Central air-conditioning full-link energy-saving system and method for subway stations based on wind balance

Abstract

The present invention provides a full-link energy-saving system and method for the central air-conditioning system in a subway station based on air balance, belonging to the technical field of air-conditioning energy saving. The method includes: real-time collecting environmental data inside and outside the subway station through a sensor network, and uploading the collected environmental data to the full-link energy-saving control platform for the central air-conditioning system; the full-link energy-saving control platform for the central air-conditioning system dynamically adjusts the air volume of the supply air duct and the return air duct through fan control according to the collected data; by real-time collecting environmental data and combining with advanced control algorithms, the system can dynamically adjust the fan speed, the load of the refrigeration unit, the ratio of fresh air to return air, etc., so as to optimize the operating state of the air-conditioning system, effectively reduce energy consumption, and improve the overall energy-saving effect of the system.

Description

Technical Field

[0001] The present invention provides a full-link energy-saving system and method for the central air-conditioning system of subway stations based on air balance, belonging to the technical field of air-conditioning energy saving. Background Art

[0002] As an important node of urban transportation, the central air-conditioning system of subway stations has an important impact on passenger comfort and energy consumption. The traditional central air-conditioning system of subway stations has problems such as inconsistent design load and actual load, frequent problems in the chilled water system, and improper control of the cooling water system, resulting in serious energy waste and difficulty in achieving precise temperature and humidity control. Therefore, a full-link energy-saving method for the central air-conditioning system of subway stations that can achieve air balance, intelligent control, and significantly improve energy efficiency is needed. Summary of the Invention

[0003] The present invention provides a full-link energy-saving system and method for the central air-conditioning system of subway stations based on air balance to solve the problems mentioned in the above background art:

[0004] The full-link energy-saving method for the central air-conditioning system of subway stations based on air balance proposed by the present invention includes:

[0005] S1. Real-time collect the environmental data inside and outside the subway station through a sensor network, and upload the collected environmental data to the full-link energy-saving control platform of the central air-conditioning system;

[0006] S2. The full-link energy-saving control platform of the central air-conditioning system dynamically adjusts the air volume of the supply air duct and the return air duct through fan control according to the collected data;

[0007] S3. Read all the technical parameters of the refrigeration unit through the Modbus network protocol, optimize the overall COP of the central air-conditioning system by using the extremum search algorithm, and control the host to add or subtract units according to the cooling capacity demand;

[0008] S4. Adjust the air volume and number of units of the cooling tower fan according to the relevant situation, and adjust the cold and heat source supply in real time according to the load status of the fresh air unit, perform joint air and water adjustment, and adjust the supply air temperature according to the corresponding parameters;

[0009] S5. Adjust the opening degree of the air valve according to the changes in the indoor and outdoor environment, and perform centralized intelligent management of the central air-conditioning equipment;

[0010] S6. Adjust the opening angle of the electric proportional integral regulating air valve in the corresponding area through the signal fed back by the high-precision temperature sensors set in different areas of the platform layer.

[0011] The full-link energy-saving system for the central air-conditioning system of subway stations based on air balance proposed by the present invention includes:

[0012] Data acquisition module: It collects the environmental data inside and outside the subway station in real time through the sensor network, and uploads the collected environmental data to the full-link energy-saving control platform for central air conditioning;

[0013] Dynamic adjustment module: The full-link energy-saving control platform for central air conditioning dynamically adjusts the air volume of the supply air duct and the return air duct through fan control according to the collected data;

[0014] Parameter reading module: It reads all the technical parameters of the refrigeration unit through the Modbus network protocol, optimizes the overall COP of the central air conditioning by using the extremum search algorithm, and controls the addition and subtraction of the main unit according to the cooling capacity demand;

[0015] Supply regulation module: It adjusts the air volume and the number of units of the cooling tower fan according to the cooling water temperature difference and related conditions, and adjusts the cold and heat source supply in real time according to the load status of the fresh air unit, conducts joint adjustment of air and water, and adjusts the supply air temperature according to the corresponding parameters;

[0016] Opening adjustment module: It adjusts the opening of the air valve according to the changes in the indoor and outdoor environment, and conducts centralized intelligent management of the central air conditioning equipment;

[0017] Angle adjustment module: It adjusts the opening angle of the electric proportional integral regulating air valve in the corresponding area through the signals fed back by the high-precision temperature sensors set in different areas of the platform layer.

