An intelligent adjustment system and adjustment method for air conditioner heat transfer

Abstract

The present invention provides an intelligent regulation system and method for air conditioner heat transfer, which adopts a heat transfer regulation system based on real-time monitoring, data-driven and intelligent prediction to achieve precise, automated and flexible application control of air conditioner heat transfer. It can combine the sequence features and external features related to heat transfer to intelligently regulate the operating parameters at the next time point. The regulation method is flexible, and it can automatically adjust the control parameters related to air conditioner heat transfer following the environmental features, and intelligently and flexibly regulate the air conditioner heat transfer strategy following the heat load change rate of the heat transfer system, achieving the technical effects of energy-saving and high-efficiency, intelligent regulation, data-driven optimization, and improving the user experience, and can significantly improve the operating efficiency of the air conditioner system and user satisfaction.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent regulation, and particularly to an intelligent regulation system for air-conditioning heat transfer, an intelligent regulation method for air-conditioning heat transfer, an electronic device, and a computer-readable storage medium. Background Art

[0002] The heat transfer system of an air conditioner mainly involves the circulation of refrigerant and the operation of components such as a compressor, a condenser, and an evaporator. The traditional regulation method for air-conditioning heat transfer mainly realizes PID control by the air-conditioning system. However, the traditional PID control also has the following application defects:

[0003] The traditional PID control may not respond quickly enough in a dynamic environment, resulting in temperature fluctuations; and the PID control is a preset parameter regulation, and the regulation method is mechanical and rigid, and it cannot follow the heat load change rate of the heat transfer system to intelligently and flexibly regulate the air-conditioning heat transfer strategy, with low efficiency.

[0004] The insufficient accuracy of the sensor leads to inaccurate regulation.

[0005] In addition, when the environmental temperature changes greatly or the indoor-outdoor temperature difference is large, the system may not be able to adjust in time, resulting in a decrease in the energy efficiency ratio.

[0006] The system relies too much on the preset program parameters of the PID controller and cannot adapt to changes, resulting in low efficiency under different loads; and it cannot comprehensively consider the overall load situation of the heat transfer system and external parameters for dynamic heat transfer regulation, so the regulation method is relatively inflexible. Summary of the Invention

[0007] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions:

[0008] On the one hand, an intelligent regulation method for air-conditioning heat transfer is provided. This method is implemented by an electronic device and includes:

[0009] S1. Monitor the operating power consumption parameters of the air-conditioning heat transfer system: the heat of refrigerant thermal cycle, the heat load change rate, the compressor power consumption, and the indoor three-dimensional image at the preset air-conditioning working time point, and upload them to the air-conditioning background server.

[0010] S2. Calculate the indoor personnel density in the indoor three-dimensional image at the air-conditioning working time point by the air-conditioning background server, and input the operating power consumption parameters and indoor personnel density at the air-conditioning working time point into the pre-deployed heat transfer intelligent regulation LSTM model.

[0011] S3. Based on the operating power consumption parameters, the heat transfer intelligent regulation LSTM model predicts the regulation sequence data features of the air conditioner's working time point, and uses the regulation sequence data features and the indoor personnel density as the input sequence. Then, based on the feature correlation between adjacent time points, it predicts again and outputs the regulation sequence data features of the next air conditioner working time point. and the corresponding indoor personnel density ;

[0012] S4. Monitor the indoor personnel density ρ(t + 1) at the next air conditioner working time point and determine whether the following conditions are met:

[0013] ,

[0014] If yes, when the next air conditioner working time point is reached, parse and execute the system heat transfer control parameters in the regulation sequence data features to perform automatic regulation of air conditioner heat transfer;

[0015] Otherwise, use the operating power consumption parameters at the next air conditioner working time point and the indoor personnel density ρ(t + 1) as the input sequence. The heat transfer intelligent regulation LSTM model predicts the regulation sequence data features of the next air conditioner working time point and parses and executes them.

[0016] Preferably, the calculation method of the operating power consumption parameters includes:

[0017] (1) Refrigerant heat cycle heat

[0018] Heat absorption of the evaporator evap:

[0019] ,

[0020] Heat release of the condenser cond:

[0021] ,

[0022] Wherein, is the refrigerant mass flow rate, which is positively correlated with the opening of the electronic expansion valve of the air conditioner;

[0023] are specific enthalpy values, and their subscripts (evap, out), (evap, in), (cond, out), (cond, in) represent the evaporator outlet, evaporator inlet, condenser outlet, and condenser inlet respectively;

[0024] (2) Heat load change rate

[0025] Set:

[0026] ,

[0027] Among them: ,

[0028] The heat load is calculated as: ;

[0029] By introducing time t, the heat load is calculated as: The rate of change of the heat load varying with time t:

[0030] ;

[0031] Among them, is the equivalent heat capacity of the room, in which is the specific heat capacity of air (1.005 kJ / kg·K), is the outlet temperature of the room air conditioner, is the outlet temperature of the evaporator; is the supply air mass flow rate, which is positively correlated with both the fan speed and the air deflector angle of the air conditioner;

[0032] (3) Compressor power consumption

[0033] It is set that:

[0034] ,

[0035] Among them, is the isentropic efficiency of the compressor, ranging from 0.65 to 0.85.

