Energy-saving optimization control method for an air-conditioning rotary wheel dehumidification system based on a mechanism model

Abstract

The present invention discloses an energy-saving optimization control method for an air-conditioning rotary wheel dehumidification system based on a mechanism model, belonging to the technical field of air-conditioning energy-saving control. Specifically, it includes: establishing and validating a mechanism model by collecting historical operation data; based on the validated model, using a model predictive control method to predict the system state, and applying an adaptive learning algorithm and a deep reinforcement learning algorithm to adaptively adjust the model and the predictive control method; using the adjusted model and predictive control method, combining the current state and load prediction, and calculating the optimal control input through an optimization algorithm; real-time monitoring the system operation data, and using an intelligent decision-making algorithm and a deep reinforcement learning algorithm to correct and optimize the model; applying the optimal control input to the system, implementing the control strategy, evaluating the effect and optimizing the control strategy to achieve efficient and intelligent dehumidification control.

Description

Technical Field

[0001] The present invention belongs to the technical field of air-conditioning energy-saving control, and specifically relates to an energy-saving optimization control method for an air-conditioning rotary wheel dehumidification system based on a mechanism model. Background Art

[0002] In industrial production and living environments, the control of air humidity is crucial. The air-conditioning rotary wheel dehumidification system is a common dehumidification device widely used in industrial, commercial, and civil buildings to adjust air humidity. However, traditional control methods mainly rely on empirical rules or simple feedback control, making it difficult to achieve the optimal operation of the system, resulting in a high energy consumption problem. The existing control methods mainly rely on empirical rules or simple feedback control, making it difficult to achieve the optimal operation of the system, and most of them are based on experience or simple set-point control, without fully considering the complex relationships between the various parameters in the system and the changes in the actual operating conditions, leading to serious energy waste and high operating costs. With the increasing requirements for energy conservation and emission reduction, how to reduce the system energy consumption through an optimized control method has become an urgent problem to be solved.

[0003] For example, the Chinese patent with the authorization announcement number CN115325665B discloses an energy-saving optimization control method, device, and system for a central air conditioner, including: outputting a test instruction for selecting a system operation mode in response to a startup instruction; selecting an operating parameter combination in a preset database in response to the test instruction, and sending a current round of test requests to the central air-conditioning system according to the operating parameter combination; receiving the energy efficiency detection result obtained by the central air-conditioning system operating in response to the test request, and outputting the next round of test instructions based on the mapping relationship table in the preset detection mechanism for the energy efficiency detection result; repeating multiple rounds of tests, and when the number of operating parameter combinations that have been run reaches a set proportion of the total number of all operating parameter combinations in the database, outputting the operating parameter combination with the highest energy efficiency as the final detection result and configuring the final detection result into the central air-conditioning system. This technical solution has the effect of facilitating the central air-conditioning system to maintain efficient operation.

[0004] For example, the Chinese patent with the authorization announcement number CN104633857B discloses an air-conditioning energy-saving optimization control method and device, including: collecting and storing the current operating parameters of the chiller unit, chilled water pump, and cooling water pump of the air-conditioning system at a preset period; determining the energy consumption increment of the air-conditioning system in the operating state of the to-be-adjusted operating parameters relative to the current operating state according to the current operating parameters and the to-be-adjusted operating parameters input by the user; when the energy consumption increment is less than zero, adjusting the operating state of the air-conditioning system according to the to-be-adjusted operating parameters. The air-conditioning control method and device provided by this technical solution adjust the air-conditioning system according to the to-be-adjusted operating parameters when the energy consumption increment is less than zero, achieving energy conservation and being easy to implement.

[0005] The existing technologies above have the following problems: lack of utilization of the inherent physical laws of the system and lack of consideration of the comprehensive physical characteristics of the system; relying on the combination of operating parameters in the preset database for testing and lacking real-time adaptability; lacking dynamic adjustment ability and long-term optimization ability, and causing energy consumption and resource waste. Summary of the Invention

[0006] In view of the deficiencies of the existing technologies, the present invention proposes an energy-saving optimization control method for an air-conditioning rotary wheel dehumidification system based on a mechanism model. By collecting historical operation data, a mechanism model is established and verified; based on the verified model, a model predictive control method is used to predict the system state, and an adaptive learning algorithm and a deep reinforcement learning algorithm are used to adaptively adjust the model and the model predictive control method; using the adjusted model and the model predictive control method, combined with the current state and load prediction, the optimal control input is calculated through an optimization algorithm; the system operation data is monitored in real time, and an intelligent decision-making algorithm and a deep reinforcement learning algorithm are used to correct and optimize the model; the optimal control input is applied to the system, the control strategy is implemented, the effect is evaluated, and the control strategy is optimized to achieve efficient and intelligent dehumidification control.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] An energy-saving optimization control method for an air-conditioning rotary wheel dehumidification system based on a mechanism model, comprising:

[0009] Step S1: Collect the historical operation data of the air-conditioning rotary wheel dehumidification system, establish a mechanism model of the air-conditioning rotary wheel dehumidification system, and verify the mechanism model;

[0010] Step S2: Based on the verified mechanism model, adopt a model predictive control method to predict the operation state of the air-conditioning rotary wheel dehumidification system, and according to the prediction result and the operation data collected in real time, use an adaptive learning algorithm and a deep reinforcement learning algorithm to adaptively adjust the mechanism model and the model predictive control method;

[0011] Step S3: Based on the mechanism model after adaptive adjustment, predict the current operation state and load of the air-conditioning rotary wheel dehumidification system, and calculate the optimal control input through an optimization algorithm;

[0012] Step S4: Use an intelligent decision-making algorithm and a deep reinforcement learning algorithm to correct and optimize and iterate the mechanism model after adaptive adjustment;

[0013] Step S5: Apply the calculated optimal control input to the air-conditioning rotary wheel dehumidification system, implement the control strategy, monitor the operation state and energy consumption of the system in real time, evaluate the effect of the control strategy, and adjust and optimize the control strategy according to the evaluation result.

