Refrigerating unit based on intelligent control

Abstract

The invention relates to the technical field of intelligent refrigerators, and particularly discloses a refrigerating unit based on intelligent control, which comprises a data acquisition module, a control optimization module, a system management module and a data visualization and report module, the data acquisition module acquires equipment parameters by using a sensor, and records and stores data in real time; the control optimization module analyzes historical data through an intelligent control algorithm, establishes a function relationship between the operation parameters and the refrigeration effect, and optimizes the operation parameters of the assembly in real time; the system management module is used for maintaining user permissions, including permission setting and user behavior recording, and providing sensor calibration, equipment state monitoring and preventive maintenance prompts; and the data visualization and report module displays the operation state and parameters of the refrigerator through a visual interface, and automatically generates an operation report and an energy efficiency analysis report. According to the refrigerating system, the operation efficiency and stability of the system can be remarkably improved, the energy consumption is reduced, the fault occurrence rate is reduced, and the user experience and the production quality are improved.

Description

Technical Field

[0001] The invention relates to the field of intelligent refrigerators, and in particular to a refrigeration unit based on intelligent control. Background Art

[0002] In recent years, with the continuous improvement of people's living standards and the rapid development of industrial production, refrigeration technology has been used more and more widely in various fields. Whether it is air conditioners and refrigerators in homes, or cold chain transportation and cold storage management in industrial production, refrigeration equipment has played a vital role. However, with the increase in application demand, higher requirements have been put forward for the operation efficiency, energy consumption management and intelligent control of refrigeration equipment. Traditional refrigeration systems mostly use fixed parameter control, lack real-time monitoring and adjustment of environmental changes and operating status, resulting in high energy consumption, low efficiency and frequent failures in the actual operation process. Especially in large-scale refrigeration systems, the energy consumption problem of equipment is particularly prominent, which not only increases operating costs, but also has an adverse impact on the environment. Therefore, how to optimize the operation of the refrigeration system through intelligent means, improve its energy efficiency ratio and reduce energy consumption has become an urgent problem to be solved. With the rapid development of the Internet of Things, big data and intelligent control technology, new ideas and methods have been provided for the intelligent control of refrigeration systems. By using sensing technology to collect various parameters in the operation of the refrigeration system in real time, such as temperature, pressure, humidity, flow, compressor speed, refrigerant fan pressure, and expansion valve opening, and using big data analysis and machine learning algorithms, it is possible to achieve precise control and optimization of the refrigeration system and improve the operating efficiency and reliability of the system. The present invention proposes a refrigeration system based on big data and intelligent control. Through the collaborative work of modules such as real-time data collection, historical data analysis, and intelligent optimization control, it can achieve comprehensive monitoring and intelligent adjustment of the refrigeration process, which can not only significantly improve the operating efficiency of the refrigeration system and reduce energy consumption, but also timely detect and handle abnormal situations to ensure the safe and stable operation of the system. The realization of this system will inject new vitality into the development of the refrigeration industry and promote its development in a more energy-saving, efficient and intelligent direction. Summary of the invention

[0003] In view of the above problems, the present invention aims to provide a refrigeration unit based on intelligent control.

[0004] The purpose of the present invention is achieved through the following technical solutions:

[0005] A refrigeration unit based on intelligent control includes the following modules: a data acquisition module, which uses sensing technology to collect temperature, pressure, humidity, flow, compressor speed, condenser fan speed, and expansion valve opening parameters during the refrigeration process, and records them in the control system; a control optimization module, which uses a machine learning algorithm to analyze historical data and real-time data to establish a functional relationship between the operating parameters of the refrigeration system and the refrigeration effect, and intelligently adjusts and optimizes the operating parameters of the compressor, fan, and expansion valve to improve refrigeration efficiency and reduce energy consumption; a system management module, including a system maintenance and monitoring unit and a security and authority control unit, the system maintenance and monitoring unit is used to monitor system performance and fault detection, and the security and authority control unit is used for user identity authentication and authority control; a data visualization and reporting module, which provides an intuitive data visualization interface, displays data and analysis results during the control process, and generates analysis reports to help users intuitively understand system performance and optimize it.

[0006] Furthermore, the data acquisition module includes a sensing unit and a data recording unit, wherein the sensing unit utilizes a temperature sensor, a pressure sensor, a humidity sensor, a flow sensor, a compressor speed sensor, a condenser fan speed sensor, and an expansion valve opening sensor to collect data in the refrigeration system in real time, wherein the data includes evaporator temperature and condenser temperature, refrigerant pressure, ambient humidity, refrigerant flow, compressor speed, condenser fan speed, and expansion valve opening; the temperature sensor is used to detect the operating temperature of the evaporator and condenser to ensure that the refrigeration system operates within a preset range; the pressure sensor is used to measure the pressure of the refrigerant in the system, monitor the state of the refrigeration cycle, and prevent abnormal pressure from causing system failure; the humidity sensor is used to monitor the ambient humidity to ensure stable operation of the system The flow sensor is used to monitor the flow of refrigerant, ensure the uniform distribution of refrigerant in the system and improve the system efficiency. The compressor speed sensor is used to monitor the speed of the compressor to ensure that the compressor operates within the optimal speed range. The condenser fan speed sensor is used to monitor the rotation speed of the fan to ensure the heat dissipation effect of the condenser. The expansion valve opening sensor is used to monitor the opening and closing angle of the expansion valve, accurately control the refrigerant flow and improve the refrigeration efficiency. The data recording unit is used to record and store all the data collected by the sensor unit in real time in the control system. The data recording unit ensures the integrity and timeliness of the data. The collected data provides a basis for subsequent analysis and optimization. Through the analysis of historical data, it helps to optimize the operating parameters of the refrigeration system and improve the refrigeration efficiency and energy utilization.