[0036] Preferably, the method for generating the heat transfer intelligent regulation LSTM model includes:

[0037] Collecting big data of the historical regulation sequence of the heat transfer system of the air conditioner:

[0038] Data(T)=∏Data(t),

[0039] Data(T + 1)=∏Data(t + 1),

[0040] Data(T) and Data(T + 1) are the historical regulation sequence data at time point (t) and time point (t + 1) respectively;

[0041] The historical regulation sequence data = {refrigerant heat cycle heat, rate of change of heat load, compressor power consumption, system heat transfer control parameters: fan speed, air deflector angle, compressor frequency and electronic expansion valve};

[0042] Collecting indoor three-dimensional images at time point (t) and time point (t + 1) respectively, and calculating the indoor personnel density at time point (t) and time point (t + 1) based on the indoor three-dimensional images: ρ(t) and ρ(t + 1);

[0043] Construct a regulation sequence data set with X = {[Data(T - n), ρ(t - n)],..., [Data(T), ρ(t)]} as the input sequence and Y = [ų(T + 1), ρ(t + 1)] as the output result, where ų(T + 1) represents the system heat transfer control parameter at time point (t + 1);

[0044] Divide the regulation sequence data set into a training set and a validation set according to a preset ratio;

[0045] Input the training set into a pre - constructed LSTM model, and let the model train and learn the regulation sequence data features of X in the training set and the regulation sequence data features related before and after between time point (t) and time point (t + 1), to construct a heat transfer intelligent regulation LSTM model with X as the input sequence and Y as the output result;

[0046] Use the validation set to verify the prediction performance of the heat transfer intelligent regulation LSTM model:

[0047] If the verification passes, deploy and apply the heat transfer intelligent regulation LSTM model to the air - conditioner background server;

[0048] If the verification fails, repeat the above steps to reconstruct the heat transfer intelligent regulation LSTM model.

[0049] Preferably, the LSTM model adopts a double - layer LSTM architecture structure, including:

[0050] An input layer for inputting X or (X, Y) in turns;

[0051] The first - layer bidirectional LSTM for training and learning the regulation sequence data features of X;

[0052] The second - layer bidirectional LSTM for training and learning the regulation sequence data features related before and after in (X, Y);

[0053] An output layer for outputting the prediction result.

[0054] On the other hand, a heat transfer intelligent regulation system for an air - conditioner is provided. This system is applied to the heat transfer intelligent regulation method for an air - conditioner, and this system includes:

[0055] A data acquisition module for monitoring the operating power consumption parameters of the air - conditioner heat transfer system according to the preset air - conditioner working time points: the refrigerant heat cycle heat, the heat load change rate, the compressor power consumption, and the indoor three - dimensional image at the air - conditioner working time point and uploading them to the air - conditioner background server;

[0056] A data processing module, configured to calculate the indoor personnel density in the indoor three-dimensional image at the air conditioner working time point by the air conditioner background server, and input the operating power consumption parameter and the indoor personnel density at the air conditioner working time point into a pre-deployed heat transfer intelligent regulation LSTM model;

[0057] A heat transfer intelligent prediction module, configured to predict the regulation sequence data characteristics at the air conditioner working time point through the heat transfer intelligent regulation LSTM model according to the operating power consumption parameter, and use the regulation sequence data characteristics and the indoor personnel density as input sequences, and predict again based on the feature correlation between the front and back time points, and output the regulation sequence data characteristics at the next air conditioner working time point and the corresponding indoor personnel density ;

[0058] A heat transfer response module, configured to monitor the indoor personnel density ρ(t + 1) at the next air conditioner working time point, and determine whether the following conditions are satisfied:

[0059] ,

[0060] If it is satisfied, then when reaching the next air conditioner working time point, parse and execute the system heat transfer control parameters in the regulation sequence data characteristics to perform automatic regulation of air conditioner heat transfer;

[0061] Otherwise, use the operating power consumption parameter and the indoor personnel density ρ(t + 1) at the next air conditioner working time point as input sequences, and predict the regulation sequence data characteristics at the next air conditioner working time point by the heat transfer intelligent regulation LSTM model, and parse and execute.

[0062] On the other hand, an electronic device is provided, and the electronic device includes: a processor; a memory, and a computer-readable instruction is stored on the memory, and when the computer-readable instruction is executed by the processor, any one of the methods in the above air conditioner heat transfer intelligent regulation method is implemented.

[0063] On the other hand, a computer-readable storage medium is provided, and at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by the processor to implement any one of the methods in the above air conditioner heat transfer intelligent regulation method.

[0064] The beneficial effects brought by the technical solutions provided by the embodiments of the present invention at least include:

[0065] The present invention adopts a heat transfer regulation system through real-time monitoring, data-driven and intelligent prediction, realizing precise, automated and flexible application control of air-conditioning heat transfer. It can combine the sequence features and external features related to heat transfer to intelligently regulate the operating parameters at the next time point. The regulation method is flexible, and it can automatically adjust the control parameters related to air-conditioning heat transfer following the environmental features, and intelligently and flexibly regulate the air-conditioning heat transfer strategy following the heat load change rate of the heat transfer system, achieving the technical effects of energy conservation, high efficiency, intelligent regulation, data-driven optimization and improving the user experience, and can significantly improve the operating efficiency of the air-conditioning system and user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0067] Figure 1 is a flowchart of an intelligent regulation method for air-conditioning heat transfer provided by an embodiment of the present invention;

[0068] Figure 2 is a schematic diagram of the model structure of LSTM;

[0069] Figure 3 is a schematic diagram of the architecture structure of a double-layer LSTM provided by an embodiment of the present invention;

[0070] Figure 4 is a block diagram of an intelligent regulation system for air-conditioning heat transfer provided by an embodiment of the present invention;

[0071] Figure 5 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0072] The following will describe the technical solutions in the present invention with reference to the drawings.

[0073] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of the word "example" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0074] In the embodiments of the present invention, the terms "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, their intended meanings are the same. The terms "of", "corresponding", and "corresponding to" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, their intended meanings are the same.

[0075] In the embodiments of the present invention, sometimes a subscript such as W1 may be miswritten as a non-subscript form such as W1. When the difference between them is not emphasized, their intended meanings are the same.

