Digital air duct control system and method for air conditioning system

Abstract

The invention relates to the technical field of air conditioning, and discloses a digital air duct control system and method for an air conditioning system. According to the method, environment parameters and air conditioner air pipe state parameters are collected through Internet of Things equipment, a sample set is constructed based on the collected air conditioner air pipe state parameter data, and meanwhile the air conditioner air pipe state parameter data in the constructed sample set are preprocessed; establishing a temperature and humidity prediction model based on the obtained preprocessed state parameter data of the air conditioner duct and the acquired environmental parameters; and meanwhile, the established temperature and humidity prediction model is trained through a genetic algorithm, the trained temperature and humidity prediction model is output, the air conditioner air pipe control quantity is calculated through a PID control algorithm based on the obtained trained temperature and humidity prediction model, and the air conditioner air pipe is controlled based on the calculated air conditioner air pipe control quantity. And the real-time performance and the accuracy of digital air pipe control are improved.

Description

Technical Field

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

[0002] At present, air conditioning systems are still mainly based on simple switch control and PID control. The switch control method is to start or shut down the air conditioner by detecting whether the regional temperature reaches the set threshold through the temperature sensor. Although this method can control the regional temperature within a certain range, the control accuracy is low; PID control uses dynamic feedback correction to adjust the regional temperature to obtain a better control effect, but because PID control is prone to slow adjustment speed and temperature overshoot, it cannot meet actual needs.

[0003] Existing technologies such as Chinese patent application CN105352133B obtain the user's age stage information by detecting the initial values ​​of the user's vital sign parameters, and control the air conditioner to enter the corresponding control mode according to the age stage information, and then detect the user's vital sign parameters at predetermined intervals, and determine whether the user is in the light sleep stage and the deep sleep stage according to the changes in the user's vital sign parameters, and control the air conditioner to adjust to the corresponding sleep mode. It does not solve the problem of slow adjustment speed and temperature overshoot in PID control, and has great limitations. Summary of the invention

[0004] 1. Technical issues to be resolved In view of the deficiencies in the prior art, the present invention provides a digital duct control system and method for an air-conditioning system, which has the advantages of real-time and accuracy, and solves the problems of slow adjustment speed and temperature overshoot in PID control.

[0005] (II) Technical solution In order to solve the technical problems that the above PID control is prone to slow adjustment speed and temperature overshoot, the present invention provides the following technical solutions: The present invention discloses a digital air duct control method for an air conditioning system, which specifically comprises the following steps: S1. Collect environmental parameters and air conditioning duct status parameters through IoT devices, and build a sample set based on the collected air conditioning duct status parameter data; S2, preprocessing the air conditioning duct state parameter data in the constructed sample set to obtain the preprocessed air conditioning duct state parameter data; S3, establishing a temperature and humidity prediction model based on the obtained pre-processed air conditioning duct state parameter data and the collected environmental parameters; S4, training the established temperature and humidity prediction model through a genetic algorithm, and outputting the trained temperature and humidity prediction model; S5. Based on the trained temperature and humidity prediction model, the air conditioning duct control amount is calculated by a PID control algorithm, and the air conditioning duct is controlled based on the calculated air conditioning duct control amount.

[0006] The present invention collects environmental parameters and air-conditioning duct state parameters through Internet of Things devices, and constructs a sample set based on the collected air-conditioning duct state parameter data, and pre-processes the air-conditioning duct state parameter data in the constructed sample set, and establishes a temperature and humidity prediction model based on the obtained pre-processed air-conditioning duct state parameter data and the collected environmental parameters; at the same time, the established temperature and humidity prediction model is trained through a genetic algorithm, the trained temperature and humidity prediction model is output, and based on the obtained trained temperature and humidity prediction model, the air-conditioning duct control amount is calculated through a PID control algorithm, and the air-conditioning duct control amount is controlled based on the calculated air-conditioning duct control amount, thereby improving the real-time and accuracy of digital duct control.