[0007] Furthermore, the control optimization module includes an intelligent energy-saving control unit, a parameter optimization unit, a minimum loss control unit, a model training and updating unit, a data feedback and early warning unit, and a user-defined parameter setting unit, wherein: the intelligent energy-saving control unit preliminarily extracts the original data features by integrating convolutional neural network (CNN), long short-term memory network (LSTM), variational autoencoder (VAE) and graph neural network (GNN), and enriches the feature expression method through multi-layer perceptron (MLP), improves the generalization ability of the model, analyzes historical data and real-time data, and establishes a functional relationship between the operating parameters of the refrigeration system and the refrigeration energy consumption. The minimum loss control unit optimizes the operating parameters of the compressor, fan, and expansion valve components in real time according to the functional relationship established by the intelligent energy-saving control unit. The parameter optimization unit combines the multi-objective Lagrangian relaxation method (MOLR) to achieve global optimization. The model training and updating unit uses new data to continuously improve and optimize the model to adapt to changes in ambient temperature and humidity. The model training and updating unit dynamically adjusts the parameters in the optimization model based on the strategies provided by the intelligent energy-saving control unit and the minimum loss control unit. The user-defined parameter setting unit allows the user to adjust the parameter settings according to needs, and provides personalized parameter optimization solutions through algorithm optimization, combined with historical data and real-time monitoring results.

[0008] Multiple input variables: Refrigeration systems involve multiple variables, such as evaporator temperature, condenser temperature, refrigerant pressure, ambient humidity, and refrigerant flow. These variables are multidimensional in nature, and each variable can vary at different times and conditions, forming a high-dimensional data set.

[0009] Furthermore, the control optimization module includes a minimum loss control unit. The minimum loss control unit achieves an optimal balance between energy consumption, cooling effect and equipment wear by introducing Kalman filtering and multi-objective Lagrangian relaxation (MOLR). Specifically, a multi-objective optimization function is defined. The objective function for: , in, , is the input vector, are the compressor speed, condenser fan speed and expansion valve opening, represents the system energy consumption, , in, is the total time the system is running, , , are the weight coefficients related to the energy consumption of the compressor, fan and expansion valve, respectively. The compressor is at time The power consumption, as The function of is the control variable of the compressor, Is the fan in time The power consumption, as The function of is the control variable of the fan, The expansion valve is at time The power consumption, as The function of is the control variable of the expansion valve, is the system internal temperature The time derivative of , which represents the rate of temperature change, is the system cooling capacity The time derivative of represents the rate of change of cooling capacity, are the penalty coefficients for the temperature change rate and cooling capacity change rate, respectively, indicating the sensitivity of energy consumption to the temperature change rate and cooling capacity change. is the evaporator temperature, representing the cooling effect, which is obtained in real time through the temperature sensor and controlled according to the input Establish nonlinear mapping relationship, Set the cooling temperature for the system, is the estimated function of equipment wear, integrating the running time, load status and operation frequency of the compressor, condenser and evaporator components. , is the power consumption of the compressor at time t, as The function of is the control variable of the compressor, is the power consumption of the condenser at time t, as The function of is the control variable of the condenser, is the power consumption of the evaporator at time t, as The function of is the control variable of the evaporator, , , , respectively, represent the weight functions of the compressor, condenser, and evaporator that change with time, representing the load state or wear coefficient of the equipment in different time periods, derived from historical data, , , are the maximum rated power of the compressor, condenser and evaporator respectively, , , They are the operating frequency functions of the compressor, condenser and evaporator, respectively, reflecting the effect of the operating frequency on the wear of the equipment during operation. , , is an exponential coefficient related to the degree of wear of the compressor, condenser and evaporator, reflecting the nonlinear dependence of wear on power consumption. , , is the weight coefficient related to the wear of the compressor, condenser and evaporator, During the optimization process, by calculating the partial derivative of the objective function, the optimization conditions are as follows: , They are Lagrange multipliers, which are used to adjust the relative weights among the three objective functions of energy consumption, refrigeration effect and equipment wear. The weight setting is dynamically adjusted according to user needs and equipment performance requirements. In the process of optimization and solution, Kalman filtering technology is used to predict and update the system state. The recursive formula of Kalman filtering is: , The predicted value of the control input for the next moment, is the predicted value of the control input at the current moment, is the measured value vector at the current moment, including temperature, pressure and humidity parameters, is the Kalman gain, which is a dynamically adjusted coefficient used to determine the weight of the measurement data and the prediction model, and dynamically adjust the accuracy of the system state prediction. , Where R is the measurement error covariance matrix, which represents the noise uncertainty in the measurement data, is the prediction error covariance matrix, which represents the uncertainty of the current state estimate and is calculated as: , represents the transfer estimation error matrix, A is the state transfer matrix, which describes the system from the previous moment To the present The state transition at time is the process noise covariance matrix, which describes the uncertainty in the system model. The input vector Applied to the actual control of refrigeration units, this control strategy can dynamically adjust the operating parameters of the equipment according to the real-time working conditions, ensuring the refrigeration effect while minimizing energy consumption and reducing equipment wear.