[0076] To make the technical problems to be solved, technical solutions, and advantages of the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0077] The embodiments of the present invention provide an intelligent air-conditioning heat transfer adjustment method, which can be implemented by an electronic device, and the electronic device can be a terminal or a server. As Figure 1 shown in the flowchart of the intelligent air-conditioning heat transfer adjustment method, the processing flow of the method may include the following steps:

[0078] S1. Monitor the operating power consumption parameters of the air-conditioning heat transfer system: the refrigerant heat cycle heat, the heat load change rate, the compressor power consumption, and the indoor three-dimensional image at the preset air-conditioning working time point, and upload them to the air-conditioning background server;

[0079] S2. Calculate the indoor personnel density in the indoor three-dimensional image at the air-conditioning working time point by the air-conditioning background server, and input the operating power consumption parameters and the indoor personnel density at the air-conditioning working time point into the pre-deployed heat transfer intelligent adjustment LSTM model;

[0080] S3. Predict the regulation sequence data features at the air-conditioning working time point according to the operating power consumption parameters through the heat transfer intelligent adjustment LSTM model, and use the regulation sequence data features and the indoor personnel density as the input sequence, and predict again based on the feature correlation between the front and back time points to output the regulation sequence data features at the next air-conditioning working time point and the corresponding indoor personnel density ;

[0081] S4. Monitor the indoor personnel density ρ(t + 1) at the next air-conditioning working time point, and judge whether the following conditions are satisfied:

[0082] ,

[0083] If it holds, when reaching the next air conditioner working time point, parse and execute the control sequence data features in the system heat transfer control parameters to perform automatic adjustment of the air conditioner heat transfer;

[0084] Otherwise, use the operating power consumption parameters at the next air conditioner working time point and the indoor personnel density ρ(t + 1) as the input sequence, and predict the control sequence data features at the next air conditioner working time point by the heat transfer intelligent adjustment LSTM model, and then parse and execute.

[0085] The present invention adopts a heat transfer adjustment system through real-time monitoring, data-driven and intelligent prediction, realizing precise, automatic and flexible application control of air conditioner heat transfer. It can combine heat transfer related sequence features and external features to intelligently control the operating parameters at the next time point. The control method is flexible, and it can automatically adjust the control parameters related to air conditioner heat transfer following the environmental features, and intelligently and flexibly adjust the air conditioner heat transfer strategy following the heat load change rate of the heat transfer system, achieving the technical effects of energy-saving and high-efficiency, intelligent control, data-driven optimization, and improving the user experience, and can significantly improve the operating efficiency of the air conditioner system and user satisfaction.

[0086] The present invention mainly includes the following steps:

[0087] S1. Monitor the operating parameters of the air conditioner heat transfer system

[0088] 1) Data acquisition:

[0089] Operating power consumption parameters, including:

[0090] Refrigerant heat cycle heat;

[0091] Heat load change rate;

[0092] Compressor power consumption.

[0093] The above data is collected by system sensors and uploaded to the host computer. For example, the temperature at the inlet and outlet of the condenser or the heat release / absorption amount (each device such as the condenser can pre-collect and calculate by its own MCU processor and then upload to the host computer). The data interaction and communication control between each collection end and the host computer (air conditioner background server) can be understood in combination with the communication mode of the existing air conditioner system.

[0094] For the default parameter values of the system air conditioner, such as enthalpy value, etc., they can be queried from the air conditioner manual, etc. The system generally stores the corresponding original factory data by default.

[0095] Regarding the indoor three-dimensional image: Use a 3D camera or depth sensor (such as Kinect) to capture the indoor three-dimensional image in real time.

[0096] Time point: Collect data according to the preset air conditioner working time point (such as every 15 minutes). The air conditioner working time point can be set by the user or set at the factory.

[0097] 2) Data upload:

[0098] Upload the collected operating power consumption parameters and 3D images to the air conditioner background server.

[0099] Use an efficient communication protocol (such as MQTT or HTTP) to ensure the real-time and reliability of data transmission.

[0100] S2. Calculate the indoor personnel density and input it into the LSTM model

[0101] 1) Indoor personnel density calculation:

[0102] Use computer vision algorithms (such as YOLO or OpenCV) to analyze the 3D image and detect the number and location of indoor personnel.

[0103] Calculate the personnel density (number of people per unit area): the number of detected people / indoor area (pre-entered in the system).

[0104] 2) Data preprocessing:

[0105] Standardize the operating power consumption parameters and personnel density to ensure that the input data is in the same dimension.

[0106] Organize the data in a time series to form an input feature matrix.

[0107] 3) Input into the LSTM model:

[0108] Input the operating power consumption parameters and personnel density into the pre-deployed heat transfer intelligent regulation LSTM model.

[0109] The input features include:

[0110] Operating power consumption parameters: [refrigerant heat cycle heat, heat load change rate, compressor power consumption], personnel density ρ(t);

[0111] S3. Predict the data characteristics of the regulation sequence

[0112] 1) LSTM model prediction:

[0113] Use the LSTM model to predict the data characteristics of the regulation sequence based on the operating power consumption parameters at the current time point.

[0114] The data characteristics of the regulation sequence include: target temperature, compressor frequency, fan speed, electronic expansion valve opening, etc.

[0115] 2) Prediction in combination with personnel density:

[0116] Use the predicted regulatory sequence data features and the personnel density as the input sequence and input them into the LSTM model again.

[0117] Predict the regulatory sequence data features at the next time point based on the feature correlation between the previous and next time points and the personnel density .

[0118] S4. Monitoring and implementing regulation

[0119] 1) Monitor the personnel density at the next time point:

[0120] At the next air conditioner working time point, monitor the indoor personnel density in real time .