[0018] Advantages of the present invention: By collecting environmental data in real time and combining advanced control algorithms (such as PID control, fuzzy control, extremum seeking algorithm, etc.), the system can dynamically adjust the fan speed, the load of the refrigeration unit, the ratio of fresh air to return air, etc., thereby optimizing the operating state of the air conditioning system, effectively reducing energy consumption, and improving the overall energy-saving effect of the system; The system realizes the centralized intelligent management of central air conditioning equipment through technical means such as integrating sensor networks, data acquisition platforms, and machine learning algorithms. The system can monitor the equipment status in real time, automatically identify and eliminate outliers, perform adaptive learning and adjustment, and further improve the stability and reliability of the operation of air conditioning equipment; Through machine learning and data analysis, the system can predict the load demand based on historical data and environmental change trends, and formulate energy-saving strategies according to the prediction results. This can not only help optimize the equipment operation parameters, prevent energy waste, but also early warn of potential system failure risks and avoid unnecessary energy consumption caused by over-operation of equipment; With the help of technologies such as fluid dynamics models, time series analysis, and cluster analysis, the system can accurately calculate the air volume of the supply air duct and the return air duct, and timely adjust the control strategy, realizing the precise control of the central air conditioning system. Especially in aspects such as the cooling tower fan, the opening degree of the air valve, and the cooling water temperature difference, it can be adjusted in real time according to environmental changes to ensure that the air conditioning system is always in the optimal operating state; The system realizes remote monitoring of equipment through the Internet of Things technology. Combined with the fault warning mechanism, potential problems can be identified in advance by analyzing historical data and real-time monitoring information before the occurrence of faults, and preventive maintenance can be carried out, greatly improving the service life of the equipment and the operation reliability of the system; During the operation of the system, the machine learning model is continuously optimized and iterated through feedback data, which not only improves the current energy-saving effect, but also provides data support for future system upgrades and performance improvements. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flowchart of the method steps of the present invention;

[0020] Figure 2 It is a block diagram of the system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0022] One embodiment of the present invention, as Figure 1 shown, is a full-link energy-saving method for central air conditioning in a subway station based on air balance. The method includes:

[0023] S1. Real-time collect environmental data inside and outside the subway station through a sensor network, and upload the collected environmental data to the full-link energy-saving control platform of the central air conditioning system;

[0024] S2. Based on the collected data, the full-link energy-saving control platform of the central air conditioner dynamically adjusts the air volume of the supply air duct and the return air duct through fan control;

[0025] S3. Read all the technical parameters of the refrigeration unit through the Modbus network protocol, optimize the overall COP of the central air conditioner using the extremum search algorithm, and control the host to add or subtract units according to the cooling capacity demand;

[0026] S4. According to the relevant conditions such as the cooling water temperature difference, the real-time load of the air conditioner, and the outdoor wet bulb temperature, adjust the air volume and the number of units of the cooling tower fan, and adjust the cold and heat source supply in real time according to the load state of the fresh air unit, conduct joint adjustment of air and water, and adjust the supply air temperature according to the changes in outdoor temperature and humidity and corresponding parameters such as the on-site temperature;

[0027] S5. Adjust the opening degree of the air valve according to the changes in the indoor and outdoor environment, and conduct centralized intelligent management of the central air conditioner equipment;

[0028] S6. Adjust the opening angle of the electric proportional integral regulating air valve in the corresponding area through the signals fed back by the high-precision temperature sensors set in different areas of the platform layer.