[0007] Preferably, the collecting of environmental parameters and air conditioning duct status parameters by means of an Internet of Things device comprises the following steps: Based on the data collected by the Internet of Things device, the collected air conditioning duct status data includes: timestamp, air conditioning duct temperature and air conditioning duct humidity; The collected environmental parameters include: indoor temperature and indoor humidity; Within the set indoor temperature range, the specific temperature value of the indoor temperature in the environmental parameters is adjusted by adjusting the state parameters of the air-conditioning duct. The variable data of each parameter in the air-conditioning duct is recorded every time the temperature changes by 1°C, and the proportional coefficient between the variable data of each parameter in the air-conditioning duct and the temperature is determined.

[0008] The present invention adjusts the specific temperature of the indoor temperature by a method of controlling variables, records the variable data of each parameter in the air duct of the air conditioner according to the temperature change, quantifies the variable data of each parameter in the air duct, and improves the accuracy of digital air duct control.

[0009] Preferably, the preprocessing of the air conditioning duct state parameter data in the constructed sample set comprises the following steps: Set the sampling period, and repeatedly collect the variable data of each parameter in the air conditioning duct based on the sampling period; After repeatedly collecting the data of various parameters in the air conditioning duct when the temperature changes, the collected data are standardized; The data standardization processing formula is as follows:

[0010] in, represents the data before standardization. Indicates the data after standardization; Indicates the maximum value of each parameter variable data; Indicates the minimum value of each parameter variable data; The standardized data is set as the pre-processed air conditioning duct state parameter data.

[0011] The present invention sets a sampling period, repeatedly collects the data of various parameter variables in the air-conditioning duct based on the sampling period, and standardizes the data of various parameter variables in the air-conditioning duct through a data standardization processing method, thereby ensuring the accuracy of digital air-duct control.

[0012] Preferably, the establishment of a temperature and humidity prediction model based on the obtained pre-processed air conditioning duct state parameter data and the collected environmental parameters comprises the following steps: set up For the collected The matrix of air conditioning duct state parameters and environmental state parameters at all times, for The air conditioning duct control parameter matrix input at any time is used to Adjust the air conditioning duct status parameters and environmental parameters at all times. For output prediction The air conditioning duct state parameters and environmental parameter matrix at the moment;

[0013] in, represents the sampling period, Indicates time, represents the identity matrix, Indicates time, represents the parameter matrix of the periodic air conditioning duct control quantity, represents the air conditioning duct state parameter and environmental parameter matrix after unit matrix processing, Represents the state vector corresponding to the state data of the air conditioning duct state parameters, Represents the state vector corresponding to the predicted state data of the air conditioning duct state parameters, Indicates The state vector corresponding to the state data of the air conditioning duct state parameters at the moment, Indicates The state vector corresponding to the state data of the air conditioning duct state parameters at the moment, Indicates The parameter matrix of periodic air conditioning duct control quantity at time.

[0014] The present invention establishes a preliminary temperature and humidity prediction model by obtaining preprocessed air conditioning duct state parameter data and environmental parameters, collects data based on the established preliminary temperature and humidity prediction model to complete the prediction of temperature and humidity at the next moment, thereby improving the real-time performance of digital duct control.