[0121] 2) Condition judgment:

[0122] Judge whether the condition is met:

[0123] ,

[0124] If it holds:

[0125] Analyze and execute the predicted regulatory sequence data features , and perform automatic adjustment of air conditioner heat transfer;

[0126] If it does not hold: Use the operating power consumption parameters and the actual personnel density at the next time point as the input, re-predict the regulatory sequence data features and execute.

[0127] Therefore, by using the above-mentioned auxiliary prediction technology of the air conditioner regulation strategy based on the LSTM model for the next time point of the present invention, it is possible to perform intelligent regulation according to the user's air conditioner usage habits and home environmental parameters, thereby avoiding the user from manually activating the air conditioner and spending time regulating the corresponding air conditioner operating parameters, and greatly improving its control flexibility.

[0128] The present invention has the following application advantages:

[0129] 1. Precise regulation

[0130] Dynamic adaptation: By monitoring the operating parameters and personnel density in real time, dynamically adjust the air conditioner operation strategy to ensure the optimal heat transfer efficiency.

[0131] Personalized adjustment: Combine personnel density prediction to achieve precise regulation based on the actual indoor needs and improve comfort.

[0132] 2. Energy saving and high efficiency

[0133] Optimize energy consumption: By predicting the characteristics of the regulation sequence data, avoid unnecessary energy waste, and reduce the power consumption of the compressor and the heat in the thermal cycle.

[0134] Intelligent adjustment: Automatically adjust the operating parameters of the air conditioner according to the heat load change rate and the personnel density, and improve the overall energy efficiency of the system.

[0135] 3. Intelligence and automation

[0136] Intelligent prediction: Use the LSTM model to capture the complex dependencies of time series data and achieve high-precision prediction.

[0137] Automated execution: Automatically execute the regulation strategy according to the prediction results, reduce manual intervention, and improve the intelligence level of the system.

[0138] 4. Data-driven

[0139] Multi-source data fusion: Combine the operating power consumption parameters and three-dimensional image data to comprehensively reflect the operating status of the air conditioner system and the indoor environment.

[0140] Continuous optimization: Continuously accumulate data, optimize the prediction accuracy of the LSTM model, and improve the system performance.

[0141] 5. Improve user experience

[0142] Quick response: Real-time monitoring and prediction ensure that the air conditioner system quickly responds to user needs and improves the usage experience.

[0143] Comfortable environment: Based on the regulation strategy of personnel density, ensure that the indoor environment is always in a comfortable state.

[0144] Preferably, the calculation method of the operating power consumption parameters includes:

[0145] (1) Refrigerant heat in the thermal cycle

[0146] Heat absorbed by the evaporator evap:

[0147] ,

[0148] Heat released by the condenser cond:

[0149] ,

[0150] Among them, is the refrigerant mass flow rate, which is positively correlated with the opening of the electronic expansion valve of the air conditioner;

[0151] is the specific enthalpy value, and its subscripts (evap, out), (evap, in), (cond, out), and (cond, in) represent the evaporator outlet, evaporator inlet, condenser outlet, and condenser inlet respectively;

[0152] The values of each inlet and outlet can be determined based on the original factory data. The above calculation formulas for heat release and heat absorption can be calculated in combination with the corresponding parameters.

[0153] Here, it is necessary to proportionally regulate the opening of the electronic expansion valve of the air conditioner according to the calculation results, because it is related to the refrigerant mass flow rate . In the air conditioning system, there is a certain positive correlation between the refrigerant mass flow rate and the opening of the electronic expansion valve EEV. This relationship can be described by a proportionality coefficient, usually called the flow coefficient or opening - flow coefficient. The following is a detailed description and mathematical expression of this relationship:

[0154] 1) Relationship description

[0155] Opening of the electronic expansion valve: The opening of the electronic expansion valve (usually expressed as a percentage, 0% is fully closed, 100% is fully open) determines the flow area of the refrigerant through the valve.

[0156] Refrigerant mass flow rate: The refrigerant mass flow rate (unit: kg / s) is positively correlated with the opening of the electronic expansion valve, that is, the larger the opening, the larger the flow rate.

[0157] 2) Mathematical expression

[0158] The relationship between the refrigerant mass flow rate and the opening of the electronic expansion valve can be expressed as:

[0159] ,

[0160] The meanings of each letter / character from left to right are: refrigerant mass flow rate (kg / s), opening of the electronic expansion valve (%), proportionality coefficient (kg / (s·%)) (representing the refrigerant mass flow rate corresponding to a unit opening).

[0161] And the determination of the proportionality coefficient k:

[0162] The specific value of the proportionality coefficient k depends on the following factors:

[0163] Refrigerant type: Different refrigerants have different densities and flow characteristics, which affect the flow coefficient;

[0164] Valve characteristics: The design of the electronic expansion valve (such as flow area, spool shape) affects the relationship between flow rate and opening;

[0165] System operating conditions: System parameters such as evaporation temperature, condensation temperature, and pressure difference also affect the flow coefficient.

[0166] The refrigerant mass flow at different opening degrees can be measured through experiments, and the value of k can be fitted. For example:

[0167] At the opening degree = 50%, the measured flow rate .

[0168] Then .

[0169] For example: In practical applications, the relationship between the flow rate and the opening degree may not be completely linear, especially when the opening degree is small or large. Therefore, the following correction methods can be adopted:

[0170] Piecewise linear model:

[0171] The opening degree range is divided into multiple intervals, and different k values are used for each interval.

[0172] .

[0173] For example: Suppose the relationship between the opening degree of the electronic expansion valve and the refrigerant mass flow of an air conditioning system is as follows:

[0174]

[0175] Then the proportionality coefficient is:

[0176] .