[0014] Specifically, the specific steps for establishing the mechanism model of the air-conditioning rotary wheel dehumidification system in step S1 include:

[0015] S1.1: Collect the historical operation data of the air-conditioning rotary wheel dehumidification system and perform preprocessing;

[0016] S1.2: Determine the scope of the air-conditioning rotary wheel dehumidification system and analyze the functions of each component; the components include a rotary wheel dehumidifier, a regeneration heating device, a fan, and an air treatment channel;

[0017] S1.3: According to the analysis results of S1.2, considering the adsorption characteristics of the desiccant and the mass and heat transfer processes, establish a rotary wheel moisture absorption and desorption model , the rotary wheel moisture absorption and desorption model includes an adsorption isotherm model and a mass and heat transfer model, where q represents the adsorption amount of the desiccant, represents the maximum adsorption amount, K represents the adsorption equilibrium constant, represents the water vapor partial pressure, represents the water vapor density, represents the control volume, and respectively represent the water vapor mass flow rates entering and leaving the control volume, represents the adsorption mass flow rate of the desiccant, t represents time, represents the air density, represents the specific heat capacity at constant pressure of air, T represents the air temperature, and respectively represent the heat flow rates entering and leaving the control volume, represents the adsorption heat flow rate, represents the partial derivative;

[0018] S1.4: Similarly, based on the analysis results of S1.2, according to the thermodynamic properties of air, establish an air heat and moisture exchange model , where, represents the air mass flow rate, and respectively represent the moisture content of the air when entering and leaving the rotary wheel, represents the change in the mass flow rate of water vapor in the air, and respectively represent the enthalpy values of the air when entering and leaving the rotary wheel, represents the sensible heat exchange amount, represents the latent heat exchange amount;

[0019] S1.5: According to the fan and the heating device, establish a component characteristic model , where, represents the wind pressure of the fan, Q represents the air volume of the fan, 、 , represents the fitting coefficient, where \(P\) represents the heating power, \(V\) represents the voltage, and \(I\) represents the current.

[0020] Specifically, the specific steps of establishing the mechanism model of the air-conditioning rotary wheel dehumidification system in step S1 further include:

[0021] S1.6: Integrate the rotary wheel moisture absorption and dehumidification model, the air heat and moisture exchange model, and the component characteristic model to form the mechanism model of the air-conditioning rotary wheel dehumidification system;

[0022] S1.7: Use the finite difference method to discretize the mechanism model equation of the air-conditioning rotary wheel dehumidification system into difference equations and solve them to obtain the operating state parameters of the air-conditioning rotary wheel dehumidification system under different working conditions;

[0023] S1.8: Verify the output results of the mechanism model of the air-conditioning rotary wheel dehumidification system according to the preprocessed historical operation data. By comparing the mechanism model prediction results with the actual operation data, calculate the mean square error index;

[0024] If the mean square error index is less than or equal to the preset threshold, the mechanism model is considered valid;

[0025] If the mean square error index is greater than the preset threshold, adjust the mechanism model.

[0026] Specifically, the specific steps of S1.7 include:

[0027] S1.71: Obtain the mechanism model of the air-conditioning rotary wheel dehumidification system, and perform spatial domain and time domain discretization to generate the mechanism model equation; the spatial domain divides the solution region of the rotary wheel dehumidification system into a series of uniform grid points; the time domain is divided into discrete time steps;

[0028] S1.72: For each grid unit, transform the mechanism model equation into a difference equation through the forward difference format;

[0029] S1.73: Organize the discretized difference equations into the form of a linear algebraic equation set, and use the Jacobi iterative method to solve the linear algebraic equation set to obtain the variable values of each grid node at different time steps, that is, the operating state parameters of the system.

[0030] Specifically, the specific steps of step S2 include:

[0031] S2.1: Set the prediction horizon and the control horizon , and establish an objective function \(J\) according to the operation target of the air-conditioning rotary wheel dehumidification system. The formula is:

[0032] ;

[0033] Among them, represents the system state at time k + 1 predicted based on the information at time k, represents the state variable of the air-conditioning rotary wheel dehumidification system at time k, E represents the state error, represents the control input at time k, and R represents the weighting matrix of the control input;

[0034] S2.2: Using the verified mechanism model, combined with the current operating state and interference factor results of the air-conditioning rotary wheel dehumidification system, predict the operating state of the air-conditioning rotary wheel dehumidification system within the set prediction time domain;

[0035] S2.3: Use sensors to collect the operating data of the air-conditioning rotary wheel dehumidification system in real time, compare the operating state within the time domain in S2.2 with the real-time collected data, and calculate the error between the two;

[0036] S2.4: According to the error result, use the adaptive learning algorithm based on the least squares method to adjust the parameters of the mechanism model.

[0037] Specifically, the specific steps of step S2 further include:

[0038] S2.5: Take the operating state of the air-conditioning rotary wheel dehumidification system as the state space and the control input as the action space, and define the reward function according to the operating target of the system ; The control input includes the rotary wheel speed and the heating power; the operating targets include energy saving and humidity control accuracy, where z represents the air-conditioning rotary wheel dehumidification system, g represents the control action, and represent the weighting coefficients, G represents the system energy consumption, hum represents the operating state of the air-conditioning rotary wheel dehumidification system, represents the reference value of the operating state of the air-conditioning rotary wheel dehumidification system;

[0039] S2.6: Use the deep reinforcement learning algorithm to learn the optimal control strategy by interacting with the air-conditioning rotary wheel dehumidification system;

[0040] S2.7: Update the control strategy in the model predictive control method according to the optimal strategy learned by the deep reinforcement learning model.

