Self-adaptive comfort adjusting system and method for air conditioner

Abstract

The invention relates to the field of air conditioners, in particular to an air conditioner self-adaption comfort adjusting method which is applied to an air conditioner system with a fresh air adjusting function and comprises the steps that operation parameters of a flow dividing control assembly are obtained; environment parameters of a working area of the tail end air outlet device are obtained; working parameters of a working area of the tail end air outlet device are obtained, wherein the working parameters comprise normal function data of the working area, the current number of users and personnel characteristics; meteorological parameters of the working area of the tail end air outlet device are obtained; the meteorological parameters and the working parameters serve as input parameters of a Bayesian comfort model obtained through deep learning algorithm fitting, and corresponding comfort parameters are obtained through calculation; and the difference value between the environment parameter and the comfort parameter is solved, and the operation state of the shunting control assembly is controlled based on the difference value. According to the adjusting method, the comfort parameters are obtained based on the constructed Bayesian comfort model, autonomous adjustment of the comfortable operation state of the air conditioner is achieved, the use comfort is improved, and meanwhile energy use is optimized.

Description

Technical Field

[0001] The invention relates to the technical field of air conditioning, and in particular to an air conditioning adaptive comfort adjustment system. Background Art

[0002] Compared with split air conditioners, central air conditioning systems have a higher energy efficiency ratio, and their application scenarios have also been extended from the initial large buildings to family homes. Compared with large buildings such as shopping malls, hotels, and commercial office buildings, family homes have the characteristics of relatively small application areas, relatively few users, and fixed users. In addition, as the main living area for family members, the residence is one of the most direct manifestations of quality of life. Traditional household central air conditioners mostly rely on static settings and cannot respond to changes in the external environment, the activities of users, and changes in characteristics in real time. On the one hand, this causes a waste of resources, and on the other hand, it also affects the user experience. Summary of the invention

[0003] In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide an air-conditioning adaptive comfort adjustment system, which is capable of autonomously optimizing and adjusting air-conditioning operating parameters to achieve personalized comfort adjustment and energy consumption optimization.

[0004] To achieve the above objectives and other related objectives, the present invention provides the following technical solutions:

[0005] An air conditioning adaptive comfort adjustment method is applied to an air conditioning system with a fresh air adjustment function, comprising: a terminal air outlet device for discharging air to a working area, a fan for drawing in and pressurizing outdoor air, a heat exchange component for performing heat exchange on the fresh air drawn in by the fan to adjust the temperature and humidity of the fresh air, and an air-cooled heat pump for supplying cold and heat source media to the heat exchange component; and also comprising a shunt control component connected one by one with the terminal air outlet device through a pipeline. The air conditioning adaptive comfort adjustment method comprises:

[0006] Obtaining operating parameters of the diversion control component;

[0007] Obtaining environmental parameters of the working area of ​​the terminal air outlet device;

[0008] Obtaining working parameters of the working area of ​​the terminal air outlet device, including normal function data of the working area, the current number of users and personnel characteristics;

[0009] Obtaining meteorological parameters of the working area of ​​the terminal air outlet device;

[0010] The meteorological parameters and the working parameters are used as input parameters of the Bayesian comfort model obtained by fitting the deep learning algorithm to calculate the corresponding comfort parameters;

[0011] The difference between the environmental parameter and the comfort parameter is calculated, and the operating state of the diversion control component is controlled based on the difference.

[0012] To implement the above technical solution, the comfort parameters corresponding to the current working parameters and meteorological parameters are calculated based on the Bayesian comfort model fitted by the deep learning algorithm, and the difference between the environmental parameters and the comfort parameters is calculated with the comfort parameters as the reference value. The difference is used as the input parameter to control the operating state of the diversion control component to make the environmental parameters close to the comfort parameters, thereby improving the user's comfort experience.

[0013] In one embodiment of the present invention, the operating state of the shunt control component is controlled based on the difference, and when the difference is within a preset threshold range, the shunt control component is controlled to maintain the operating state; when the difference is within both sides of the preset threshold range, the operating state of the shunt control component is adjusted.

[0014] In one embodiment of the present invention, if the difference is located on both sides of a preset threshold range, the operating state of the diversion control component is adjusted based on a correction value, wherein the correction value is equal to a correction coefficient multiplied by the difference, and the correction coefficient is estimated by a random forest algorithm.

[0015] To implement the above technical solution, when the difference between the obtained environmental parameters and the comfort parameters is within a preset threshold range, there is no difference in human comfort experience, and the operating state of the shunt control component is maintained; when the obtained difference is on both sides of the preset threshold range, that is, it is significantly lower than or significantly higher than the comfort range, the adjusted operating parameters of the shunt control component are corrected according to the correction value, so that the environmental parameters after the adjusted operating parameters work are close to the comfort parameters; the correction value is obtained by multiplying the correction coefficient by the difference, wherein the correction coefficient is obtained by a linear interpolation algorithm using sample experimental data.

