An AI intelligent regulation-based drying and dehumidifying adaptive control method and system

Abstract

The application discloses a drying and dehumidifying self-adaptive control method and system based on AI intelligent regulation and control, belongs to the technical field of drying and dehumidifying regulation and control, and accurately predicts real-time processing mouth humidity and real-time equipment energy consumption through a drying and dehumidifying machine performance prediction model to obtain accurate prediction values, constructs a target optimization function corresponding to dehumidifying effect and equipment energy consumption for the prediction values, forms a drying and dehumidifying target regulation and optimization function which takes into account high-precision dehumidifying and deep energy saving, and performs accurate parameter optimization calculation according to the drying and dehumidifying target regulation and optimization function to accurately and efficiently obtain an optimal control parameter combination and generate corresponding drying and dehumidifying machine control instructions to accurately and dynamically and adaptively regulate and control the drying and dehumidifying machine, so that the drying and dehumidifying machine can always work in an optimal working state.

Description

Technical Field

[0001] This invention belongs to the technical field of drying and dehumidification control, specifically relating to an adaptive control method and system for drying and dehumidification based on AI intelligent control. Background Technology

[0002] Dehumidifiers are common equipment used in production and daily life for dehumidifying and drying food, medicinal materials, and other products. Their core function is to continuously provide low-dew-point dry air to dehumidify these products, then use high-temperature regeneration airflow to heat and dry them, and finally cool the products to obtain the desired dried state. In recent years, some intelligent dehumidifiers have emerged. However, the control strategies of these existing dehumidifiers mostly rely on experience-based settings based on fixed rules or simple PID open-loop control. This open-loop or simple feedback control method cannot adaptively sense and respond to real-time temperature and humidity fluctuations within the dehumidifier's chamber. This leads to the dehumidifier operating in an unoptimized state of over-dehumidification or under-dehumidification for extended periods. Over-dehumidification means consuming far more heat energy (for regeneration) and cold energy (for cooling) than actually needed, resulting in significant energy waste; while under-dehumidification directly leads to substandard product quality and safety.

[0003] As mentioned above, how to provide an AI-based intelligent control method and system for drying and dehumidification that can achieve both high-precision dehumidification and deep energy saving, and can perform accurate adaptive regulation, has become an urgent problem to be solved in this field. Summary of the Invention

[0004] The purpose of this invention is to provide an AI-based intelligent control method and system for drying and dehumidification to solve the aforementioned problems in the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides an adaptive control method for drying and dehumidifying based on AI intelligent regulation, comprising: Acquire real-time drying scene vector data and real-time equipment operation vector data of the drying and dehumidifying machine, and integrate the real-time drying scene vector data and the real-time equipment operation vector data to obtain real-time drying and dehumidifying status vector data; A preset drying and dehumidifying machine performance prediction model is obtained, and the real-time drying and dehumidifying state vector data is input into the drying and dehumidifying machine performance prediction model so as to output the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value through the drying and dehumidifying machine performance prediction model. The drying and dehumidifying machine performance prediction model includes a drying and dehumidifying machine simulation mechanism model and a data-driven compensation model connected in sequence. Obtain preset control targets and control constraints. Based on the control targets and control constraints, establish corresponding target optimization functions for the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value, respectively. Integrate the target optimization functions corresponding to the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value to form a drying and dehumidification target control optimization function. The decision variable of the drying and dehumidification target control optimization function is the combination of drying and dehumidification machine control parameters. Based on a preset AI intelligent control algorithm, the optimal decision variables of the drying and dehumidification target control optimization function are calculated. The optimal decision variables of the drying and dehumidification target control optimization function are used as the optimal control parameter combination. The corresponding drying and dehumidification machine control command is generated according to the optimal control parameter combination, so as to control the drying and dehumidification machine to perform adaptive adjustment through the drying and dehumidification machine control command.

[0006] In one possible design, real-time drying scenario vector data and real-time equipment operation vector data of the dryer / dehumidifier are acquired, and the real-time drying scenario vector data and the real-time equipment operation vector data are integrated to obtain real-time drying / dehumidification status vector data, including: The original ambient temperature information inside the drying and dehumidifying machine is collected by the temperature sensor inside the drying and dehumidifying machine, and the original ambient humidity information inside the drying and dehumidifying machine is collected by the humidity sensor inside the drying and dehumidifying machine. The original scene temperature information and the original scene humidity information are respectively screened for outliers and filled with missing values. The original scene temperature information and the original scene humidity information after outlier screening and missing value filling are then standardized to obtain real-time drying scene temperature data and real-time drying scene humidity data. The real-time drying scene temperature data and real-time drying scene humidity data are respectively structured and then vector-mapped to obtain real-time drying scene temperature vector data and real-time drying scene humidity vector data. The current operating parameters of the drying and dehumidifying machine are obtained, and the current operating parameters are used as real-time equipment operating data. The real-time equipment operating data is then processed in a structured manner and vector-mapped to obtain real-time equipment operating vector data. The real-time equipment operating vector data includes equipment drying process operating vector data and equipment dehumidification process operating vector data. The real-time drying scene temperature vector data and the real-time drying scene humidity vector data are concatenated to form the real-time drying scene vector data of the drying and dehumidifying machine, and the real-time drying scene vector data and the real-time equipment operation vector data are concatenated to form the real-time drying and dehumidifying status vector data of the drying and dehumidifying machine.