[0041] Specifically, the specific steps of step S3 include:

[0042] S3.1: Obtain the mechanism model after adaptive adjustment and the current operating data of the air-conditioning rotary wheel dehumidification system;

[0043] S3.2: Based on the historical operation data, use the time series analysis method to predict the load of the air-conditioning rotary wheel dehumidification system; the load includes dehumidification load, heating load, and ventilation load;

[0044] S3.3: Determine the constraint conditions according to the operation requirements of the air-conditioning rotary wheel dehumidification system , where and respectively represent the lower limit and upper limit of the rotary wheel speed, represents the rotary wheel speed at time k, and respectively represent the lower limit and upper limit of the heating power, represents the heating power at time k, and respectively represent the allowable lower limit and upper limit of the air humidity, represents the air humidity at time k.

[0045] Specifically, the specific steps of step S3 further include:

[0046] S3.4: Substitute the current operating state, load prediction result, objective function, and constraint conditions into the genetic algorithm. The genetic algorithm searches for the control input combination that makes the objective function reach the optimal value through iterative calculation; the control inputs include the speed of the rotary wheel, the power of the heating device, and the air volume of the fan;

[0047] S3.5: Verify the calculated optimal control input to check whether it meets the physical feasibility and operation requirements of the system;

[0048] If the optimal control input does not meet the constraint conditions or causes the system to operate unstably, re-adjust the parameters of the genetic algorithm and perform the calculation again.

[0049] Specifically, the model predictive control algorithm predicts the operation results of the air-conditioning rotary wheel dehumidification system under different control strategies based on the current operating state and load prediction of the system, and obtains the optimal control parameters, including the rotary wheel speed, heating power, and fan frequency, through optimization calculation.

[0050] Specifically, the mechanism model includes the adsorption and desorption processes of the rotary wheel and the heat exchange process of air flow; the historical operation data of the air-conditioning rotary wheel dehumidification system includes indoor and outdoor air humidity, temperature, air volume, and energy consumption; the optimal control inputs include the optimal speed of the rotary wheel, the optimal power of the heating device, and the optimal frequency of the fan.

[0051] Compared with the prior art, the beneficial effects of the present invention are:

[0052] The present invention proposes an energy-saving optimization control method for an air-conditioning rotary wheel dehumidification system based on a mechanism model. By collecting historical operation data to establish a mechanism model and using a model predictive control method to predict the system state, combined with an adaptive learning algorithm and a deep reinforcement learning algorithm, the model and the predictive control method are adaptively adjusted, thereby realizing efficient and precise control of the air-conditioning rotary wheel dehumidification system. It can not only improve the operation efficiency of the system, but also effectively reduce energy consumption and achieve the goal of energy conservation and emission reduction.

[0053] The present invention also proposes an energy-saving optimization control method for an air-conditioning rotary wheel dehumidification system based on a mechanism model. By real-time monitoring of the system operation data, using an intelligent decision-making algorithm and a deep reinforcement learning algorithm to correct and optimize the mechanism model iteratively, ensuring that the model always reflects the latest state of the system. This real-time feedback and iterative optimization mechanism enables the control strategy to continuously adapt to changes in the system environment, further improving the stability and reliability of the system. Brief Description of the Drawings

[0054] Figure 1 It is a schematic diagram of the energy-saving optimization control method for the air-conditioning rotary wheel dehumidification system based on the mechanism model of the present invention;

[0055] Figure 2 It is a principle flow chart of the energy-saving optimization control method for the air-conditioning rotary wheel dehumidification system based on the mechanism model of the present invention;

[0056] Figure 3 It is a flow chart for constructing the mechanism model of the energy-saving optimization control method for the air-conditioning rotary wheel dehumidification system based on the mechanism model of the present invention. Detailed Embodiments

[0057] Embodiment 1

[0058] Please refer to Figure 1 - Figure 2 , an embodiment provided by the present invention: an energy-saving optimization control method for an air-conditioning rotary wheel dehumidification system based on a mechanism model, including the following steps:

[0059] Step S1: Collect the historical operation data of the air-conditioning rotary wheel dehumidification system, establish a mechanism model of the air-conditioning rotary wheel dehumidification system, and verify the mechanism model;

[0060] Furthermore, the process of collecting historical operation data includes:

[0061] (1) Data collection:

[0062] Determine the types and ranges of data to be collected, such as temperature, humidity, pressure, flow rate, and key energy consumption parameters;

[0063] Select appropriate data collection devices and sensors to ensure the accuracy and reliability of the data;

[0064] Set the frequency and time range of data collection to obtain sufficient historical operation data.

[0065] (2)Data preprocessing:

[0066] Clean the collected data to remove outliers and noise;

[0067] Normalize the data to make different parameters comparable;

[0068] Sort the data according to the time series for subsequent modeling and analysis.

[0069] Step S2: Based on the verified mechanism model, adopt the model predictive control method to predict the operating state of the air-conditioning rotary wheel dehumidification system, and according to the prediction results and the real-time collected operating data, use the adaptive learning algorithm and the deep reinforcement learning algorithm to dynamically adjust the mechanism model and the model predictive control method;

[0070] Step S3: Based on the mechanism model after adaptive adjustment, predict the current operating state and load of the air-conditioning rotary wheel dehumidification system, and calculate the optimal control input through the optimization algorithm;

[0071] Step S4: Use the intelligent decision-making algorithm and the deep reinforcement learning algorithm to correct and optimize the mechanism model after adaptive adjustment iteratively;

[0072] Further, the specific steps of Step S4 include:

[0073] (1)Obtain the mechanism model after adaptive adjustment;

[0074] (2)Collect and preprocess the system operation data;

[0075] (3)Use the fuzzy logic algorithm to preliminarily correct the mechanism model after adaptive adjustment. At the same time, use the deep reinforcement learning algorithm to further optimize the mechanism model and update the parameters. Among them, the fuzzy logic algorithm is the existing technical content in this field and is not the creative solution of this application, so it will not be elaborated here;

[0076] (4)Evaluate the performance of the corrected and optimized mechanism model, and calculate the error index. In the present invention, the error index adopts the mean square error, and the mean square error is the existing technical content in this field and is not the creative solution of this application, so it will not be elaborated here;

[0077] (5)Judge whether the termination condition is satisfied. If not, return to (3) to continue the iteration;

[0078] (6)Output the corrected and optimized mechanism model.