[0016] On the other hand, the present invention provides an air-conditioning adaptive comfort adjustment system, comprising: a terminal air outlet device for discharging air to a working area, a fan for drawing in and pressurizing outdoor air, a heat exchange component for performing heat exchange on the fresh air drawn in by the fan to adjust the temperature and humidity of the fresh air, and an air-cooled heat pump for supplying cold and heat source media to the heat exchange component; also comprising a shunt control component connected one by one to the terminal air outlet device through a pipeline, an internal sensor module installed on the air outlet side of the shunt control component to collect operating parameters of the shunt control component, and an external sensor module installed on the air outlet side of the terminal air outlet device to collect environmental parameters of the working area and a human detection module, and an operation control center that communicates and interacts with the internal sensor module, the external sensor module and the human detection module, the operation control center storing a Bayesian comfort model fitted based on a deep learning algorithm, the operation control center communicates and interacts with a meteorological database and obtains meteorological parameters of a corresponding working area based on the geographical location of the working area, and uses the received meteorological parameters and working parameters as input parameters of the Bayesian comfort model to calculate comfort parameters, uses the comfort parameters as a reference value to calculate the difference between the environmental parameters and the comfort parameters, and inputs the difference into the diversion control component to control the operating state.

[0017] To implement the above technical solution, the internal sensing module collects the temperature, humidity, wind speed and other parameters of the shunt control component, the external sensing module collects the temperature, humidity, wind speed and other parameters of the working area, and the human detection module collects the number of people and their characteristics in the working area. The internal sensing module, the external sensing module and the human detection module respectively input the collected operating parameters, environmental parameters and working parameters into the operation control center. The operation control center uses the geographical location of the working area as a keyword to access the meteorological data and obtain the meteorological parameters of the corresponding area. The operation control center uses the meteorological parameters and working parameters as the input parameters of the Bayesian comfort model to calculate the comfort parameters, and uses the comfort parameters as the reference value to calculate the difference between the environmental parameters and the comfort parameters, and inputs the difference into the shunt control component and uses the value as the control parameter of the operating state.

[0018] In one embodiment of the present invention, the diversion control component includes a plurality of air outlet pipes connected to the air outlet of the fan, and the plurality of air outlet pipes are connected one by one to a plurality of terminal air outlet devices through pipelines. Each of the air outlet pipes is provided with an electrically controlled air volume control valve that communicates and interacts with the operation control center.

[0019] In one embodiment of the present invention, the terminal air outlet device comprises a chilled beam box, a condensing coil for heat exchange of airflow is arranged in the chilled beam box, and a chilled beam air outlet is arranged on the chilled beam box.

[0020] To implement the above technical solution, the chilled beam box is connected to the air outlet duct through a pipe, thereby completing the air distribution effect. The entire chilled beam box has a simple structure and does not produce noise from the operation of equipment such as fans, thereby greatly reducing wind noise. At the same time, the condensing coil is set to perform heat exchange on the outlet air again, thereby ensuring the outlet air temperature and humidity. At the same time, because the fresh air entering the condensing box has been processed by the heat exchange component, the power of the condensing coil does not need to be too large and the noise will not be too high, thereby ensuring the comfort of personnel use.

[0021] In one embodiment of the present invention, a temperature and humidity auxiliary adjustment component is provided on the air outlet side of the heat exchange component, and the temperature and humidity auxiliary adjustment component includes a humidifier arranged on the air outlet side of the heat exchange component, and an electric heater is provided at one end of the air outlet side of the humidifier.

[0022] To implement the above technical solution, after the air passes through the heat exchange component for heat exchange, its temperature and relative humidity change. For example, when dehumidification is needed in spring and autumn, the heat exchange component cools the air, and its temperature decreases, and the water vapor carried in the air condenses, thereby reducing the water vapor carried in the air. However, at the same time, the temperature will decrease, resulting in the wind flow temperature blown out by the terminal air outlet device being too low, affecting the comfort of personnel, and then the temperature of the fresh air needs to be adjusted. When cooling or heating is needed in summer and winter, the absolute humidity or relative humidity in the air will decrease, so it is necessary to adjust the humidity of the air after heat exchange, that is, to humidify the air through a humidifier. Water vapor is added to the air to assist in adjusting the humidity of the air, thereby improving the comfort of the personnel. The fresh air can be heated by an electric heater to adjust the fresh air temperature; that is, under the joint action of the humidifier and the electric heater, dehumidification can be completed in spring and summer while ensuring the appropriate temperature; in autumn and winter, heating can be completed while ensuring the air humidity, thereby improving the comfort of personnel; at the same time, the electric heater is arranged at the rear end of the humidifier, so that after the air is humidified, its relative humidity decreases when it is heated, thereby preventing the subsequent temperature from dropping after long-section transportation in the pipeline, resulting in the occurrence of condensed water in the pipeline, thereby ensuring the comfort of the users.

[0023] In one embodiment of the present invention, it also includes a box body with a main air inlet and a main air outlet, and the heat exchange component, temperature and humidity auxiliary adjustment component, fan and diversion control component are arranged in sequence along the wind flow direction from the air inlet to the air outlet.

[0024] To implement the above technical solution, the design of the box allows the heat exchange component, temperature and humidity auxiliary adjustment component, fan and diversion control component to be integrated in the box, which is convenient for subsequent installation and maintenance.

[0025] In one embodiment of the present invention, a mounting frame is provided in the box body, the fan is configured as a centrifugal fan, the centrifugal fan is arranged above the mounting frame, an L-shaped wind shield is provided on the air outlet side of the centrifugal fan, and the diversion control component is arranged on the L-shaped wind shield; a water retaining frame is provided on the air outlet side of the humidifier, and a water retaining frame is provided with a water retaining plate inclined downward away from the humidifier.