[0010] Deep learning models: The multivariate hybrid neural networks used (including CNN, LSTM, VAE, and GNN) are able to handle complex nonlinear relationships and high-dimensional features. The structure of these models enables them to abstract and extract features from data at multiple levels, capturing deeper feature relationships.

[0011] High-dimensional feature extraction:

[0012] Convolutional Neural Network (CNN): Used to process spatial features, capable of extracting local features and patterns, and suitable for processing time series data.

[0013] Long Short-Term Memory Network (LSTM): Good at processing time series data and can capture the dynamic characteristics of variables changing over time.

[0014] Variational Autoencoder (VAE): used to generate models that capture the distribution characteristics of high-dimensional data through latent space representation.

[0015] Graph Neural Network (GNN): Used to process structured data and can capture complex relationships between variables.

[0016] Multilayer Perceptron (MLP): By mapping the extracted high-dimensional implicit features into system energy consumption prediction values, the high-dimensional expression ability of the model is further enhanced, enabling the model to learn and optimize complex nonlinear mapping relationships.

[0017] Furthermore, the intelligent energy-saving control unit includes a multivariable hybrid neural network and deep reinforcement learning optimization subunit, which is composed of a convolutional neural network (CNN), a long short-term memory network (LSTM), a variational autoencoder (VAE) and a graph neural network (GNN). , condenser temperature , Refrigerant pressure , Ambient humidity and refrigerant flow The multivariate hybrid neural network and deep reinforcement learning optimization subunits use multi-layer perceptron (MLP) to enrich the feature expression based on the feature extraction of convolutional neural network (CNN), long short-term memory network (LSTM), variational autoencoder (VAE) and graph neural network (GNN), and express it as the system energy consumption prediction value. , , in: represents the system state vector at time t, , , , Represent the feature vectors extracted by CNN, LSTM, VAE and GNN respectively, Represents multi-layer perceptron (MLP) extraction , , , The characteristics of The deep learning optimization subunit optimizes the control strategy by interacting with the dynamic environment of the refrigeration system , to minimize the total energy consumption of the system defined by the objective function: , in, is the discount factor, It indicates that the expected benefit under the guidance of strategy π is used to balance the weights of current and future energy consumption. The following constraints must be met during the optimization process: , , in, , , , , , Respectively represent the refrigerant pressure of the refrigeration system , Ambient humidity and refrigerant flow The minimum and maximum values ​​of the policy gradient algorithm used in deep reinforcement learning to update the strategy , and its optimization steps can be expressed as: , in, is the learning rate, It is a policy gradient operator that optimizes the expected values ​​of system state and energy consumption in different time periods and finally converges to the global optimal solution.

[0018] Furthermore, the system management module includes a system maintenance and monitoring unit, a security and authority control unit, a data backup and recovery unit, a log recording and auditing unit, a system update and upgrade unit, and a user support and help unit, wherein: the system maintenance and monitoring unit is used to monitor system performance in real time, perform fault detection and diagnosis, and can automatically identify and repair faults, while providing diagnostic reports to facilitate maintenance personnel to conduct in-depth analysis and processing; the security and authority control unit includes user identity authentication and authority control, which can ensure the security of system data and prevent unauthorized access and operation. Through authority settings, the system administrator defines and assigns operation permissions to different users to ensure the compliance and security of operations. ; Data backup and recovery unit, which regularly backs up system data to ensure that in the event of data loss or system crash, data can be quickly restored to reduce the impact on production; Logging and auditing unit, which records all system operations and event logs for easy auditing and tracking, and can record each user's operation behavior to ensure that problems can be quickly located and resolved; System update and upgrade unit, which regularly checks and updates system software to ensure that the system is always running on the latest version to obtain the latest functions and security patches; User support and help unit, which provides system usage guides, technical problem answers and technical support to help users quickly get started and resolve problems encountered during use, thereby improving user experience and satisfaction.

[0019] Furthermore, the data visualization and reporting module includes a data visualization unit, a historical data analysis unit, a report generation unit, a user-defined view unit, and a data export and sharing unit, wherein: the data visualization unit provides an intuitive graphical interface to display data in the control process, and can generate line graphs, bar graphs, and pie charts to help users quickly understand the changing trends and distribution of data, including a real-time monitoring panel for real-time display of temperature, pressure, humidity, flow, compressor speed, condenser fan speed, and expansion valve opening parameters in the refrigeration system. Users can monitor the system status in real time through the real-time monitoring panel and promptly discover and handle abnormal situations; the historical data analysis unit is used to analyze historical data during the operation of the refrigeration system and generate trend graphs and statistical reports. Users can understand the long-term changing trends during the operation of the system through the historical data analysis unit to assist in optimizing the system operation parameters; the report generation unit automatically generates an analysis report, including parameter changing trends, records of abnormal events, and processing results; the user-defined view unit allows users to customize the data display interface and report content as needed, and users can select required parameters and time periods to generate personalized data views and reports; the data export and sharing unit supports exporting visualized data and reports as files for saving.

