Rotary dehumidification system control optimization method and system based on digital drive and Internet of Things platform, medium, program product and terminal

Abstract

The invention provides a rotary dehumidification system control optimization method and system based on digital driving and an Internet of Things platform, a medium, a program product and a terminal. Through the control optimization method combining digital driving and the Internet of Things technology, the operation state of the system is monitored in real time; and key operation parameters such as rotating wheel rotating speed, regenerated air temperature and air volume are dynamically adjusted, so that the humidity control precision is improved, the energy consumption is reduced, and the adaptability of the system to complex working conditions is enhanced. According to the method, an architecture platform of'edge end + cloud end + terminal equipment 'is established, the edge end is responsible for improving the response speed of local control, and the cloud end is responsible for performing long-term data analysis, optimization and feedback, so that the rotating wheel dehumidification system can perform real-time monitoring and dynamic adjustment, the dehumidification efficiency is improved, the energy consumption is reduced, and the energy-saving target is achieved; and the optimal dehumidification effect can be achieved under various working conditions.

Description

Technical Field

[0001] The present application relates to the field of industrial energy saving and intelligent control technology, and in particular to a control optimization method, system, medium, program product and terminal for a rotary dehumidification system based on digital drive and an Internet of Things platform. Background Art

[0002] In industrial fields that require strict humidity control, such as the manufacture of lithium batteries, the production of pharmaceutical products, and the processing of precision machinery, the rotary dehumidification system has demonstrated its irreplaceable importance and key role. The rotary dehumidification system ensures the stability and reliability of product quality during the production process by accurately controlling air humidity, thus playing a core role in maintaining industrial production environment standards.

[0003] At present, the control of the rotary dehumidification system mainly relies on the traditional PID control method and the rule-based control method. The traditional PID control method adjusts the temperature and humidity close to the target value through real-time feedback adjustment, and has a good control effect when the dehumidification demand is relatively stable. The rule-based control method usually adjusts the rotor speed, regeneration temperature and wind speed according to empirical rules or preset parameters to achieve the humidity control target. In addition, some systems also use a fixed value control method, that is, set fixed parameters of the rotor and fan according to specific environmental conditions, and achieve the dehumidification effect by increasing the processing air volume or increasing the regeneration temperature.

[0004] However, these control methods still have some limitations: although traditional PID control methods and rule-based control methods perform well in stable environments, they are not flexible enough to adapt to rapidly changing humidity requirements when the environment changes. Although the fixed value control method is simple to implement and has a fast response speed, its effect is relatively limited in more complex scenarios due to the lack of dynamic adjustment capabilities. Therefore, these control methods will cause energy waste and low humidity control accuracy when facing complex environmental changes. Summary of the invention

[0005] In view of the above-mentioned shortcomings of the prior art, the present invention provides a rotary dehumidification system control optimization method, system, medium, program product and terminal based on digital drive and Internet of Things platform, which are used to solve the problem that the prior art cannot achieve humidity control accuracy and energy consumption optimization under complex working conditions.

[0006] To achieve the above-mentioned purpose and other related purposes, the first aspect of the present application provides a control optimization method for a rotary dehumidification system based on a digital drive and an Internet of Things platform, comprising: collecting real-time operation data of a rotary dehumidification system that is communicated with the edge terminal through the edge terminal, and preprocessing the real-time operation data of the rotary dehumidification system; inputting the preprocessed real-time operation data into a pre-built system multi-objective control optimization model deployed on the cloud, and using an improved particle swarm algorithm to solve the system multi-objective control optimization model to obtain an optimal control strategy for the operation of the rotary dehumidification system; the cloud terminal sends the optimal control strategy to the edge terminal through the MQTT protocol, and the edge terminal issues a control instruction to the rotary dehumidification system based on the optimal control strategy, so that the rotary dehumidification system executes the optimal control strategy in real time according to the control instruction.

[0007] In some embodiments of the first aspect of the present application, the construction process of the pre-built system multi-objective control optimization model includes: using a machine learning method to build and train a system multi-objective prediction model based on the historical operating data of the rotary dehumidification system; establishing a system multi-objective control optimization model based on the system multi-objective prediction model in combination with optimization objectives and constraints.

[0008] In some embodiments of the first aspect of the present application, the system multi-objective prediction model includes: a wheel humidity adsorption prediction model, a wheel temperature change prediction model, a cooling consumption prediction model, an electric power consumption prediction model, a heat exchanger energy consumption prediction model, and a dew point temperature prediction model.

[0009] In some embodiments of the first aspect of the present application, the improved particle swarm algorithm includes: using an adaptive weight factor and a dynamic contraction mechanism to adjust the particle speed.

[0010] In some embodiments of the first aspect of the present application, the process of using an improved particle swarm algorithm to solve the multi-objective control optimization model of the system includes: initializing the speed and position of each particle in the particle population, each particle corresponds to each optimization objective, and calculating the fitness function value of each particle; calculating the individual optimal solution of each particle and the global optimal solution of the particle population; updating the speed and position of each particle, and determining whether the maximum number of iterations has been reached, if so, stopping the iteration, otherwise repeating the above steps.

[0011] In some embodiments of the first aspect of the present application, the calculation formula of the fitness function value is: ;in, is the fitness function value of the current particle, is the total energy consumption of the system, is the target humidity value, is the actual humidity value, and is the corresponding weight coefficient.

[0012] To achieve the above-mentioned purpose and other related purposes, the second aspect of the present application provides a rotary dehumidification system control optimization system based on digital drive and Internet of Things platform, including: a data acquisition and processing module, which is used to collect real-time operation data of the rotary dehumidification system connected to it through the edge end, and pre-process the real-time operation data of the rotary dehumidification system; an optimal control strategy acquisition module, which is used to input the pre-processed real-time operation data into a pre-built system multi-objective control optimization model deployed on the cloud, and use an improved particle swarm algorithm to solve the system multi-objective control optimization model to obtain the optimal control strategy for the operation of the rotary dehumidification system; a control instruction execution module, which is used for the cloud end to send the optimal control strategy to the edge end through the MQTT protocol, and the edge end issues a control instruction to the rotary dehumidification system based on the optimal control strategy, so that the rotary dehumidification system executes the optimal control strategy in real time according to the control instruction.

[0013] To achieve the above-mentioned purpose and other related purposes, the third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the control optimization method of the rotary dehumidification system based on digital drive and Internet of Things platform is implemented.