[0007] In one possible design, the pre-setting method for the performance prediction model of the dryer / dehumidifier includes: Obtain the geometric parameters and physical property parameters of the drying and dehumidifying machine, and use the geometric parameters and physical property parameters as fixed parameters to establish an initial simulation mechanism model of the drying and dehumidifying machine. The initial simulation mechanism model of the drying and dehumidifying machine includes multiple adjustable key model parameters. The adjustable key model parameters of the initial drying and dehumidifying machine simulation mechanism model are initialized by random parameter values ​​to form the initial adjustable key model parameters. Obtain the working records of the drying and dehumidifying machine, and extract historical working status and performance data of the drying and dehumidifying machine from the working records; Randomly select one historical drying and dehumidifying machine operating status performance data from the historical drying and dehumidifying machine operating status performance data as parameter setting reference data. Based on the parameter setting reference data, set the initial adjustable key model parameters of the initial drying and dehumidifying machine simulation mechanism model to obtain the reference adjustable key model parameters. Based on the aforementioned adjustable key model parameters and the aforementioned fixed parameters, the initial drying and dehumidifying machine simulation mechanism model is updated to the pre-drying and dehumidifying machine simulation mechanism model. The historical operating performance data of the drying and dehumidifying machine is used as training data for the simulation mechanism model of the drying and dehumidifying machine. The simulation mechanism model of the pre-drying and dehumidifying machine is iteratively trained based on the training data of the simulation mechanism model of the drying and dehumidifying machine to obtain the simulation mechanism model of the drying and dehumidifying machine. During the iterative training of the simulation mechanism model of the pre-drying dehumidifier, the simulation output value obtained in each training session is obtained. The simulation output value obtained in each training session is then compared with the training data of the simulation mechanism model of the drying dehumidifier to obtain the simulation output error value of each training session. The simulation output error value of each training session is then integrated with the training data of the simulation mechanism model of the drying dehumidifier to obtain the data-driven compensation model training data. A preset feedforward neural network model structure is obtained, and the model weights in the feedforward neural network model structure are initialized to obtain a pre-data-driven compensation model, wherein the feedforward neural network model structure includes at least 3 fully connected networks. Based on the training data of the data-driven compensation model, the pre-data-driven compensation model is iteratively trained to obtain the data-driven compensation model. The drying and dehumidifying machine simulation mechanism model is used as the drying and dehumidifying machine performance simulation and prediction layer, the data-driven compensation model is used as the drying and dehumidifying machine performance error compensation layer, and the first output terminal of the drying and dehumidifying machine performance simulation and prediction layer is connected to the first input terminal of the drying and dehumidifying machine performance error compensation layer. The input terminal of the drying and dehumidifying machine performance simulation prediction layer and the second input terminal of the drying and dehumidifying machine performance error compensation layer are connected to a preset model input layer, and the second output terminal of the drying and dehumidifying machine performance simulation prediction layer and the output terminal of the drying and dehumidifying machine performance error compensation layer are connected to a preset model output layer to construct a drying and dehumidifying machine performance prediction model. The model output layer is used to integrate the output of the drying and dehumidifying machine performance simulation prediction layer and the output of the drying and dehumidifying machine performance error compensation layer into a drying and dehumidifying machine performance prediction output, and then output it.

[0008] In one possible design, the real-time drying scenario vector data is input into the drying and dehumidifying machine performance prediction model, so that the model outputs real-time processing port humidity prediction values ​​and real-time equipment energy consumption prediction values, including: The real-time drying scenario vector data is used as input and input into the model input layer of the drying and dehumidifying machine performance prediction model; The model input layer of the drying and dehumidifying machine performance prediction model outputs the real-time drying scenario vector data to the drying and dehumidifying machine performance simulation prediction layer and the drying and dehumidifying machine performance error compensation layer, respectively. Using the drying and dehumidifying machine performance simulation prediction layer, the real-time drying scenario vector data is simulated and predicted to obtain the real-time processing port humidity simulation prediction value and the real-time equipment energy consumption simulation prediction value. The real-time processing port humidity simulation prediction value and the real-time equipment energy consumption simulation prediction value are then output to the drying and dehumidifying machine performance error compensation layer and the model output layer of the drying and dehumidifying machine performance prediction model. Using the drying and dehumidifying machine performance error compensation layer, error compensation calculations are performed on the real-time drying scenario vector data, the real-time processing port humidity simulation prediction value, and the real-time equipment energy consumption simulation prediction value to obtain the real-time processing port humidity simulation prediction error compensation value and the real-time equipment energy consumption simulation prediction error compensation value. The real-time processing port humidity simulation prediction error compensation value and the real-time equipment energy consumption simulation prediction error compensation value are then output to the model output layer of the drying and dehumidifying machine performance prediction model. Using the model output layer, the real-time processing port humidity simulation prediction error compensation value and the real-time processing port humidity simulation prediction value are summed to obtain the real-time processing port humidity prediction value. The real-time equipment energy consumption simulation prediction error compensation value and the real-time equipment energy consumption simulation prediction value are summed to obtain the real-time equipment energy consumption prediction value.

[0009] In one possible design, a preset control target and control constraints are obtained. Based on the control target and control constraints, corresponding target optimization functions are established for the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value, respectively. These target optimization functions are then integrated to form a drying and dehumidification target control optimization function, including: Multiple adjustable control parameters of the drying and dehumidifying machine are obtained. Based on each adjustable control parameter of the drying and dehumidifying machine, a combination of control parameters of the drying and dehumidifying machine is constructed, and the combination of control parameters of the drying and dehumidifying machine is defined as a decision variable. Obtain preset control targets and control constraints, wherein the control targets include the maximum target of achieving the humidity demand value of the treatment port and the minimum target of equipment energy consumption, and the control constraints include temperature constraints and wind speed constraints. Based on the maximum target of achieving the humidity demand value of the processing port, an objective function is established for the real-time humidity prediction value of the processing port regarding the decision variable, which serves as the humidity target optimization function; Based on the goal of minimizing equipment energy consumption, an objective function is established for the real-time predicted equipment energy consumption value regarding the decision variable, which serves as the energy consumption target optimization function. Obtain the preset target weight coefficients, and based on the target weight coefficients, integrate the humidity target optimization function and the energy consumption target optimization function into a drying and dehumidification target control optimization function using the following formula (1): (1) in, The target weight coefficient, This represents the humidity target optimization function. Denotes the energy consumption target optimization function. This represents the target control and optimization function for drying and dehumidification.

[0010] In one possible design, based on a preset AI intelligent control algorithm, the optimal decision variables of the drying and dehumidification target control optimization function are calculated, and the optimal decision variables of the drying and dehumidification target control optimization function are used as the optimal combination of control parameters, including: Based on the drying and dehumidification target control optimization function, the definition and value range of the decision variables are determined to construct the decision variable search space; A random particle is initialized in the search space of the decision variables, and the corresponding decision variable is randomly selected for the random particle as the initial individual historical optimal position of the random particle. Using a preset AI intelligent control algorithm, the initial individual historical optimal position of the random particle is updated, and the function value of the corresponding drying and dehumidification target control optimization function is calculated for the updated individual position of the random particle. The updated function value of the random particle is compared with the function value of the initial individual historical optimal position to obtain the comparison result. If the comparison result is that the function value corresponding to the random particle is lower than the function value of the individual's historical best position, then the updated position of the random particle is taken as the current individual's historical best position, so as to use the current individual's historical best position to perform the next round of iteration for the random particle; If the comparison result is that the function value corresponding to the random particle is not lower than the function value of the individual's historical best position, then the initial individual historical best position of the random particle is taken as the current individual historical best position, so as to use the current individual historical best position to perform the next round of iteration for the random particle; Obtain a preset iteration termination condition, perform multiple iterations on the random particle according to the iteration termination condition until termination, and obtain the stopping position of the random particle. Use the decision variable corresponding to the stopping position of the random particle as the optimal decision variable of the drying and dehumidification target control optimization function. The combination of control parameters for the drying and dehumidifying machine corresponding to the optimal decision variable is taken as the optimal control parameter combination.