[0026] To implement the above technical solution, the design of the L-shaped wind shield realizes the bending design of the air duct inside the box, thereby compressing the volume of the box so that it can be directly installed on the ceiling of the room, thus meeting the needs of small users; the design of the water retaining rack prevents the water vapor sprayed by the humidifier from spreading in the pipes of the entire air-conditioning system.

[0027] In one embodiment of the present invention, the air-conditioning adaptive comfort adjustment system adopts any one of the air-conditioning adaptive comfort adjustment methods described above.

[0028] As described above, the air conditioner adaptive comfort adjustment system and the air conditioner adaptive comfort adjustment method provided by the present invention have the following beneficial effects:

[0029] 1. Based on the constructed Bayesian comfort model, the working parameters and meteorological parameters are used as input parameters to calculate the comfort parameters. The difference between the environmental parameters and the comfort parameters is calculated based on the comfort parameters, and the difference is used as the input parameter to control the operating state of the shunt control component, so that the environmental parameters are close to the comfort parameters, thereby improving the user's comfort. In addition, the operating state of the shunt control component is adjusted in time based on the changes in the working parameters and meteorological parameters, which plays a role in optimizing energy use.

[0030] 2. The temperature and humidity of fresh air are uniformly adjusted in the heat exchange component, and the diversion control component is used to deliver fresh air to different terminal air outlet devices according to the comfort parameter requirements. On the one hand, it realizes the adaptive adjustment of the operation requirements of different areas according to the working parameters and meteorological parameters. On the other hand, the functional design of centralized processing and distribution of fresh air can meet the use needs of the family. That is, in actual family applications, the centralized fresh air processing part can be installed in areas such as kitchens, balconies or bathrooms where people's daily activities are weak or the noise requirements are low, and the terminal air outlet device can be installed in the bedroom, living room or study, etc., to ensure that the environmental noise is low when people are resting normally, thereby improving the comfort of people. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a structural logic diagram of an embodiment of the present application.

[0032] Figure 2 It is a schematic diagram of the overall structure of an embodiment of the present application.

[0033] Figure 3It is a schematic diagram of the overall structure of the fresh air centralized processing unit in the embodiment of the present application.

[0034] Figure 4 It is a schematic diagram of the internal structure of the fresh air centralized processing unit in the embodiment of the present application.

[0035] Figure 5 It is a side view of the internal structure of the fresh air centralized processing unit in the embodiment of the present application.

[0036] Figure 6 It is a schematic diagram of the structure of the terminal air outlet device in an embodiment of the present application.

[0037] Description of technical feature numbers in the accompanying drawings:

[0038] 1. Fresh air centralized processing unit; 11. Box; 12. Air filter assembly; 13. Heat exchange assembly; 14. Temperature and humidity auxiliary adjustment assembly; 141. Humidifier; 142. Water retaining rack; 143. Air guide plate; 144. Electric heater; 15. Centrifugal fan; 16. Diversion control assembly; 161. Air outlet duct; 162. Electric air volume control valve; 17. Mounting rack; 18. L-shaped wind shield; 19. Condensate tray; 2. Terminal air outlet device; 21. Chilled beam box; 22. Condensing coil; 3. Air-cooled heat pump; 4. Self-circulating chilled beam device; 41. Drum-type constant air volume fan; 42. Coil heat exchanger; 5. Buried coil. DETAILED DESCRIPTION

[0039] The following is a description of the implementation of the present invention by means of specific embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification.

[0040] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the present invention, so they have no substantial technical significance. Any modification of the structure, change of the proportion relationship or adjustment of the size should still fall within the scope of the technical content disclosed by the present invention without affecting the effects and purposes that can be achieved by the present invention. At the same time, the terms such as "upper", "lower", "left", "right", "middle" and "one" quoted in this specification are only for the convenience of description, and are not used to limit the scope of the implementation of the present invention. The change or adjustment of their relative relationship should also be regarded as the scope of the implementation of the present invention without substantially changing the technical content.

[0041] Embodiment 1:

[0042] See also Figure 1-2The present invention provides an air conditioning adaptive comfort adjustment system, comprising: a terminal air outlet device 2 for discharging air to a working area, a fan for drawing in and pressurizing outdoor air, a heat exchange component 13 for performing heat exchange on the fresh air drawn in by the fan to adjust the temperature and humidity of the fresh air, and an air-cooled heat pump 3 for supplying cold and heat source media to the heat exchange component 13; and also comprising a shunt control component 16 connected one by one with the terminal air outlet device 2 through a pipeline, an internal sensor module installed on the air outlet side of the shunt control component 16 to collect operating parameters of the shunt control component 16, and a sensor module installed on the air outlet side of the terminal air outlet device 2 to collect environmental information of the working area. The external sensing module and the human body detection module for environmental parameters, and the operation control center that communicates and interacts with the internal sensing module, the external sensing module and the human body detection module, the operation control center stores a Bayesian comfort model fitted based on a deep learning algorithm, the operation control center communicates and interacts with the meteorological database and obtains the meteorological parameters of the corresponding working area based on the geographical location of the working area, and uses the received meteorological parameters and working parameters as input parameters of the Bayesian comfort model to calculate the comfort parameters, uses the comfort parameters as a reference value to calculate the difference between the environmental parameters and the comfort parameters, and inputs the difference into the shunt control component 16 to control the operating status.