[0020] The beneficial effects of the present invention are as follows: The refrigeration system of the present invention achieves the following gain effects through big data technology and artificial intelligence technology: Real-time monitoring and optimization: The system can monitor the key parameters of temperature, pressure, humidity, flow, compressor speed, condenser fan speed, and expansion valve opening in the refrigeration system in real time, and adjust these parameters in real time to ensure that the system operates in the optimal state. This not only improves the refrigeration effect, but also effectively reduces energy consumption. Historical data analysis and prediction: The historical data analysis unit can analyze the historical data during the operation of the refrigeration system and generate trend charts and statistical reports. These data analysis results can assist in optimizing the system operation parameters and improve the operation efficiency and stability of the system. Abnormal detection and early warning: The system monitors the system operation parameters in real time through the data feedback and early warning unit. When an abnormal situation is found or the parameters deviate from the preset range, the system can issue an early warning in time and feedback to the operator to ensure that measures are taken quickly to avoid production accidents and quality problems. User customization and personalized reports: The user-defined view unit allows users to customize the data display interface and report content as needed. Users can select specific parameters and time periods to generate personalized data views and reports to meet different analysis needs and improve user experience and decision support. Data backup and recovery: The system's security and permission control unit and data backup and recovery unit ensure the security and reliability of system data. In the event of data loss or system crash, data can be quickly restored to reduce the impact on production and ensure the continuity and stability of the system. System maintenance and upgrade: The system update and upgrade unit ensures that the system software is updated regularly and always runs on the latest version to obtain the latest functions and security patches. This improves the security and performance of the system. User support and help: The user support and help unit provides system usage guides, technical problem answers and technical support to help users get started quickly and solve problems encountered during use, thereby improving user satisfaction and system usage efficiency. Through the above-mentioned gain effect, the refrigeration system of the present invention can significantly improve the operating efficiency and stability of the system, reduce energy consumption, reduce the occurrence of failures, and improve user experience and production quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The invention is further illustrated by the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0022] Figure 1 It is a schematic diagram of the system of the present invention. DETAILED DESCRIPTION

[0023] The present invention is further described in conjunction with the following examples.

[0024] See also Figure 1In this embodiment, a refrigeration unit based on intelligent control includes a user terminal and a system terminal, wherein: a data acquisition module is used to use sensing technology to collect temperature, pressure, humidity, flow, compressor speed, condenser fan speed, and expansion valve opening parameters during the refrigeration process, and record them in the control system; a control optimization module uses a machine learning algorithm to analyze historical data and real-time data to establish a functional relationship between the operating parameters of the refrigeration system and the refrigeration effect, and intelligently adjusts and optimizes the operating parameters of the compressor, fan, and expansion valve to improve refrigeration efficiency and reduce energy consumption; a system management module includes a system maintenance and monitoring unit and a security and authority control unit, the system maintenance and monitoring unit is used to monitor system performance and fault detection, and the security and authority control unit is used for user identity authentication and authority control; a data visualization and reporting module provides an intuitive data visualization interface, displays data and analysis results during the control process, and generates analysis reports to help users intuitively understand system performance and optimize it.

[0025] Specifically, the data acquisition module includes a sensing unit and a data recording unit, wherein the sensing unit utilizes a temperature sensor, a pressure sensor, a humidity sensor, a flow sensor, a compressor speed sensor, a condenser fan speed sensor, and an expansion valve opening sensor to collect data in the refrigeration system in real time, wherein the data include evaporator temperature and condenser temperature, refrigerant pressure, ambient humidity, refrigerant flow, compressor speed, condenser fan speed, and expansion valve opening; the temperature sensor is used to detect the operating temperature of the evaporator and condenser to ensure that the refrigeration system operates within a preset range; the pressure sensor is used to measure the pressure of the refrigerant in the system, monitor the state of the refrigeration cycle, and prevent abnormal pressure from causing system failure; the humidity sensor is used to monitor the ambient humidity to ensure stable operation of the system The flow sensor is used to monitor the flow of refrigerant, ensure the uniform distribution of refrigerant in the system and improve the system efficiency. The compressor speed sensor is used to monitor the speed of the compressor to ensure that the compressor operates within the optimal speed range. The condenser fan speed sensor is used to monitor the rotation speed of the fan to ensure the heat dissipation effect of the condenser. The expansion valve opening sensor is used to monitor the opening and closing angle of the expansion valve, accurately control the refrigerant flow and improve the refrigeration efficiency. The data recording unit is used to record and store all the data collected by the sensor unit in real time in the control system. The data recording unit ensures the integrity and timeliness of the data. The collected data provides a basis for subsequent analysis and optimization. Through the analysis of historical data, it helps to optimize the operating parameters of the refrigeration system and improve the refrigeration efficiency and energy utilization.