[0015] Preferably, the step of training the established temperature and humidity prediction model by a genetic algorithm and outputting the trained temperature and humidity prediction model comprises the following steps: S41, set the genetic population size, number of iterations and chromosome encoding; Set all environmental parameters and air conditioning duct status parameters collected in the sample set as the population size; Based on the timestamps saved in the sample set, the environmental parameters and air conditioning duct status parameters at the same time are taken as a set of parameter data; S42, Randomly generate initial population ; Randomly select m groups of parameter data from the sample set as the initial population ; S43, using the correction function of the prediction error in the temperature and humidity prediction model as the fitness function of the genetic algorithm, and calculating the fitness of each individual in the population; S44, selecting the best individuals from all individuals based on the roulette wheel method; S44, cross the selected excellent individuals by sequential crossover to generate a new population after crossover ; S46. Randomly select an individual in the population to perform marginalization with a set probability to produce a mutated population ; S47. Compare the fitness difference between the initial population and the population after genetic algorithm crossover mutation ; when <0, indicating that the fitness of the mutated population is higher than that of the initial population. Accept the population. ≥0, indicating that the fitness of the mutated population is lower than that of the initial population, and the population is rejected; S48, judging whether the maximum number of iterations has been reached according to the number of iterations of the algorithm, outputting the optimal solution when the maximum number of iterations has been reached, and continuing to execute step S44 when the maximum number of iterations has not been reached; The optimal solution of the output is set to be the temperature and humidity prediction model after training.

[0016] Preferably, the method of using the correction function of the prediction error in the temperature and humidity prediction model as the fitness function of the genetic algorithm and calculating the fitness of each individual in the population comprises the following steps: The prediction error formula in the temperature and humidity prediction model is as follows:

[0017] in, express The real air conditioning duct status parameter data at all times, express The predicted status parameter data of the air conditioning duct at each moment. express The prediction error at the moment; The correction function formula of the prediction error in the temperature and humidity prediction model is as follows:

[0018] in, After correction The predicted status parameter data of the air conditioning duct at each moment. Represents the correction coefficient, the value range is [-1,1]; Assume that each individual represents a set of parameter data; The fitness calculation formula for each individual is as follows:

[0019] in, Indicates The fitness of an individual, Represents the correction function of the prediction error in the temperature and humidity prediction model.

[0020] Preferably, the roulette-based method of selecting excellent individuals from all individuals comprises the following steps: The calculation formula for selecting the best individuals among all individuals by roulette is as follows:

[0021] in, Represents an individual The probability of being selected, Indicates the population size.

[0022] The present invention trains the established temperature and humidity prediction model through a genetic algorithm, outputs the optimal temperature and humidity prediction model through continuous crossover, selection, mutation, and iteration of the genetic algorithm, and predicts the state of the air duct of the air conditioner based on the output optimal temperature and humidity prediction model, thereby improving the accuracy of digital air duct control.

[0023] Preferably, the step of calculating the air conditioning duct control amount by using a PID control algorithm based on the obtained trained temperature and humidity prediction model comprises the following steps: The trained temperature and humidity prediction model is as follows:

[0024] in, After correction The predicted status parameter data of the air conditioning duct at each moment. Represents the correction coefficient, the value range is [-1,1], express The prediction error at the moment; S51, calculating the control amount error of the air duct of the air conditioner; Collect the variable data of air conditioning duct state parameters in real time and perform standardization processing, and set the temperature and humidity at the next moment predicted by the trained temperature and humidity prediction model as the target value of the air conditioning duct control quantity; Air conditioning duct control quantity error = air conditioning duct control quantity target value - real-time collection of air conditioning duct state parameter variable data; S52, proportion link; Set the proportional coefficient between the variable data of each parameter and the temperature in the air conditioning duct to , the control quantity of the air conditioning duct proportional link is , the error of the air conditioning duct control quantity is ; = × ; S53, points phase; Set the proportional integral control amount of the air conditioning duct to ; = ×

[0025] in, Indicates The integration time constant, Indicates the time interval between the next moment and the current moment. Indicates the number of points, Indicates The error of the integral; S54, differential link; Set the differential integral control quantity of the air conditioning duct to ; = ×

[0026] in, Indicates The differential time constant, Indicates The error of the integral, Indicates The error of the integral; S55, summarizing and calculating the air duct control quantity of the air conditioner; = + +

[0027] in, Indicates the air duct control quantity of the air conditioner; The air conditioning duct is controlled based on the calculated air conditioning duct control quantity.