[0043] Specifically, the basic idea of ​​the Bayesian comfort model is to use the conditional dependencies between variables, train the parameters of the network based on historical data, and then perform probabilistic reasoning to predict future values. The prediction principle can be summarized as the following steps:

[0044] 1) Construct the network structure. According to the causal relationship between variables, determine the nodes and directed edges of the network to form a DAG graph.

[0045] 2) Learning parameters. Given training data D = {X1, X2, ..., Xn}, maximize the marginal likelihood of the data to the current network structure, that is, learn the CPT conditional probability through the formula: P[Xi|pa(Xi)] = argmax_P.P(D|G,P); where G is the network structure, P is all CPT parameters, and the parameter learning method is the Bayesian method.

[0046] 3) Inference prediction. For a given piece of evidence e and query variable Y, the Bayesian rule is used for probabilistic reasoning to calculate the posterior probability P(Y|e), that is: P(Y|e) = α.P(e|Y)P(Y) = α.∑yP(e|y)P(y); where α is the normalization factor. The posterior distribution or most likely value of variable Y can be predicted through inference prediction.

[0047] 4) Evaluate the prediction. Use indicators such as accuracy and recall to evaluate the prediction effect and optimize the model.

[0048] The embodiment of the present application uses the Bayesian Network Toolbox (BNT) in Matlab software to construct a Bayesian comfort model, wherein meteorological parameters and working parameters are used as variable nodes of the Bayesian network. Specifically, meteorological parameters include temperature, humidity, and wind speed, but are not limited thereto; working parameters include the number of personnel and personnel characteristics in the working area, and normal function data of the working area, but are not limited thereto. The Bayesian Network Toolbox in Matlab software is used to realize the structure learning, parameter learning, and network reasoning of the Bayesian network.

[0049] The learning of Bayesian network is to explore the implicit internal connection through learning and training of a large number of samples, that is, to solve the conditional probability between node variables. The sample data used in the Bayesian learning process is called training set data. The data used to test the rationality and accuracy of the prediction model is the test set data, and the actual value of the test set data is compared with the predicted value for verification.

[0050] The training set data and test set data used in the embodiment of the present application are from user usage data of a sufficiently long period of time. The period of user usage data in the embodiment of the present application is one year, wherein the actual value in the test set data is a user-defined parameter. The Bayesian comfort model in the embodiment of the present application is obtained based on one-year user usage data training, learning and fitting, and its variables imply the relationship between the user's personalized comfort settings, so the Bayesian comfort model has a personalized prediction function.

[0051] The internal sensing module and the external sensing module in the embodiment of the present application include a temperature and humidity sensor and a wind speed sensor. The internal sensing module is used to collect the operating parameters of the diversion control component 16, and the operating parameters include temperature, humidity, and wind speed; the external sensing module is used to collect the environmental parameters of the working area, and the environmental parameters include temperature, humidity, and wind speed.

[0052] The human detection module in the embodiment of the present application adopts a space occupancy sensor based on an AI vision algorithm, such as a VS121 sensor, which analyzes human characteristics through an AI vision algorithm to achieve headcount and area coverage.

[0053] Furthermore, the operation control center in the embodiment of the present application is deployed on a cloud server, which can be a remote public cloud server or a local private cloud server. The operation control center communicates with the meteorological database and can access and read the meteorological data in the meteorological database. The specific access rules are as follows: the operation control center uses the geographical location of the working area as a keyword to access and read the meteorological data of the corresponding geographical location in the meteorological database; wherein, the geographical location of the working area can be collected and obtained by the locator provided in the external sensor module, or can be input by the user through the control panel and stored.

[0054] The flow shunt control component 16 works based on the received difference. Specifically, when the difference is within the preset threshold range, the flow shunt control component 16 is controlled to maintain the operation state; when the difference is within both sides of the preset threshold range, the operation state of the flow shunt control component 16 is adjusted. The preset threshold range is set according to the human body's general sensitivity to comfort.

[0055] Among them, if the difference is on both sides of the preset threshold range, the operating state of the shunt control component is adjusted based on the correction value, and the correction value is equal to the correction coefficient multiplied by the difference, and the correction coefficient is estimated by the random forest algorithm. Random forest is an integrated learning method that improves the accuracy and stability of the model by constructing multiple decision trees and combining their prediction results. In regression problems, random forest obtains the final prediction result by averaging the prediction values ​​of multiple decision trees. This embodiment estimates the correction coefficient K with the help of Matlab random forest tool, and the main steps can be summarized as follows:

[0056] 1) Data preparation: Based on the fitted Bayesian comfort model, a sufficient number of training and testing data sets are set.

[0057] 2) Create a random forest model. Use the TreeBagger function in Matlab to create a random forest model and specify the number of trees. In this embodiment, the number of trees is set to 1000. For example:

[0058] numTrees=1000; %Set the number of decision trees;

[0059] model=TreeBagger(numTrees,X(idxTrain,:),Y(idxTrain));

[0060] Here X(idxTrain,:) and Y(idxTrain) represent the feature matrix and target variable of the training set, respectively.