[0029] The working principle of the above technical solution is as follows: A dense sensor network is arranged inside and outside the subway station. These sensors can capture key environmental data such as temperature, humidity, and passenger flow inside and outside the subway station in real time. These data are uploaded to the central air-conditioning full-link energy-saving control platform in real time through a high-speed communication network. The control platform is a central system integrating advanced algorithms and data processing capabilities, capable of quickly analyzing and processing massive amounts of data; The central air-conditioning full-link energy-saving control platform dynamically adjusts the air volume of the supply air duct and the return air duct according to the collected environmental data, including fine-tuning parameters such as the fan speed and damper opening. By avoiding excessive fresh air intake or excessive return air discharge, it can ensure that the air circulation inside the subway station meets the comfort requirements of passengers while achieving the maximum utilization of energy; Through the Modbus network protocol, the central air-conditioning full-link energy-saving control platform can read all technical parameters of the chiller, including operating status, energy consumption, refrigeration efficiency, etc. Using the extremum search algorithm, the platform can optimize the overall COP (coefficient of performance) of the central air-conditioning. According to the actual cooling demand of the subway station, the platform can intelligently control the addition and subtraction of the main unit to ensure that the refrigeration efficiency is always in the optimal state; The cooling tower is an important part of the subway station central air-conditioning system, and its operating efficiency directly affects the energy consumption of the entire system. The central air-conditioning full-link energy-saving control platform intelligently adjusts the air volume and number of units of the cooling tower fan according to relevant conditions such as the cooling water temperature difference, the real-time load of the air-conditioning, and the outdoor wet-bulb temperature. At the same time, the platform also adjusts the cold and heat source supply in real time according to the load status of the fresh air unit to achieve coordinated control of air and water. In addition, the platform can also finely adjust the supply air temperature according to the changes in outdoor temperature and humidity and corresponding parameters such as the on-site temperature to ensure that the air environment inside the subway station is always in the best state; According to the changes in the indoor and outdoor environment, the central air-conditioning full-link energy-saving control platform can intelligently adjust the damper opening. By installing an electric proportional integral regulating damper at the air outlet position of each damper and setting high-precision temperature sensors in different areas such as the strong cooling area, weak cooling area, and comfort area on the platform layer. These temperature sensors can monitor the temperature changes in the area in real time and accurately and feedback the data to the control system. The control system accurately adjusts the opening angle of the electric proportional integral regulating damper in the corresponding area according to the signals feedback by these temperature sensors and the preset temperature values in different areas, so as to effectively control the temperature in different areas. When the air outlet is close to the air handling unit, due to the large air volume, the temperature in this area is more likely to reach the set temperature. At this time, the system automatically reduces the opening angle of the electric regulating damper, so that the excess air volume can be transported to the area of the farther air outlet, thereby ensuring that the temperature in the area of the farther air outlet can also reach the set value. At the same time, a lower temperature value is set for the strong cooling area. When the temperature sensor in the strong cooling area feedbacks that the temperature does not meet the standard, the system appropriately increases the damper opening in this area; For the weak cooling area and the comfort area, the damper opening is adjusted according to their respective preset temperatures.This can not only ensure that the air circulation in the subway station meets the comfort requirements of passengers, but also achieve the maximum utilization of energy. At the same time, the platform also conducts centralized intelligent management of the central air-conditioning equipment, including monitoring the operating status of the equipment, fault warning, and remote control, etc. Through centralized management, the global optimization and energy conservation of the central air-conditioning system in the subway station can be realized.

[0030] The effects of the above technical solutions are as follows: The environmental data inside and outside the subway station are collected in real time through the sensor network and uploaded to the energy-saving control platform, enabling the system to make precise adjustments according to the actual situation; The dynamic adjustment of the fan control ensures the pressure balance in the mixing chamber, avoiding excessive fresh air intake or excessive return air discharge, thus reducing energy waste; The overall COP of the central air-conditioning is optimized using the extremum search algorithm, making the operation of the refrigeration unit more efficient and further improving the energy utilization efficiency; Due to the improvement of the energy utilization efficiency, the energy consumption of the central air-conditioning system in the subway station is significantly reduced, thereby reducing the operating cost; The centralized intelligent management makes the operation of the equipment more stable, reducing the downtime and maintenance cost caused by equipment failures; By precisely adjusting the supply air temperature and volume, the air environment in the subway station is made more comfortable, meeting the needs of passengers; The coordinated adjustment of water and air ensures that the supply of cold and heat sources matches the changes in the environment inside and outside the subway station, further improving the comfort of passengers; This technical solution contributes to energy conservation and emission reduction by improving the energy utilization efficiency and reducing energy consumption; The reduced energy consumption means less consumption of fossil fuels and greenhouse gas emissions, which is beneficial to environmental protection and sustainable development; The centralized intelligent management makes the operation of the central air-conditioning system in the subway station more intelligent and automated, reducing manual intervention and operation difficulty; The real-time monitoring and warning function enables managers to discover and solve problems in a timely manner, improving the management efficiency; Measures such as dynamic adjustment of fan control, optimization of refrigeration units, and coordinated adjustment of water and air make the operation of the central air-conditioning system in the subway station more stable and reliable; The downtime caused by equipment failures and the impact on subway operations are reduced.