[0079] Step S5: Apply the calculated optimal control input to the air-conditioning rotary wheel dehumidification system, implement the control strategy, monitor the operating status and energy consumption of the system in real time, evaluate the effect of the control strategy, and adjust and optimize the control strategy according to the evaluation results.

[0080] Further, the specific steps of Step S5 include:

[0081] (1) Convert the calculated optimal control input, such as the rotary wheel speed, heating power, and fan air volume, into control signals for the actuators of the air-conditioning rotary wheel dehumidification system. For example, convert digital signals into analog voltage or current signals. Among them, digital-to-analog conversion is the prior art content in this field and is not the creative solution of this application, so it will not be elaborated here;

[0082] (2) Transmit the control signals to the actuators of the air-conditioning rotary wheel dehumidification system, such as frequency converters and heater controllers, through the control system, so that the system operates according to the optimal control input; the frequency converter is used to adjust the rotary wheel speed and fan air volume; the heater controller is used to adjust the heating power;

[0083] (3) Obtain the real-time operation data, and transmit the collected real-time operation data to the monitoring center through the wireless communication network and store it in real time for subsequent analysis and processing;

[0084] (4) Set the indicators for evaluating the effect of the control strategy according to the operation objectives of the system, including the energy consumption reduction rate, humidity control accuracy, and temperature stability;

[0085] (5) Calculate the values of each evaluation index according to the real-time monitored data. For example, the energy consumption reduction rate can be calculated by comparing the current energy consumption with the historical energy consumption or the reference energy consumption; the humidity control accuracy can be evaluated by calculating the deviation between the actual humidity and the set humidity;

[0086] (6) Compare the calculated evaluation index values with the pre-set expected goals to judge whether the control strategy has achieved the expected effect;

[0087] If there is a deviation between the evaluation index value and the expected goal, analyze the reasons for the deviation. The reasons for the deviation include inaccurate models, changes in external interference factors, and actuator failures;

[0088] (7) Adjust the control strategy according to the deviation reasons. For example, if the energy consumption reduction rate does not reach the expected goal, the heating power can be appropriately reduced or the rotary wheel speed can be adjusted; if the humidity control accuracy is not high, the dehumidification time can be increased or the ventilation volume can be adjusted;

[0089] (8) Use the adjusted control strategy, combined with the current operating status and load prediction of the system, to recalculate the optimal control input to achieve the optimization of the control strategy.

[0090] Exemplarily, the air humidity in the drug production workshop of a large pharmaceutical factory is required to be extremely strict, and the humidity needs to be controlled between 30% - 40%RH to ensure the stable quality of drugs. The original air-conditioning rotary wheel dehumidification system uses traditional control methods, with high energy consumption and insufficient humidity control accuracy, and the humidity fluctuation often exceeds the allowable range. To solve these problems, an energy-saving optimization control method based on a mechanism model is used to upgrade and transform the system, including:

[0091] Within one month, historical operation data of the air-conditioning rotary wheel dehumidification system is collected in real time using high-precision sensors, including data such as the temperature and humidity of indoor and outdoor air, the rotational speed of the rotary wheel, the temperature and flow rate of the regeneration air, the operating frequency of the fan, and the energy consumption of the system. Among them, the collection frequency is set to once per minute to ensure the integrity and accuracy of the data; determine the system scope, clearly including components such as the rotary wheel dehumidifier, regeneration heating device, fan, and air treatment channel. Considering the adsorption characteristics of the desiccant and the mass and heat transfer processes, use the Langmuir adsorption isotherm model and the mass and energy conservation equations to establish a rotary wheel moisture absorption and dehumidification model. According to the thermodynamic properties of air, establish an air heat and moisture exchange model to describe the temperature and humidity changes of air in the system. For the fan and heating device, establish their performance characteristic models respectively, such as the air volume - pressure - power relationship model of the fan and the relationship model between the heating power of the heating device and temperature and energy consumption, and integrate the above sub-models to form a complete mechanism model of the air-conditioning rotary wheel dehumidification system; use the historical operation data of the second half of the month collected to verify the mechanism model. By comparing the predicted operation state parameters of the model, such as air humidity and temperature with the actual measured values, calculate the mean square error and mean absolute error. After multiple parameter adjustments and optimizations, control the error within 5%, indicating that the mechanism model has high accuracy and reliability; based on the verified mechanism model, adopt the model predictive control method, with the next 24 hours as the prediction time domain, predict the operation state of the air-conditioning rotary wheel dehumidification system. Considering factors such as the production plan of the pharmaceutical production workshop and weather changes, predict parameters such as air humidity, temperature, and energy consumption at different times; collect the operation data of the system in real time, compare the prediction results with the real-time data, adopt an adaptive learning algorithm, and dynamically adjust the parameters of the mechanism model according to the error between the two to improve the adaptability of the model. At the same time, introduce a deep reinforcement learning algorithm, and continuously optimize the control strategy of the model predictive control method through a reward mechanism, so that the system can better cope with various complex working conditions; combine factors such as the production plan of the pharmaceutical production workshop, personnel flow, and outdoor weather changes to predict the load of the air-conditioning rotary wheel dehumidification system. For example, during the production peak period, the heat and moisture generated by personnel and equipment in the workshop increase, and the system load increases accordingly. During the night rest period, the load is relatively low; based on the mechanism model and model predictive control method after adaptive adjustment, adopt the genetic algorithm as the optimization algorithm, with the minimum system energy consumption as the objective function, and calculate the optimal control input according to the current operation state and load prediction, including the optimal rotational speed of the rotary wheel, the optimal power of the heating device, the optimal frequency of the fan, etc.;

