Intelligent energy-saving air conditioner refrigerating system based on frequency conversion technology and control method of intelligent energy-saving air conditioner refrigerating system

Abstract

The invention relates to the technical field of air conditioner refrigeration, and discloses an intelligent energy-saving air conditioner refrigeration system based on the frequency conversion technology and a control method thereof.The intelligent energy-saving air conditioner refrigeration system comprises various sensors used for collecting environment data in real time, and the environment data comprise but not limited to temperature, humidity, illumination and personnel activity information; the control unit is connected with the inverter compressor and the multivariable sensor network and is used for generating a control signal according to the environment data so as to dynamically adjust the operation frequency of the inverter compressor; the control unit comprises a data processing module used for preprocessing environment data collected by the multivariable sensor network; through a multivariable adaptive control algorithm, various environmental factors such as temperature, humidity, illumination and personnel activity information are comprehensively considered, and the operation frequency of the inverter compressor is dynamically adjusted. Compared with a traditional air conditioning system which only depends on a single temperature variable for control, the indoor set temperature can be more precisely maintained, temperature fluctuation is reduced, and the temperature control precision is remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of air conditioning and refrigeration technology, and particularly to an intelligent energy-saving air conditioning and refrigeration system based on frequency conversion technology and a control method thereof. BACKGROUND

[0002] With the increasing global energy demand and the growing awareness of environmental protection, energy saving and efficient operation of air conditioning and refrigeration systems have become an important research topic. Traditional air conditioning systems mostly use fixed-frequency compressors, which have a fixed operating mode and cannot flexibly adjust the refrigeration capacity according to changes in indoor and outdoor environments, resulting in high energy consumption and increased operating costs. In recent years, frequency conversion technology has gradually been popularized in the field of air conditioning, which adjusts the refrigeration capacity by changing the operating frequency of the compressor, and can achieve energy saving to some extent. However, the existing frequency conversion air conditioning systems still have some technical limitations in actual application, which limit the further development of their energy saving potential.

[0003] Firstly, the existing frequency conversion air conditioning systems mainly rely on a single temperature variable for control, usually using a PID (Proportional-Integral-Derivative) control algorithm to adjust the temperature. Although this control method can adjust the refrigeration power according to the temperature deviation, it lacks accuracy in complex environments, such as large indoor and outdoor temperature differences, frequent personnel flow, or changes in lighting conditions, which can easily cause overshooting and result in large indoor temperature fluctuations, affecting user comfort and increasing unnecessary energy consumption.

[0004] Secondly, the existing frequency conversion air conditioning systems still have room for improvement in energy efficiency ratio in extreme weather or high load operation. Although frequency conversion technology can maintain high energy efficiency at different operating frequencies, in harsh environments such as high temperature and high humidity, the system's refrigeration efficiency will be affected, and it cannot always maintain the best energy efficiency. In addition, the existing system has limited perception and response ability to environmental factors, and cannot comprehensively consider multiple variable factors such as humidity, light, and personnel activity, making it difficult to achieve more precise energy saving control.

[0005] Furthermore, the existing frequency conversion air conditioning systems have low intelligence and lack deep analysis and prediction capabilities for real-time environmental data. Although some high-end air conditioning products are equipped with intelligent sensors, these sensors have relatively simple functions and are not highly integrated with the control system, which cannot fully utilize their capabilities. In actual operation, the air conditioning system often cannot adjust the refrigeration power in advance according to environmental changes, resulting in insufficient or excessive refrigeration in some cases, which affects the overall performance of the system.

[0006] In summary, the existing variable frequency air conditioning system has certain technical problems in temperature control accuracy, energy efficiency ratio and intelligent degree, which limits its further improvement in energy saving and comfort. Therefore, the technical personnel in the field propose an intelligent energy-saving air conditioning refrigeration system based on variable frequency technology and its control method to solve the above problems. SUMMARY

[0007] In view of the deficiencies of the prior art, the present application provides an intelligent energy-saving air conditioning refrigeration system based on variable frequency technology and its control method, which solves the problems of insufficient temperature control accuracy, limited energy efficiency ratio improvement and low intelligent degree of the existing variable frequency air conditioning system.