[0031] In one embodiment of the present invention, S1 includes:

[0032] S11. Collect environmental data through a high-precision sensor network deployed at key positions inside and outside the subway station (such as platforms, concourses, entrances and exits, tunnels, etc.), including temperature sensors, humidity sensors, CO2 concentration sensors, PM2.5 sensors, and infrared passenger flow counters.

[0033] S12. Through a data verification and anomaly detection mechanism, preliminarily process the collected environmental data and eliminate outliers.

[0034] S13. Upload the preliminarily processed environmental data to the full-link energy-saving control platform of the central air-conditioning through a wired or wireless network.

[0035] S14. Store the real-time data and historical data respectively through the real-time database and historical database established on the control platform;

[0036] S15. Mine and analyze the stored data through machine learning algorithms (such as cluster analysis, time series analysis), identify the environmental change trend, and predict the future load demand; the load demand is predicted by the following formula;

[0037]

[0038] where, represents the predicted load demand at future time t + Δt; represents the value of the i-th environmental parameter at time t (such as temperature, humidity, etc.); P(t) represents the number of people flow at time t; α i represents the weight coefficient of the i-th environmental parameter; β represents the weight coefficient of the influence of the number of people flow on the load; h represents a complex non-linear function used to capture the interaction effect between the environmental parameter and the number of people flow, such as a neural network; θ represents the model parameter.

[0039] The working principle of the above technical solution is as follows: At key locations inside and outside the subway station, such as platforms, concourses, entrances and exits, and tunnels, a high-precision sensor network is deployed. These sensors include temperature sensors, humidity sensors, CO2 concentration sensors, PM2.5 sensors, and infrared pedestrian flow counters; these sensors can collect environmental data inside and outside the subway station in real time, such as temperature, humidity, CO2 concentration, PM2.5 concentration, and pedestrian flow, etc.; the collected environmental data is first subjected to data integrity verification to ensure that each sensor provides a complete data set, and then data rationality verification is carried out to check whether the data is within a reasonable range, for example, whether the temperature is between -20°C and 50°C, whether the humidity is between 0% and 100%, etc.; finally, apply statistical-based anomaly detection algorithms, such as threshold detection, box plot detection, or machine learning-based anomaly detection models, to further analyze the data and eliminate possible outliers; the preliminarily processed environmental data is uploaded to the full-link energy-saving control platform of the central air conditioner through wired or wireless networks. The wired network may include high-speed transmission media such as optical fibers, while the wireless network may include 4G / 5G or private networks, etc.; a real-time database and a historical database are established on the control platform for storing real-time data and historical data respectively; the real-time database is used to store the data that is currently being collected and processed for quickly responding to environmental changes; the historical database is used to store the data over a period of time in the past for long-term analysis and trend prediction; through machine learning algorithms, such as cluster analysis, time series analysis, etc., the stored data is mined and analyzed; cluster analysis can help identify the environmental data characteristics in different time periods or different regions, so as to formulate more precise energy-saving strategies; time series analysis can be used to predict future load demands and provide a scientific basis for the operation and scheduling of the central air conditioner system.