[0061] 3) Make predictions. Use the test set data to make predictions and call the model’s predict method to predict the target variable, for example: yPred = predict(model, X(idxTest,:)); here X(idxTest,:) represents the feature matrix of the test set.

[0062] 4) Evaluate the model. Evaluate the performance of the model through mean square error, for example:

[0063] mse=mean((Y(idxTest)-yPred).^2);

[0064] Here Y(idxTest) represents the true target variable of the test set.

[0065] 5) Adjust parameters. According to the performance of the model, adjust the parameters of the random forest to optimize the performance of the model.

[0066] 6) Estimate the value of the correction coefficient K. Through multiple training and prediction, estimate the value of K: Among them, ki is the coefficient of each decision tree.

[0067] See also Figure 2-6 The embodiment of the present invention further includes a box 11 with a total air inlet and a total air outlet, a fan, a heat exchange component 13, a temperature and humidity auxiliary adjustment component 14, and a diversion control component 16. The heat exchange component 13, the temperature and humidity auxiliary adjustment component 14, the fan, and the diversion control component 16 are sequentially arranged along the air flow direction from the air inlet to the air outlet. The box 11 and the structural components in the box 11 constitute a fresh air centralized processing unit 1. The entire fresh air centralized processing unit 1 is integrated in a box 11, which is convenient for installation.

[0068] Specifically, a mounting frame 17 is provided in the box body 11, and the fan is a centrifugal fan 15, which is arranged above the mounting frame 17. An L-shaped windshield 18 is provided on the air outlet side of the centrifugal fan 15, and the diversion control component 16 is arranged on the L-shaped windshield 18. The air duct of the entire fresh air centralized processing unit 1 adopts a bending design, which compresses the volume of the entire fresh air centralized processing unit 1 so that it can be directly installed in the ceiling of the room, thereby meeting the use needs of small users.

[0069] Specifically, the temperature and humidity auxiliary adjustment component 14 is arranged on the air outlet side of the heat exchange component 13, including a humidifier 141 arranged on the air outlet side of the heat exchange component 13, an electric heater 144 is arranged at one end of the air outlet side of the humidifier 141, and a water retaining frame 142 is arranged on the air outlet side of the humidifier 141. The water retaining frame 142 is provided with a water retaining plate inclined downward away from the humidifier 141; the setting of the water retaining plate prevents the water vapor sprayed from the humidifier 141 from spreading in the pipeline of the entire air-conditioning system.

[0070] Specifically, the diversion control component 16 includes a plurality of air outlet pipes 161 connected to the fan outlet, and the plurality of air outlet pipes 161 are connected to a plurality of terminal air outlet devices 2 one by one through pipelines. Each air outlet pipe 161 is provided with an electrically controlled air volume control valve 162 that communicates and interacts with the operation control center.

[0071] The terminal air outlet device 2 includes a cold beam box 21, on which a cold beam air outlet is provided; a condensing coil 22 for heat exchange of the airflow is provided in the cold beam box 21. The cold beam box 21 is connected to the air outlet pipe 161 in the fresh air centralized processing unit 1 through a pipeline, thereby completing the air distribution effect. The entire cold beam box 21 has a simple structure and does not produce noise from the operation of equipment such as a fan, and greatly reduces wind noise; at the same time, the outlet air is heat exchanged again through the condensing coil 22, thereby ensuring the outlet air temperature and humidity, because the fresh air entering the condensing box has been processed by the fresh air centralized processing unit 1, so that the power of the condensing coil 22 does not need to be too large, and its noise will not be too high, thereby ensuring the comfort of personnel.

[0072] The air-cooled heat pump 3 is connected to a self-circulating chilled beam device 4, which includes a drum-type constant air volume fan 41 and a coil heat exchanger 42 connected to the air-cooled heat pump 3. While the drum-type constant air volume fan 41 ensures the air outlet pressure, the coil heat exchanger 42 adjusts the temperature and humidity of the airflow, so as to be used in rooms such as mahjong rooms or e-sports rooms that require a quick response to temperature adjustment but have low noise requirements, thereby improving its adaptability.

[0073] The air-cooled heat pump 3 is also connected to the buried coil 5 through a pipeline, that is, the buried coil 5 can be buried in the floor to form floor heating or floor cooling, thereby improving the adaptability of use; and because the buried coil 5 is connected to the inlet and outlet pipes of the air-cooled heat pump 3, the high-temperature cooling medium can flow into the buried coil 5 to heat and dry the room after the cooling medium in the fresh air centralized processing unit 1 cools the cold flow in spring and autumn, and at the same time reduce the temperature of the cooling medium, so that the subsequent air-cooled heat pump 3 can make the cooling medium reach the preset temperature with lower energy consumption, thereby achieving the effect of energy saving.

[0074] Among them, the internal sensor module is installed on the air outlet side of the diversion control component, and the external sensor module and the human body detection module are installed on the air outlet side of the terminal air outlet device.