[0014] To achieve the above-mentioned purpose and other related purposes, the fourth aspect of the present application provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer implements the control optimization method of the rotary dehumidification system based on digital drive and Internet of Things platform.

[0015] To achieve the above-mentioned purpose and other related purposes, the fifth aspect of the present application provides an electronic terminal, including a memory, a processor and a computer program stored in the memory; the processor executes the computer program to implement the control optimization method of the rotary dehumidification system based on digital drive and Internet of Things platform.

[0016] As described above, the rotary dehumidification system control optimization method, system, medium, program product and terminal provided by the present application based on digital drive and Internet of Things platform have the following beneficial effects:

[0017] (1) This application is to improve the intelligent control level of the rotary dehumidification system by combining digital drive and Internet of Things technology. The method monitors the operating status of the system in real time and dynamically adjusts key operating parameters such as the rotary speed, regeneration air temperature and air volume to improve the accuracy of humidity control, reduce energy consumption, and enhance the system's adaptability to complex working conditions.

[0018] (2) This application realizes real-time data monitoring, dynamic adjustment and intelligent optimization of the rotary dehumidification system by building an "edge + cloud + terminal device" architecture platform. In this architecture, the edge is responsible for improving the response speed of local control, while the cloud is responsible for long-term data analysis, optimization and feedback, so that the rotary dehumidification system can be monitored and adjusted dynamically in real time, which not only improves the dehumidification efficiency, reduces energy consumption, and achieves the energy-saving goal, but also ensures that the best dehumidification effect can be achieved under various working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 Shown is a flow chart of a method for optimizing the control of a rotary dehumidification system based on digital drive and an Internet of Things platform in one embodiment of the present application.

[0020] Figure 2 Shown is a flowchart of a construction process of a pre-built system multi-objective control optimization model in one embodiment of the present application.

[0021] Figure 3 Shown is a structural schematic diagram of an improved particle swarm algorithm solution in one embodiment of the present application.

[0022] Figure 4 Shown is a specific embodiment diagram of a rotary dehumidification system control optimization method based on digital drive and Internet of Things platform in one embodiment of the present application.

[0023] Figure 5 Shown is a structural schematic diagram of a rotary dehumidification system control optimization system based on digital drive and Internet of Things platform in one embodiment of the present application.

[0024] Figure 6 Shown is a schematic diagram of the structure of an electronic terminal in one embodiment of the present application. DETAILED DESCRIPTION

[0025] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0026] Before further describing the present invention in detail, the nouns and terms involved in the embodiments of the present invention are explained. The nouns and terms involved in the embodiments of the present invention are applicable to the following interpretations:

[0027] <1> Rotary dehumidification system: a system that uses physical principles to remove water vapor from the air. It is widely used in dehumidification of household appliances, vehicle interiors, automobiles, industrial enterprises and other industrial equipment. It is an effective dehumidification method that is energy-saving and pollution-free. The rotary dehumidification system is an environmentally friendly energy-saving dehumidification system. It adopts a precise constant temperature control method, which can automatically adjust the air humidity, achieve accurate humidity control, save energy, reduce pollution, and achieve energy conservation and emission reduction.

[0028] <2> Internet of Things (IoT) platform: It is a network composed of the Internet, traditional telecommunications networks, sensor networks and other networks. It allows objects to connect to each other and exchange data through embedded systems without the need for direct interaction between people or between people and devices. Its core is "connecting things to things", that is, connecting objects in the real world to the Internet through information sensing devices to achieve intelligent identification, positioning, tracking, monitoring and management.

[0029] <3> MQTT (Message Queuing Telemetry Transport): MQTT is a message protocol based on the publish-subscribe paradigm under the ISO standard (ISO / IEC PRF 20922). MQTT is a client-server based publish / subscribe message transport protocol. It works on top of the TCP / IP protocol and is a publish / subscribe message protocol designed for remote devices with low hardware performance and poor network conditions. The MQTT protocol is lightweight, simple, open and easy to implement, which makes it very widely applicable. In many cases, including restricted environments, such as machine-to-machine (M2M) communication and the Internet of Things (IoT).

[0030] <4> Machine Learning Methods: Machine learning methods are an important field in computer science, mainly based on probability theory, statistics, information theory, optimization theory, computational theory and other disciplines. It involves the process of using algorithms to allow computer systems to learn from data and make predictions or decisions. Machine learning methods can be divided into supervised learning, unsupervised learning and reinforcement learning. Machine learning methods are widely used in various fields, such as natural language processing, image recognition, recommendation systems, etc.

[0031] <5> Support Vector Machine (SVM) is a supervised learning algorithm mainly used for classification and regression analysis. Its basic idea is to find a hyperplane that separates data points of different categories. This hyperplane makes the data points of each category as far away from it as possible. The advantages of SVM are that it has good generalization ability, robustness and strong adaptability, and it shows excellent performance when processing small samples, nonlinear and high-dimensional data. Support vector machine is a powerful and flexible machine learning algorithm, which has a wide range of applications in many fields, such as text classification, image recognition, bioinformatics, etc.

[0032] <6> Multilayer Perceptron (MLP): MLP is a neural network model consisting of multiple neurons, which are connected through fully connected layers. Each neuron receives an input signal and outputs a nonlinear result through an activation function (such as Siqmoid, ReLU). The back propagation algorithm is used to adjust the weight of each connection so that the model can better fit the data. Due to its powerful expression ability and flexibility, MLP is widely used in various machine learning tasks.

[0033] <7> XGBoost (Extreme Gradient Boosting) is a machine learning algorithm based on gradient boosting decision trees. It improves on the original GBDT (Gradient Boosting Decision Tree) by optimizing the objective function and regularization term, which greatly improves the model effect. The core idea of ​​XGBoost is to use the ensemble learning method - Boosting idea, which integrates multiple weak learners into a strong learner through a certain method. Specifically, XGBoost uses multiple trees to make decisions together. The result of each tree is the difference between the target value and the prediction results of all previous trees, and all the results are accumulated to get the final result, so as to improve the effect of the entire model.