[0026] Specifically, the control optimization module includes an intelligent energy-saving control unit, a parameter optimization unit, a minimum loss control unit, a model training and updating unit, a data feedback and early warning unit, and a user-defined parameter setting unit, wherein: the intelligent energy-saving control unit preliminarily extracts the original data features by integrating convolutional neural network (CNN), long short-term memory network (LSTM), variational autoencoder (VAE) and graph neural network (GNN), and enriches the feature expression method through multi-layer perceptron (MLP), improves the generalization ability of the model, analyzes historical data and real-time data, and establishes a functional relationship between the operating parameters of the refrigeration system and the refrigeration energy consumption. The minimum loss control unit optimizes the operating parameters of the compressor, fan, and expansion valve components in real time according to the functional relationship established by the intelligent energy-saving control unit. The parameter optimization unit combines the multi-objective Lagrangian relaxation method (MOLR) to achieve global optimization. The model training and updating unit uses new data to continuously improve and optimize the model to adapt to changes in ambient temperature and humidity. The model training and updating unit dynamically adjusts the parameters in the optimization model based on the strategies provided by the intelligent energy-saving control unit and the minimum loss control unit. The user-defined parameter setting unit allows the user to adjust the parameter settings according to needs, and through algorithm optimization, combined with historical data and real-time monitoring results, provides a personalized parameter optimization solution.

[0027] Specifically, the control optimization module includes a minimum loss control unit. The minimum loss control unit achieves an optimal balance between energy consumption, cooling effect and equipment wear by introducing Kalman filtering and multi-objective Lagrangian relaxation (MOLR). Specifically, a multi-objective optimization function is defined. The objective function for: , in, , is the input vector, are the compressor speed, condenser fan speed and expansion valve opening, represents the system energy consumption, , in, is the total time the system is running, , , are the weight coefficients related to the energy consumption of the compressor, fan and expansion valve, respectively. The compressor is at time The power consumption, as The function of is the control variable of the compressor, Is the fan in time The power consumption, as The function of is the control variable of the fan, The expansion valve is at time The power consumption, as The function of is the control variable of the expansion valve, is the system internal temperature The time derivative of , which represents the rate of temperature change, is the system cooling capacity The time derivative of represents the rate of change of cooling capacity, are the penalty coefficients for the temperature change rate and cooling capacity change rate, respectively, indicating the sensitivity of energy consumption to the temperature change rate and cooling capacity change. is the evaporator temperature, representing the cooling effect, which is obtained in real time through the temperature sensor and controlled according to the input Establish nonlinear mapping relationship, Set the cooling temperature for the system, is the estimated function of equipment wear, integrating the running time, load status and operation frequency of the compressor, condenser and evaporator components. , is the power consumption of the compressor at time t, as The function of is the control variable of the compressor, is the power consumption of the condenser at time t, as The function of is the control variable of the condenser, is the power consumption of the evaporator at time t, as The function of is the control variable of the evaporator, , , , respectively, represent the weight functions of the compressor, condenser, and evaporator that change with time, representing the load state or wear coefficient of the equipment in different time periods, derived from historical data, , , are the maximum rated power of the compressor, condenser and evaporator, respectively, and are the operating frequency functions of the compressor, condenser and evaporator, respectively, reflecting the effect of the operating frequency on wear during equipment operation. , , They are the operating frequency functions of the compressor, condenser and evaporator, respectively, reflecting the effect of the operating frequency on the wear of the equipment during operation. , , is an exponential coefficient related to the degree of wear of the compressor, condenser and evaporator, reflecting the nonlinear dependence of wear on power consumption. , , is the weight coefficient related to the wear of the compressor, condenser and evaporator, During the optimization process, by calculating the partial derivative of the objective function, the optimization conditions are as follows: , They are Lagrange multipliers, which are used to adjust the relative weights among the three objective functions of energy consumption, refrigeration effect and equipment wear. The weight setting is dynamically adjusted according to user needs and equipment performance requirements. In the process of optimization and solution, Kalman filtering technology is used to predict and update the system state. The recursive formula of Kalman filtering is: , The predicted value of the control input for the next moment, is the predicted value of the control input at the current moment, is the measured value vector at the current moment, including temperature, pressure and humidity parameters, is the Kalman gain, which is a dynamically adjusted coefficient used to determine the weight of the measurement data and the prediction model, and dynamically adjust the accuracy of the system state prediction. , Where R is the measurement error covariance matrix, which represents the noise uncertainty in the measurement data, is the prediction error covariance matrix, which represents the uncertainty of the current state estimate and is calculated as: , represents the transfer estimation error matrix, A is the state transfer matrix, which describes the system from the previous moment To the present The state transition at time is the process noise covariance matrix, which describes the uncertainty in the system model. The input vector Applied to the actual control of refrigeration units, this control strategy can dynamically adjust the operating parameters of the equipment according to the real-time working conditions, ensuring the refrigeration effect while minimizing energy consumption and reducing equipment wear.