[0008] To achieve the above purpose, the present application is realized by the following technical scheme: an intelligent energy-saving air conditioning refrigeration system based on variable frequency technology, comprising:

[0009] a variable frequency compressor for adjusting the operating frequency to adjust the refrigeration capacity according to the control signal;

[0010] a multivariate sensor network comprising a plurality of sensors for real-time collection of environmental data, including but not limited to temperature, humidity, illumination and personnel activity information;

[0011] a control unit connected with the variable frequency compressor and the multivariate sensor network for generating a control signal according to the environmental data to dynamically adjust the operating frequency of the variable frequency compressor;

[0012] an optimization module for dynamically adjusting the operating parameters of the air conditioning refrigeration system by an optimization algorithm to achieve the best energy efficiency ratio;

[0013] a data processing module for preprocessing the environmental data collected by the multivariate sensor network, including data cleaning, filtering and normalization processing to improve the accuracy and reliability of the data;

[0014] a prediction module for modeling and predicting the environmental data using a deep learning model to predict the environmental changes in the future period, the deep learning model including but not limited to a long short-term memory network;

[0015] a control algorithm module for generating the control signal using a multivariate adaptive control algorithm according to the prediction results of the prediction module, the multivariate adaptive control algorithm considering temperature, humidity, illumination and personnel activity information to dynamically adjust the operating frequency of the variable frequency compressor to achieve more accurate temperature control and energy saving effect;

[0016] a user interface module for receiving user input control instructions and sending the control instructions to the control algorithm module while providing real-time feedback of the system operating state;

[0017] a feedback module configured to feed back the running state of the air conditioning and refrigeration system to a user, including current temperature, humidity, energy consumption, and the like;

[0018] a dynamic adjustment module configured to dynamically adjust the sampling frequency of the multivariate sensor network according to the running state of the air conditioning and refrigeration system and the environmental data, so as to optimize the data collection efficiency and system response speed.

[0019] Preferably, the control unit comprises:

[0020] a data processing module configured to preprocess the environmental data collected by the multivariate sensor network;

[0021] a prediction module configured to model and predict the environmental data by using a deep learning model, so as to predict the environmental change in a future period of time;

[0022] a control algorithm module configured to generate the control signal by using a multivariate adaptive control algorithm according to the prediction result of the prediction module.

[0023] Preferably, the multivariate adaptive control algorithm dynamically adjusts the running frequency of the variable frequency compressor by comprehensively considering the temperature, humidity, illumination, and personnel activity information.

[0024] Preferably, the optimization module optimizes the running parameters of the air conditioning and refrigeration system by using a genetic algorithm or a particle swarm optimization algorithm.

[0025] Preferably, the multivariate sensor network further comprises:

[0026] a temperature and humidity sensor configured to collect indoor temperature and humidity data in real time;

[0027] an illumination sensor configured to collect indoor illumination intensity data in real time;

[0028] a human body infrared sensor configured to detect indoor personnel activity information in real time.

[0029] Preferably, the control unit further comprises:

[0030] a user interface module configured to receive a control instruction input by a user and send the control instruction to the control algorithm module;

[0031] a feedback module configured to feed back the running state of the air conditioning and refrigeration system to the user.

[0032] Preferably, the optimization module is further configured to dynamically adjust the sampling frequency of the multivariate sensor network according to the running state of the air conditioning and refrigeration system and the environmental data.

[0033] A control method for an intelligent energy-saving air conditioning refrigeration system based on variable frequency technology, comprising the following steps:

[0034] Collecting environmental data: Real-time collection of environmental data through a multivariate sensor network, including but not limited to temperature, humidity, light, and human activity information;

[0035] Data preprocessing: Preprocessing of environmental data collected by the multivariate sensor network, including data cleaning, filtering, and normalization processing to improve data accuracy and reliability;

[0036] Environmental prediction: Modeling and predicting future environmental changes using a deep learning model, including but not limited to a long short-term memory network;

[0037] Generating control signals: Generating control signals using a multivariate adaptive control algorithm based on the prediction results of the prediction module, which considers temperature, humidity, light, and human activity information to dynamically adjust the operating frequency of the variable frequency compressor for more accurate temperature control and energy saving;