[0034] The existing rotary dehumidification system control has the following technical problems: (1) Poor adaptability: Traditional PID controllers rely on fixed control parameters. When environmental conditions change significantly (such as seasonal changes or operating conditions), the control effect may drop significantly, and it is impossible to provide a stable dehumidification effect under dynamic conditions. (2) High energy consumption: In traditional control methods, in order to ensure that the humidity reaches the target value, it is often necessary to set a higher regeneration temperature or increase the air volume, which easily leads to high overall energy consumption of the system. However, traditional PID controllers cannot effectively optimize the balance between various parameters, resulting in insufficient energy consumption control in actual operation. (3) Dependence on manual adjustment: Rule-based control methods usually rely on the experience of operators, lack data-driven dynamic optimization, and are difficult to automatically adjust to the optimal state. In more complex environments, manual parameter adjustment is time-consuming and lacks accuracy. (4) Difficulty in handling complex working conditions: Traditional PID controllers and fixed value control methods perform poorly when facing multivariable and nonlinear systems, and it is difficult to achieve effective control of the multidimensional parameters of the rotary dehumidification system. For example, there is a complex coupling relationship between the air temperature, humidity, air volume, and regeneration temperature in the system. It is difficult for traditional methods to achieve linkage optimization control of these variables.

[0035] Therefore, the present application provides a rotary dehumidification system control optimization method, system, medium, program product and terminal based on digital drive and Internet of Things platform, which can not only dynamically adapt to the changing environment, accurately regulate the key operating parameters of the rotary dehumidification system and optimize energy consumption management, but also improve the operating efficiency and stability of the system. It has important practical significance and broad application prospects.

[0036] To facilitate understanding of the embodiments of the present application, first Figure 1 Detailed description. Figure 1 The flowchart of a rotary dehumidification system control optimization method based on digital drive and Internet of Things platform in an embodiment of the present invention is shown. The rotary dehumidification system control optimization method based on digital drive and Internet of Things platform in this embodiment mainly includes the following steps:

[0037] Step S11: collecting the real-time operation data of the rotary dehumidification system connected to the rotary dehumidification system through the edge end, and preprocessing the real-time operation data of the rotary dehumidification system.

[0038] It should be understood that the rotary dehumidification system, as a terminal device, includes a dehumidification wheel, a regeneration fan, and a temperature and humidity sensor, etc., which are used for air dehumidification and temperature and humidity control. Among them, the dehumidification wheel is the core component of the rotary dehumidification system. The surface of the dehumidification wheel is coated with a hygroscopic material (such as silica gel), and the surface is provided with a honeycomb multi-porous channel. The wheel is usually divided into a processing area and a regeneration area. When the air passes through the processing area, the moisture is adsorbed by the hygroscopic material, and when passing through the regeneration area, the hygroscopic material releases moisture and is regenerated. The regeneration fan is used to transport heated regeneration air for the regeneration process of the wheel. The fan blows the hot air through the regeneration area of ​​the wheel to release the moisture in the hygroscopic material, thereby restoring the dehumidification capacity of the wheel to ensure the recycling capacity of the hygroscopic material. The temperature and humidity sensor is used to monitor the air temperature and humidity in real time during the operation of the rotary dehumidification system to ensure that the system can obtain accurate operating data in real time under the current operating state.

[0039] The rotary dehumidification system is equipped with a data acquisition module, which acquires the air temperature and humidity collected by the temperature and humidity sensor, the regeneration air temperature, the rotor speed collected by the speed sensor, the wind speed and air volume measured by the wind speed sensor and other operating data in real time. These data can fully reflect the working status of the rotary dehumidification system and ensure the accuracy of subsequent optimization. At the same time, the rotary dehumidification system is connected to the edge end in communication, and the real-time operating data obtained by the data acquisition module is transmitted to the edge end. The edge end includes an edge computing gateway. As the local computing unit of the rotary dehumidification system, the edge computing gateway is responsible for collecting and processing real-time operating data, that is, after the edge computing gateway receives the real-time operating data transmitted by the rotary dehumidification system, it also pre-processes the real-time operating data.

[0040] In one embodiment of the present invention, the method of preprocessing the real-time operation data of the rotary dehumidification system includes: cleaning the collected real-time operation data of the rotary dehumidification system to remove outliers and noise; normalizing the cleaned real-time operation data so that various types of real-time operation data can be effectively compared in subsequent processes; integrating the normalized operation data to form a unified operation database. Specifically, the edge computing gateway at the edge end collects the operation data of the rotary dehumidification system in real time, such as key operating parameters such as air temperature and humidity, regeneration wind temperature, rotary wheel speed, wind speed, and air volume. After collecting the data, the collected real-time operation data is cleaned to remove outliers and noise, such as data anomalies caused by external factors, so as to ensure the high quality and stability of the data and ensure the accuracy of the data.

[0041] Furthermore, since the dimensions of various operating parameters after cleaning are different, it is necessary to standardize the data of different units and dimensions so that they fall within a unified range, that is, to normalize the various types of collected operating data, which can improve the stability and accuracy of the calculation, thereby ensuring that different data can be effectively compared in the subsequent modeling and optimization process, improving the convergence speed and accuracy of model training, enhancing the system's adaptability and response efficiency, and providing strong data support for system optimization and control. The calculation formula for normalizing real-time operating data is as follows:

[0042] ;(Formula 1)

[0043] ;(Formula 2)

[0044] in, represents the input variable; represents the output variable; and They refer to The minimum and maximum values ​​of ; and They refer to The minimum and maximum values ​​of ; and They represent the normalized input and output variables respectively.

[0045] The cleaned and normalized operating data are integrated to form a unified rotary dehumidification system operation database, providing a solid data foundation for subsequent modeling and optimization processes.

[0046] Step S12: input the preprocessed real-time operation data into a pre-built system multi-objective control optimization model deployed on the cloud, and use an improved particle swarm algorithm to solve the system multi-objective control optimization model to obtain the optimal control strategy for the operation of the rotary dehumidification system.

[0047] It should be noted that the edge end is connected to the terminal device (rotary dehumidification system), and the cloud end is connected to the edge end through the MQTT protocol. The cloud end deploys the pre-built system multi-objective control optimization model in advance, and the edge end sends the pre-processed real-time operation data to the cloud end through the MQTT protocol. The cloud end receives the pre-processed real-time operation data and inputs it into the pre-built system multi-objective control optimization model for analysis and optimization.

[0048] It should be understood that the edge is configured to communicate directly with the rotary dehumidification system and collect the real-time operating data of the warm rotary dehumidification system. These data are pre-processed at the edge, which can reduce the amount of data subsequently transmitted to the cloud and improve transmission efficiency. Through the MQTT protocol, the edge sends the processed data to the cloud in real time, and the cloud responds immediately, providing optimization control instructions, and then sends the control instructions to the edge through the MQTT protocol to achieve real-time control and optimization of the rotary dehumidification system. That is, the communication between the edge and the cloud through the MQTT protocol can achieve efficient data transmission and real-time control, and ensure stable data transmission. The multi-objective control optimization model pre-deployed in the cloud can use these real-time operating data to optimize and control the system and improve the performance and efficiency of the rotary dehumidification system.