[0011] In one possible design, a corresponding drying and dehumidifying machine control command is generated based on the optimal control parameter combination, so as to control the drying and dehumidifying machine to perform adaptive adjustment through the drying and dehumidifying machine control command, including: Obtain preset control constraints for the drying and dehumidifying machine, and perform a safety verification on the optimal control parameter combination based on the control constraints for the drying and dehumidifying machine; Obtain the current operating control parameters of the drying and dehumidifying machine. After passing the safety verification, calculate the difference between the optimal control parameter combination and the current operating control parameters to obtain the control parameter difference value. Based on the difference in the control parameters, a corresponding control command for the drying and dehumidifying machine is generated; The control command for the drying and dehumidifying machine is sent to the drying and dehumidifying machine to enable adaptive adjustment of the drying and dehumidifying machine.

[0012] Secondly, the present invention provides an AI-based intelligent control system for drying and dehumidifying, comprising: The data acquisition unit is used to acquire real-time drying scene vector data and real-time equipment operation vector data of the drying and dehumidifying machine, and integrate the real-time drying scene vector data and the real-time equipment operation vector data to obtain real-time drying and dehumidifying status vector data. The performance prediction unit is used to acquire a preset drying and dehumidifying machine performance prediction model, input the real-time drying and dehumidifying state vector data into the drying and dehumidifying machine performance prediction model, and output the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value through the drying and dehumidifying machine performance prediction model. The drying and dehumidifying machine performance prediction model includes a drying and dehumidifying machine simulation mechanism model and a data-driven compensation model connected in sequence. The objective function construction unit is used to obtain preset control objectives and control constraints. Based on the control objectives and control constraints, it establishes corresponding objective optimization functions for the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value, and integrates the objective optimization functions corresponding to the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value to form a drying and dehumidification objective control optimization function. The decision variable of the drying and dehumidification objective control optimization function is the combination of control parameters of the drying and dehumidification machine. The parameter optimization and instruction generation unit is used to calculate the optimal decision variables of the drying and dehumidification target regulation optimization function based on a preset AI intelligent regulation algorithm, use the optimal decision variables of the drying and dehumidification target regulation optimization function as the optimal control parameter combination, and generate corresponding drying and dehumidification machine control instructions according to the optimal control parameter combination, so as to control the drying and dehumidification machine to perform adaptive adjustment through the drying and dehumidification machine control instructions.

[0013] Thirdly, the present invention provides an electronic device comprising a memory, a processor, and a transceiver connected in sequence and communication, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the AI-based intelligent control method for drying and dehumidifying as described in the first aspect or any possible design of the first aspect.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the AI-based intelligent control method for drying and dehumidification as described in the first aspect or any possible design of the first aspect.

[0015] Fifthly, the present invention provides a computer program product containing instructions that, when the instructions are executed on a computer, cause the computer to perform the AI-based intelligent control method for drying and dehumidification as described in the first aspect or any possible design of the first aspect.

[0016] Beneficial Effects: A drying and dehumidification adaptive control method and system based on AI intelligent regulation includes: First, acquiring real-time drying scenario vector data and real-time equipment operation vector data of the drying and dehumidification machine, and integrating the real-time drying scenario vector data and the real-time equipment operation vector data to obtain real-time drying and dehumidification state vector data; Second, acquiring a preset drying and dehumidification machine performance prediction model, inputting the real-time drying and dehumidification state vector data into the drying and dehumidification machine performance prediction model, so as to output real-time processing port humidity prediction value and real-time equipment energy consumption prediction value through the drying and dehumidification machine performance prediction model, wherein the drying and dehumidification machine performance prediction model includes a drying and dehumidification machine simulation mechanism model and a data-driven compensation model connected in sequence; Then, acquiring a preset regulation target and regulation constraint, and based on the regulation... Based on the control objectives and the control constraints, corresponding target optimization functions are established for the real-time humidity prediction value at the processing port and the real-time energy consumption prediction value of the equipment. These target optimization functions are then integrated to form a drying and dehumidification target control optimization function, wherein the decision variable of the drying and dehumidification target control optimization function is the combination of drying and dehumidifier control parameters. Finally, based on a preset AI intelligent control algorithm, the optimal decision variable of the drying and dehumidification target control optimization function is calculated. This optimal decision variable is used as the optimal control parameter combination, and a corresponding drying and dehumidifier control command is generated based on the optimal control parameter combination to control the drying and dehumidifier for adaptive adjustment. By using a performance prediction model for the dehumidifier, the real-time humidity at the processing port and the real-time energy consumption of the equipment are accurately predicted to obtain accurate values. Based on the predicted values, a target optimization function corresponding to the dehumidification effect and equipment energy consumption is constructed to form a dehumidifier target control optimization function that takes into account both high-precision dehumidification and deep energy saving. Based on the dehumidifier target control optimization function, accurate parameter optimization calculations are performed to obtain the optimal combination of control parameters accurately and efficiently, and corresponding dehumidifier control commands are generated to perform accurate dynamic adaptive control of the dehumidifier, so as to ensure that the dehumidifier always works in the optimal working state. Attached Figure Description

[0017] Figure 1 A flowchart illustrating the AI-based intelligent control method for adaptive drying and dehumidification provided in this embodiment of the invention. Figure 2 A schematic diagram of the model structure of the performance prediction model for the dryer / dehumidifier provided in an embodiment of the present invention; Figure 3 A functional structure diagram of the AI-based intelligent control and drying / dehumidification adaptive control system provided in an embodiment of the present invention; Figure 4This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0019] It should be understood that although the terms first, second, etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, without departing from the scope of the exemplary embodiments of the invention.

[0020] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0021] Example: like Figure 1 As shown, the first aspect of this embodiment provides an adaptive control method for drying and dehumidifying based on AI intelligent regulation, which may include, but is not limited to, the following steps: S1. Obtain real-time drying scene vector data and real-time equipment operation vector data of the drying and dehumidifying machine, and integrate the real-time drying scene vector data and the real-time equipment operation vector data to obtain real-time drying and dehumidifying status vector data; In one possible implementation, step S1 involves acquiring real-time drying scene vector data and real-time equipment operation vector data of the dryer / dehumidifier, and integrating the real-time drying scene vector data and the real-time equipment operation vector data to obtain real-time drying / dehumidification status vector data. This can be, but is not limited to, decomposed into the following steps S11-15, specifically including: S11. Collect the original scene temperature information inside the drying and dehumidifying machine box through the temperature sensor installed inside the drying and dehumidifying machine, and collect the original scene humidity information inside the drying and dehumidifying machine box through the humidity sensor installed inside the drying and dehumidifying machine. S12. Perform outlier screening and missing value filling on the original scene temperature information and the original scene humidity information respectively, and perform standardization processing on the original scene temperature information and the original scene humidity information after outlier screening and missing value filling to obtain real-time drying scene temperature data and real-time drying scene humidity data. S13. The real-time drying scene temperature data and real-time drying scene humidity data are respectively structured and vector-mapped to obtain real-time drying scene temperature vector data and real-time drying scene humidity vector data. S14. Obtain the current operating parameters of the drying and dehumidifying machine, use the current operating parameters as real-time equipment operating data, perform structured processing and vector mapping on the real-time equipment operating data to obtain real-time equipment operating vector data, wherein the real-time equipment operating vector data includes equipment drying processing operating vector data and equipment dehumidification processing operating vector data; S15. The real-time drying scene temperature vector data and the real-time drying scene humidity vector data are concatenated to form the real-time drying scene vector data of the drying and dehumidifying machine, and the real-time drying scene vector data and the real-time equipment operation vector data are concatenated to form the real-time drying and dehumidifying status vector data of the drying and dehumidifying machine.