[0038] Optimizing operating parameters: Optimizing operating parameters of the air conditioning refrigeration system using an optimization algorithm through an optimization module to achieve the best energy efficiency ratio, including but not limited to genetic algorithms or particle swarm optimization algorithms;

[0039] User interaction: Receiving user input control instructions through a user interface module and sending them to the control algorithm module while providing real-time feedback on system operating status;

[0040] Feedback on operating status: Providing feedback on the operating status of the air conditioning refrigeration system to users through a feedback module, including current temperature, humidity, energy consumption, and other information;

[0041] Dynamic adjustment of sampling frequency: Dynamically adjusting the sampling frequency of the multivariate sensor network based on the operating status of the air conditioning refrigeration system and the environmental data to optimize data collection efficiency and system response speed.

[0042] Preferably, the step of generating control signals includes:

[0043] Data preprocessing: Preprocessing of environmental data collected by the multivariate sensor network;

[0044] Environmental prediction: Modeling and predicting future environmental changes using a deep learning model;

[0045] Control signal generation: based on the prediction results, a multivariate adaptive control algorithm is used to generate the control signal.

[0046] Preferably, the step of optimizing the operating parameters comprises:

[0047] Parameter optimization: the operating parameters of the air conditioning refrigeration system are optimized using a genetic algorithm or a particle swarm optimization algorithm.

[0048] Dynamic adjustment: according to the operating state of the air conditioning refrigeration system and the environmental data, the sampling frequency of the multivariate sensor network is dynamically adjusted.

[0049] The present application provides an intelligent energy-saving air conditioning refrigeration system based on variable frequency technology and its control method. It has the following beneficial effects:

[0050] 1. The present application uses a multivariate adaptive control algorithm to dynamically adjust the operating frequency of the variable frequency compressor by considering temperature, humidity, light, and personnel activity information and other environmental factors. Compared with the traditional air conditioning system which only relies on a single temperature variable for control, the present application can more accurately maintain the indoor set temperature, reduce temperature fluctuations, and significantly improve the temperature control accuracy. This precise temperature control method not only provides users with a more comfortable indoor environment and avoids discomfort caused by large temperature changes, but also allows for flexible adjustment according to individual user needs, improving user satisfaction.

[0051] 2. The present application uses an optimization module to dynamically adjust the operating parameters of the air conditioning refrigeration system using a genetic algorithm or a particle swarm optimization algorithm to achieve the best energy efficiency ratio. In traditional air conditioning systems, the energy efficiency ratio has limited room for improvement in extreme weather or high load operation, while the present application can intelligently optimize key parameters such as compressor frequency and fan speed based on real-time environmental data and system operating state to ensure that the system always operates in the most energy-efficient state. In addition, combined with the prediction of environmental changes by a deep learning model, the system can adjust the refrigeration power in advance to avoid unnecessary energy consumption. This intelligent energy-saving control method not only effectively reduces the energy consumption of the air conditioning system, but also reduces electricity bills, has significant economic and environmental benefits, and conforms to the development trend of energy saving and emission reduction.

[0052] 3. The present application integrates multivariate sensor network, deep learning model, optimization algorithm and other advanced technologies to build a highly intelligent air conditioning refrigeration system. The multivariate sensor network collects various environmental data in real time, providing comprehensive and accurate input information for the system. The deep learning model can model and predict complex environmental data, enabling the system to have stronger environmental adaptability. The optimization algorithm ensures that the system operating parameters are always in the optimal state. This intelligent system design not only improves the operation stability of the air conditioning system, reduces the operation abnormalities caused by environmental changes or equipment failures, but also realizes convenient user interaction through the user interface module, provides real-time feedback of the system operation status, and facilitates user monitoring and management. Compared with the prior art, the present application significantly improves the intelligent level of the air conditioning system, providing users with a more efficient, reliable and convenient air conditioning experience. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 The present application is a general flowchart. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present application will be described in detail below with reference to the accompanying drawings of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0055] Please refer to the accompanying drawings of the present application Figure 1 The present application provides an intelligent energy-saving air conditioning refrigeration system based on frequency conversion technology, comprising:

[0056] A variable frequency compressor is used to adjust the operating frequency according to the control signal to adjust the refrigeration capacity.