[0177] (2) Heat load change rate

[0178] Set:

[0179] ,

[0180] Where: ,

[0181] The calculated heat load: ;

[0182] By introducing time t, the heat load is calculated: The heat load change rate varying with time t:

[0183] ;

[0184] Where, is the room equivalent heat capacity, in which is the specific heat capacity of air (1.005 kJ / kg·K), is the room air conditioner outlet temperature, is the evaporator outlet temperature; is the air supply mass flow rate, which is positively correlated with both the fan speed and the air deflector angle of the air conditioner;

[0185] The above-mentioned inlet and outlet temperatures can also be monitored and collected by sensors deployed at various locations, and after being processed, they are sent to the host computer (background). For other parameters such as the air supply quality, etc., refer to the factory settings.

[0186] The air supply mass flow rate is positively correlated with both the fan speed and the air deflector angle of the air conditioner. By controlling the fan speed or the air deflector angle of the air conditioner, the air supply mass flow rate can be regulated.

[0187] In the air-conditioning heat transfer system, the air supply mass flow rate is one of the key parameters affecting the heat load change rate. The air supply mass flow rate has a positive correlation with the fan speed and the air deflector angle. By adjusting the fan speed or the air deflector angle, the air supply mass flow rate can be controlled, thereby affecting the heat load change rate.

[0188] 1. Influencing factors of the air supply mass flow rate

[0189] 1.1 Fan speed

[0190] Relationship description: The higher the fan speed, the greater the air supply mass flow rate.

[0191] 1.2 Air deflector angle

[0192] Relationship description: The larger the air deflector angle, the larger the flow area of the air supply channel, and the greater the air supply mass flow rate.

[0193] Air supply mass flow rate can be expressed as a function of the fan speed N and the air deflector angle θ:

[0194] , where k is a proportionality coefficient related to the fan characteristics, the air duct design, and the air density;

[0195] The mathematical expression of the heat load change rate and the air supply mass flow rate is constructed as follows:

[0196] ,

[0197] is the difference between the room air conditioner outlet temperature and the evaporator outlet temperature.

[0198] By adjusting the fan speed or the air deflector angle, the air supply mass flow rate can be controlled, thereby regulating the heat load change rate.

[0199] Adjust the fan speed.

[0200] Method: Adjust the rotational speed of the fan motor through a frequency converter.

[0201] Advantages:

[0202] Precisely control the mass flow rate of the supplied air.

[0203] Significant energy-saving effect, especially under partial load conditions.

[0204] Adjust the angle of the air deflector.

[0205] Method: Adjust the angle of the air deflector through a stepper motor or a servo motor.

[0206] Advantages:

[0207] Quickly change the air supply direction and mass flow rate.

[0208] Suitable for local heat load adjustment.

[0209] (3) Compressor power consumption

[0210] Settings:

[0211] ,

[0212] Among them, is the isentropic efficiency of the compressor, ranging from 0.65 to 0.85.

[0213] The compressor power consumption can be calculated by the system, in combination with the above-mentioned various factory-set parameters.

[0214] The present invention uses an LSTM model with bidirectional LSTM for model training.

[0215] The LSTM model adopts a two-layer LSTM architecture structure, including:

[0216] An input layer for sequentially inputting X or (X, Y);

[0217] The first layer of bidirectional LSTM for training and learning the regulatory sequence data features of X;

[0218] The second layer of bidirectional LSTM for training and learning the regulatory sequence data features related before and after in (X, Y);

[0219] An output layer for outputting the prediction result.

[0220] The model structure of the bidirectional LSTM is as Figure 2As shown, by using the LSTM model, it is possible to predict and output the sequence data features at future associated time points based on the environmental data sequence data at past time points. Therefore, the present invention uses the big data of the historical regulation sequences of the air-conditioning heat transfer system for LSTM training, so as to construct a heat transfer intelligent regulation LSTM model that can identify the heat transfer regulation sequence data features at the current point and predict those at future time points.

[0221] The structure, model training, and application principle of the LSTM model are well-known technologies and will not be elaborated here.

[0222] As Figure 3 shown, the present invention proposes an architecture structure of a double-layer LSTM, which includes 2 layers of LSTM:

[0223] The first-layer bidirectional LSTM is used to train and learn the regulation sequence data features of X; mainly to memorize and learn the heat transfer regulation sequence data features (including the corresponding system control parameters and the matching environmental features) at each past time point.

[0224] The second-layer bidirectional LSTM is used to train and learn the regulation sequence data features related before and after in (X, Y); mainly to memorize and learn the dependence relationship between the heat transfer regulation sequence data features at the time points before and after in the historical regulation, that is, to memorize and learn the front-back dependence relationship between the regulation strategies at two time points of time (t) and time (t + 1), so as to facilitate comprehensively predicting the air-conditioning heat transfer strategy at the next time point according to the heat transfer regulation sequence data features and / or environmental features (indoor personnel density) at the previous time (t).

[0225] Therefore, by using the bidirectional structure to capture the front-back dependence relationship of the historical regulation data simultaneously, through the bidirectional LSTM model, it is possible to efficiently capture the time dependence relationship in the air-conditioning heat transfer regulation sequence, combine historical data to predict future regulation parameters, and thus optimize the air-conditioning operation strategy. In practical applications, it is necessary to adjust the model structure and hyperparameters according to the data characteristics, and continuously improve the prediction accuracy and robustness through iteration.