[0022] It should be noted that the AI-based intelligent control method for drying and dehumidification provided in this embodiment includes at least regeneration heating temperature data and regeneration heating wind speed data in the equipment drying operation vector data, and drying operation wind speed data in the equipment dehumidification operation vector data. In addition, in practical applications, the real-time equipment operation vector data also includes cooling medium flow rate data and real-time power data.

[0023] S2. Obtain a preset drying and dehumidifying machine performance prediction model, input the real-time drying and dehumidifying state vector data into the drying and dehumidifying machine performance prediction model, so as to output the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value through the drying and dehumidifying machine performance prediction model, wherein the drying and dehumidifying machine performance prediction model includes a drying and dehumidifying machine simulation mechanism model and a data-driven compensation model connected in sequence. like Figure 2 As shown, in one possible implementation, the preset method for the performance prediction model of the dryer / dehumidifier in step S2 may include, but is not limited to, the following steps S201-S2011, specifically: S201. Obtain the geometric parameters and physical property parameters of the drying and dehumidifying machine, and use the geometric parameters and physical property parameters as fixed parameters to establish an initial simulation mechanism model of the drying and dehumidifying machine, wherein the initial simulation mechanism model of the drying and dehumidifying machine includes multiple adjustable key model parameters; S202. Initialize the adjustable key model parameters of the initial drying and dehumidifying machine simulation mechanism model by using random parameter values ​​to form the initial adjustable key model parameters; S203. Obtain the working record of the drying and dehumidifying machine, and extract historical working status performance data of the drying and dehumidifying machine from the working record; S204. Randomly select one historical drying and dehumidifying machine operating status performance data from the historical drying and dehumidifying machine operating status performance data as parameter setting reference data. Based on the parameter setting reference data, set the initial adjustable key model parameters of the initial drying and dehumidifying machine simulation mechanism model to obtain the reference adjustable key model parameters. S205. Based on the reference adjustable key model parameters and the fixed parameters, update the initial drying dehumidifier simulation mechanism model to the pre-drying dehumidifier simulation mechanism model; S206. Use the historical operating status performance data of the drying and dehumidifying machine as training data for the simulation mechanism model of the drying and dehumidifying machine, and iteratively train the simulation mechanism model of the pre-drying and dehumidifying machine based on the training data of the simulation mechanism model of the drying and dehumidifying machine to obtain the simulation mechanism model of the drying and dehumidifying machine. S207. During the iterative training of the simulation mechanism model of the pre-drying dehumidifier, the simulation output obtained in each training session is obtained, and the simulation output obtained in each training session is compared with the training data of the simulation mechanism model of the drying dehumidifier to obtain the simulation output error value of each training session. The simulation output error value of each training session is integrated with the training data of the simulation mechanism model of the drying dehumidifier in a one-to-one correspondence to obtain the data-driven compensation model training data. S208. Obtain a preset feedforward neural network model structure and initialize the model weights in the feedforward neural network model structure to obtain a pre-data-driven compensation model, wherein the feedforward neural network model structure includes at least 3 fully connected networks. S209. Based on the training data of the data-driven compensation model, iteratively train the pre-data-driven compensation model to obtain the data-driven compensation model; S2010. The drying and dehumidifying machine simulation mechanism model is used as the drying and dehumidifying machine performance simulation prediction layer, the data-driven compensation model is used as the drying and dehumidifying machine performance error compensation layer, and the first output terminal of the drying and dehumidifying machine performance simulation prediction layer is connected to the first input terminal of the drying and dehumidifying machine performance error compensation layer. S2011. Connect the input terminal of the drying and dehumidifying machine performance simulation prediction layer and the second input terminal of the drying and dehumidifying machine performance error compensation layer to a preset model input layer, and connect the second output terminal of the drying and dehumidifying machine performance simulation prediction layer and the output terminal of the drying and dehumidifying machine performance error compensation layer to a preset model output layer to construct a drying and dehumidifying machine performance prediction model. The model output layer is used to integrate the output of the drying and dehumidifying machine performance simulation prediction layer and the output of the drying and dehumidifying machine performance error compensation layer into a drying and dehumidifying machine performance prediction output, and complete the output.

[0024] It should be noted that in the drying and dehumidifying machine performance prediction model provided in this embodiment, the model output layer is used to obtain the output of the drying and dehumidifying machine performance simulation prediction layer and the output of the drying and dehumidifying machine performance error compensation layer. The output of the drying and dehumidifying machine simulation mechanism model (drying and dehumidifying machine performance simulation prediction layer) is the performance simulation prediction value, and the output of the data-driven compensation model (drying and dehumidifying machine performance error compensation layer) is the error compensation value. By summing the performance simulation prediction value and the error compensation value, the final output of the drying and dehumidifying machine performance prediction model can be obtained. The drying and dehumidifying machine performance prediction output includes the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value. The geometric parameters of the drying and dehumidifying machine include at least the dimensions of the cold air channel, the dimensions of the regeneration air channel, and the ratio of the channel area of ​​the housing. The physical properties of the drying and dehumidifying machine include at least the regeneration airflow temperature, the regeneration air velocity, the drying air velocity, and the cooling air velocity.