[0028] Specifically, the control optimization module includes an intelligent energy-saving control unit, wherein: the intelligent energy-saving control unit includes a multivariable hybrid neural network and a deep reinforcement learning optimization subunit, and the multivariable hybrid neural network and the deep reinforcement learning optimization subunit are composed of a convolutional neural network (CNN), a long short-term memory network (LSTM), a variational autoencoder (VAE) and a graph neural network (GNN), for the evaporator temperature of the refrigeration system , condenser temperature , Refrigerant pressure , Ambient humidity and refrigerant flow The multivariate hybrid neural network and deep reinforcement learning optimization subunits use multi-layer perceptron (MLP) to enrich the feature expression based on the feature extraction of convolutional neural network (CNN), long short-term memory network (LSTM), variational autoencoder (VAE) and graph neural network (GNN), and express it as the system energy consumption prediction value. , , in: represents the system state vector at time t, , , , Represent the feature vectors extracted by CNN, LSTM, VAE and GNN respectively, Represents multi-layer perceptron (MLP) extraction , , , The characteristics of The deep learning optimization subunit controls the variables by interacting with the dynamic environment of the refrigeration system. , to minimize the total energy consumption of the system defined by the objective function: , in, is the discount factor, It indicates that the expected benefit under the guidance of strategy π is used to balance the weights of current and future energy consumption. The following constraints must be met during the optimization process: , , in, , , , , , Respectively represent the refrigerant pressure of the refrigeration system , Ambient humidity and refrigerant flow The minimum and maximum values ​​of the policy gradient algorithm used in deep reinforcement learning to update the strategy , and its optimization steps can be expressed as: , in, is the learning rate, It is a policy gradient operator that optimizes the expected values ​​of system state and energy consumption in different time periods and finally converges to the global optimal solution.

[0029] Specifically, the system management module includes a system maintenance and monitoring unit, a security and authority control unit, a data backup and recovery unit, a log recording and auditing unit, a system update and upgrade unit, and a user support and help unit, wherein: the system maintenance and monitoring unit is used to monitor system performance in real time, perform fault detection and diagnosis, and can automatically identify and repair faults, while providing diagnostic reports to facilitate maintenance personnel to conduct in-depth analysis and processing; the security and authority control unit includes user identity authentication and authority control, which can ensure the security of system data and prevent unauthorized access and operation. Through authority settings, the system administrator defines and allocates operation permissions for different users to ensure the compliance and security of operations; The data backup and recovery unit regularly backs up system data to ensure that in the event of data loss or system crash, data can be quickly restored to reduce the impact on production; the logging and auditing unit records all system operations and event logs for easy auditing and tracking, and can record each user's operation behavior to ensure that problems can be quickly located and resolved; the system update and upgrade unit regularly checks and updates system software to ensure that the system is always running on the latest version to obtain the latest functions and security patches; the user support and help unit provides system usage guides, technical problem answers and technical support to help users quickly get started and resolve problems encountered during use, thereby improving user experience and satisfaction.

[0030] Specifically, the data visualization and reporting module includes a data visualization unit, a historical data analysis unit, a report generation unit, a user-defined view unit, and a data export and sharing unit, wherein: the data visualization unit provides an intuitive graphical interface to display data in the control process, and can generate line graphs, bar graphs, and pie charts to help users quickly understand the changing trends and distribution of data, including a real-time monitoring panel for real-time display of temperature, pressure, humidity, flow, compressor speed, condenser fan speed, and expansion valve opening parameters in the refrigeration system. Users can monitor the system status in real time through the real-time monitoring panel and promptly discover and handle abnormal situations; the historical data analysis unit is used to analyze historical data during the operation of the refrigeration system and generate trend graphs and statistical reports. Users can understand the long-term changing trends during the operation of the system through the historical data analysis unit to assist in optimizing the system operation parameters; the report generation unit automatically generates an analysis report, including parameter changing trends, abnormal event records, and processing results; the user-defined view unit allows users to customize the data display interface and report content as needed, and users can select required parameters and time periods to generate personalized data views and reports; the data export and sharing unit supports exporting visualized data and reports as files for saving.

[0031] In a specific embodiment of the refrigerant control system, first, the user monitors the key parameters of the refrigeration system through a variety of sensors, including evaporator temperature and condenser temperature, refrigerant pressure, ambient humidity, refrigerant flow, compressor speed, condenser fan speed and expansion valve opening; each sensor is connected to the control system through a wired connection to form a data transmission network, and the collected signal data is transmitted to the microcomputer inside the refrigeration system through the data transmission network; the transmitted data first passes through a central data cleaning algorithm to clean and denoise the noise data to improve the accuracy and stability of the data; then, the system uses an adaptive control algorithm to calculate the optimal control strategy based on the cleaned data, and performs an optimal control strategy on the key parameters of the refrigeration system. The system controls the key components; these components include evaporator, condenser, compressor and expansion valve. The flow, pressure and temperature of the refrigerant are controlled by adjusting the working power or opening of these components, thereby adjusting the temperature control effect of the entire system. During the regulation process, the adaptive algorithm can be dynamically adjusted according to the actual measured data and the set target temperature to ensure that the refrigerant control system can respond to external environmental changes and system load conditions in real time to provide a stable refrigeration effect. The working status of the refrigeration system is displayed in real time on the display, including the current evaporator temperature and condenser temperature, refrigerant pressure, ambient humidity, refrigerant flow, compressor speed, condenser fan speed and expansion valve opening, to help operators monitor the system operation status.

[0032] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention, rather than to limit the scope of protection of the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the essence and scope of the technical solution of the present invention.