[0092] Install multiple high-precision sensors at key positions in the air-conditioning rotary wheel dehumidification system to monitor the operating status of the system in real time, including parameters such as the temperature, humidity, and flow rate of the air, the rotational speed of the rotary wheel, and the temperature and power of the heating device. Among them, the data of the sensors is updated every 10 seconds to ensure that the real-time changes of the system can be reflected in a timely manner. Input the real-time monitored operating data into the mechanism model, and use intelligent decision-making algorithms to judge whether the mechanism model needs to be corrected according to the changes in the data. At the same time, use the deep reinforcement learning algorithm to iteratively update the mechanism model through continuous learning and optimization, so that the mechanism model can more accurately reflect the actual operating conditions of the system. Send the calculated optimal control input to the actuators of the air-conditioning rotary wheel dehumidification system, such as adjusting the rotational speed of the rotary wheel motor, the power of the heating device, and the frequency of the fan, to implement the control strategy. Monitor the operating status and energy consumption of the system in real time, compare the air humidity control accuracy and system energy consumption before and after implementing the control strategy, and set evaluation indicators such as the humidity control error rate and the energy consumption reduction rate. If the humidity control error rate exceeds 3% or the energy consumption reduction rate fails to reach the expected target, then according to the evaluation results, re-adjust the parameters in the control strategy, such as adjusting the prediction horizon of the model predictive control method and the parameters of the optimization algorithm, for re-optimization. After running for a predetermined time, the energy-saving optimization control method of this air-conditioning rotary wheel dehumidification system has achieved good results. The air humidity control accuracy has been significantly improved, and the humidity fluctuation range is controlled within ±1% RH, meeting the strict requirements of the pharmaceutical production workshop. At the same time, the system energy consumption has been reduced by more than 25%, reducing the production cost.

[0093] Embodiment 2

[0094] Please refer to Figure 3 , in this embodiment, the specific steps of establishing the mechanism model of the air-conditioning rotary wheel dehumidification system in step S1 include:

[0095] S1.1: Collect the historical operating data of the air-conditioning rotary wheel dehumidification system and perform preprocessing;

[0096] S1.2: Determine the scope of the air-conditioning rotary wheel dehumidification system and analyze the functions of each component; the components include a rotary wheel dehumidifier, a regeneration heating device, a fan, and an air treatment channel;

[0097] Furthermore, analyzing the functions of each component is to understand the role of each component in the dehumidification process. For example, the rotary wheel dehumidifier realizes dehumidification by adsorbing moisture with a desiccant, and the regeneration heating device provides the heat required for the regeneration of the rotary wheel.

[0098] S1.3: According to the analysis results of S1.2, considering the adsorption characteristics of the desiccant and the mass and heat transfer processes, establish a rotary wheel moisture adsorption and desorption model , the rotary wheel moisture adsorption and desorption model includes an adsorption isotherm model and a mass and heat transfer model, where q represents the adsorption amount of the desiccant, represents the maximum adsorption capacity, and K represents the adsorption equilibrium constant. represents the partial pressure of water vapor. represents the water vapor density. represents the control volume. and respectively represent the mass flow rates of water vapor entering and leaving the control volume. represents the adsorption mass flow rate of the desiccant, and t represents time. represents the air density. represents the specific heat capacity at constant pressure of air, and T represents the air temperature. and respectively represent the heat flow rates entering and leaving the control volume. represents the heat flow rate of adsorption. represents the partial derivative.

[0099] It should be noted that represents the rate of change of the energy of the air in the control volume with respect to time, that is, it reflects the change of energy with time in the control volume due to the comprehensive factors such as the air density, specific heat capacity at constant pressure, temperature, and control volume at different times.

[0100] S1.4: Similarly, based on the analysis results of S1.2, according to the thermodynamic properties of air, an air heat and moisture exchange model is established , where represents the air mass flow rate. and respectively represent the moisture contents of the air when entering and leaving the runner. represents the change in the mass flow rate of water vapor in the air. and respectively represent the enthalpy values of the air when entering and leaving the runner. represents the sensible heat exchange amount. represents the latent heat exchange amount.

[0101] S1.5: According to the described fan and heating device, a component characteristic model is established , where represents the air pressure of the fan, and Q represents the air volume of the fan. , , represent the fitting coefficients. represents the heating power, V represents the voltage, and I represents the current.

[0102] S1.6: Integrate the runner moisture absorption and desorption model, the air heat and moisture exchange model, and the component characteristic model to form a mechanism model of the air-conditioning runner dehumidification system.

[0103] S1.7: Discretize the mechanism model equations of the air-conditioning rotary wheel dehumidification system into difference equations using the finite difference method and solve them to obtain the operating state parameters of the air-conditioning rotary wheel dehumidification system under different working conditions;

[0104] S1.8: Verify the output results of the mechanism model of the air-conditioning rotary wheel dehumidification system based on the preprocessed historical operation data. By comparing the prediction results of the mechanism model with the actual operation data, calculate the mean square error index. The calculation formula of the mean square error is the prior art content in the field and is not the creative solution of this application, so it will not be elaborated here;

[0105] If the mean square error index is less than or equal to the preset threshold, the mechanism model is considered valid;

[0106] If the mean square error index is greater than the preset threshold, adjust the mechanism model.