[0025] In one possible implementation, step S2, where the real-time drying scenario vector data is input into the drying and dehumidifying machine performance prediction model, and the model outputs real-time processing port humidity prediction values ​​and real-time equipment energy consumption prediction values, can be decomposed into, but is not limited to, the following steps S21-S25, specifically including: S21. The real-time drying scenario vector data is used as input and input to the model input layer of the drying and dehumidifying machine performance prediction model; S22. The model input layer of the drying and dehumidifying machine performance prediction model outputs the real-time drying scenario vector data to the drying and dehumidifying machine performance simulation prediction layer and the drying and dehumidifying machine performance error compensation layer, respectively; S23. Using the drying and dehumidifying machine performance simulation prediction layer, the real-time drying scenario vector data is simulated and predicted to obtain the real-time processing port humidity simulation prediction value and the real-time equipment energy consumption simulation prediction value, and the real-time processing port humidity simulation prediction value and the real-time equipment energy consumption simulation prediction value are output to the drying and dehumidifying machine performance error compensation layer and the model output layer of the drying and dehumidifying machine performance prediction model. S24. Using the drying and dehumidifying machine performance error compensation layer, error compensation calculations are performed on the real-time drying scenario vector data, the real-time processing port humidity simulation prediction value, and the real-time equipment energy consumption simulation prediction value to obtain the real-time processing port humidity simulation prediction error compensation value and the real-time equipment energy consumption simulation prediction error compensation value. The real-time processing port humidity simulation prediction error compensation value and the real-time equipment energy consumption simulation prediction error compensation value are then output to the model output layer of the drying and dehumidifying machine performance prediction model. S25. Using the model output layer, sum the real-time processing port humidity simulation prediction error compensation value and the real-time processing port humidity simulation prediction value to obtain the real-time processing port humidity prediction value. Sum the real-time equipment energy consumption simulation prediction error compensation value and the real-time equipment energy consumption simulation prediction value to obtain the real-time equipment energy consumption prediction value.

[0026] It should be noted that the AI-based intelligent control method for drying and dehumidifying provided in this embodiment, through a performance prediction model that integrates a simulation mechanism model and a data-driven compensation model, not only possesses the interpretability of the physical working laws of the drying and dehumidifying machine but also ensures a strong error compensation capability for performance prediction. It can perform highly realistic simulation predictions of the humidity prediction value at the dehumidification port and the energy consumption of the drying and dehumidifying machine, obtaining accurate real-time humidity prediction values ​​and real-time energy consumption simulation prediction values. This allows the drying and dehumidifying machine to proactively and adaptively respond to fluctuations in the environment. Based on this accurate prediction, the adjustable parameters of the drying and dehumidifying machine can be quickly adjusted to the optimal level, achieving a humidity requirement rate of 97% or higher at the dehumidification port, providing a stable and reliable drying environment for the manufacturing of dried products.

[0027] Furthermore, the AI-based intelligent control method for drying and dehumidifying provided in this embodiment features a performance prediction model for the drying and dehumidifying machine with online calibration capabilities. This model automatically tracks performance drift caused by equipment aging, component contamination, or component replacement, ensuring that the performance prediction model remains consistent with the physical entity. This self-learning and adaptive capability ensures stable and improved performance of the drying and dehumidifying machine throughout its entire lifecycle, reducing maintenance costs associated with unexpected downtime.

[0028] S3. Obtain preset control targets and control constraints. Based on the control targets and control constraints, establish corresponding target optimization functions for the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value, and integrate the target optimization functions corresponding to the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value to form a drying and dehumidification target control optimization function. The decision variable of the drying and dehumidification target control optimization function is the combination of drying and dehumidification machine control parameters. In one possible implementation, in step S3, a preset control target and control constraint are obtained. Based on the control target and control constraint, corresponding target optimization functions are established for the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value, respectively. These target optimization functions are then integrated to form a drying and dehumidification target control optimization function. This can be decomposed into, but is not limited to, the following steps S31-S35, specifically including: S31. Obtain multiple adjustable control parameters of the drying and dehumidifying machine, and construct a control parameter combination for the drying and dehumidifying machine based on each adjustable control parameter, so as to define the control parameter combination for the drying and dehumidifying machine as a decision variable; S32. Obtain preset control targets and control constraints, wherein the control targets include the maximum target of the achievement rate of the humidity demand value of the treatment port and the minimum target of the equipment energy consumption, and the control constraints include temperature constraints and wind speed constraints; S33. Based on the maximum target of the humidity demand achievement rate of the processing port, establish an objective function for the real-time humidity prediction value of the processing port regarding the decision variable, as the humidity target optimization function; S34. Based on the target of minimizing equipment energy consumption, establish an objective function for the real-time predicted equipment energy consumption value with respect to the decision variable, as the energy consumption target optimization function; S35. Obtain the preset target weight coefficients, and based on the target weight coefficients, integrate the humidity target optimization function and the energy consumption target optimization function into a drying and dehumidification target control optimization function using the following formula (1): (1) in, The target weight coefficient, This represents the humidity target optimization function. Denotes the energy consumption target optimization function. This represents the target control and optimization function for drying and dehumidification.

[0029] The adjustable control parameters include at least the overall mass transfer coefficient and the convective heat transfer coefficient.

[0030] It should be noted that in the AI-based intelligent control method for drying and dehumidification provided in this embodiment, the humidity target optimization function describes the deviation between the simulated predicted humidity value at the treatment port and the required humidity value at the treatment port. The smaller this deviation, the higher the achievement rate of the required humidity value at the treatment port, and the larger the function value of the humidity target optimization function. The energy consumption target optimization function describes the magnitude of the real-time predicted energy consumption value of the equipment. The smaller the real-time predicted energy consumption value, the lower the energy consumption of the equipment, and the larger the function value of the energy consumption target optimization function. By introducing the target weight coefficient, the multi-objective problem of dehumidification performance and energy consumption index is effectively balanced, ultimately forming a problem of finding the minimum value of the drying and dehumidification target control optimization function. Through the design of the drying and dehumidification target control optimization function, it can be ensured that the optimal combination of control parameters obtained in the end prioritizes ensuring that the achievement rate of dehumidification and drying reaches a high standard while taking into account the controllable energy consumption of the drying and dehumidification machine, thus achieving precise, balanced, and stable equipment control.

[0031] It should be noted that the AI-based adaptive control method for drying and dehumidifying provided in this embodiment, through the construction of a target control optimization function for drying and dehumidifying, and the use of a preset AI intelligent control algorithm to perform online real-time optimization search on decision variables, can quickly explore the lowest energy consumption operating point that meets the strict humidity requirements of the drying and dehumidifying machine under the current operating conditions. The introduction of the target weight coefficient in the target control optimization function allows this embodiment to achieve an optimal balance between ensuring dehumidification accuracy and deep energy saving, avoiding a large amount of unnecessary regenerative heating and cooling energy consumption. Simulation experiments conducted under varying operating conditions using the target control optimization function for drying and dehumidifying show that the adaptive control method in this embodiment can reduce the overall energy consumption of the drying and dehumidifying machine by an average of 10%-30% or more in over 30 experiments, resulting in significant energy cost savings for the drying and dehumidifying machine.

[0032] S4. Based on a preset AI intelligent control algorithm, calculate the optimal decision variable of the drying and dehumidification target control optimization function, use the optimal decision variable of the drying and dehumidification target control optimization function as the optimal control parameter combination, and generate a corresponding drying and dehumidification machine control command according to the optimal control parameter combination, so as to control the drying and dehumidification machine to perform adaptive adjustment through the drying and dehumidification machine control command.