[0075] The fan is used to draw in outdoor air and then boost its pressure to send it to the shunt control component 16. The heat exchange component 13 performs heat exchange on the fresh air drawn in by the fan to adjust the temperature and humidity of the fresh air. The shunt control component 16 is connected to a plurality of terminal air outlet devices 2 one by one through a pipeline. The shunt control component 16 works according to the adjusted operating parameters calculated based on the difference and the correction value to send the regulated fresh air to different terminal air outlet devices 2. After the air passes through the heat exchange component 13 for heat exchange, its temperature and relative humidity change. For example, when dehumidification is needed in spring and autumn, the heat exchange component 13 cools the air, and its temperature decreases, and the water vapor carried in the air condenses, thereby reducing the water vapor carried in the air. However, at the same time, the temperature will decrease, resulting in the temperature of the airflow blown out by the terminal air outlet device 2 being too low, affecting the comfort of personnel, and thus the temperature of the fresh air needs to be adjusted. In summer and winter, When cooling or heating is required, the absolute humidity or relative humidity in the air will decrease, so it is necessary to adjust the air humidity after heat exchange, that is, to add water vapor to the air through the humidifier 141, and then assist in adjusting the humidity of the gas, so as to improve the comfort of the personnel. The fresh air can be heated by the electric heater 144, so as to adjust the fresh air temperature; that is, under the joint action of the humidifier 141 and the electric heater 144, dehumidification can be completed in spring and summer while ensuring the appropriate temperature; in autumn and winter, heating can be completed while ensuring the air humidity, so as to improve the comfort of personnel; at the same time, the electric heater 144 is arranged at the rear end of the humidifier 141, so that after the air is humidified, its relative humidity decreases when it is heated, so as to prevent the temperature from dropping after the subsequent long-section transportation in the pipeline, resulting in the occurrence of condensation water in the pipeline, so as to ensure the comfort of the users.

[0076] The specific adjustment process of the present application is: the operation control center takes the received working parameters and meteorological parameters as input parameters, calculates the comfort parameters based on the Bayesian comfort model, and calculates the difference between the environmental parameters and the comfort parameters using the comfort parameters as the reference number, and the operation control center inputs the difference to the diversion control component, and the diversion control component takes the difference as an input parameter, obtains the correction value and the corrected operating parameters according to the correction formula, and the electric air volume control valve uses the corrected operating parameters as working parameters to supply air to the terminal air outlet device.

[0077] Among them, the processing process of fresh air is as follows: after the cold and heat sources are supplied to the fresh air centralized processing unit 1 through the air-cooled heat pump 3, the fresh air is heated or cooled to adjust the temperature and humidity of the fresh air, and then the processed fresh air is transported to different terminal air outlet devices 2 through the diversion control component to meet the air demand of the terminal space. At this time, there is no need to set up an independent fresh air processing device in each terminal air outlet device 2, and there is no need to lay out the corresponding cooling pipe system to connect with the air-cooled heat pump 3, thereby reducing the complexity of the entire air-conditioning structure. At the same time, the terminal air outlet device 2 does not need to perform fresh air processing, so that the terminal air outlet device 2 does not need to install processing equipment for adjusting the outlet air temperature, humidity, wind speed and wind pressure. Therefore, the entire terminal air outlet device 2 has a simple structure and a low space occupancy rate. Small, so as to be easy for personnel to install; and the terminal air outlet device 2 does not need to perform on-site processing of the fresh air, thereby reducing the noise of the terminal air outlet device 2, thereby ensuring the comfort of the user; that is, during use, the air-conditioning fresh air is uniformly completed in the fresh air centralized processing unit 1, and then the fresh air is sent to different terminal air outlet devices 2 through the diversion control component 16 according to the optimized operating parameters calculated by the Bayesian comfort model. In actual home applications, the fresh air centralized processing unit 1 can be installed in areas such as kitchens, balconies or bathrooms where people's daily activities are weak or the noise requirements are low, and the terminal air outlet device 2 can be installed in locations such as bedrooms, living rooms or studies, to ensure that the environmental noise when people are resting normally is low, thereby improving the comfort of people.

[0078] Embodiment 2:

[0079] The present invention also provides an air conditioner adaptive comfort adjustment method, which is applied to the air conditioner adaptive comfort adjustment system of the first embodiment. The air conditioner adaptive comfort adjustment method includes:

[0080] S100, obtaining operating parameters of the shunt control component; the parameters are collected by an internal sensor module installed on the air outlet side of the shunt control component, including temperature, humidity, and wind speed, but not limited thereto;

[0081] S200, obtaining environmental parameters of the working area of ​​the terminal air outlet device; collected by an external sensor module installed on the air outlet side of the diversion control component, including temperature, humidity, wind speed, but not limited to these;

[0082] S300, obtaining working parameters of the working area of ​​the terminal air outlet device, including normal function data of the working area, the current number of users and personnel characteristics; the data is collected by a human body detection module installed on the air outlet side of the terminal air outlet device, wherein the normal function data of the working area can be input by the user, such as an elderly room, a children's room, a study room, etc.;

[0083] S400, obtaining meteorological parameters of the working area of ​​the terminal air outlet device; the meteorological parameters are read by the operation control center using the geographical location of the working area as a keyword to access the meteorological data of the corresponding geographical location in the meteorological database; wherein the geographical location of the working area can be acquired by the locator provided in the external sensor module, or can be input by the user through the control panel and then stored; the meteorological parameters include temperature, humidity, and wind speed, but are not limited thereto;

[0084] S500, using the meteorological parameters and the working parameters as input parameters of a Bayesian comfort model obtained by fitting with a deep learning algorithm, and calculating corresponding comfort parameters;

[0085] Specifically, the basic idea of ​​the Bayesian comfort model is to use the conditional dependencies between variables, train the parameters of the network based on historical data, and then perform probabilistic reasoning to predict future values. The prediction principle can be summarized as the following steps:

[0086] 1) Construct the network structure. According to the causal relationship between variables, determine the nodes and directed edges of the network to form a DAG graph.