[0107] The specific steps of S1.7 include:

[0108] S1.71: Obtain the mechanism model of the air-conditioning rotary wheel dehumidification system, and perform discretization in the spatial domain and time domain to generate mechanism model equations; the spatial domain is to divide the solution area of the rotary wheel dehumidification system into a series of uniform grid points; the time domain is divided into discrete time steps;

[0109] Further, the specific steps of S1.71 include:

[0110] (1) Sort out the working principles and interaction relationships of each component in the air-conditioning rotary wheel dehumidification system, and summarize the application equations of mass conservation, energy conservation, and mass and heat transfer to form a complete mechanism model;

[0111] (2) According to the geometric shape of the system and the calculation requirements, divide the spatial area of the entire system into multiple small control volumes or grid cells. Exemplarily, for the rotary wheel dehumidifier, it can be divided according to axial, radial and other directions; for the air handling channel, it can be divided according to its length, cross-section, etc.;

[0112] (3) Determine the nodes in each control volume or grid, which will be used to describe physical quantities such as temperature, humidity, and pressure. At the same time, clarify the boundaries of the system, such as the inlet and outlet boundaries, the interfaces with other components, etc., and determine the physical quantity values or boundary condition types on the boundaries;

[0113] (4) Determine the time step according to the dynamic characteristics and calculation accuracy requirements of the air-conditioning rotary wheel dehumidification system , where too small a time step will increase the calculation amount, and too large a time step may affect the calculation accuracy and stability;

[0114] (5) Divide the entire time process into n discrete time nodes ;

[0115] (6) For each discrete control volume and time node, organize the algebraic equations of mass conservation, energy conservation, and mass and heat transfer to form a system of equations containing all unknowns, that is, the system of equations of physical quantities at each node, which is also called the discretized mechanism model equation.

[0116] S1.72: For each grid cell, transform the mechanism model equation into a difference equation through the forward difference scheme;

[0117] Further, the specific steps of S1.72 include:

[0118] (1) Obtain the discretized mechanism model equation;

[0119] (2) Divide the entire computational domain into grids, determine the numbers and positions of each grid cell. At the same time, clarify the variables to be solved in each grid cell, such as temperature, humidity, etc., and mark the values of the variables at the grid nodes;

[0120] (3) For the time derivative term in the mechanism model equation , discretize it using the forward difference scheme. Among them, the formula for the forward difference is: , where represents the variable to be solved, such as temperature, humidity, etc., and represent the values of the variable at the current time step n and the next time step n + 1 respectively, and represent the values of the variable at two adjacent grid nodes i and i + 1 respectively, represents the spatial grid spacing, and x represents the number of spatial grids;

[0121] (4) Replace the time derivative and spatial derivative in the mechanism model equation with the forward difference scheme to obtain a difference equation for the variable values at the grid nodes.

[0122] S1.73: Organize the discretized difference equation into the form of a system of linear algebraic equations, and use the Jacobi iterative method to solve this system of linear algebraic equations to obtain the variable values at each grid node under different time steps, that is, the operating state parameters of the system. Among them, the process of using the Jacobi iterative method to solve the system of linear algebraic equations is the prior art content in this field and is not the creative solution of this application, so it will not be elaborated here.

[0123] The specific steps of step S2 include:

[0124] S2.1: Set the prediction horizon and the control horizon , and according to the operation target of the air-conditioning rotary wheel dehumidification system, an objective function J is established, and the formula is:

[0125] ;

[0126] Among them, represents the system state at the (k + 1)-th moment predicted based on the information at the k-th moment, represents the state variable of the air-conditioning rotary wheel dehumidification system at the k-th moment, E represents the state error, represents the control input at the k-th moment, and R represents the weighting matrix of the control input;

[0127] S2.2: Using the verified mechanism model, combined with the current operation state and interference factor results of the air-conditioning rotary wheel dehumidification system, predict the operation state of the air-conditioning rotary wheel dehumidification system within the set prediction time domain;

[0128] Furthermore, the specific steps of S2.2 include:

[0129] (1) Obtain the verified mechanism model;

[0130] (2) Use various sensors to collect the current operation data of the air-conditioning rotary wheel dehumidification system in real time;

[0131] (3) Identify the interference factors affecting the operation of the air-conditioning rotary wheel dehumidification system, and obtain the predicted values of outdoor environmental parameters through weather forecasting; the interference factors include the changes in outdoor environmental temperature, humidity, wind speed, as well as indoor personnel activities and equipment heat dissipation;

[0132] (4) Obtain the prediction time domain ;

[0133] (5) Take the current operation data and the interference factor results as inputs and substitute them into the verified mechanism model;

[0134] (6) Calculate step by step within the prediction time domain according to the time step, and use the equations and parameters of the mechanism model to calculate the values of the system state variables at each time step in turn;

[0135] (7) Post-process the predicted operation data, such as performing data visualization, analyzing the change trends and characteristics of the data, and outputting the prediction results.

[0136] S2.3: Use sensors to collect the operation data of the air-conditioning rotary wheel dehumidification system in real time, compare the operation state within the time domain in S2.2 with the real-time collected data, and calculate the error between the two;

[0137] S2.4: According to the error results, use an adaptive learning algorithm based on the least squares method to adjust the parameters of the mechanism model. The least squares method is the prior art in this field and is not the creative solution of this application, so it will not be elaborated here.

[0138] S2.5: Take the operating state of the air-conditioning rotary wheel dehumidification system as the state space and the control input as the action space, and define the reward function according to the operating objectives of the system ; The control inputs include the rotary wheel speed and the heating power; the operating objectives include energy conservation and humidity control accuracy. Among them, z represents the state of the air-conditioning rotary wheel dehumidification system, g represents the control action, and represent the weighting coefficients, G represents the system energy consumption, hum represents the operating state of the air-conditioning rotary wheel dehumidification system, represents the reference value of the operating state of the air-conditioning rotary wheel dehumidification system.