[0057] A multivariate sensor network comprising various sensors is used to collect environmental data in real time, including but not limited to temperature, humidity, light and personnel activity information.

[0058] A control unit is connected with the variable frequency compressor and the multivariate sensor network, used to generate a control signal according to the environmental data to dynamically adjust the operating frequency of the variable frequency compressor; the control unit comprises:

[0059] A data processing module is used to preprocess the environmental data collected by the multivariate sensor network.

[0060] A prediction module uses a deep learning model to model and predict the environmental data to predict the environmental changes in the future period of time.

[0061] Specifically, the variable frequency compressor can adjust its operating frequency according to the control signals issued by the control unit, thereby achieving precise adjustment of the refrigeration capacity. The application of this variable frequency technology enables the air conditioning system to flexibly change the refrigeration power according to actual needs, which has significant advantages in energy saving effect and running stability compared with traditional fixed frequency compressors.

[0062] The multivariate sensor network working in cooperation with the variable frequency compressor is composed of multiple different types of sensors responsible for real-time collection of environmental data. The collected environmental data types are diverse, including not only basic temperature and humidity information but also illumination intensity and indoor personnel activity conditions. By collecting these multi-dimensional data, the system can more comprehensively understand the current indoor environmental conditions and provide data support for subsequent precise control.

[0063] The control unit is closely connected with the variable frequency compressor and the multivariate sensor network. It receives environmental data from the sensor network and generates corresponding control signals based on these data, and then dynamically adjusts the operating frequency of the variable frequency compressor. The control unit integrates multiple functional modules, among which the data processing module is responsible for preprocessing the original environmental data collected by the sensors, including removing noise, filling missing values, and standardizing data, to ensure data quality and usability, providing a reliable data foundation for subsequent analysis and processing. The prediction module uses deep learning models such as long short-term memory networks to model and predict the preprocessed environmental data. By learning the historical variation rules of environmental data, this module can predict the environmental change trend in the future, such as temperature rise and fall, humidity increase and decrease, etc. This prediction capability enables the air conditioning system to make proactive responses rather than only passive adjustments to the current environmental conditions, thereby realizing more intelligent and forward-looking control strategies, further improving the system's energy saving effect and user's comfort experience.

[0064] The control algorithm module generates control signals based on the prediction results of the prediction module using a multivariate adaptive control algorithm.

[0065] In the present invention, the control algorithm module generates control signals based on the prediction results of the prediction module using a multivariate adaptive control algorithm. This algorithm considers multiple environmental factors such as temperature, humidity, illumination, and personnel activity information to dynamically adjust the operating frequency of the variable frequency compressor, achieving more precise temperature control and energy saving effect. The formula of the control algorithm module is as follows:

[0066]

[0067] Where: u(t) is the control signal used to adjust the operating frequency of the variable frequency compressor. e(t) is the error signal defined as the set temperature T setThe difference between the actual temperature T(t) and the setpoint temperature Tsp, i.e., e(t) = T set -T(t). K p Kp is the proportional gain, used to adjust the proportional part of the error signal. i Ki is the integral gain, used to adjust the integral part of the error signal to eliminate steady-state error. d Kd is the derivative gain, used to adjust the derivative part of the error signal to improve the response speed and stability of the system. i (t) is the value of the ith environmental variable, such as humidity H(t), illumination L(t), personnel activity information A(t), etc. wi is the weight coefficient of the ith environmental variable, used to adjust the influence of each environmental variable on the control signal. n is the total number of environmental variables.

[0068] The optimization module is used to dynamically adjust the operating parameters of the air conditioning refrigeration system through optimization algorithms to achieve the best energy efficiency ratio. The optimization module is also used to dynamically adjust the sampling frequency of the multivariate sensor network according to the operating state of the air conditioning refrigeration system and environmental data.

[0069] The data processing module is used to preprocess the environmental data collected by the multivariate sensor network, including data cleaning, filtering and normalization processing, to improve the accuracy and reliability of the data.