[0049] In one embodiment of the present invention, Figure 2 As shown, the construction process of the pre-built system multi-objective control optimization model includes:

[0050] Step S21: using a machine learning method to construct and train a system multi-objective prediction model based on the historical operating data of the rotary dehumidification system.

[0051] It should be noted that based on the historical operation data of the rotary dehumidification system, it is divided into a training set and a test set, and a system multi-objective prediction model is established using a machine learning method. The training set is input into the system multi-objective prediction model for training, and then tested with the test set to obtain a system multi-objective prediction model with high prediction accuracy. The system multi-objective prediction model predicts energy consumption, temperature and humidity under different input conditions, thereby providing data support and decision-making basis for subsequent optimization analysis of the system.

[0052] In some examples, the system multi-objective prediction model includes: a wheel humidity adsorption prediction model, a wheel temperature change prediction model, a cooling consumption prediction model, an electric power consumption prediction model, a heat exchanger energy consumption prediction model, and a dew point temperature prediction model.

[0053] In this embodiment, the system multi-objective prediction model includes multiple prediction models, through which energy consumption prediction, temperature and humidity prediction, etc. can be performed for different positions or areas in the rotary dehumidification system, thereby realizing a comprehensive analysis of the multi-dimensional operating parameters of the system. Through a comprehensive analysis of the multi-dimensional operating parameters, an optimization strategy for the overall control of the system can be obtained, which can help achieve optimal control of energy consumption and temperature and humidity under different environmental conditions, thereby improving the energy efficiency and performance of the rotary dehumidification system.

[0054] In some examples, the construction process of the wheel humidity adsorption prediction model and the wheel temperature change prediction model is as follows: using the support vector machine method (SVM) in machine learning, the wheel humidity adsorption prediction model and the wheel temperature change prediction model are respectively constructed and trained through the historical operation data of the wheel dehumidification system. The historical operation data includes the front surface cold temperature, the front surface cold humidity, the regeneration temperature, the processing fan frequency, the regeneration fan frequency, etc.

[0055] It should be understood that the support vector machine method can handle complex nonlinear relationships. Based on the support vector machine method, the wheel humidity adsorption prediction model and the wheel temperature change prediction model of the wheel treatment area are established, which can predict the humidity and temperature response under different input conditions, thereby realizing the accurate prediction of the wheel treatment area of ​​the wheel dehumidification system under different environmental inputs. Because the model can predict humidity and temperature changes in real time, it can provide support for real-time control and regulation of the wheel system. Optimizing operations through the prediction results of the prediction model can reduce additional costs caused by improper operation and improve economic benefits.

[0056] In some examples, the process of constructing a cooling consumption prediction model is as follows: Based on the historical operation data of the rotary dehumidification system, a multi-layer perceptron neural network method (MLP) is used to construct and train the cooling consumption prediction model. The historical operation data is divided into input and output, the input is the initial air temperature and humidity, and the rotary speed, and the output is the required cooling capacity. Then, the constructed cooling consumption prediction model is trained. The trained cooling consumption prediction model can dynamically evaluate the cooling demand under different operating conditions, so as to estimate the system energy consumption in the subsequent temperature and humidity control.

[0057] Specifically, the multi-layer perceptron neural network method can capture the complex relationship between input parameters (such as initial air temperature and humidity, rotor speed) and the required cooling capacity. The model built using the multi-layer perceptron neural network can adapt to different input parameter ranges, has good flexibility, and can handle a variety of different air states and rotor operating conditions. The constructed prediction model can respond to changes in input parameters in real time, quickly predict the required cooling capacity, and help achieve real-time energy consumption control.

[0058] In some examples, the process of constructing the electric power consumption prediction model is as follows: constructing and training the electric power consumption prediction model based on the historical operation data of the rotary dehumidification system using a multi-layer perceptron neural network method. After the model is constructed, the input parameters for training the model are valve opening, processing fan frequency, regeneration fan frequency, etc., and the output parameter is fan power, so as to obtain the electric power consumption prediction model through training.

[0059] It should be noted that the power consumption prediction model predicts the real-time power consumption of the rotary dehumidification system, that is, predicts the power demand of the system under different operating conditions. Since the power consumption of the system control cabinet and the rotary motor is constant, the main focus is on the power fluctuations of the processing fan and the regeneration fan. According to the model prediction results, the main factors of energy consumption changes can be identified, which helps to achieve energy efficiency optimization.

[0060] In some examples, the process of building a heat exchanger energy consumption prediction model is as follows: Based on the historical operation data of the rotary dehumidification system, the extreme gradient boosting decision tree algorithm (XGBoost) is used to build and train the heat exchanger energy consumption prediction model. The input of the training model is air temperature, humidity, air volume, etc., and the output is the energy consumption of the heat exchanger.

[0061] It should be noted that the traditional heat exchanger energy consumption calculation uses a thermal balance method, which has many limitations. For example, this method relies on experience and iterative calculations, is difficult to cope with complex working conditions, has cumbersome calculation steps, and cannot adapt to dynamic changes. In this embodiment, the heat exchanger energy consumption prediction model is established through the extreme gradient boosting decision tree algorithm in the machine learning method, which can predict the heat transfer power of each heat exchanger under different working conditions. The extreme gradient boosting decision tree algorithm can capture complex nonlinear relationships, thereby processing complex data relationships and patterns. The use of this algorithm can also improve the robustness of the prediction model and reduce the risk of overfitting. At the same time, it also reduces the reliance on manual experience and iterative calculations, thereby reducing human errors and improving the reliability of predictions.

[0062] In some examples, the dew point temperature prediction model is constructed by using a support vector machine method based on historical operating data of a rotary dehumidification system to construct and train a dew point temperature prediction model. The input parameters for model construction are historical operating parameters such as ambient temperature, humidity, and fan frequency, and the output is a dew point temperature prediction value.

[0063] It is worth noting that the support vector machine method is particularly good at dealing with small samples and nonlinear problems, so it can provide high accuracy when predicting dew point temperature. The model is trained based on multiple input parameters such as ambient temperature, humidity, fan frequency, etc., so that it can adapt to different operating conditions and accurately predict dew point temperature. According to the model, the air dew point temperature is predicted in real time under the current operating conditions, providing immediate data support for workshop humidity control, which helps to meet the workshop's precise control needs for humidity. The model can maintain good prediction accuracy under changing temperature and humidity conditions, that is, by accurately predicting the dew point temperature, it can provide an important basis for humidity control, thereby realizing the optimized operation of the rotary dehumidification system, reducing energy consumption, improving energy efficiency, and thus reducing operating costs.