[0139] S2.6: Use the deep reinforcement learning algorithm to learn the optimal control strategy by interacting with the air-conditioning rotary wheel dehumidification system;

[0140] Further, the specific steps of S2.6 include:

[0141] (1) Obtain the state space, action space, and reward function;

[0142] (2) Regard the air-conditioning rotary wheel dehumidification system as an environment, and this environment will generate corresponding feedback according to the actions of the intelligent agent; the intelligent agent refers to the controller;

[0143] (3) Construct the state space according to the parameters of the operating state of the air-conditioning rotary wheel dehumidification system;

[0144] (4) Determine the control actions that the intelligent agent can take. In the present invention, for the air-conditioning rotary wheel dehumidification system, the actions usually include adjusting the speed of the rotary wheel, changing the power of the heating device, and adjusting the air volume of the fan, and the action space is discrete. For example, the rotary wheel speed is divided into several fixed gears;

[0145] (5) According to the characteristics and requirements of the problem, use the deep reinforcement learning algorithm based on the deep Q-network to let the intelligent agent interact with the environment to learn:

[0146] The intelligent agent uses the greedy strategy to select an action according to the current state ;

[0147] After executing the action , the environment generates the next state and the reward ;

[0148] Store the sample into the experience replay buffer;

[0149] According to the selected deep reinforcement learning algorithm based on the deep Q-network, update the parameters of the neural network by using the stored samples to optimize the policy;

[0150] (6) When the termination condition is satisfied, stop the training to obtain the learned optimal control policy; the termination condition is the preset number of training steps.

[0151] S2.7: Update the control policy in the model predictive control method according to the optimal policy learned by the deep reinforcement learning model.

[0152] The specific steps of step S3 include:

[0153] S3.1: Obtain the mechanism model after adaptive adjustment and the current operation data of the air-conditioning rotary wheel dehumidification system;

[0154] S3.2: According to the historical operation data, use the time series analysis method to predict the load of the air-conditioning rotary wheel dehumidification system; the load includes the dehumidification load, heating load, and ventilation load. Among them, the time series analysis method is the prior art content in this field and is not the creative solution of this application, so it will not be elaborated here;

[0155] S3.3: Determine the constraint conditions according to the operation requirements of the air-conditioning rotary wheel dehumidification system , where, and represent the lower and upper limits of the rotary wheel speed respectively, represents the rotary wheel speed at time k, and represent the lower and upper limits of the heating power respectively, represents the heating power at time k, and represent the allowable lower and upper limits of the air humidity respectively, represents the air humidity at time k;

[0156] S3.4: Substitute the current operation state, load prediction result, objective function, and constraint conditions into the genetic algorithm. The genetic algorithm searches for the control input combination that makes the objective function reach the optimal value through iterative calculation; the control inputs include the rotary wheel speed, the power of the heating device, and the air volume of the fan. Among them, the genetic algorithm is the prior art content in this field and is not the creative solution of this application, so it will not be elaborated here;

[0157] S3.5: Verify the calculated optimal control input to check whether it meets the physical feasibility and operation requirements of the system;

[0158] If the optimal control input does not satisfy the constraint conditions or causes the system to operate unstably, the parameters of the genetic algorithm are readjusted and the calculation is performed again.

[0159] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make changes, modifications, substitutions, and variations to the above embodiments without departing from the spirit and scope of the present invention, and these all fall within the protection scope of the present invention.

Claims

1. An energy-saving optimization control method for an air-conditioning rotary dehumidification system based on a mechanism model, characterized in that: include: Step S1: collecting historical operation data of the air-conditioning rotary dehumidification system, establishing a mechanism model of the air-conditioning rotary dehumidification system, and verifying the mechanism model; Step S2: Based on the verified mechanism model, a model predictive control method is used to predict the operating state of the air-conditioning rotary dehumidification system, and according to the prediction results and the real-time collected operating data, an adaptive learning algorithm and a deep reinforcement learning algorithm are used to adaptively adjust the mechanism model and the model predictive control method; Step S3: Based on the adaptively adjusted mechanism model, the current operating state and load of the air-conditioning rotary dehumidification system are predicted, and the optimal control input is calculated through the optimization algorithm; Step S4: using intelligent decision-making algorithms and deep reinforcement learning algorithms to correct and iterate the adaptively adjusted mechanism model; Step S5: applying the calculated optimal control input to the air-conditioning rotary dehumidification system, implementing the control strategy, monitoring the operating status and energy consumption of the system in real time, evaluating the effect of the control strategy, and adjusting and optimizing the control strategy according to the evaluation results; The specific steps of step S2 include: S2.1: Setting the prediction horizon and control time domain , and according to the operation target of the air-conditioning rotary dehumidification system, the objective function J is established, and the formula is: ； in, represents the system state at time k+1 predicted based on the information at time k, represents the state variable of the air-conditioning rotary dehumidification system at time k, E represents the state error, represents the control input at time k, and R represents the weighted matrix of the control input; S2.2: Using the verified mechanism model, combined with the current operating status of the air-conditioning rotary dehumidification system and the interference factor results, predict the operating status of the air-conditioning rotary dehumidification system within the set prediction time domain; S2.3: Use sensors to collect the operating data of the air-conditioning rotary dehumidification system in real time, compare the operating status in the time domain in S2.2 with the operating data collected in real time, and calculate the error between the two; S2.4: According to the error results, the parameters of the mechanism model are adjusted using an adaptive learning algorithm based on the least squares method; The specific steps of step S2 also include: S2.5: The operating state of the air-conditioning rotary dehumidification system is used as the state space, the control input is used as the action space, and the reward function is defined according to the operating goal of the system. ; The control input includes the wheel speed and heating power; the operation target includes energy saving and humidity control accuracy, where z represents the air-conditioning wheel dehumidification system, g represents the control action, and represents the weighting coefficient, G represents the system energy consumption, hum represents the operating status of the air-conditioning rotary dehumidification system, Indicates the operating status reference value of the air-conditioning rotary dehumidification system; S2.6: Use deep reinforcement learning algorithms to learn the optimal control strategy by interacting with the air conditioning rotary dehumidification system; S2.7: Update the control strategy in the model predictive control method based on the optimal strategy learned by the deep reinforcement learning model.