[0028] The present invention obtains the trained temperature and humidity prediction model, calculates the air conditioning duct control quantity through the PID control algorithm, calculates the air conditioning duct control quantity through the proportion, integration and differentiation summary calculation of the PID control algorithm, and controls the air conditioning duct based on the calculated air conditioning duct control quantity.

[0029] The present invention discloses a digital air duct control system for an air conditioning system, comprising an Internet of Things device, a data acquisition module, a data processing module, a model prediction module and a control quantity determination module; The IoT device includes a temperature sensor and a humidity sensor; The temperature sensor is used to monitor the temperature changes in the current area in real time; The humidity sensor is used to monitor the humidity changes in the current area in real time; The data acquisition module is used to collect parameter data in the air conditioning duct in the current area in real time; The data processing module is used to pre-process the parameter data collected in real time in the air conditioning duct in the current area; The model prediction module is used to establish a prediction model based on the preprocessed parameter data in the air conditioning duct, and determine the prediction model based on a genetic algorithm; The control quantity determination module is used to calculate the air conditioning duct control quantity through the PID control algorithm according to the obtained prediction model, and control the air conditioning duct based on the calculated air conditioning duct control quantity.

[0030] (III) Beneficial effects Compared with the prior art, the present invention provides a digital air duct control system and method for an air conditioning system, which has the following beneficial effects: 1. The invention collects environmental parameters and air-conditioning duct status parameters through Internet of Things devices, and constructs a sample set based on the collected air-conditioning duct status parameter data. At the same time, the air-conditioning duct status parameter data in the constructed sample set is preprocessed, and a temperature and humidity prediction model is established based on the preprocessed air-conditioning duct status parameter data and the collected environmental parameters; at the same time, the established temperature and humidity prediction model is trained through a genetic algorithm, and the trained temperature and humidity prediction model is output. Based on the trained temperature and humidity prediction model, the air-conditioning duct control amount is calculated through a PID control algorithm, and the air-conditioning duct control amount is controlled based on the calculated air-conditioning duct control amount, thereby improving the real-time and accuracy of digital duct control.

[0031] 2. The invention adjusts the specific temperature of the indoor temperature by controlling variables, records the variable data of each parameter in the air duct of the air conditioner according to the temperature change, quantifies the variable data of each parameter in the air duct, and improves the accuracy of digital air duct control.

[0032] 3. The invention sets a sampling period, repeatedly collects the data of various parameter variables in the air-conditioning duct based on the sampling period, and standardizes the data of various parameter variables in the air-conditioning duct through a data standardization processing method, thereby ensuring the accuracy of digital duct control.

[0033] 4. The invention trains the established temperature and humidity prediction model through genetic algorithm, outputs the optimal temperature and humidity prediction model through continuous crossover, selection, mutation and iteration of the genetic algorithm, and predicts the state of the air conditioning duct based on the output optimal temperature and humidity prediction model, thereby improving the accuracy of digital duct control.

[0034] 5. The invention obtains the trained temperature and humidity prediction model, calculates the air conditioning duct control quantity through the PID control algorithm, calculates the air conditioning duct control quantity through the proportional, integral and differential summary of the PID control algorithm, and controls the air conditioning duct based on the calculated air conditioning duct control quantity.