[0040] The effects of the above technical solutions are as follows: By deploying a high-precision sensor network at key positions inside and outside the subway station, it is possible to collect environmental data inside and outside the subway station in real time and accurately, such as temperature, humidity, CO2 concentration, PM2.5 concentration, and passenger flow. These data provide important input information for the energy-saving control of the central air-conditioning system; ensuring that each sensor provides a complete data set and avoiding inaccurate control caused by missing data; through data rationality verification, it is possible to check whether the data is within a reasonable range, thereby eliminating unreasonable data and improving the reliability of the data; the anomaly detection algorithm based on statistics can further identify and eliminate outliers, ensuring the accuracy and effectiveness of the data. This helps to avoid miscontrol caused by sensor failures or sudden changes in environmental factors; uploading the preliminarily processed environmental data to the central air-conditioning full-link energy-saving control platform through wired or wireless networks realizes real-time data transmission. It helps the control platform to obtain the latest environmental data in a timely manner, so as to make accurate control decisions; the real-time database and historical database established on the control platform are used to store real-time data and historical data respectively. It helps to achieve long-term data storage and efficient retrieval, providing convenience for subsequent data analysis and mining; by using machine learning algorithms such as cluster analysis and time series analysis to mine and analyze the stored data, it is possible to identify environmental change trends and predict future load demands. This provides a scientific basis for the intelligent control and decision-making optimization of the central air-conditioning system; the intelligent control and decision-making optimization based on environmental data helps to achieve energy conservation and consumption reduction of the central air-conditioning system. For example, adjusting the operating state of the refrigeration unit according to the predicted future load demand to avoid energy consumption waste caused by over-cooling or under-cooling; by real-time monitoring the environmental data inside and outside the subway station and adjusting the operating state of the central air-conditioning system according to these data, it is possible to provide a more comfortable and healthy riding environment for passengers; intelligent control and decision-making optimization helps to reduce the failure rate and downtime of the central air-conditioning system and improve the subway operation efficiency. At the same time, energy conservation and consumption reduction also help to reduce the subway operation cost and improve the economic benefits of subway operation. The above load demand formula contains multiple environmental parameters (such as temperature, humidity, etc.) and passenger flow as independent variables, which can more comprehensively reflect the changes in actual load demand. By comprehensively considering these factors, the prediction results are more accurate and closer to the change trend of the real load demand; the weight coefficients in the formula can be flexibly adjusted according to the actual situation to reflect the relative importance of different factors on future load demand. This flexibility enables the prediction model to better adapt to the demand changes in different scenarios and time periods. The non-linear function h in the formula can capture the complex interaction effects between environmental parameters and passenger flow. Such interaction effects often exist in the actual environment and are difficult to describe with simple linear relationships. By introducing the non-linear function, the prediction model can better capture these complex relationships, thereby improving the accuracy of the prediction.The formula implies the idea of time series analysis, that is, using historical data to predict future load demand. Time series analysis can capture the trends and periodicity of load demand changes over time, thereby further improving the accuracy of prediction. Although the specific form of the time series analysis model f is not directly given in the formula, its existence provides stronger time series analysis capabilities for the prediction model. The θ in the formula represents model parameters, and these parameters can be optimized through machine learning algorithms to minimize the prediction error. By continuously optimizing the model parameters, the generalization ability and prediction accuracy of the prediction model can be improved. Through accurate load demand prediction, strong data support can be provided for relevant decision-making departments. This helps to formulate more scientific and reasonable resource scheduling plans, improve resource utilization efficiency, reduce operating costs, and at the same time enhance user satisfaction and service quality.

[0041] In one embodiment of the present invention, S15 includes:

[0042] S151. Based on the characteristics of environmental data, select features that have an important impact on load demand prediction, such as temperature, humidity, CO2 concentration, PM2.5 concentration, pedestrian flow, etc., and perform feature extraction, and normalize or standardize the feature data;

[0043] S152. According to the characteristics of historical data and prediction requirements, select machine learning algorithms, such as time series analysis (ARIMA, LSTM), clustering analysis (K-means, DBSCAN), regression models (linear regression, decision tree regression, random forest regression), etc.;

[0044] S153. Use the processed stored data to train the selected machine learning model, and verify the trained model through cross-validation to evaluate the generalization ability of the model on unknown data; the generalization ability is evaluated by the following formula:

[0045]

[0046] where k represents the number of folds of cross-validation; N i represents the number of data points in the i-th fold; y ij represents the true value of the j-th data point in the i-th fold; represents the predicted value of the j-th data point in the i-th fold;

[0047] S154. Use time series analysis or clustering analysis methods to identify the change trends of environmental parameters in the stored data, such as seasonal changes, periodic changes, etc., and based on the trained machine learning model, predict the load demand in the future for a period of time, including predicting the air-conditioning load demand in the next few hours, days or weeks;