2. The energy-saving optimization control method for the air-conditioning rotary dehumidification system based on the mechanism model according to claim 1 is characterized in that: The specific steps of establishing the mechanism model of the air-conditioning rotary dehumidification system in step S1 include: S1.1: Collect historical operation data of the air-conditioning rotary dehumidification system and perform preprocessing; S1.2: Determine the scope of the air conditioning rotary dehumidification system and analyze the functions of each component; the components include rotary dehumidifier, regenerative heating device, fan, and air handling channel; S1.3: Based on the analysis results of S1.2, considering the adsorption characteristics of the desiccant, mass transfer and heat transfer process, establish the wheel dehumidification and absorption model The wheel moisture absorption and dehumidification model includes an adsorption isotherm model and a mass transfer and heat transfer model, wherein q represents the adsorption amount of the moisture absorbent, represents the maximum adsorption capacity, K represents the adsorption equilibrium constant, is the water vapor partial pressure, is the water vapor density, represents the volume of the control volume, and denote the water vapor mass flow rates entering and leaving the control volume, respectively, represents the adsorption mass flow rate of the desiccant, t represents the time, represents the air density, represents the constant pressure specific heat capacity of air, T represents the air temperature, and denote the heat fluxes entering and leaving the control volume, respectively, is the adsorption heat flow, represents partial derivative; S1.4: Similarly, based on the analysis results of S1.2 and the thermodynamic properties of air, an air heat and moisture exchange model is established. ,in, represents the air mass flow rate, and Respectively represent the moisture content of the air when it enters and leaves the rotor, represents the change in the mass flow rate of water vapor in the air, and are the enthalpy values ​​of air entering and leaving the rotor, represents the sensible heat exchange capacity, represents the amount of latent heat exchange; S1.5: Establish component characteristic model based on the fan and heating device ,in, represents the wind pressure of the fan, Q represents the wind volume of the fan, , , represents the fitting coefficient, represents heating power, V represents voltage, and I represents current.

3. The energy-saving optimization control method for the air-conditioning rotary dehumidification system based on the mechanism model according to claim 2 is characterized in that: The specific steps of establishing the mechanism model of the air-conditioning rotary dehumidification system in step S1 also include: S1.6: Integrate the wheel moisture absorption and dehumidification model, air heat and moisture exchange model and component characteristic model to form a mechanism model of the air conditioning wheel dehumidification system; S1.7: Use the finite difference method to discretize the mechanism model equation of the air-conditioning rotary dehumidification system into a difference equation and solve it to obtain the operating state parameters of the air-conditioning rotary dehumidification system under different working conditions; S1.8: Verify the output result of the mechanism model of the air-conditioning rotary dehumidification system according to the preprocessed historical operation data, and calculate the mean square error index by comparing the prediction result of the mechanism model with the actual operation data; If the mean square error index is less than or equal to the preset threshold, the mechanism model is considered valid; If the mean square error index is greater than the preset threshold, the mechanism model is adjusted.

4. The energy-saving optimization control method for the air-conditioning rotary dehumidification system based on the mechanism model according to claim 3 is characterized in that: The specific steps of S1.7 include: S1.71: Obtain the mechanism model of the air-conditioning rotary dehumidification system, and discretize it in the space domain and time domain to generate the mechanism model equation; the space domain is to divide the solution area of ​​the rotary dehumidification system into a series of uniform grid points; the time domain is to divide it into discrete time steps; S1.72: For each grid cell, transform the mechanism model equation into a difference equation using the forward difference format; S1.73: The discretized difference equations are organized into a system of linear algebraic equations, and the Jacobi iteration method is used to solve the system of linear algebraic equations to obtain the variable values ​​of each grid node at different time steps, that is, the operating state parameters of the system.

5. The energy-saving optimization control method for the air-conditioning rotary dehumidification system based on the mechanism model according to claim 4 is characterized in that: The specific steps of step S3 include: S3.1: Obtain the adaptively adjusted mechanism model and current operating data of the air-conditioning rotary dehumidification system; S3.2: Based on the historical operation data, use a time series analysis method to predict the load of the air-conditioning rotary dehumidification system; the load includes dehumidification load, heating load, and ventilation load; S3.3: Determine the constraints based on the operating requirements of the air conditioning rotary dehumidification system ,in, and Respectively represent the lower and upper limits of the wheel speed, represents the wheel speed at time k, and Respectively represent the lower and upper limits of the heating power, represents the heating power at time k, and Respectively represent the lower and upper limits of air humidity. represents the air humidity at time k.

6. The energy-saving optimization control method for the air-conditioning rotary dehumidification system based on the mechanism model according to claim 5 is characterized in that: The specific steps of step S3 also include: S3.4: Substitute the current operating state, load forecast results, objective function and constraint conditions into the genetic algorithm, and the genetic algorithm searches for a control input combination that makes the objective function reach the optimal value through iterative calculation; the control input includes the rotation speed of the rotor, the power of the heating device, and the air volume of the fan; S3.5: Verify the calculated optimal control input to check whether it meets the physical feasibility and operation requirements of the system; If the optimal control input does not satisfy the constraints or causes unstable system operation, the parameters of the genetic algorithm are readjusted and the calculation is performed again.

7. The energy-saving optimization control method for the air-conditioning rotary dehumidification system based on the mechanism model according to claim 6 is characterized in that: The model predictive control algorithm predicts the operating results of the air-conditioning rotary dehumidification system under different control strategies based on the current system operating status and load prediction, and obtains the optimal control parameters, including the rotary wheel speed, heating power, and fan frequency, through optimization calculation.

8. The energy-saving optimization control method for the air-conditioning rotary dehumidification system based on the mechanism model according to claim 7 is characterized in that: The mechanism model includes the adsorption and desorption process of the wheel and the heat exchange process of the air flow; the historical operation data of the air-conditioning rotary dehumidification system includes indoor and outdoor air humidity, temperature, air volume and energy consumption; the optimal control input includes the optimal speed of the wheel, the optimal power of the heating device and the optimal frequency of the fan.

Images