[0035] 6. The invention establishes a preliminary temperature and humidity prediction model by obtaining pre-processed air-conditioning duct state parameter data and environmental parameters, collects data based on the established preliminary temperature and humidity prediction model to complete the prediction of temperature and humidity at the next moment, thereby improving the real-time performance of digital duct control. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The figure is a schematic diagram of the structure of the digital air duct control method for an air conditioning system according to the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] The present invention discloses a digital air duct control method for an air conditioning system, which specifically comprises the following steps: S1. Collect environmental parameters and air conditioning duct status parameters through IoT devices, and build a sample set based on the collected air conditioning duct status parameter data; The IoT device includes: a temperature sensor and a humidity sensor; Based on the data collected by the Internet of Things device, the collected air conditioning duct status data includes: timestamp, air conditioning duct temperature and air conditioning duct humidity; The collected environmental parameters include: indoor temperature and indoor humidity; Furthermore, within the set indoor temperature range, the specific temperature value of the indoor temperature in the environmental parameter is adjusted by adjusting the state parameters of the air conditioning duct, and the variable data of each parameter in the air conditioning duct is recorded every time the temperature changes by 1°C, and the proportional coefficient between the variable data of each parameter in the air conditioning duct and the temperature is determined; S2, preprocessing the air conditioning duct state parameter data in the constructed sample set to obtain the preprocessed air conditioning duct state parameter data; Set the sampling period, and repeatedly collect the variable data of each parameter in the air conditioning duct based on the sampling period; After repeatedly collecting the data of various parameters in the air conditioning duct when the temperature changes, the collected data are standardized; The data standardization processing formula is as follows:

[0039] in, represents the data before standardization. Indicates the data after standardization; Indicates the maximum value of each parameter variable data; Indicates the minimum value of each parameter variable data; Further, the standardized data is set as the pre-processed air conditioning duct state parameter data; S3, establishing a temperature and humidity prediction model based on the obtained pre-processed air conditioning duct state parameter data and the collected environmental parameters; set up For the collected The matrix of air conditioning duct state parameters and environmental state parameters at all times, for The air conditioning duct control parameter matrix input at any time is used to Adjust the air conditioning duct status parameters and environmental parameters at all times. For output prediction The air conditioning duct state parameters and environmental parameter matrix at the moment;

[0040] in, represents the sampling period, Indicates time, represents the identity matrix, Indicates time, represents the parameter matrix of the periodic air conditioning duct control quantity, represents the air conditioning duct state parameter and environmental parameter matrix after unit matrix processing, Represents the state vector corresponding to the state data of the air conditioning duct state parameters, Represents the state vector corresponding to the predicted state data of the air conditioning duct state parameters, Indicates The state vector corresponding to the state data of the air conditioning duct state parameters at the moment, Indicates The state vector corresponding to the state data of the air conditioning duct state parameters at the moment, Indicates The parameter matrix of periodic air conditioning duct control quantity at time.

[0041] S4, training the established temperature and humidity prediction model through a genetic algorithm, and outputting the trained temperature and humidity prediction model; The established temperature and humidity prediction model is trained by genetic algorithm, and outputting the trained temperature and humidity prediction model includes the following steps: S41, set the genetic population size, number of iterations and chromosome encoding; Set all environmental parameters and air conditioning duct status parameters collected in the sample set as the population size; Furthermore, based on the timestamps saved in the sample set, the environmental parameters and the air conditioning duct status parameters at the same time are taken as a set of parameter data; S42, Randomly generate initial population ; Randomly select m groups of parameter data from the sample set as the initial population ; S43, using the correction function of the prediction error in the temperature and humidity prediction model as the fitness function of the genetic algorithm, and calculating the fitness of each individual in the population; The prediction error formula in the temperature and humidity prediction model is as follows:

[0042] in, express The real air conditioning duct status parameter data at all times, express The predicted status parameter data of the air conditioning duct at each moment. express The prediction error at the moment; The correction function formula of the prediction error in the temperature and humidity prediction model is as follows:

[0043] in, After correction The predicted status parameter data of the air conditioning duct at each moment. Represents the correction coefficient, the value range is [-1,1]; Assume that each individual represents a set of parameter data; The fitness calculation formula for each individual is as follows:

[0044] in, represents the fitness of the rth individual, Represents the correction function of the prediction error in the temperature and humidity prediction model; S44, selecting the best individuals from all individuals based on the roulette wheel method; The calculation formula for selecting the best individuals among all individuals by roulette is as follows:

[0045] in, represents the probability of individual r being selected, and R represents the population size; S44, cross the selected excellent individuals by sequential crossover to generate a new population after crossover ; S46. Randomly select an individual in the population and perform marginalization with a set probability to generate a mutated population ; S47. Compare the fitness difference between the initial population and the population after genetic algorithm crossover mutation ; when <0, indicating that the fitness of the mutated population is higher than that of the initial population. Accept the population. ≥0, indicating that the fitness of the mutated population is lower than that of the initial population, and the population is rejected; S48, judging whether the maximum number of iterations has been reached according to the number of iterations of the algorithm, outputting the optimal solution when the maximum number of iterations has been reached, and continuing to execute step S44 when the maximum number of iterations has not been reached; Set the optimal output solution to the trained temperature and humidity prediction model; The trained temperature and humidity prediction model is as follows:

[0046] in, After correction The predicted status parameter data of the air conditioning duct at each moment. Represents the correction coefficient, the value range is [-1,1], express The prediction error at the moment; S5. Based on the trained temperature and humidity prediction model, the air conditioning duct control amount is calculated by a PID control algorithm, and the air conditioning duct is controlled based on the calculated air conditioning duct control amount; Based on the trained temperature and humidity prediction model, the air conditioning duct control quantity is calculated by the PID control algorithm, including the following steps: S51, calculating the control amount error of the air duct of the air conditioner; Collect the variable data of air conditioning duct state parameters in real time and perform standardization processing, and set the temperature and humidity at the next moment predicted by the trained temperature and humidity prediction model as the target value of the air conditioning duct control quantity; Air conditioning duct control quantity error = air conditioning duct control quantity target value - real-time collection of air conditioning duct state parameter variable data; S52, proportion link; Set the proportional coefficient between the variable data of each parameter and the temperature in the air conditioning duct to , the control quantity of the air conditioning duct proportional link is , the error of the air conditioning duct control quantity is ; = × ; S53, points phase; Set the proportional integral control amount of the air conditioning duct to ; = ×

[0047] in, Indicates The integration time constant, Indicates the time interval between the next moment and the current moment. Indicates the number of points, Indicates The error of the integral; S54, differential link; Set the differential integral control quantity of the air conditioning duct to ; = ×

[0048] in, Indicates The differential time constant, Indicates The error of the integral, Indicates The error of the integral; S55, summarizing and calculating the air duct control quantity of the air conditioner; = + +

[0049] in, Indicates the air duct control quantity of the air conditioner; Further, the air conditioning duct is controlled based on the calculated air conditioning duct control amount; The present invention discloses a digital air duct control system for an air conditioning system, comprising an Internet of Things device, a data acquisition module, a data processing module, a model prediction module and a control quantity determination module; The IoT device includes a temperature sensor and a humidity sensor; The temperature sensor is used to monitor the temperature changes in the current area in real time; The humidity sensor is used to monitor the humidity changes in the current area in real time; The data acquisition module is used to collect parameter data in the air conditioning duct in the current area in real time; The data processing module is used to pre-process the parameter data collected in real time in the air conditioning duct in the current area; The model prediction module is used to establish a prediction model based on the preprocessed parameter data in the air conditioning duct, and determine the prediction model based on a genetic algorithm; The control quantity determination module is used to calculate the air conditioning duct control quantity through the PID control algorithm according to the obtained prediction model, and control the air conditioning duct based on the calculated air conditioning duct control quantity.

[0050] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A digital air duct control method for an air conditioning system, characterized in that: The following steps are involved: S1. Collect environmental parameters and air conditioning duct status parameters through IoT devices, and build a sample set based on the collected air conditioning duct status parameter data; S2, preprocessing the air conditioning duct state parameter data in the constructed sample set to obtain the preprocessed air conditioning duct state parameter data; S3, establishing a temperature and humidity prediction model based on the obtained pre-processed air conditioning duct state parameter data and the collected environmental parameters; S4, training the established temperature and humidity prediction model through a genetic algorithm, and outputting the trained temperature and humidity prediction model; S5. Based on the trained temperature and humidity prediction model, the air conditioning duct control amount is calculated by a PID control algorithm, and the air conditioning duct is controlled based on the calculated air conditioning duct control amount.