Claims

1. A refrigeration unit based on intelligent control, characterized in that: It includes the following modules: data acquisition module, which collects temperature, pressure, humidity, flow, compressor speed, condenser fan speed, and expansion valve opening parameters during the refrigeration process through sensor technology; The control optimization module uses machine learning algorithms to analyze historical data and real-time data to establish a functional relationship between the operating parameters of the refrigeration system and the refrigeration effect, and intelligently adjusts and optimizes the operating parameters of the compressor, fan, and expansion valve. The system management module includes a system maintenance and monitoring unit and a security and authority control unit. The system maintenance and monitoring unit is used to monitor system performance and fault detection, and the security and authority control unit is used for user identity authentication and authority control. The data visualization and reporting module provides a data visualization interface to display the data and analysis results of the control process, generate analysis reports, and help users understand the system performance.

2. According to claim 1, a refrigeration unit based on intelligent control is characterized in that: The data acquisition module includes a sensing unit and a data recording unit, wherein the sensing unit utilizes a temperature sensor, a pressure sensor, a humidity sensor, a flow sensor, a compressor speed sensor, a condenser fan speed sensor, and an expansion valve opening sensor to collect data in the refrigeration system in real time, wherein the data includes evaporator temperature and condenser temperature, refrigerant pressure, ambient humidity, refrigerant flow, compressor speed, condenser fan speed, and expansion valve opening; wherein the temperature sensor is used to detect the operating temperature of the evaporator and condenser to ensure that the refrigeration system operates within a preset range; the pressure sensor is used to measure the pressure of the refrigerant in the system to monitor the refrigeration cycle status to prevent abnormal pressure from causing system failure; the humidity sensor is used to monitor the ambient humidity to ensure stable operation of the system; the flow sensor is used to monitor the flow of refrigerant to ensure the uniform distribution of refrigerant in the system and improve system efficiency; the compressor speed sensor is used to monitor the speed of the compressor to ensure that the compressor operates within the optimal speed range; the condenser fan speed sensor is used to monitor the rotation speed of the fan to ensure the heat dissipation effect of the condenser; the expansion valve opening sensor is used to monitor the opening and closing angles of the expansion valve, accurately control the refrigerant flow and improve the refrigeration efficiency; the data recording unit is used to record all data collected by the sensing unit in real time and store them in the control system.

3. The refrigeration unit based on intelligent control according to claim 1, characterized in that: The control optimization module includes an intelligent energy-saving control unit, a parameter optimization unit, a minimum loss control unit, a model training and updating unit, a data feedback and early warning unit, and a user-defined parameter setting unit, wherein the intelligent energy-saving control unit preliminarily extracts the original data features by integrating convolutional neural networks, long short-term memory networks, variational autoencoders and graph neural networks, and enriches the feature expression method through multi-layer perceptrons to improve the generalization ability of the model, analyze historical data and real-time data, and establish a functional relationship between the operating parameters of the refrigeration system and the refrigeration energy consumption; the minimum loss control unit optimizes the operating parameters of the compressor, fan, and expansion valve components in real time according to the functional relationship established by the intelligent energy-saving control unit; the parameter optimization unit combines the multi-objective Lagrangian relaxation method to achieve global optimization; the model training and updating unit uses new data to continuously improve and optimize the model to adapt to changes in ambient temperature and humidity. The model training and updating unit dynamically adjusts the parameters in the optimization model based on the strategies provided by the intelligent energy-saving control unit and the minimum loss control unit; the user-defined parameter setting unit allows the user to adjust the parameter settings according to needs, and provides personalized parameter optimization solutions through algorithm optimization combined with historical data and real-time monitoring results.

4. The refrigeration unit based on intelligent control according to claim 3, characterized in that: The minimum loss control unit achieves an optimal balance between energy consumption, refrigeration effect and equipment wear by introducing Kalman filtering and multi-objective Lagrangian relaxation method, specifically defining a multi-objective optimization function, the objective function for: ， in, , is the input vector, are the compressor speed, condenser fan speed and expansion valve opening, represents the system energy consumption, ， in, is the total time the system is running, , , are the weight coefficients related to the energy consumption of the compressor, fan and expansion valve, respectively. The compressor is at time The power consumption, as The function of is the control variable of the compressor, Is the fan in time The power consumption, as The function of is the control variable of the fan, The expansion valve is at time The power consumption, as The function of is the control variable of the expansion valve, is the system internal temperature The time derivative of , which represents the rate of temperature change, is the system cooling capacity The time derivative of represents the rate of change of cooling capacity, are the penalty coefficients for the temperature change rate and cooling capacity change rate, respectively, indicating the sensitivity of energy consumption to the temperature change rate and cooling capacity change; is the evaporator temperature, representing the cooling effect, which is obtained in real time through the temperature sensor and controlled according to the input Establish nonlinear mapping relationship, Set the cooling temperature for the system, is the estimated function of equipment wear, integrating the running time, load status and operation frequency of the compressor, condenser and evaporator components. ， is the power consumption of the compressor at time t, as The function of is the control variable of the compressor, is the power consumption of the condenser at time t, as The function of is the control variable of the condenser, is the power consumption of the evaporator at time t, as The function of is the control variable of the evaporator, , , , respectively, represent the weight functions of the compressor, condenser, and evaporator that change with time, representing the load state or wear coefficient of the equipment in different time periods, derived from historical data, , , are the maximum rated power of the compressor, condenser and evaporator respectively, , , They are the operating frequency functions of the compressor, condenser and evaporator, respectively, reflecting the effect of the operating frequency on the wear of the equipment during operation. , , is an exponential coefficient related to the degree of wear of the compressor, condenser and evaporator, reflecting the nonlinear dependence of wear on power consumption. , , is the weighting factor related to the wear of the compressor, condenser and evaporator; During the optimization process, by calculating the partial derivative of the objective function, the optimization conditions are as follows: ， They are Lagrange multipliers, which are used to adjust the relative weights among the three objective functions of energy consumption, refrigeration effect and equipment wear. The weight setting is dynamically adjusted according to user needs and equipment performance requirements. In the process of optimization and solution, Kalman filtering technology is used to predict and update the system state. The recursive formula of Kalman filtering is: ， The predicted value of the control input for the next moment, is the predicted value of the control input at the current moment, is the measured value vector at the current moment, including temperature, pressure and humidity parameters, is the Kalman gain, which is a dynamically adjusted coefficient used to determine the weight of the measurement data and the prediction model, and dynamically adjust the accuracy of the system state prediction. ， Where R is the measurement error covariance matrix, which represents the noise uncertainty in the measurement data, is the prediction error covariance matrix, which represents the uncertainty of the current state estimate and is calculated as: ， represents the transfer estimation error matrix, A is the state transfer matrix, which describes the system from the previous moment To the present The state transition at time is the process noise covariance matrix, which describes the uncertainty in the system model. The input vector It is used in the actual control of refrigeration units.