[0033] In one possible implementation, step S4, based on a preset AI intelligent control algorithm, calculates the optimal decision variable of the drying and dehumidification target control optimization function, and uses the optimal decision variable of the drying and dehumidification target control optimization function as the optimal control parameter combination. This can be decomposed into, but is not limited to, the following steps S41-S47, specifically including: S41. Based on the drying and dehumidification target control optimization function, determine the definition and value range of the decision variables to construct the decision variable search space; S42. Initialize random particles in the decision variable search space, and randomly select the corresponding decision variables for the random particles as the initial individual historical optimal position of the random particles; S43. Using a preset AI intelligent control algorithm, update the initial individual historical optimal position of the random particle, and calculate the function value of the corresponding drying and dehumidification target control optimization function for the updated individual position of the random particle. Compare the updated function value of the random particle with the function value of the initial individual historical optimal position to obtain the comparison result. S44. If the comparison result is that the function value corresponding to the random particle is lower than the function value of the individual's historical best position, then the updated position of the random particle is taken as the current individual's historical best position, so as to use the current individual's historical best position to perform the next round of iteration on the random particle; S45. If the comparison result is that the function value corresponding to the random particle is not lower than the function value of the individual's historical best position, then the initial individual historical best position of the random particle is taken as the current individual historical best position, so as to use the current individual historical best position to perform the next round of iteration on the random particle; S46. Obtain a preset iteration termination condition, perform multiple iterations on the random particle according to the iteration termination condition until termination, and obtain the stopping position of the random particle, and use the decision variable corresponding to the stopping position of the random particle as the optimal decision variable of the drying and dehumidification target control optimization function. S47. The combination of control parameters for the drying and dehumidifying machine corresponding to the optimal decision variable is taken as the optimal control parameter combination.

[0034] In one possible implementation, step S4, generating a corresponding drying and dehumidifying machine control command based on the optimal control parameter combination, to control the drying and dehumidifying machine for adaptive adjustment via the drying and dehumidifying machine control command, can be decomposed into, but is not limited to, the following steps S48-S411, specifically including: S48. Obtain preset control constraints for the drying and dehumidifying machine, and perform a safety verification on the optimal control parameter combination based on the control constraints for the drying and dehumidifying machine; S49. Obtain the current operating control parameters of the drying and dehumidifying machine. After passing the safety verification, calculate the difference between the optimal control parameter combination and the current operating control parameters to obtain the control parameter difference value. S410. Generate corresponding control instructions for the drying and dehumidifying machine based on the difference in the control parameters; S411. Send the control command of the drying and dehumidifying machine to the drying and dehumidifying machine to perform adaptive adjustment of the drying and dehumidifying machine.

[0035] It should be noted that the AI-based intelligent control method for drying and dehumidification provided in this embodiment requires no manual intervention throughout the entire adaptive control process. From data acquisition, performance prediction, intelligent decision-making to execution adjustment, the entire process is autonomously and adaptively adjusted, achieving unmanned intelligent operation.

[0036] like Figure 3 As shown, the second aspect of this embodiment provides a hardware system for implementing the AI-based intelligent control method for adaptive drying and dehumidification described in the first aspect of the embodiment, including: The data acquisition unit is used to acquire real-time drying scene vector data and real-time equipment operation vector data of the drying and dehumidifying machine, and integrate the real-time drying scene vector data and the real-time equipment operation vector data to obtain real-time drying and dehumidifying status vector data. The performance prediction unit is used to acquire a preset drying and dehumidifying machine performance prediction model, input the real-time drying and dehumidifying state vector data into the drying and dehumidifying machine performance prediction model, and output the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value through the drying and dehumidifying machine performance prediction model. The drying and dehumidifying machine performance prediction model includes a drying and dehumidifying machine simulation mechanism model and a data-driven compensation model connected in sequence. The objective function construction unit is used to obtain preset control objectives and control constraints. Based on the control objectives and control constraints, it establishes corresponding objective optimization functions for the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value, and integrates the objective optimization functions corresponding to the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value to form a drying and dehumidification objective control optimization function. The decision variable of the drying and dehumidification objective control optimization function is the combination of control parameters of the drying and dehumidification machine. The parameter optimization and instruction generation unit is used to calculate the optimal decision variables of the drying and dehumidification target regulation optimization function based on a preset AI intelligent regulation algorithm, use the optimal decision variables of the drying and dehumidification target regulation optimization function as the optimal control parameter combination, and generate corresponding drying and dehumidification machine control instructions according to the optimal control parameter combination, so as to control the drying and dehumidification machine to perform adaptive adjustment through the drying and dehumidification machine control instructions.

[0037] The working process, working details and technical effects of the system provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0038] like Figure 4As shown, the third aspect of this embodiment provides an electronic device, including: a memory, a processor, and a transceiver that are sequentially and communicatively connected, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the AI-based intelligent control method for drying and dehumidifying adaptive control as described in the first aspect of the embodiment.

[0039] For specific examples, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; specifically, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor, also known as the CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state.

[0040] In some embodiments, the processor may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. For example, the processor may not be limited to microprocessors of the STM32F105 series, reduced instruction set computer (RISC) microprocessors, x86 architecture processors, or processors with integrated neural network processing units (NPUs). The transceiver may be, but is not limited to, a Wi-Fi transceiver, a Bluetooth transceiver, a General Packet Radio Service (GPRS) transceiver, a ZigBee transceiver (a low-power LAN protocol based on the IEEE 802.15.4 standard), a 3G transceiver, a 4G transceiver, and / or a 5G transceiver. Furthermore, the device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0041] The working process, working details and technical effects of the electronic device provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0042] The fourth aspect of this embodiment provides a storage medium that stores instructions containing the AI-based intelligent control method for drying and dehumidification as described in the first aspect of the embodiment. That is, the storage medium stores instructions that, when executed on a computer, perform the AI-based intelligent control method for drying and dehumidification as described in the first aspect of the embodiment.

[0043] The storage medium refers to a carrier for storing data, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or memory sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0044] The working process, working details and technical effects of the storage medium provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0045] The fifth aspect of this embodiment provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the AI-based intelligent control method for drying and dehumidification as described in the first aspect of this embodiment. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0046] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A drying and dehumidification adaptive control method based on AI intelligent regulation, characterized in that, include: Acquire real-time drying scene vector data and real-time equipment operation vector data of the drying and dehumidifying machine, and integrate the real-time drying scene vector data and the real-time equipment operation vector data to obtain real-time drying and dehumidifying status vector data; A preset drying and dehumidifying machine performance prediction model is obtained, and the real-time drying and dehumidifying state vector data is input into the drying and dehumidifying machine performance prediction model so as to output the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value through the drying and dehumidifying machine performance prediction model. The drying and dehumidifying machine performance prediction model includes a drying and dehumidifying machine simulation mechanism model and a data-driven compensation model connected in sequence. Obtain preset control targets and control constraints. Based on the control targets and control constraints, establish corresponding target optimization functions for the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value, respectively. Integrate the target optimization functions corresponding to the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value to form a drying and dehumidification target control optimization function. The decision variable of the drying and dehumidification target control optimization function is the combination of drying and dehumidification machine control parameters. Based on a preset AI intelligent control algorithm, the optimal decision variables of the drying and dehumidification target control optimization function are calculated. The optimal decision variables of the drying and dehumidification target control optimization function are used as the optimal control parameter combination. The corresponding drying and dehumidification machine control command is generated according to the optimal control parameter combination, so as to control the drying and dehumidification machine to perform adaptive adjustment through the drying and dehumidification machine control command.