2. A digital air duct control method for an air conditioning system according to claim 1, characterized in that: The collecting of environmental parameters and air conditioning duct status parameters by the Internet of Things device comprises the following steps: Based on the data collected by the Internet of Things device, the collected air conditioning duct status data includes: timestamp, air conditioning duct temperature and air conditioning duct humidity; The collected environmental parameters include: indoor temperature and indoor humidity; Within the set indoor temperature range, the specific temperature value of the indoor temperature in the environmental parameters is adjusted by adjusting the state parameters of the air-conditioning duct. The variable data of each parameter in the air-conditioning duct is recorded every time the temperature changes by 1°C, and the proportional coefficient between the variable data of each parameter in the air-conditioning duct and the temperature is determined.

3. A digital air duct control method for an air conditioning system according to claim 1, characterized in that: The preprocessing of the air conditioning duct state parameter data in the constructed sample set includes the following steps: Set the sampling period, and repeatedly collect the variable data of each parameter in the air conditioning duct based on the sampling period; Repeatedly collect the data of various parameter variables in the air conditioning duct when the temperature changes, and standardize the collected data; The data standardization processing formula is as follows: ； in, represents the data before standardization. Indicates the data after standardization; Indicates the maximum value of each parameter variable data; Indicates the minimum value of each parameter variable data; The standardized data is set as the pre-processed air conditioning duct state parameter data.

4. A digital air duct control method for an air conditioning system according to claim 1, characterized in that: The establishment of a temperature and humidity prediction model based on the obtained pre-processed air conditioning duct state parameter data and the collected environmental parameters includes the following steps: set up For the collected The matrix of air conditioning duct state parameters and environmental state parameters at all times, for The air conditioning duct control parameter matrix input at any time is used to Adjust the air conditioning duct status parameters and environmental parameters at all times. For output prediction The air conditioning duct state parameters and environmental parameter matrix at the moment; ； in, represents the sampling period, Indicates time, represents the identity matrix, Indicates time, represents the parameter matrix of the periodic air conditioning duct control quantity, represents the air conditioning duct state parameter and environmental parameter matrix after unit matrix processing, Represents the state vector corresponding to the state data of the air conditioning duct state parameters, Represents the state vector corresponding to the predicted state data of the air conditioning duct state parameters, Indicates The state vector corresponding to the state data of the air conditioning duct state parameters at the moment, Indicates The state vector corresponding to the state data of the air conditioning duct state parameters at the moment, Indicates The parameter matrix of periodic air conditioning duct control quantity at time.

5. A digital air duct control method for an air conditioning system according to claim 1, characterized in that: The method of training the established temperature and humidity prediction model by using a genetic algorithm and outputting the trained temperature and humidity prediction model comprises the following steps: S41, set the genetic population size, number of iterations and chromosome encoding; Set all environmental parameters and air conditioning duct status parameters collected in the sample set as the population size; Based on the timestamps saved in the sample set, the environmental parameters and air conditioning duct status parameters at the same time are taken as a set of parameter data; S42, Randomly generate initial population ; Randomly select m groups of parameter data from the sample set as the initial population ; S43, using the correction function of the prediction error in the temperature and humidity prediction model as the fitness function of the genetic algorithm, and calculating the fitness of each individual in the population; S44, selecting the best individuals from all individuals based on the roulette wheel method; S44, cross the selected excellent individuals by sequential crossover to generate a new population after crossover ; S46. Randomly select an individual in the population and perform marginalization with a set probability to generate a mutated population ; S47. Compare the fitness difference between the initial population and the population after genetic algorithm crossover mutation ; when <0, indicating that the fitness of the mutated population is higher than that of the initial population. Accept the population. ≥0, indicating that the fitness of the mutated population is lower than that of the initial population, and the population is rejected; S48, judging whether the maximum number of iterations has been reached according to the number of iterations of the algorithm, outputting the optimal solution when the maximum number of iterations has been reached, and continuing to execute step S44 when the maximum number of iterations has not been reached; The optimal solution of the output is set to be the temperature and humidity prediction model after training.