[0064] It should be understood that during the operation of the rotary dehumidification system, there is a delay in the acquisition of data such as energy consumption or temperature changes. Therefore, it is necessary to build a corresponding prediction model to input the real-time operation data of the system to predict the current energy consumption or temperature change data, so as to provide data support for subsequent energy consumption analysis and humidity control analysis.

[0065] It should be emphasized that in this embodiment, multiple prediction models are constructed by machine learning methods, which can achieve accurate prediction of the rotary dehumidification system under different operating conditions. The machine learning method can provide more accurate prediction results by learning historical operating data under different operating conditions, especially when processing large amounts of data, it can discover complex patterns and trends in the data; once the prediction model constructed by machine learning is trained, it can quickly predict new data with a high degree of automation, saving a lot of time and computing resources; the prediction model constructed by machine learning has good adaptability and generalization ability, can adapt to the performance changes of the rotary dehumidification system under different operating conditions, and can be generalized to unseen data; the machine learning prediction model can be integrated into the real-time running rotary dehumidification system to provide real-time rotary dehumidification system energy consumption and temperature and humidity prediction, etc., which is helpful for timely maintenance and optimization of operations.

[0066] Step S22: Establish a system multi-objective control optimization model based on the system multi-objective prediction model combined with optimization objectives and constraints. In order to significantly reduce the energy consumption of the rotary dehumidification system, improve the dehumidification efficiency, and ensure that the best dehumidification effect can be achieved under various working conditions, this embodiment constructs a system multi-objective control optimization model based on the system multi-objective prediction model combined with pre-set optimization objectives and constraints.

[0067] In some examples, the optimization objectives include minimizing total system energy consumption and ensuring that the dew point temperature meets preset requirements.

[0068] Specifically, under the premise of meeting the humidity requirements of the production workshop, the total energy consumption of the system is minimized by optimizing key operating parameters such as the rotor speed, regeneration temperature and air volume. The method to minimize the total energy consumption of the system is to comprehensively consider the energy consumption of the heat exchanger, the cooling capacity consumption and the electrical power consumption to minimize the total energy consumption of the system. The calculation formula of the total energy consumption of the system is as follows:

[0069] ;(Formula 3)

[0070] in, is the total energy consumption of the system, is the energy consumption of the heat exchanger; is the cooling consumption; For electrical power consumption.

[0071] It should be noted that the energy consumption of the heat exchanger, the cooling consumption, and the electric power consumption are obtained through the heat exchanger energy consumption prediction model, the cooling consumption prediction model, and the electric power consumption prediction model in the system multi-objective prediction model. The real-time operation data of the rotary dehumidification system is input into each prediction model in the system multi-objective prediction model to predict the corresponding energy consumption or consumption. The calculation formula of the total energy consumption of the system is input according to the obtained energy consumption or consumption, so as to obtain the total energy consumption of the system. The operating parameters of the rotary dehumidification system are further optimized and adjusted to minimize the total energy consumption of the system, thereby reducing energy consumption, reducing operating costs, and improving economic benefits.

[0072] Furthermore, the dew point temperature meeting the preset requirements means ensuring that the air dew point temperature meets the control standard within the set humidity threshold, so as to achieve the precise requirements for humidity control of the rotary dehumidification system.

[0073] ;(Formula 4)

[0074] in, is the dew point temperature, is the minimum dew point temperature, It is the maximum dew point temperature. It should be noted that the preset requirement of the dew point temperature is set according to actual conditions and is not limited in this embodiment.

[0075] In some examples, the constraints include: fresh air valve opening constraint, regeneration fan frequency constraint, processing fan frequency constraint, regeneration temperature setting constraint, supply air temperature setting constraint, and control workshop humidity requirement constraint.

[0076] It should be noted that in order to ensure the stable operation of the rotary dehumidification system and the safety of the equipment, a series of reasonable constraints need to be added to the system multi-objective control optimization model. These constraints include factors such as the working range of the equipment and the humidity requirements of the control workshop. The setting of each control parameter needs to be within a certain range, otherwise it may cause the equipment to fail to operate stably or affect the life of the equipment, thereby affecting the reliability and durability of the entire system. The constraints for the operation of the rotary dehumidification system equipment are specifically as follows:

[0077] (1) Fresh air valve opening constraint:

[0078] ;(Formula 5)

[0079] in, Open for fresh air, is the minimum fresh air opening, is the maximum fresh air opening. Preferably, Set it to 30%, Set to 40%.

[0080] (2) Regeneration fan frequency constraint:

[0081] ;(Formula 6)

[0082] in, is the regeneration fan frequency, is the minimum regeneration fan frequency, is the maximum regeneration fan frequency. Preferably, Set to 32Hz, Set to 50Hz.

[0083] (3) Dealing with fan frequency constraints:

[0084] ;(Formula 7)

[0085] in, To handle fan frequency, is the minimum processing fan frequency, is the maximum processing fan frequency. Preferably, Set to 35Hz, Set to 50Hz.

[0086] (4) Regeneration temperature setting constraints:

[0087] ;(Formula 8)

[0088] in, is the regeneration temperature, is the minimum regeneration temperature, is the maximum regeneration temperature. Preferably, Set to 90℃, Set to 140°C.

[0089] (5) Supply air temperature setting constraints:

[0090] ;(Formula 9)

[0091] in, is the supply air temperature, is the maximum air supply temperature. Preferably, Set to 20℃.

[0092] (6) Constraints on workshop humidity requirements:

[0093] ;(Formula 10)

[0094] in, is the workshop humidity, is the maximum workshop humidity. Preferably, Set to -50°C.

[0095] Combining the above optimization objectives and constraints, the system multi-objective control optimization model can be expressed as:

[0096] ;(Formula 11)

[0097] in, Optimize the multi-objective control model for the system.

[0098] It should be noted that by solving the multi-objective control optimization model of the system, the operating parameters of the rotary dehumidification system can be optimized and controlled, unnecessary energy consumption can be reduced, and rational use of energy and cost savings can be achieved.

[0099] In one embodiment of the present invention, the improved particle swarm algorithm includes: using an adaptive weight factor and a dynamic contraction mechanism to adjust the particle speed.