[0226] Preferably, the method for generating the heat transfer intelligent regulation LSTM model includes:

[0227] Collect the big data of the historical regulation sequences of the air-conditioning heat transfer system (constituted by the regulation sequence data recorded by the air-conditioning heat transfer system at each time point):

[0228] Data(T) = ∏Data(t),

[0229] Data(T + 1) = ∏Data(t + 1),

[0230] Data(T) and Data(T + 1) are historical control sequence data at time points (t) and (t + 1) respectively;

[0231] The historical control sequence data = {refrigerant heat cycle heat, heat load change rate, compressor power consumption, system heat transfer control parameters: fan speed, air deflector angle, compressor frequency, and electronic expansion valve};

[0232] Indoor three - dimensional images at time points (t) and (t + 1) are collected respectively, and the indoor population densities at time points (t) and (t + 1) are analyzed and calculated based on the indoor three - dimensional images: ρ(t) and ρ(t + 1);

[0233] A control sequence data set is constructed with X = {[Data(T - n), ρ(t - n)],..., [Data(T), ρ(t)]} as the input sequence and Y = [ų(T + 1), ρ(t + 1)] as the output result, where ų(T + 1) represents the system heat transfer control parameter at time point (t + 1);

[0234] The control sequence data set is divided into a training set and a validation set according to a preset ratio;

[0235] The training set is input into a pre - constructed LSTM model, and the model trains and learns the control sequence data features of X in the training set and the control sequence data features related before and after between time points (t) and (t + 1), and a heat transfer intelligent adjustment LSTM model with X as the input sequence and Y as the output result is constructed;

[0236] The prediction performance of the heat transfer intelligent adjustment LSTM model is verified using the validation set;

[0237] If the verification passes, the heat transfer intelligent adjustment LSTM model is deployed and applied to the air - conditioner background server;

[0238] If the verification fails, the above steps are repeated to reconstruct the heat transfer intelligent adjustment LSTM model.

[0239] For data collection at each time point, please collect, process and upload to the background in combination with the previous description.

[0240] Construct a control sequence data set:

[0241] Input sequence X:

[0242] X = {[Data(T - n), ρ(t - n)],..., [Data(T), ρ(t)]}

[0243] where n is the time window length.

[0244] Output result Y:

[0245] Y = [ų(T + 1), ρ(t + 1)]

[0246] Where ų(T + 1) is the system heat transfer control parameter at time point t + 1.

[0247] Dataset division:

[0248] Divide the dataset according to a preset ratio (e.g., 80% training set, 20% validation set). Here, X and (X, Y) are divided into two datasets, and the training set and validation set will be divided respectively for the round input and training of the two-layer model.

[0249] Construct a heat transfer intelligent adjustment LSTM model:

[0250] 1) Model input and output

[0251] Input: Time series data X, including historical regulation sequence data and personnel density. First, it is trained and learned by the first-layer bidirectional LSTM to identify the corresponding regulation sequence data features and the adapted personnel density at each time; then (X, Y) is input into the second-layer bidirectional LSTM to memorize and learn the dependency relationship between the heat transfer regulation sequence data features at the previous and next time points in the historical regulation, so as to train the model recognition characteristic of "automatically identifying and outputting the regulation sequence data features of the next time point with a dependency / association relationship under the regulation sequence data features of the previous time point".

[0252] Output: Prediction result Y, including the system heat transfer control parameter and personnel density at future time points.

[0253] Its execution process can be simplified as the following code display:

[0254] # Input layer

[0255] model.add(Bidirectional)

[0256] LSTM(units = 64, return_sequences = True)

[0257] # The first-layer bidirectional LSTM, returning the complete sequence input_shape=(window_size, num_features)

[0258] model.add(Dropout(8.2)) # Prevent overfitting

[0259] # The second-layer bidirectional LSTM

[0260] model.add(Bidirectional(LSTM(units=32)))

[0261] model.add(Dropout(8.2))

[0262] # Output layer (predict target parameters)

[0263] model.add(Dense(units=2)) # Assume the output target temperature and compressor frequency

[0264] # Compile the model

[0265] model.compile(optimizer='adam', loss='mse', metrics=['mae'])

[0266] For training data: Use the training set X and (X, Y) for training.

[0267] 2) Training parameters

[0268] Optimizer: Adam;

[0269] Loss function: Mean Squared Error (MSE);

[0270] Evaluation metric: Mean Absolute Error (MAE);

[0271] Early stopping: Prevent overfitting.

[0272] For example, adopt the following parameters:

[0273] epochs = 188,

[0274] batch_size = 32

[0275] 3) Validate the model performance

[0276] Validation data: Use the validation sets of X and (X, Y) to evaluate the model performance respectively

[0277] The following evaluation metrics can be adopted:

[0278] Mean Squared Error (MSE);

[0279] Mean Absolute Error (MAE);

[0280] Visual comparison of predicted values and true values. Specific validation can be operated by the administrator.

[0281] If the validation passes:

[0282] The model performance meets the requirements and can be directly deployed;

[0283] If verification fails:

[0284] Adjust model hyperparameters (such as the number of LSTM units, learning rate, and Dropout rate), or increase the amount of training data or improve the data quality, and retrain the model.

[0285] The model can be integrated into the server, loaded using Python or C++, and a prediction interface can be provided.

[0286] First, the model predicts the characteristics of the regulatory sequence data at the next time point based on the characteristics of the regulatory sequence data and the density of personnel at the current time point. The predicted regulatory sequence data characteristics It contains the control parameters of each device in the air conditioning heat transfer system at the next time point, such as fan speed, etc. However, this part combines the external feature, that is, the number of people in the room at the next time point, to determine whether to apply the previously predicted and outputted If the indoor population density ρ(t+1) at time t+1 satisfies the predicted indoor population density , then the previous prediction output can be executed If the number of people exceeds the limit, it is necessary to combine the actual number of people at the current time t+1 and the operating power consumption parameters at the current time t+1, return to the previous step, and re-predict by the first layer (bidirectional) LSTM of the heat transfer intelligent adjustment LSTM model to avoid the situation where the system control strategy is not adjusted in time due to changes in environmental characteristics and the indoor air-conditioning temperature does not match the actual number of people.

[0287] Please understand the application of the above model in conjunction with the description of the previous steps S3 and S4, which will not be repeated here.