6. A digital air duct control method for an air conditioning system according to claim 5, characterized in that: The method of using the correction function of the prediction error in the temperature and humidity prediction model as the fitness function of the genetic algorithm and calculating the fitness of each individual in the population includes the following steps: The prediction error formula in the temperature and humidity prediction model is as follows: ； in, express The real air conditioning duct status parameter data at all times, express The predicted status parameter data of the air conditioning duct at each moment. express The prediction error at the moment; The correction function formula of the prediction error in the temperature and humidity prediction model is as follows: ； in, After correction The predicted status parameter data of the air conditioning duct at each moment. Represents the correction coefficient, the value range is [-1,1]; Assume that each individual represents a set of parameter data; The fitness calculation formula for each individual is as follows: ； in, Indicates The fitness of an individual, Represents the correction function of the prediction error in the temperature and humidity prediction model.

7. A digital air duct control method for an air conditioning system according to claim 5, characterized in that: The roulette-based method for selecting excellent individuals from all individuals comprises the following steps: The calculation formula for selecting the best individuals among all individuals by roulette is as follows: ； in, Represents an individual The probability of being selected, Indicates the population size.

8. A digital air duct control method for an air conditioning system according to claim 1, characterized in that: The method of calculating the air conditioning duct control quantity by using a PID control algorithm based on the obtained trained temperature and humidity prediction model comprises the following steps: The trained temperature and humidity prediction model is as follows: ； in, After correction The predicted status parameter data of the air conditioning duct at each moment. Represents the correction coefficient, the value range is [-1,1], express The prediction error at the moment; S51, calculating the control amount error of the air duct of the air conditioner; Collect the variable data of air conditioning duct state parameters in real time and perform standardization processing, and set the temperature and humidity at the next moment predicted by the trained temperature and humidity prediction model as the target value of the air conditioning duct control quantity; Air conditioning duct control quantity error = air conditioning duct control quantity target value - real-time collection of air conditioning duct state parameter variable data; S52, proportion link; Set the proportional coefficient between the variable data of each parameter and the temperature in the air conditioning duct to , the control quantity of the air conditioning duct proportional link is , the error of the air conditioning duct control quantity is ; = × ； S53, points phase; Set the proportional integral control amount of the air conditioning duct to ; = × ； in, Indicates The integration time constant, Indicates the time interval between the next moment and the current moment. Indicates the number of points, Indicates The error of the integral; S54, differential link; Set the differential integral control quantity of the air conditioning duct to ; = × ； in, Indicates The differential time constant, Indicates The error of the integral, Indicates The error of the integral; S55, summarizing and calculating the air duct control quantity of the air conditioner; = + + ； in, Indicates the air duct control quantity of the air conditioner; The air conditioning duct is controlled based on the calculated air conditioning duct control quantity.

9. A system for implementing the digital air duct control method for an air conditioning system according to any one of claims 1 to 8, characterized in that: It includes Internet of Things devices, data acquisition module, data processing module, model prediction module and control quantity determination module; The IoT device includes a temperature sensor and a humidity sensor; The temperature sensor is used to monitor the temperature changes in the current area in real time; The humidity sensor is used to monitor the humidity changes in the current area in real time; The data acquisition module is used to collect parameter data in the air conditioning duct in the current area in real time; The data processing module is used to pre-process the parameter data collected in real time in the air conditioning duct in the current area; The model prediction module is used to establish a prediction model based on the preprocessed parameter data in the air conditioning duct, and determine the prediction model based on a genetic algorithm; The control quantity determination module is used to calculate the air conditioning duct control quantity through the PID control algorithm according to the obtained prediction model, and control the air conditioning duct based on the calculated air conditioning duct control quantity.

Images