2. The adaptive control method for drying and dehumidification based on AI intelligent regulation according to claim 1, characterized in that, Acquire real-time drying scene vector data and real-time equipment operation vector data of the dryer / dehumidifier, and integrate the real-time drying scene vector data and the real-time equipment operation vector data to obtain real-time drying / dehumidification status vector data, including: The original ambient temperature information inside the drying and dehumidifying machine is collected by the temperature sensor inside the drying and dehumidifying machine, and the original ambient humidity information inside the drying and dehumidifying machine is collected by the humidity sensor inside the drying and dehumidifying machine. The original scene temperature information and the original scene humidity information are respectively screened for outliers and filled with missing values. The original scene temperature information and the original scene humidity information after outlier screening and missing value filling are then standardized to obtain real-time drying scene temperature data and real-time drying scene humidity data. The real-time drying scene temperature data and real-time drying scene humidity data are respectively structured and then vector-mapped to obtain real-time drying scene temperature vector data and real-time drying scene humidity vector data. The current operating parameters of the drying and dehumidifying machine are obtained, and the current operating parameters are used as real-time equipment operating data. The real-time equipment operating data is then processed in a structured manner and vector-mapped to obtain real-time equipment operating vector data. The real-time equipment operating vector data includes equipment drying process operating vector data and equipment dehumidification process operating vector data. The real-time drying scene temperature vector data and the real-time drying scene humidity vector data are concatenated to form the real-time drying scene vector data of the drying and dehumidifying machine, and the real-time drying scene vector data and the real-time equipment operation vector data are concatenated to form the real-time drying and dehumidifying status vector data of the drying and dehumidifying machine.

3. The adaptive control method for drying and dehumidification based on AI intelligent regulation according to claim 1, characterized in that, The preset method for the performance prediction model of the dryer / dehumidifier includes: Obtain the geometric parameters and physical property parameters of the drying and dehumidifying machine, and use the geometric parameters and physical property parameters as fixed parameters to establish an initial simulation mechanism model of the drying and dehumidifying machine. The initial simulation mechanism model of the drying and dehumidifying machine includes multiple adjustable key model parameters. The adjustable key model parameters of the initial drying and dehumidifying machine simulation mechanism model are initialized by random parameter values ​​to form the initial adjustable key model parameters. Obtain the working records of the drying and dehumidifying machine, and extract historical working status and performance data of the drying and dehumidifying machine from the working records; Randomly select one historical drying and dehumidifying machine operating status performance data from the historical drying and dehumidifying machine operating status performance data as parameter setting reference data. Based on the parameter setting reference data, set the initial adjustable key model parameters of the initial drying and dehumidifying machine simulation mechanism model to obtain the reference adjustable key model parameters. Based on the aforementioned adjustable key model parameters and the aforementioned fixed parameters, the initial drying and dehumidifying machine simulation mechanism model is updated to the pre-drying and dehumidifying machine simulation mechanism model. The historical operating performance data of the drying and dehumidifying machine is used as training data for the simulation mechanism model of the drying and dehumidifying machine. The simulation mechanism model of the pre-drying and dehumidifying machine is iteratively trained based on the training data of the simulation mechanism model of the drying and dehumidifying machine to obtain the simulation mechanism model of the drying and dehumidifying machine. During the iterative training of the simulation mechanism model of the pre-drying dehumidifier, the simulation output value obtained in each training session is obtained. The simulation output value obtained in each training session is then compared with the training data of the simulation mechanism model of the drying dehumidifier to obtain the simulation output error value of each training session. The simulation output error value of each training session is then integrated with the training data of the simulation mechanism model of the drying dehumidifier to obtain the data-driven compensation model training data. A preset feedforward neural network model structure is obtained, and the model weights in the feedforward neural network model structure are initialized to obtain a pre-data-driven compensation model, wherein the feedforward neural network model structure includes at least 3 fully connected networks. Based on the training data of the data-driven compensation model, the pre-data-driven compensation model is iteratively trained to obtain the data-driven compensation model. The drying and dehumidifying machine simulation mechanism model is used as the drying and dehumidifying machine performance simulation and prediction layer, the data-driven compensation model is used as the drying and dehumidifying machine performance error compensation layer, and the first output terminal of the drying and dehumidifying machine performance simulation and prediction layer is connected to the first input terminal of the drying and dehumidifying machine performance error compensation layer. The input terminal of the drying and dehumidifying machine performance simulation prediction layer and the second input terminal of the drying and dehumidifying machine performance error compensation layer are connected to a preset model input layer, and the second output terminal of the drying and dehumidifying machine performance simulation prediction layer and the output terminal of the drying and dehumidifying machine performance error compensation layer are connected to a preset model output layer to construct a drying and dehumidifying machine performance prediction model. The model output layer is used to integrate the output of the drying and dehumidifying machine performance simulation prediction layer and the output of the drying and dehumidifying machine performance error compensation layer into a drying and dehumidifying machine performance prediction output, and then output it.

4. The adaptive control method for drying and dehumidification based on AI intelligent regulation according to claim 3, characterized in that, The real-time drying scenario vector data is input into the drying and dehumidifying machine performance prediction model to output real-time processing port humidity prediction values ​​and real-time equipment energy consumption prediction values, including: The real-time drying scenario vector data is used as input and input into the model input layer of the drying and dehumidifying machine performance prediction model; The model input layer of the drying and dehumidifying machine performance prediction model outputs the real-time drying scenario vector data to the drying and dehumidifying machine performance simulation prediction layer and the drying and dehumidifying machine performance error compensation layer, respectively. Using the drying and dehumidifying machine performance simulation prediction layer, the real-time drying scenario vector data is simulated and predicted to obtain the real-time processing port humidity simulation prediction value and the real-time equipment energy consumption simulation prediction value. The real-time processing port humidity simulation prediction value and the real-time equipment energy consumption simulation prediction value are then output to the drying and dehumidifying machine performance error compensation layer and the model output layer of the drying and dehumidifying machine performance prediction model. Using the drying and dehumidifying machine performance error compensation layer, error compensation calculations are performed on the real-time drying scenario vector data, the real-time processing port humidity simulation prediction value, and the real-time equipment energy consumption simulation prediction value to obtain the real-time processing port humidity simulation prediction error compensation value and the real-time equipment energy consumption simulation prediction error compensation value. The real-time processing port humidity simulation prediction error compensation value and the real-time equipment energy consumption simulation prediction error compensation value are then output to the model output layer of the drying and dehumidifying machine performance prediction model. Using the model output layer, the real-time processing port humidity simulation prediction error compensation value and the real-time processing port humidity simulation prediction value are summed to obtain the real-time processing port humidity prediction value. The real-time equipment energy consumption simulation prediction error compensation value and the real-time equipment energy consumption simulation prediction value are summed to obtain the real-time equipment energy consumption prediction value.