[0288] Figure 4 1 is a block diagram of an air conditioning heat transfer intelligent adjustment system according to an exemplary embodiment, the system is used for an air conditioning heat transfer intelligent adjustment method. Figure 4 The system includes a data acquisition module 401, a data processing module 402, a heat transfer intelligent prediction module 403, and a heat transfer response module 404. Among them:

[0289] The data acquisition module 401 is used to monitor the operating power consumption parameters of the air conditioning heat transfer system according to the preset air conditioning working time point: the refrigerant heat cycle heat, the heat load change rate and the compressor power consumption, and the indoor three-dimensional image at the air conditioning working time point and upload it to the air conditioning backend server;

[0290] A data processing module 402, configured to calculate the indoor personnel density in the indoor three-dimensional image at the air conditioner working time point by the air conditioner background server, and input the operation power consumption parameter and the indoor personnel density at the air conditioner working time point into a pre-deployed heat transfer intelligent regulation LSTM model;

[0291] A heat transfer intelligent prediction module 403, configured to predict the regulation sequence data feature at the air conditioner working time point through the heat transfer intelligent regulation LSTM model according to the operation power consumption parameter, and use the regulation sequence data feature and the indoor personnel density as input sequences, and predict again based on the feature correlation between the front and back time points, and output the regulation sequence data feature at the next air conditioner working time point and the corresponding indoor personnel density ;

[0292] A heat transfer response module 404, configured to monitor the indoor personnel density ρ(t + 1) at the next air conditioner working time point, and judge whether the following conditions are satisfied:

[0293] ,

[0294] If it holds, then when reaching the next air conditioner working time point, parse and execute the system heat transfer control parameter in the regulation sequence data feature for automatic adjustment of air conditioner heat transfer;

[0295] Otherwise, use the operation power consumption parameter and the indoor personnel density ρ(t + 1) at the next air conditioner working time point as input sequences, predict the regulation sequence data feature at the next air conditioner working time point by the heat transfer intelligent regulation LSTM model, and parse and execute.

[0296] For the corresponding functions and interactions of the above-mentioned modules, please understand in combination with the corresponding steps of the previous method.

[0297] Figure 5 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. As Figure 5 shown, the electronic device may include the above-mentioned Figure 4 shown air conditioner heat transfer intelligent regulation system. Optionally, the electronic device 410 may include a first processor 2001.

[0298] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003.

[0299] Among them, the first processor 2001 is connected to the memory 2002 and the transceiver 2003, such as through a communication bus.

[0300] Next, in combination with Figure 5Specifically introduce each component of the electronic device 410:

[0301] Among them, the first processor 2001 is the control center of the electronic device 410, which can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or can be an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. For example: one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs).

[0302] Optionally, the first processor 2001 can execute various functions of the electronic device 410 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0303] In a specific implementation, as an embodiment, the first processor 2001 can include one or more CPUs, such as Figure 5 CPU0 and CPU1 shown in

[0304] In a specific implementation, as an embodiment, the electronic device 410 can also include multiple processors, such as Figure 5 the first processor 2001 and the second processor 2004 shown in

[0305] Among them, the memory 2002 is used to store software programs for executing the solutions of the present invention and is controlled by the first processor 2001 for execution. The specific implementation method can refer to the above method embodiments and will not be elaborated here.

[0306] Optionally, the memory 2002 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001 or may exist independently and be coupled to the first processor 2001 through an interface circuit ( Figure 5 not shown) of the electronic device 410. The embodiments of the present invention do not make specific limitations in this regard.

[0307] The transceiver 2003 is used to communicate with a network device or communicate with a terminal device.

[0308] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 5 not shown separately). Among them, the receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.

[0309] Optionally, the transceiver 2003 may be integrated with the first processor 2001 or may exist independently and be coupled to the first processor 2001 through an interface circuit ( Figure 5 not shown) of the electronic device 410. The embodiments of the present invention do not make specific limitations in this regard.

[0310] It should be noted that Figure 5 the structure of the electronic device 410 shown does not constitute a limitation on the router. The actual knowledge structure recognition device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0311] In addition, the technical effects of the electronic device 410 may refer to the technical effects of the air-conditioning heat transfer intelligent adjustment method described in the above method embodiments, and will not be elaborated here.

[0312] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0313] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM) or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DR RAM).

[0314] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0315] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be understood specifically by referring to the context before and after.

[0316] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0317] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0318] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0319] Those skilled in the art can clearly understand that for the sake of convenience and brevity of description, the specific working processes of the devices, systems, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0320] In several embodiments provided by the present invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of systems or units can be in electrical, mechanical, or other forms.