[0048] S155. Quantitatively evaluate the prediction results, such as calculating the prediction error, etc. Fine-tune the model according to the evaluation results. Based on the prediction results, formulate energy-saving strategies, such as adjusting the operating parameters of the air-conditioning system, optimizing the operating strategies of the fans and refrigeration units, etc.; the prediction error is obtained through the following formula:

[0049]

[0050] where n represents the number of test data points; y i represents the true value of the i-th data point; represents the predicted value of the i-th data point;

[0051] S156. Real-time feedback the prediction results to the central air-conditioning full-link energy-saving control platform, and adjust the operating state of the air-conditioning system in real time according to the predicted load demand;

[0052] S157. According to the actual operating effect of the air-conditioning system, collect feedback data, and continuously optimize and iterate the prediction model.

[0053] The working principle of the above technical solution is as follows: Based on the characteristics of environmental data, features that have an important impact on load demand prediction are selected, such as temperature, humidity, CO2 concentration, PM2.5 concentration, passenger flow, etc. These features can reflect the environmental conditions inside and outside the subway station and are closely related to the air-conditioning load demand; these features are extracted from the original data and normalized or standardized to eliminate the dimensional differences between different features and improve the training efficiency and prediction accuracy of the model; according to the characteristics of historical data and prediction requirements, appropriate machine learning algorithms are selected. For example, for data with time series characteristics, time series analysis algorithms (such as ARIMA, LSTM) can be selected; for data that requires clustering analysis, clustering analysis algorithms (such as K-means, DBSCAN) can be selected; for data that requires establishing a prediction model, regression models (such as linear regression, decision tree regression, random forest regression) can be selected, etc.; taking LSTM (Long Short-Term Memory Network) in time series analysis as an example, it is a neural network that is particularly suitable for processing and predicting important events with long intervals and delays in time series. LSTM can learn long-term dependence information and store and update information by adding special units (i.e., memory units) in the hidden layer, so as to achieve accurate prediction of time series data; the selected machine learning model is trained using the processed stored data. During the training process, the model will learn the mapping relationship between the feature data and the target load demand; the trained model is verified through cross-validation. Cross-validation is a commonly used model evaluation method that divides the dataset into multiple subsets, and each time one subset is used as the validation set and the remaining subsets are used as the training set. Through multiple training and validation processes, the generalization ability of the model on unknown data can be evaluated; time series analysis or clustering analysis methods are used to identify the change trends of environmental parameters in the stored data, such as seasonal changes, periodic changes, etc. These trends help to understand the change rules of load demand and provide a basis for future predictions; based on the trained machine learning model, the load demand for a future period of time is predicted. The prediction time range can be set according to actual needs, such as predicting the air-conditioning load demand for the next few hours, days or weeks; the prediction results are quantitatively evaluated, such as calculating the prediction error, confidence interval, etc. These evaluation indicators can reflect the prediction accuracy and reliability of the model; the model is fine-tuned according to the evaluation results to improve the prediction performance of the model. The fine-tuning methods include adjusting model parameters, increasing training data, etc.; based on the prediction results, energy-saving strategies are formulated, such as adjusting the operating parameters of the air-conditioning system, optimizing the operating strategies of the fans and refrigeration units, etc. These strategies aim to reduce the energy consumption of the air-conditioning system on the premise of meeting the comfort of passengers; the prediction results are fed back to the central air-conditioning full-link energy-saving control platform in real time.The control platform can adjust the operating state of the air conditioning system in real time according to the predicted load demand to achieve the goal of energy conservation and consumption reduction; collect feedback data based on the actual operating effect of the air conditioning system, and continuously optimize and iterate the prediction model. By continuously optimizing the model, the prediction accuracy and adaptability of the model can be improved, providing more reliable support for future load demand prediction.