[0087] 2) Learning parameters. Given training data D = {X1, X2, ..., Xn}, maximize the marginal likelihood of the data to the current network structure, that is, learn the CPT conditional probability through the formula: P[Xi|pa(Xi)] = argmax_P.P(D|G,P); where G is the network structure, P is all CPT parameters, and the parameter learning method is the Bayesian method.

[0088] 3) Inference prediction. For a given piece of evidence e and query variable Y, the Bayesian rule is used for probabilistic reasoning to calculate the posterior probability P(Y|e), that is: P(Y|e) = α.P(e|Y)P(Y) = α.∑yP(e|y)P(y); where α is the normalization factor. The posterior distribution or most likely value of variable Y can be predicted through inference prediction.

[0089] 4) Evaluate the prediction. Use indicators such as accuracy and recall to evaluate the prediction effect and optimize the model.

[0090] The embodiment of the present application uses the Bayesian Network Toolbox (BNT) in Matlab software to construct a Bayesian comfort model, wherein meteorological parameters and working parameters are used as variable nodes of the Bayesian network. Specifically, meteorological parameters include temperature, humidity, and wind speed, but are not limited thereto; working parameters include the number of personnel and personnel characteristics in the working area, and normal function data of the working area, but are not limited thereto. The Bayesian Network Toolbox in Matlab software is used to realize the structure learning, parameter learning, and network reasoning of the Bayesian network.

[0091] The learning of Bayesian network is to explore the implicit internal connection through learning and training of a large number of samples, that is, to solve the conditional probability between node variables. The sample data used in the Bayesian learning process is called training set data. The data used to test the rationality and accuracy of the prediction model is the test set data, and the actual value of the test set data is compared with the predicted value for verification.

[0092] The training set data and test set data used in the embodiment of the present application are from user usage data of a sufficiently long period of time. The period of user usage data in the embodiment of the present application is one year, wherein the actual value in the test set data is a user-defined parameter. The Bayesian comfort model in the embodiment of the present application is obtained based on one-year user usage data training, learning and fitting, and its variables imply the relationship between the user's personalized comfort settings, so the Bayesian comfort model has a personalized prediction function.

[0093] S600, obtaining the difference between the environmental parameter and the comfort parameter, and controlling the operating state of the diversion control component based on the difference. Wherein, if the difference is within the preset threshold range, the diversion control component is controlled to maintain the operating state; if the difference is on both sides of the preset threshold range, the operating state of the diversion control component is adjusted, and the specific adjustment method is to adjust the operating state of the diversion control component based on the correction value, the correction value is equal to the correction coefficient multiplied by the difference, and the correction coefficient is estimated by the random forest algorithm.

[0094] Specifically, random forest is an integrated learning method that improves the accuracy and stability of the model by constructing multiple decision trees and combining their prediction results. In the regression problem, random forest obtains the final prediction result by averaging the prediction values ​​of multiple decision trees. This embodiment estimates the correction coefficient K with the help of Matlab random forest tool, and the main steps can be summarized as follows:

[0095] 1) Data preparation: Based on the fitted Bayesian comfort model, a sufficient number of training and testing data sets are set.

[0096] 2) Create a random forest model. Use the TreeBagger function in Matlab to create a random forest model and specify the number of trees. In this embodiment, the number of trees is set to 1000. For example:

[0097] numTrees=1000; %Set the number of decision trees;

[0098] model=TreeBagger(numTrees,X(idxTrain,:),Y(idxTrain));

[0099] Here X(idxTrain,:) and Y(idxTrain) represent the feature matrix and target variable of the training set, respectively.

[0100] 3) Make predictions. Use the test set data to make predictions and call the model’s predict method to predict the target variable, for example: yPred = predict(model, X(idxTest,:)); here X(idxTest,:) represents the feature matrix of the test set.

[0101] 4) Evaluate the model. Evaluate the performance of the model through mean square error, for example:

[0102] mse=mean((Y(idxTest)-yPred).^2);

[0103] Here Y(idxTest) represents the true target variable of the test set.

[0104] 5) Adjust parameters. According to the performance of the model, adjust the parameters of the random forest to optimize the performance of the model.

[0105] 6) Estimate the value of the correction coefficient K. Through multiple training and prediction, estimate the value of K: Among them, ki is the coefficient of each decision tree.

[0106] Based on the correction coefficient K estimated by random forest, the correction value of the operating parameter of the shunt control component 16 to achieve the comfort parameter is obtained, so that the operating parameter of the shunt control component 16 is adjusted according to the correction value so that the difference between the environmental parameter and the comfort parameter is within the preset threshold range.