[0321] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0322] In addition, the functional units in various embodiments of the present invention can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0323] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0324] As described above, the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An intelligent adjustment method for air conditioner heat transfer, characterized in that The method includes: S1. Monitor the operating power consumption parameters of the air-conditioning heat transfer system at a preset air-conditioning operating time point: the refrigerant heat cycle heat, the heat load change rate, the compressor power consumption, and the indoor three-dimensional image at the air-conditioning operating time point, and upload them to the air-conditioning background server; S2. The air-conditioning background server calculates the indoor personnel density in the indoor three-dimensional image at the air-conditioning operating time point, and inputs the operating power consumption parameters and the indoor personnel density at the air-conditioning operating time point into a pre-deployed heat transfer intelligent regulation LSTM model; S3. Based on the operating power consumption parameters, the heat transfer intelligent adjustment LSTM model predicts the regulatory sequence data characteristics of the air conditioner operating time point, and uses the regulatory sequence data characteristics and the indoor personnel density as the input sequence. Again, based on the feature correlation between the front and back time points, it makes a prediction and outputs the regulatory sequence data characteristics of the next air conditioner operating time point and the corresponding indoor personnel density ; S4. Monitor the indoor personnel density ρ(t + 1) at the next air conditioner working time point, and determine whether the following conditions are met: If it holds, then when reaching the next air conditioner working time point, analyze and execute the control sequence data features in the system heat transfer control parameters for automatic adjustment of air conditioner heat transfer; otherwise, use the operating power consumption parameters at the next air conditioner working time point and the indoor personnel density ρ(t + 1) as the input sequence, predict the control sequence data features at the next air conditioner working time point by the heat transfer intelligent adjustment LSTM model, and analyze and execute them; The method for generating the thermal transfer intelligent regulation LSTM model includes: collecting big data of historical regulation sequences of the air conditioner thermal transfer system: Data(T)=∏Data(t), Data(T + 1)=∏Data(t + 1), where Data(T) and Data(T + 1) are historical regulation sequence data at time points (t) and (t + 1) respectively; the historical regulation sequence data = {refrigerant heat cycle heat, heat load change rate, compressor power consumption, system thermal transfer control parameters: fan speed, air deflector angle, compressor frequency and electronic expansion valve}; respectively collecting indoor three-dimensional images at time points (t) and (t + 1), and based on the indoor three-dimensional images, using computer vision algorithms to analyze the three-dimensional images, detecting the number and position of indoor people, and analyzing and calculating the indoor people density at time points (t) and (t + 1): ρ(t) and ρ(t + 1); constructing a regulation sequence data set with X = {[Data(T - n), ρ(t - n)],...[Data(T), ρ(t)]} as the input sequence and as the output result, where represents the system thermal transfer control parameters at time point (t + 1); dividing the regulation sequence data set into a training set and a validation set according to a preset ratio; inputting the training set into a pre-constructed LSTM model, and having the model train and learn the regulation sequence data features of X in the training set and the regulation sequence data features associated before and after between time points (t) and (t + 1), to construct a thermal transfer intelligent regulation LSTM model with X as the input sequence and Y as the output result; using the validation set to verify the prediction performance of the thermal transfer intelligent regulation LSTM model: if the verification passes, then deploy and apply the thermal transfer intelligent regulation LSTM model to the air conditioner background server; if the verification fails, then repeat the above steps to reconstruct the thermal transfer intelligent regulation LSTM model.

2. The intelligent adjustment method for heat transfer of an air conditioner according to claim 1, characterized in that, The calculation method of the operating power consumption parameters includes: (1) Refrigerant heat cycle heat Evaporator evap heat absorption: ， Condenser cond heat release: , wherein, is the refrigerant mass flow rate, which is positively correlated with the opening degree of the electronic expansion valve of the air conditioner; h is the specific enthalpy value, and its subscripts (evap, out), (evap, in), (cond, out), (cond, in) represent the evaporator outlet, evaporator inlet, condenser outlet, and condenser inlet respectively; (2) Heat load change rate setting: ， Wherein: , The calculated heat load: ; By introducing time t, the heat load is calculated: The rate of change of the heat load varying with time t: ; Among them, is the equivalent heat capacity of the room, is the specific heat capacity of air (1.005 kJ / kg·K), is the outlet temperature of the room air conditioner, is the outlet temperature of the evaporator; is the supply air mass flow rate, which is positively correlated with both the fan speed and the air deflector angle of the air conditioner. (3) Compressor power consumption setting: , where is the isentropic efficiency of the compressor, ranging from 0.65 to 0.

85.

3. The intelligent adjustment method for air-conditioning heat transfer according to claim 1, characterized in that The LSTM model adopts a double-layer LSTM architecture structure, including: an input layer for sequentially inputting X or (X, Y); a first-layer bidirectional LSTM for training and learning the regulatory sequence data features of X; a second-layer bidirectional LSTM for training and learning the regulatory sequence data features related before and after in (X, Y); and an output layer for outputting the prediction result.

4. An intelligent air-conditioning heat transfer adjustment system, which is used to implement the air-conditioning heat transfer adjustment method according to any one of claims 1-3, and is characterized in that, The system includes: A data acquisition module for monitoring the operating power consumption parameters of the air-conditioning heat transfer system at a preset air-conditioning operating time point: the refrigerant heat cycle heat, the heat load change rate, the compressor power consumption, and the indoor three-dimensional image at the air-conditioning operating time point, and uploading them to the air-conditioning background server; A data processing module for the air-conditioning background server to calculate the indoor personnel density in the indoor three-dimensional image at the air-conditioning operating time point, and input the operating power consumption parameters and the indoor personnel density at the air-conditioning operating time point into a pre-deployed heat transfer intelligent regulation LSTM model; The heat transfer intelligent prediction module is used to predict the control sequence data features of the air conditioner working time point according to the operating power consumption parameters through the heat transfer intelligent regulation LSTM model, and use the control sequence data features and the indoor personnel density as the input sequence, and predict again based on the feature correlation between the front and back time points, and output the control sequence data features of the next air conditioner working time point and the corresponding indoor personnel density; the heat transfer response module is used to monitor the indoor personnel density ρ(t + 1) at the next air conditioner working time point and judge whether the following conditions are satisfied: , if it holds, then when the next air conditioner working time point is reached, parse and execute the system heat transfer control parameters in the control sequence data features to perform automatic adjustment of air conditioner heat transfer; otherwise, use the operating power consumption parameters at the next air conditioner working time point and the indoor personnel density ρ(t + 1) as the input sequence, and predict the control sequence data features of the next air conditioner working time point by the heat transfer intelligent regulation LSTM model, and parse and execute them.

5. An electronic device, characterized in that, The electronic device includes: a processor; a memory, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, the method described in any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program codes, and the program codes can be called by the processor to execute the method described in any one of claims 1 to 3.

Images