5. The adaptive control method for drying and dehumidification based on AI intelligent regulation according to claim 1, characterized in that, Obtain preset control targets and constraints. Based on the control targets and constraints, establish corresponding target optimization functions for the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value, respectively. Integrate the target optimization functions corresponding to the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value to form a drying and dehumidification target control optimization function, including: Multiple adjustable control parameters of the drying and dehumidifying machine are obtained. Based on each adjustable control parameter of the drying and dehumidifying machine, a combination of control parameters of the drying and dehumidifying machine is constructed, and the combination of control parameters of the drying and dehumidifying machine is defined as a decision variable. Obtain preset control targets and control constraints, wherein the control targets include the maximum target of achieving the humidity demand value of the treatment port and the minimum target of equipment energy consumption, and the control constraints include temperature constraints and wind speed constraints. Based on the maximum target of achieving the humidity demand value of the processing port, an objective function is established for the real-time humidity prediction value of the processing port regarding the decision variable, which serves as the humidity target optimization function; Based on the goal of minimizing equipment energy consumption, an objective function is established for the real-time predicted equipment energy consumption value regarding the decision variable, which serves as the energy consumption target optimization function. Obtain the preset target weight coefficients, and based on the target weight coefficients, integrate the humidity target optimization function and the energy consumption target optimization function into a drying and dehumidification target control optimization function using the following formula (1): （1） in, The target weight coefficient, This represents the humidity target optimization function. Denotes the energy consumption target optimization function. This represents the target control and optimization function for drying and dehumidification.

6. The adaptive control method for drying and dehumidification based on AI intelligent regulation according to claim 1, characterized in that, Based on a preset AI intelligent control algorithm, the optimal decision variables of the drying and dehumidification target control optimization function are calculated, and the optimal decision variables of the drying and dehumidification target control optimization function are used as the optimal control parameter combination, including: Based on the drying and dehumidification target control optimization function, the definition and value range of the decision variables are determined to construct the decision variable search space; A random particle is initialized in the search space of the decision variables, and the corresponding decision variable is randomly selected for the random particle as the initial individual historical optimal position of the random particle. Using a preset AI intelligent control algorithm, the initial individual historical optimal position of the random particle is updated, and the function value of the corresponding drying and dehumidification target control optimization function is calculated for the updated individual position of the random particle. The updated function value of the random particle is compared with the function value of the initial individual historical optimal position to obtain the comparison result. If the comparison result is that the function value corresponding to the random particle is lower than the function value of the individual's historical best position, then the updated position of the random particle is taken as the current individual's historical best position, so as to use the current individual's historical best position to perform the next round of iteration for the random particle; If the comparison result is that the function value corresponding to the random particle is not lower than the function value of the individual's historical best position, then the initial individual historical best position of the random particle is taken as the current individual historical best position, so as to use the current individual historical best position to perform the next round of iteration for the random particle; Obtain a preset iteration termination condition, perform multiple iterations on the random particle according to the iteration termination condition until termination, and obtain the stopping position of the random particle. Use the decision variable corresponding to the stopping position of the random particle as the optimal decision variable of the drying and dehumidification target control optimization function. The combination of control parameters for the drying and dehumidifying machine corresponding to the optimal decision variable is taken as the optimal control parameter combination.

7. The adaptive control method for drying and dehumidification based on AI intelligent regulation according to claim 6, characterized in that, Generate corresponding control commands for the drying and dehumidifying machine based on the optimal control parameter combination, and control the drying and dehumidifying machine to perform adaptive adjustment through the control commands, including: Obtain preset control constraints for the drying and dehumidifying machine, and perform a safety verification on the optimal control parameter combination based on the control constraints for the drying and dehumidifying machine; Obtain the current operating control parameters of the drying and dehumidifying machine. After passing the safety verification, calculate the difference between the optimal control parameter combination and the current operating control parameters to obtain the control parameter difference value. Based on the difference in the control parameters, a corresponding control command for the drying and dehumidifying machine is generated; The control command for the drying and dehumidifying machine is sent to the drying and dehumidifying machine to enable adaptive adjustment of the drying and dehumidifying machine.

8. A drying and dehumidification adaptive control system based on AI intelligent regulation, characterized in that, The drying and dehumidification adaptive control method based on AI intelligent regulation, as described in any one of claims 1 to 7, includes: The data acquisition unit is used to acquire real-time drying scene vector data and real-time equipment operation vector data of the drying and dehumidifying machine, and integrate the real-time drying scene vector data and the real-time equipment operation vector data to obtain real-time drying and dehumidifying status vector data. The performance prediction unit is used to acquire a preset drying and dehumidifying machine performance prediction model, input the real-time drying and dehumidifying state vector data into the drying and dehumidifying machine performance prediction model, and output the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value through the drying and dehumidifying machine performance prediction model. The drying and dehumidifying machine performance prediction model includes a drying and dehumidifying machine simulation mechanism model and a data-driven compensation model connected in sequence. The objective function construction unit is used to obtain preset control objectives and control constraints. Based on the control objectives and control constraints, it establishes corresponding objective optimization functions for the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value, and integrates the objective optimization functions corresponding to the real-time processing port humidity prediction value and the real-time equipment energy consumption prediction value to form a drying and dehumidification objective control optimization function. The decision variable of the drying and dehumidification objective control optimization function is the combination of control parameters of the drying and dehumidification machine. The parameter optimization and instruction generation unit is used to calculate the optimal decision variables of the drying and dehumidification target regulation optimization function based on a preset AI intelligent regulation algorithm, use the optimal decision variables of the drying and dehumidification target regulation optimization function as the optimal control parameter combination, and generate corresponding drying and dehumidification machine control instructions according to the optimal control parameter combination, so as to control the drying and dehumidification machine to perform adaptive adjustment through the drying and dehumidification machine control instructions.

9. An electronic device, characterized in that, The device includes a memory, a processor, and a transceiver that are connected in sequence. The memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the AI-based intelligent control method for drying and dehumidification as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or the instructions are executed by the computer, they implement the AI-based intelligent control method for drying and dehumidification as described in any one of claims 1 to 7.

Images