[0107] Based on the above S100-S600, the air conditioner is adaptively adjusted for comfort, so that when the meteorological parameters and working parameters of the air conditioner change significantly, the corresponding comfort parameters are obtained based on the Bayesian comfort model, and the adjustment correction values ​​are obtained based on the comfort parameters and the current corresponding environmental parameters to adjust and correct the operating parameters of the diversion control component 16, so that the environmental parameters of the working area tend to the comfort parameters, so that the user can have a good comfort experience.

[0108] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. An air conditioning adaptive comfort adjustment method, applied to an air conditioning system with a fresh air adjustment function, comprising: A terminal air outlet device for discharging air to a working area, a fan for drawing in and pressurizing outdoor air, a heat exchange component for performing heat exchange on the fresh air drawn in by the fan to adjust the temperature and humidity of the fresh air, and an air-cooled heat pump for supplying cold and heat source media to the heat exchange component; characterized in that it also includes a shunt control component connected one by one with the terminal air outlet device through a pipeline, and the air conditioning adaptive comfort adjustment method includes: Obtaining operating parameters of the diversion control component; Obtaining environmental parameters of the working area of ​​the terminal air outlet device; Obtaining working parameters of the working area of ​​the terminal air outlet device, including normal function data of the working area, the current number of users and personnel characteristics; Obtaining meteorological parameters of the working area of ​​the terminal air outlet device; The meteorological parameters and the working parameters are used as input parameters of the Bayesian comfort model obtained by fitting the deep learning algorithm to calculate the corresponding comfort parameters; The difference between the environmental parameter and the comfort parameter is calculated, and the operating state of the diversion control component is controlled based on the difference.

2. The air conditioning adaptive comfort adjustment method according to claim 1, characterized in that: The operating state of the shunt control component is controlled based on the difference; if the difference is within a preset threshold range, the shunt control component is controlled to maintain the operating state; if the difference is within both sides of the preset threshold range, the operating state of the shunt control component is adjusted.

3. The air conditioning adaptive comfort adjustment method according to claim 2, characterized in that: If the difference is within the preset threshold range, the operating state of the diversion control component is adjusted based on the correction value, and the correction value is equal to the correction coefficient multiplied by the difference, and the correction coefficient is estimated by the random forest algorithm.

4. An air conditioning adaptive comfort adjustment system, characterized in that: include: A terminal air outlet device for discharging air to the working area, a fan for drawing in and pressurizing outdoor air, a heat exchange component for performing heat exchange on the fresh air drawn in by the fan to adjust the temperature and humidity of the fresh air, and an air-cooled heat pump for supplying cold and heat source media to the heat exchange component; characterized in that it also includes a shunt control component connected one by one with the terminal air outlet device through a pipeline, an internal sensor module installed on the air outlet side of the shunt control component to collect operating parameters of the shunt control component, an external sensor module and a human body detection module installed on the air outlet side of the terminal air outlet device to collect environmental parameters of the working area, and An operation control center that communicates and interacts with the internal sensing module, the external sensing module and the human body detection module, wherein the operation control center stores a Bayesian comfort model fitted based on a deep learning algorithm, and the operation control center communicates and interacts with a meteorological database and obtains meteorological parameters of a corresponding working area based on the geographical location of the working area, and uses the received meteorological parameters and working parameters as input parameters of the Bayesian comfort model to calculate comfort parameters, uses the comfort parameters as reference values ​​to calculate the difference between the environmental parameters and the comfort parameters, and inputs the difference into the diversion control component to control the operating status.

5. The air conditioning adaptive comfort adjustment system according to claim 4, characterized in that: The diversion control component includes a plurality of air outlet pipes connected to the air outlet of the fan, and the plurality of air outlet pipes are connected one by one with a plurality of terminal air outlet devices through pipelines. Each of the air outlet pipes is provided with an electrically controlled air volume control valve that communicates and interacts with the operation control center.

6. The air conditioning adaptive comfort adjustment system according to claim 5, characterized in that: The terminal air outlet device comprises a chilled beam box, in which a condensing coil for heat exchange of airflow is arranged, and a chilled beam air outlet is arranged on the chilled beam box.

7. The air conditioning adaptive comfort adjustment system according to claim 6, characterized in that: The air outlet side of the heat exchange component is provided with a temperature and humidity auxiliary adjustment component, and the temperature and humidity auxiliary adjustment component includes a humidifier arranged on the air outlet side of the heat exchange component, and one end of the air outlet side of the humidifier is provided with an electric heater.

8. The air conditioning adaptive comfort adjustment system according to claim 7, characterized in that: It also includes a box body with a main air inlet and a main air outlet, and the heat exchange component, the temperature and humidity auxiliary adjustment component, the fan and the diversion control component are arranged in sequence along the wind flow direction from the air inlet to the air outlet.

9. The air conditioning adaptive comfort adjustment system according to claim 8, characterized in that: A mounting frame is provided in the box body, the fan is configured as a centrifugal fan, the centrifugal fan is arranged above the mounting frame, an L-shaped wind shield is provided on the air outlet side of the centrifugal fan, and the diversion control component is arranged on the L-shaped wind shield; a water retaining frame is provided on the air outlet side of the humidifier, and a water retaining frame is provided with a water retaining plate inclined downward away from the humidifier.

10. The air conditioning adaptive comfort adjustment system according to claim 9, characterized in that: The air conditioning adaptive comfort adjustment system adopts the air conditioning adaptive comfort adjustment method according to any one of claims 1 to 3.

Images