5. The refrigeration unit based on intelligent control according to claim 3, characterized in that: The intelligent energy-saving control unit is designed to control the evaporator temperature of the refrigeration system. , condenser temperature , Refrigerant pressure , Ambient humidity and refrigerant flow The multivariable hybrid neural network and deep reinforcement learning optimization subunits use multi-layer perceptrons to enrich the feature expression based on the feature extraction of convolutional neural networks, long short-term memory networks, variational autoencoders and graph neural networks, and express them as system energy consumption prediction values. , ， in: represents the system state vector at time t, , , , Represent the feature vectors extracted by CNN, LSTM, VAE and GNN respectively, Represents multi-layer perceptron (MLP) extraction , , , The characteristics of The deep learning optimization subunit optimizes the control strategy by interacting with the dynamic environment of the refrigeration system , to minimize the total energy consumption of the system defined by the objective function: ， in, is the discount factor, It indicates that the expected benefit under the guidance of strategy π is used to balance the weights of current and future energy consumption. The following constraints must be met during the optimization process: ， ， in, , , , , , Respectively represent the refrigerant pressure of the refrigeration system , Ambient humidity and refrigerant flow The minimum and maximum values ​​of the policy gradient algorithm used in deep reinforcement learning to update the strategy , and its optimization steps can be expressed as: ， in, is the learning rate, It is a policy gradient operator that optimizes the expected values ​​of system state and energy consumption in different time periods and finally converges to the global optimal solution.

6. The refrigeration unit based on intelligent control according to claim 1, characterized in that: The system management module includes a system maintenance and monitoring unit, a security and authority control unit, a data backup and recovery unit, a log recording and auditing unit, a system update and upgrade unit, and a user support and help unit, wherein: the system maintenance and monitoring unit is used to monitor system performance in real time, perform fault detection and diagnosis, and can automatically identify and repair faults, while providing diagnostic reports to facilitate maintenance personnel to conduct in-depth analysis and processing; the security and authority control unit, including user identity authentication and authority control, can ensure the security of system data and prevent unauthorized access and operation. Through authority settings, the system administrator defines and allocates operation permissions for different users to ensure the compliance and security of operations; the data The backup and recovery unit regularly backs up system data to ensure that in the event of data loss or system crash, data can be quickly restored to reduce the impact on production; the logging and auditing unit records all system operations and event logs for easy auditing and tracking, and can record each user's operation behavior to ensure that problems can be quickly located and resolved; the system update and upgrade unit regularly checks and updates system software to ensure that the system is always running on the latest version to obtain the latest functions and security patches; the user support and help unit provides system usage guides, technical problem answers and technical support to help users quickly get started and resolve problems encountered during use, thereby improving user experience and satisfaction.

7. The refrigeration unit based on intelligent control according to claim 1, characterized in that: The data visualization and reporting module includes a data visualization unit, a historical data analysis unit, a report generation unit, a user-defined view unit, and a data export and sharing unit, wherein: the data visualization unit provides an intuitive graphical interface to display data in the control process, and can generate line graphs, bar graphs, and pie charts to help users quickly understand the changing trends and distribution of data, including a real-time monitoring panel for real-time display of temperature, pressure, humidity, flow, compressor speed, condenser fan speed, and expansion valve opening parameters in the refrigeration system. Users can monitor the system status in real time through the real-time monitoring panel and promptly discover and handle abnormal situations; the historical data analysis unit is used to analyze historical data during the operation of the refrigeration system and generate trend graphs and statistical reports. Users can understand the long-term changing trends during the operation of the system through the historical data analysis unit to assist in optimizing the system operation parameters; the report generation unit automatically generates an analysis report, including parameter changing trends, abnormal event records, and processing results; the user-defined view unit allows users to customize the data display interface and report content as needed, and users can select required parameters and time periods to generate personalized data views and reports; the data export and sharing unit supports exporting visualized data and reports as files for saving.

Images