[0070] Specifically, the optimization module is responsible for dynamically adjusting the operating parameters of the air conditioning refrigeration system through advanced optimization algorithms to ensure that the system always operates in the best energy efficiency state. These operating parameters include but are not limited to the operating frequency of the compressor, the speed of the fan, etc., which directly affect the energy consumption and refrigeration effect of the air conditioning system. The optimization module uses algorithms such as genetic algorithm or particle swarm optimization algorithm to intelligently find the optimal parameter combination according to the real-time operating state of the system and environmental data. In addition, the optimization module also has the ability to dynamically adjust the sampling frequency of the multivariate sensor network according to the operating state of the air conditioning refrigeration system and environmental data. This means that the system can flexibly change the collection frequency of sensor data according to actual needs, thereby reducing unnecessary data processing and transmission while ensuring data quality, further improving the efficiency and response speed of the system.

[0071] The data processing module focuses on pre-processing the environmental data collected by the multi-variable sensor network. These environmental data include temperature, humidity, light, and human activity information, which are important basis for the intelligent control of the system. The operations performed by the data processing module include data cleaning to remove incorrect or incomplete data, filtering to reduce the impact of noise on data, and normalization processing to ensure that data from different sources can be compared and analyzed on the same scale. Through these preprocessing steps, the data processing module can significantly improve the accuracy and reliability of the data, providing high-quality data support for subsequent environmental prediction and control signal generation, thereby enhancing the stability and control accuracy of the entire system.

[0072] The prediction module uses a deep learning model to model and predict environmental data to predict environmental changes in the future. The deep learning model includes but is not limited to long short-term memory networks.

[0073] The control algorithm module generates control signals based on the prediction results of the prediction module using a multi-variable adaptive control algorithm. The multi-variable adaptive control algorithm considers temperature, humidity, light, and human activity information to dynamically adjust the operating frequency of the variable frequency compressor to achieve more accurate temperature control and energy saving effect.

[0074] The user interface module is used to receive user input control instructions and send control instructions to the control algorithm module while providing real-time feedback of the system's running state.

[0075] The feedback module is used to feed back the running state of the air conditioning refrigeration system to the user, including current temperature, humidity, energy consumption, etc.

[0076] The dynamic adjustment module dynamically adjusts the sampling frequency of the multi-variable sensor network based on the running state of the air conditioning refrigeration system and environmental data to optimize data collection efficiency and system response speed. The multi-variable adaptive control algorithm considers temperature, humidity, light, and human activity information to dynamically adjust the operating frequency of the variable frequency compressor.

[0077] The optimization module uses a genetic algorithm to optimize the operating parameters of the air conditioning refrigeration system.

[0078] Specifically, the dynamic adjustment module intelligently adjusts the sampling frequency of the multivariate sensor network based on the real-time operating conditions of the air conditioning refrigeration system and the collected environmental data. This process is dynamic, meaning that the system can flexibly adjust the frequency of data collection according to the current operating requirements and environmental changes. For example, when the environmental conditions are relatively stable, the system can reduce the sampling frequency to save resources; when the environment changes rapidly or the system operating state requires more detailed monitoring, the sampling frequency will be correspondingly increased. In this way, the dynamic adjustment module not only optimizes the efficiency of data collection and reduces unnecessary data processing burden, but also speeds up the response speed of the system, so that the air conditioning system can more quickly adapt to environmental changes and user needs.

[0079] In the present application, the optimization module uses a genetic algorithm to optimize the operating parameters of the air conditioning refrigeration system. Genetic algorithm is a search algorithm based on the principles of natural selection and genetics, which simulates the process of biological evolution to find the optimal solution.

[0080] The formula used by the genetic algorithm is:

[0081]

[0082] Where: f(x) is the fitness value of individual x, reflecting the degree of excellence of the individual. C(x) is the cost function of individual x, usually including energy consumption, running time and other indicators. In the present application, the cost function can be a comprehensive indicator of energy consumption and running time of the air conditioning system.

[0083] The multivariate sensor network also includes:

[0084] Temperature and humidity sensors for real-time collection of indoor temperature and humidity data;

[0085] Illumination sensors for real-time collection of indoor light intensity data;

[0086] Human infrared sensors for real-time detection of indoor personnel activity information.

[0087] The control unit also includes:

[0088] User interface module for receiving user input control instructions and sending control instructions to the control algorithm module;

[0089] Feedback module for feeding back the operating state of the air conditioning refrigeration system to the user.

