and the dung beetle population is initialized using Bernoulli mapping; Calculating the fitness value of the dung beetle population, wherein the fitness value is the overall objective function; Update the current position of the dung beetle, and calculate the current fitness value for each updated dung beetle; It is determined whether a preset stop condition is met, wherein the preset stop condition includes reaching a preset maximum number of iterations.

9. The intelligent control system of a floor radiant air conditioning system according to any one of claims 1 to 8, characterized in that: include: The floor radiant air conditioning system is regulated based on the optimal control parameters of the floor radiant air conditioning system and the indoor environmental parameters.

10. The intelligent control system of a floor radiant air conditioning system according to claim 9, characterized in that: Based on the optimal control parameters and indoor environmental parameters of the floor radiant air conditioning system, the control of the floor radiant air conditioning system specifically includes: Determine whether the difference between the floor surface temperature and the dew point temperature is greater than a preset difference threshold, and if not, adjust the air volume of the fresh air fan to the highest level; If it is greater, determine whether the fresh air volume of the fresh air fan is not less than the minimum fresh air volume required by indoor personnel. If it is not less than, regulate the floor radiant air-conditioning system based on the optimal control parameters of the floor radiant air-conditioning system control; if it is less than, change the constraint conditions, reapply the improved dung beetle optimization algorithm, and solve the optimal control parameters until the fresh air volume of the fresh air fan is not less than the minimum fresh air volume required by indoor personnel.

11. An intelligent control system for a floor radiant air conditioning system, characterized in that: include: The first acquisition module acquires indoor and outdoor environmental parameters, thermal imaging video streams, non-thermal imaging video streams, air conditioning system operation data, and equipment parameters; The second acquisition module uses computer vision technology to process thermal imaging video streams and non-thermal imaging video streams, track indoor personnel, obtain indoor personnel load estimation data and thermal comfort calculation data, and estimate indoor personnel load based on the indoor personnel load estimation data; The first building module builds a thermal sensation prediction model based on indoor environmental parameters and thermal comfort calculation data to predict the thermal sensation of indoor occupants; The second establishment module establishes an indoor environment and energy consumption prediction model based on indoor and outdoor environmental parameters, equipment parameters, and air-conditioning system operating parameters to predict the indoor environment and air-conditioning system energy consumption after being adjusted by the air-conditioning system; Determine the module, determine the constraint conditions, and construct the personnel thermal comfort objective function and energy consumption objective function respectively based on the indoor and outdoor environmental parameters, indoor personnel load, thermal sensation, and air conditioning system energy consumption. Determine the overall objective function based on the weights of the personnel thermal comfort objective function and the energy consumption objective function. The solution module applies the improved dung beetle optimization algorithm to solve the overall objective function and obtain the optimal control parameters for the floor radiation air conditioning system.

Images