[0100] It should be noted that the improved particle swarm algorithm is suitable for complex multi-parameter optimization problems, and its heuristic search can quickly converge to the global optimal solution. In this embodiment, when the improved particle swarm algorithm is used to solve the system multi-objective control optimization model of the rotary dehumidification system, the particle speed is adjusted by introducing an adaptive weight factor and a dynamic contraction mechanism, which can effectively balance the algorithm's exploration ability between global search and local search, avoid falling into a local optimal solution, and improve the algorithm's convergence speed and solution accuracy.

[0101] Adaptive weight factor refers to the strategy of dynamically adjusting the inertia weight in the particle swarm algorithm. This strategy balances the global search ability and local search ability of the algorithm at different stages of the search, thereby avoiding the algorithm from converging to the local optimal solution too early and improving the convergence speed. Specifically, in the early stage of the search, a larger inertia weight helps particles to conduct a large-scale global search to escape the local optimal solution. Therefore, the inertia weight is increased in the early stage of the search to ensure the global search ability; then, as the iteration proceeds, reducing the inertia weight can enhance the local search ability of the particles to refine the search for the optimal solution. Therefore, in the later stage, the inertia weight is reduced to promote local convergence, thereby improving the convergence speed.

[0102] The dynamic shrinkage mechanism refers to the introduction of a shrinkage factor in the particle swarm algorithm to dynamically adjust the moving step of the particles, gradually narrowing the search space, thereby improving the solution accuracy. Specifically, by introducing the shrinkage factor, the moving step of the particles can be controlled, and as the number of iterations increases, the search range of the particles gradually narrows, and the search will focus on those areas that are more likely to contain the optimal solution, so that the optimal solution can be approached more finely, improving the solution accuracy.

[0103] In summary, the improved particle swarm algorithm in this embodiment effectively improves the global search capability, local convergence speed and solution accuracy of the algorithm through adaptive weight factors and dynamic shrinkage mechanism, while avoiding falling into local optimality, and enhancing the adaptability and stability of the algorithm.

[0104] In one embodiment of the present invention, Figure 3 As shown in FIG. 1 , the process of using the improved particle swarm algorithm to solve the multi-objective control optimization model of the system includes: initializing the speed and position of each particle in the particle population, each particle corresponds to each optimization target, and calculating the fitness function value of each particle; calculating the individual optimal solution of each particle and the global optimal solution of the particle population; updating the speed and position of each particle, and judging whether the maximum number of iterations is reached, if so, stopping the iteration, otherwise repeating the above steps.

[0105] It should be noted that, in this embodiment, a method for solving the multi-objective control optimization model of the system based on the improved particle swarm algorithm is provided. First, each particle in the particle population corresponds to each optimization target, then each particle in the particle population is initialized, and the fitness function value of each particle is calculated. Then, the individual optimal solution of each particle and the global optimal solution of the particle population are calculated respectively, and the speed and position of each particle are updated based on this. At this time, the number of iterations is increased by one and compared with the maximum number of iterations to determine whether the maximum number of iterations is reached. If it is reached, the iteration is terminated to obtain the optimal control strategy. If not, the initialization is continued, and the above steps are repeated until the number of iterations is reached to obtain the optimal control strategy.

[0106] In some examples, the fitness function value is calculated as:

[0107] ;(Formula 12)

[0108] in, is the fitness function value of the current particle, is the total energy consumption of the system, is the target humidity value, is the actual humidity value, and is the corresponding weight coefficient, and the setting of the weight coefficient can balance the energy consumption and humidity control accuracy.

[0109] It should be understood that the optimal control strategy is a control strategy for dynamically adjusting the operating parameters of the rotary dehumidification system obtained by solving the optimization model. By adjusting the operating parameters in real time, the energy consumption of the rotary dehumidification system can be significantly reduced, the dehumidification effect can be optimized, and energy waste can be reduced. The optimized energy efficiency reaches the expected goal of the system. In this embodiment, the improved particle swarm algorithm is used to solve the multi-objective control optimization model of the system, which can not only improve the solution speed and solution accuracy, but also enable the system to cope with environmental changes and complex working conditions to ensure the real-time dynamic adjustment and operation stability of the rotary dehumidification system.

[0110] Step S13: The cloud sends the optimal control strategy to the edge via the MQTT protocol, and the edge sends a control instruction to the rotary dehumidification system based on the optimal control strategy, so that the rotary dehumidification system executes the optimal control strategy in real time according to the control instruction.

[0111] It should be noted that the pre-built system multi-objective control optimization model and improved particle swarm algorithm are deployed in the cloud. After the cloud obtains the pre-processed real-time operation data sent by the edge, it is input into the system multi-objective control optimization model, and then the improved particle swarm algorithm is used to solve the system multi-objective control optimization model to obtain the optimal control strategy of the rotary dehumidification system. Because the edge and the cloud are connected through the MQTT protocol, that is, the optimal control strategy is sent to the edge via the MQTT protocol at this time, the edge sends the control instructions of the optimal control strategy to the rotary dehumidification system, and the rotary dehumidification system dynamically adjusts the key operating parameters according to the optimal control strategy to meet the low energy consumption requirements and workshop humidity control requirements, and ensure the real-time response and stability of the system operation.

[0112] In this embodiment, a layered architecture platform of "edge + cloud + terminal device" is constructed based on the Internet of Things platform technology. In this architecture platform, the edge end collects the real-time operation data of the terminal device (rotary dehumidification system) in real time and uploads it to the cloud. The cloud inputs the real-time operation data into the optimization model and uses the optimization algorithm for solution analysis, and can periodically output the optimal control strategy. The edge end receives the optimal control strategy from the cloud and adjusts the key operating parameters of the rotary dehumidification system such as the rotation speed, regeneration temperature and air volume in real time to adapt to the dynamic changes of the environment and ensure the efficient operation and optimal control of the rotary dehumidification system.

[0113] This embodiment also combines machine learning and optimization algorithms in digital drive to predict the behavior and performance of the system in advance, so that problems can be discovered and solved in the early stages, reducing the cost of subsequent modifications. The control of the rotary dehumidification system is also more intelligent and automated, improving system efficiency and performance.