[0090] A control method for an intelligent energy-saving air conditioning refrigeration system based on variable frequency technology, comprising the following steps:

[0091] Collecting environmental data: Real-time collection of environmental data through a multivariate sensor network, including but not limited to temperature, humidity, light, and human activity information;

[0092] Data preprocessing: Preprocessing of environmental data collected by the multivariate sensor network, including data cleaning, filtering, and normalization to improve data accuracy and reliability;

[0093] Environmental prediction: Modeling and predicting future environmental changes using a deep learning model, including but not limited to a long short-term memory network;

[0094] Generating control signals: Generating control signals based on the prediction results of the prediction module using a multivariate adaptive control algorithm that considers temperature, humidity, light, and human activity information to dynamically adjust the operating frequency of the variable frequency compressor for more accurate temperature control and energy saving;

[0095] The step of generating control signals includes:

[0096] Data preprocessing: Preprocessing of environmental data collected by the multivariate sensor network;

[0097] Environmental prediction: Modeling and predicting future environmental changes using a deep learning model;

[0098] Control signal generation: Generating control signals based on the prediction results using a multivariate adaptive control algorithm.

[0099] Optimizing operating parameters: Dynamically adjusting the operating parameters of the air conditioning and refrigeration system through the optimization module using an optimization algorithm to achieve the best energy efficiency ratio, including but not limited to genetic algorithms or particle swarm optimization algorithms;

[0100] User interaction: Receiving user input control instructions through the user interface module and sending them to the control algorithm module while providing real-time feedback on system operating status;

[0101] Feedback on operating status: Providing real-time feedback on the operating status of the air conditioning and refrigeration system to the user through the feedback module, including current temperature, humidity, energy consumption, and other information;

[0102] Dynamic adjustment of sampling frequency: Dynamically adjusting the sampling frequency of the multivariate sensor network based on the operating status of the air conditioning and refrigeration system and environmental data to optimize data collection efficiency and system response speed.

[0103] The step of optimizing operating parameters includes:

[0104] Parameter optimization: Genetic algorithm or particle swarm optimization algorithm is used to optimize the operating parameters of the air conditioning refrigeration system.

[0105] Dynamic adjustment: According to the operating state and environmental data of the air conditioning refrigeration system, the sampling frequency of the multivariate sensor network is dynamically adjusted.

[0106] Although embodiments of the present application have been shown and described, it is to be understood that various modifications, substitutions, replacements and changes can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A variable frequency technology based intelligent energy saving air conditioning refrigeration system, characterized in that, The system comprises: a variable frequency compressor for adjusting the operating frequency to regulate the cooling capacity according to the control signal; a multi-variable sensor network comprising multiple sensors for real-time collection of environmental data, including but not limited to temperature, humidity, light, and human activity information; a control unit connected to the variable frequency compressor and multi-variable sensor network for generating a control signal based on the environmental data to dynamically adjust the operating frequency of the variable frequency compressor; an optimization module for dynamically adjusting the operating parameters of the air conditioning refrigeration system through an optimization algorithm to achieve the best energy efficiency ratio; a data processing module for preprocessing the environmental data collected by the multi-variable sensor network, including data cleaning, filtering, and normalization processing to improve the accuracy and reliability of the data; a prediction module using a deep learning model to model and predict the environmental changes in the future period, the deep learning model including but not limited to long short-term memory network; a control algorithm module generating the control signal based on the prediction results of the prediction module using a multi-variable adaptive control algorithm, which considers temperature, humidity, light, and human activity information to dynamically adjust the operating frequency of the variable frequency compressor to achieve more accurate temperature control and energy saving effect; a user interface module for receiving user input control instructions and sending them to the control algorithm module while providing real-time feedback of the system's running state; a feedback module for feeding back the running state of the air conditioning refrigeration system to the user, including current temperature, humidity, energy consumption, etc. a dynamic adjustment module for dynamically adjusting the sampling frequency of the multi-variable sensor network based on the running state of the air conditioning refrigeration system and the environmental data to optimize data collection efficiency and system response speed.