[0114] It should be emphasized that the cloud regularly updates the model and optimizes the operating parameters through long-term data analysis, optimization and feedback mechanism, and generates the optimal control strategy and sends it to the edge. The cloud continuously optimizes the control strategy to ensure that the system can be optimized in real time under different working conditions, achieve efficient and stable operation, and improve the intelligence level of the system. The edge adjusts the key operating parameters of the system in real time according to the optimization results of the cloud, and provides feedback and dynamic adjustments based on the actual operating data to ensure the adaptability and stability of the system. The implementation of the control optimization method in this embodiment significantly improves the energy efficiency and humidity control capability of the rotary dehumidification system, so that the system can dynamically adjust the operating parameters according to the real-time operating data, improve the humidity control accuracy of the system and reduce energy consumption. At the same time, through automated optimization control, the intervention of operators is reduced, and the accuracy and efficiency of operation are improved.

[0115] In order to facilitate the description of the rotary dehumidification system control optimization method based on digital drive and Internet of Things platform of the present invention, Figure 4 , the following specific examples are provided for illustration.

[0116] An "edge + cloud + rotary dehumidification system" architecture platform is constructed. The rotary dehumidification system includes a rotary wheel, a regeneration fan, a heater and other equipment. The data acquisition module collects the real-time operation data of these equipment, including air temperature and humidity, rotary wheel speed, wind speed, etc., and sends these real-time operation data to the edge; the edge computing gateway at the edge receives the real-time operation data for preprocessing, and sends the preprocessed real-time operation data to the cloud; the system multi-objective control optimization model deployed in the cloud receives the real-time operation data, and uses the improved particle swarm algorithm to solve the system multi-objective control optimization model to generate the optimal control strategy; the cloud feeds back the optimal control strategy to the edge, and the edge sends the control command to execute the control strategy to the rotary dehumidification system. The rotary dehumidification system executes the optimal control strategy to adjust the rotary wheel speed, adjust the frequency of the regeneration fan, adjust the temperature of the heater, etc., thereby achieving the goals of reducing energy consumption and precise humidity control of the rotary dehumidification system.

[0117] It is worth noting that the beneficial effects of the rotary dehumidification system control optimization method based on digital drive and Internet of Things platform provided in this embodiment are specifically manifested as follows:

[0118] (1) Optimizing energy efficiency: Through real-time data monitoring and dynamic optimization based on the Internet of Things platform, the rotary dehumidification system can achieve precise adjustment of operating parameters such as rotary wheel speed, regeneration temperature and air volume, thereby significantly reducing the energy consumption of the system, optimizing the dehumidification effect and reducing energy waste.

[0119] (2) Precise humidity control: Using the improved particle swarm optimization algorithm, the system can adaptively adjust key operating parameters to ensure precise humidity control under different environmental conditions, avoiding the humidity fluctuation problem existing in traditional control methods and improving the humidity control accuracy and stability.

[0120] (3) Pre-response and intelligent control: Combining edge computing with cloud optimization, the system uses pre-response control to detect environmental and load changes in advance and dynamically adjust operating parameters to quickly respond to environmental changes. At the same time, long-term optimization is performed in the cloud, reducing the need for manual intervention and significantly enhancing the system's intelligence level and response speed.

[0121] In the embodiments of the present application, words such as "first" and "second" are used to distinguish the same or similar items with substantially the same functions and effects, and do not limit their order. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0122] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" represent examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0123] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc or abc, where a, b, c can be single or multiple.

[0124] Figure 5 Schematic diagram of the control optimization system of the rotary dehumidification system based on digital drive and Internet of Things platform provided by the embodiment of the present application. Figure 5 As shown, the rotary dehumidification system control optimization system 500 based on digital drive and Internet of Things platform includes:

[0125] The data acquisition and processing module 501 is used to acquire the real-time operation data of the rotary dehumidification system connected to the rotary dehumidification system through the edge end, and pre-process the real-time operation data of the rotary dehumidification system;

[0126] The optimal control strategy acquisition module 502 is used to input the pre-processed real-time operation data into a pre-built system multi-objective control optimization model deployed in the cloud, and solve the system multi-objective control optimization model using an improved particle swarm algorithm to obtain the optimal control strategy for the operation of the rotary dehumidification system;

[0127] The control instruction execution module 503 is used for the cloud to send the optimal control strategy to the edge end through the MQTT protocol, and the edge end sends a control instruction to the rotary dehumidification system based on the optimal control strategy, so that the rotary dehumidification system executes the optimal control strategy in real time according to the control instruction.

[0128] It should be understood that the specific process of each module executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0129] It should also be understood that the division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0130] Figure 6 is a schematic block diagram of an electronic terminal provided in an embodiment of the present application. Figure 6 As shown, the electronic terminal includes: at least one processor 601, a memory 602, at least one network interface 603 and a user interface 605. The various components in the device are coupled together through a bus system 604. It can be understood that the bus system 604 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 604 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 6 In the specification, various buses are labeled as bus systems.

[0131] The user interface 605 may include a display, a keyboard, a mouse, a trackball, a click gun, keys, buttons, a touch pad or a touch screen.

[0132] It is understood that the memory 602 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM) or a programmable read-only memory (PROM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memory described in the embodiments of the present invention is intended to include but is not limited to these and any other suitable categories of memory.

[0133] The memory 602 in the embodiment of the present invention is used to store various categories of data to support the operation of the electronic terminal 600. Examples of these data include: any executable program for operating on the electronic terminal 600, such as an operating system 6021 and an application 6022; the operating system 6021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application 6022 may include various applications, such as a media player (Media Player), a browser (Browser), etc., for implementing various application services. The control optimization method for a rotary dehumidification system based on a digital drive and an Internet of Things platform provided in an embodiment of the present invention may be included in the application 6022.

[0134] The method disclosed in the above embodiment of the present invention can be applied to the processor 601, or implemented by the processor 601. The processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 601 or the instruction in the form of software. The above processor 601 may be a general processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 601 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiment of the present invention. The general processor 601 may be a microprocessor or any conventional processor, etc. In combination with the steps of the accessory optimization method provided in the embodiment of the present invention, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0135] In an exemplary embodiment, the electronic terminal 600 may be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD) to execute the aforementioned method.

[0136] According to the method provided in the embodiments of the present application, the present application also provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, the computer executes the rotary dehumidification system control optimization method based on digital drive and Internet of Things platform of any embodiment of the shown embodiments.

[0137] According to the method provided in the embodiments of the present application, the present application also provides a computer-readable storage medium, which stores a program code. When the program code is run on a computer, the computer executes the rotary dehumidification system control optimization method based on digital drive and Internet of Things platform of any embodiment of the shown embodiments.

[0138] The terms "component", "module", "system", etc. used in this specification are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process, a processor, an object, an executable file, an execution thread, a program and / or a computer running on a processor. By way of illustration, both applications and computing devices running on a computing device can be components. One or more components may reside in a process and / or an execution thread, and a component may be located on a computer and / or distributed between two or more computers. In addition, these components may be executed from various computer-readable media having various data structures stored thereon. Components may, for example, communicate through local and / or remote processes according to signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system and / or a network, such as the Internet interacting with other systems through signals).

[0139] Those of ordinary skill in the art will appreciate that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0141] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0142] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0143] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0144] In the above embodiments, the functions of each functional unit can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. Available media may be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., high-density digital video discs (DVDs), or semiconductor media (e.g., solid state disks (SSDs)).

[0145] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0146] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0147] In summary, the present application provides a rotary dehumidification system control optimization method, system, medium, program product and terminal based on digital drive and Internet of Things platform, including: collecting real-time operation data of the rotary dehumidification system connected to it through the edge end, and preprocessing the real-time operation data of the rotary dehumidification system; inputting the preprocessed real-time operation data into a pre-built system multi-objective control optimization model deployed on the cloud, and using an improved particle swarm algorithm to solve the system multi-objective control optimization model to obtain the optimal control strategy for the operation of the rotary dehumidification system; the cloud sends the optimal control strategy to the edge end through the MQTT protocol, and the edge end issues control instructions to the rotary dehumidification system based on the optimal control strategy, so that the rotary dehumidification system executes the optimal control strategy in real time according to the control instructions.

[0148] This application is used to improve the intelligent control level of the rotary dehumidification system by combining a control optimization method with digital drive and Internet of Things technology. This method monitors the operating status of the system in real time and dynamically adjusts key operating parameters such as the rotary speed, regeneration wind temperature and air volume to improve the accuracy of humidity control, reduce energy consumption, and enhance the system's adaptability to complex working conditions. This application realizes real-time data monitoring, dynamic adjustment and intelligent optimization of the rotary dehumidification system by building an "edge + cloud + terminal device" architecture platform. In this architecture, the edge is responsible for improving the response speed of local control, while the cloud is responsible for long-term data analysis, optimization and feedback, so that the rotary dehumidification system can be monitored and dynamically adjusted in real time, which not only improves the dehumidification efficiency, reduces energy consumption, and achieves energy-saving goals, but also ensures that the best dehumidification effect can be achieved under various working conditions. Therefore, this application effectively overcomes the various shortcomings in the prior art and has a high industrial utilization value.

[0149] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A control optimization method for a rotary dehumidification system based on digital drive and Internet of Things platform, characterized in that: include: Collecting real-time operation data of a rotary dehumidification system in communication with the edge end, and preprocessing the real-time operation data of the rotary dehumidification system; The preprocessed real-time operation data is input into a pre-built system multi-objective control optimization model deployed in the cloud, and the improved particle swarm algorithm is used to solve the system multi-objective control optimization model to obtain the optimal control strategy for the operation of the rotary dehumidification system; The cloud sends the optimal control strategy to the edge via the MQTT protocol, and the edge issues a control instruction to the rotary dehumidification system based on the optimal control strategy, so that the rotary dehumidification system executes the optimal control strategy in real time according to the control instruction.

2. The control optimization method of the rotary dehumidification system based on digital drive and Internet of Things platform according to claim 1 is characterized in that: The construction process of the pre-built system multi-objective control optimization model includes: A machine learning method is used to construct and train a system multi-objective prediction model based on the historical operation data of the rotary dehumidification system; A system multi-objective control optimization model is established based on the system multi-objective prediction model combined with optimization objectives and constraint conditions.

3. The control optimization method of the rotary dehumidification system based on digital drive and Internet of Things platform according to claim 2 is characterized in that: The multi-objective prediction model of the system includes: a wheel humidity adsorption prediction model, a wheel temperature change prediction model, a cooling consumption prediction model, an electric power consumption prediction model, a heat exchanger energy consumption prediction model, and a dew point temperature prediction model.

4. The control optimization method of the rotary dehumidification system based on digital drive and Internet of Things platform according to claim 1 is characterized in that: The improved particle swarm algorithm includes: using an adaptive weight factor and a dynamic contraction mechanism to adjust the particle speed.

5. The control optimization method of the rotary dehumidification system based on digital drive and Internet of Things platform according to claim 1 is characterized in that: The process of solving the multi-objective control optimization model of the system using the improved particle swarm algorithm includes: Initialize the speed and position of each particle in the particle population, each particle corresponds to each optimization target, and calculate the fitness function value of each particle; Calculate the individual optimal solution of each particle and the global optimal solution of the particle population; Update the speed and position of each particle and determine whether the maximum number of iterations has been reached. If so, stop the iteration, otherwise repeat the above steps.

6. The control optimization method of the rotary dehumidification system based on digital drive and Internet of Things platform according to claim 5 is characterized in that: The calculation formula of the fitness function value is: ； in, is the fitness function value of the current particle, is the total energy consumption of the system, is the target humidity value, is the actual humidity value, and is the corresponding weight coefficient.

7. A rotary dehumidification system control optimization system based on digital drive and Internet of Things platform, characterized in that: include: A data acquisition and processing module, used for acquiring real-time operation data of a rotary dehumidification system in communication with the rotary dehumidification system through an edge terminal, and preprocessing the real-time operation data of the rotary dehumidification system; An optimal control strategy acquisition module is used to input the pre-processed real-time operation data into a pre-built system multi-objective control optimization model deployed in the cloud, and use an improved particle swarm algorithm to solve the system multi-objective control optimization model to obtain the optimal control strategy for the operation of the rotary dehumidification system; A control instruction execution module is used for the cloud to send the optimal control strategy to the edge end through the MQTT protocol, and the edge end issues a control instruction to the rotary dehumidification system based on the optimal control strategy, so that the rotary dehumidification system executes the optimal control strategy in real time according to the control instruction.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the control optimization method of a rotary dehumidification system based on digital drive and Internet of Things platform as described in any one of claims 1 to 6 is implemented.

9. A computer program product, characterized in that The computer program product includes computer program code, and when the computer program code is executed on a computer, the computer implements the rotary dehumidification system control optimization method based on digital drive and Internet of Things platform as described in any one of claims 1 to 6.

10. An electronic terminal comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the rotary dehumidification system control optimization method based on digital drive and Internet of Things platform as described in any one of claims 1 to 6.

Images