2. The intelligent energy-saving air conditioning and refrigeration system based on variable frequency technology according to claim 1, characterized in that, The control unit comprises: a data processing module for preprocessing the environmental data collected by the multi-variable sensor network; a prediction module using a deep learning model to model and predict the environmental changes in the future period; a control algorithm module generating the control signal based on the prediction results of the prediction module using a multi-variable adaptive control algorithm.

3. The intelligent energy-saving air conditioning and refrigeration system based on variable frequency technology according to claim 2, characterized in that, The multi-variable adaptive control algorithm considers temperature, humidity, light, and human activity information to dynamically adjust the operating frequency of the variable frequency compressor.

4. The intelligent energy-saving air conditioning and refrigeration system based on variable frequency technology according to claim 1, characterized in that, The optimization module uses genetic algorithm or particle swarm optimization algorithm to optimize the operating parameters of the air conditioning refrigeration system.

5. The intelligent energy-saving air-conditioning and refrigeration system based on variable frequency technology according to claim 1, characterized in that, The multi-variable sensor network further comprises: temperature and humidity sensors for real-time collection of indoor temperature and humidity data; light sensors for real-time collection of indoor light intensity data; human infrared sensors for real-time detection of indoor human activity information.

6. The intelligent energy-saving air-conditioning and refrigeration system based on variable frequency technology according to claim 1, characterized in that, The control unit further comprises: a user interface module for receiving user input control instructions and sending them to the control algorithm module; a feedback module for feeding back the running state of the air conditioning refrigeration system to the user.

7. The intelligent energy-saving air-conditioning and refrigeration system based on variable frequency technology according to claim 1, characterized in that, The optimization module is also used to dynamically adjust the sampling frequency of the multivariate sensor network according to the operating state of the air conditioning refrigeration system and the environmental data.

8. A control method of the intelligent energy-saving air conditioning and refrigeration system based on variable frequency technology according to any one of claims 1-7, characterized in that, The method comprises the following steps: Collecting environmental data: real-time collection of environmental data through a multivariate sensor network, including but not limited to temperature, humidity, light, and personnel activity information; Data preprocessing: preprocessing of the environmental data collected by the multivariate sensor network, including data cleaning, filtering, and normalization processing to improve data accuracy and reliability; Environmental prediction: modeling and prediction of the environmental data using a deep learning model to predict future environmental changes over a period of time, including but not limited to long short-term memory networks; Generating control signals: generating control signals using a multivariate adaptive control algorithm based on the prediction results of the prediction module, which considers temperature, humidity, light, and personnel activity information to dynamically adjust the operating frequency of the variable frequency compressor for more accurate temperature control and energy saving effect; Optimizing operating parameters: dynamically adjusting the operating parameters of the air conditioning refrigeration system using an optimization algorithm through an optimization module to achieve the best energy efficiency ratio, including but not limited to genetic algorithms or particle swarm optimization algorithms; User interaction: receiving user input control instructions through a user interface module and sending the control instructions to the control algorithm module while providing real-time feedback of system operating status; Feedback operating status: feeding back the operating status of the air conditioning refrigeration system to the user through a feedback module, including current temperature, humidity, energy consumption, etc. Dynamically adjusting the sampling frequency: dynamically adjusting the sampling frequency of the multivariate sensor network according to the operating state of the air conditioning refrigeration system and the environmental data to optimize data collection efficiency and system response speed.

9. The control method of the intelligent energy-saving air conditioning and refrigeration system based on variable frequency technology according to claim 8, characterized in that, The step of generating control signals includes: Data preprocessing: preprocessing of the environmental data collected by the multivariate sensor network; Environmental prediction: modeling and prediction of the environmental data using a deep learning model to predict future environmental changes over a period of time; Control signal generation: generating the control signal using a multivariate adaptive control algorithm based on the prediction results.

10. The control method of the intelligent energy-saving air conditioning and refrigeration system based on variable frequency technology according to claim 8, characterized in that, The step of optimizing operating parameters includes: Parameter optimization: optimizing the operating parameters of the air conditioning refrigeration system using a genetic algorithm or particle swarm optimization algorithm; Dynamic adjustment: dynamically adjusting the sampling frequency of the multivariate sensor network according to the operating state of the air conditioning refrigeration system and the environmental data.

Images