[0054] The effects of the above technical solutions are as follows: By selecting features that have an important impact on load demand prediction based on the characteristics of environmental data, and performing feature extraction and normalization or standardization processing, it can ensure that the data input into the machine learning model is of high quality and representative. This helps to improve the accuracy of the model's load demand prediction, making the prediction results closer to the actual changes in load demand; Using the processed stored data to train the selected machine learning model and validating the trained model through cross-validation can evaluate the generalization ability of the model on unknown data. This validation method helps to ensure that the model can still maintain a high prediction accuracy when facing new data, thus enhancing the practicality and reliability of the model; Based on the trained machine learning model, predicting the load demand for a period of time in the future can achieve accurate grasp of the load demand of the air conditioning system. Formulating energy-saving strategies according to the prediction results, such as adjusting the operating parameters of the air conditioning system, optimizing the operating strategies of the fan and refrigeration unit, etc., can achieve intelligent energy-saving control. This helps to reduce the energy consumption of the air conditioning system, improve energy utilization efficiency, and thus achieve the goal of energy conservation and emission reduction; Real-time feedback of the prediction results to the central air-conditioning full-link energy-saving control platform can adjust the operating state of the air conditioning system in real time according to the predicted load demand. This real-time feedback mechanism helps to improve the response speed and flexibility of the system, enabling the air conditioning system to adapt to changes in load demand faster, thus providing a more comfortable and stable indoor environment; Collecting feedback data based on the actual operating effect of the air conditioning system and continuously optimizing and iterating the prediction model can continuously improve the prediction performance and adaptability of the model. This continuous optimization and iteration process helps to ensure that the model always remains in the best state, thus providing users with more accurate and reliable load demand prediction services. The above generalization ability calculation formula comprehensively evaluates the generalization ability of the model on unknown data by calculating the average value of the mean squared error (MSE) of each fold of data in the cross-validation process. This evaluation method can fully consider the diversity and distribution characteristics of the data set, thus more accurately reflecting the actual performance of the model; Cross-validation is an effective method to prevent overfitting. By dividing the data set into multiple folds and training and validating on each fold respectively, it can ensure that the model can still maintain good performance on unseen data. This formula helps to discover possible overfitting situations of the model on a certain fold by calculating the MSE of each fold and taking the average value, so as to make timely adjustments and optimizations; During the cross-validation process, the data of each fold is randomly divided, which helps to evaluate the stability of the model on different data sets. This formula can reflect whether the performance of the model on different data sets is consistent by calculating the average value of the MSE of multiple folds, thus judging whether the stability of the model is good. This formula is simple to calculate and the result is intuitive and easy to understand. As a commonly used error metric, MSE can clearly reflect the difference between the model's predicted value and the true value.By comparing the MSE values of different models, it is possible to intuitively determine which model has stronger generalization ability on unknown data; during the model training process, the MSE value calculated according to this formula can be used to adjust the parameters and structure of the model to optimize the performance of the model. Through continuous iteration and optimization, the MSE value can be gradually reduced, thereby improving the prediction accuracy of the model on unknown data. This formula is not only applicable to regression problems, but can also be extended to other machine learning scenarios such as classification problems. By appropriately adjusting the error metric in the formula (such as replacing MSE with classification accuracy, etc.), it can be applied to model evaluation and optimization in different fields.

[0055] In one embodiment of the present invention, the S2 includes:

[0056] S21. Based on the collected environmental data, use the fluid mechanics model to calculate the current air volume values of the supply air duct and the return air duct; and through the PID control algorithm, dynamically adjust the fan speed and the output of the frequency converter; the current air volume value is calculated by the following formula:

[0057]

[0058] Where, ΔP represents the pressure loss (air volume) in the pipeline, usually in pascals (Pa); f represents the friction factor, which depends on the roughness of the pipeline and the Reynolds number (Re); L represents the length of the pipeline, in meters (m); D represents the diameter of the pipeline, in meters (m); represents the density of the fluid, in kilograms per cubic meter (kg / m³); v represents the average velocity of the fluid in the pipeline, in meters per second (m / s);

[0059] The friction factor is calculated by the following formula:

[0060]

[0061] The Reynolds number Re is obtained by the following formula:

[0062]

[0063] Where, μ represents the dynamic viscosity of the fluid, in pascal-seconds (Pa·s);

[0064] S22. Real-time monitor the pressure in the mixing chamber, and adopt the fuzzy control strategy or the neural network control strategy to dynamically adjust the ratio of fresh air to return air according to the pressure change;

[0065] S23. Based on the pressure balance simulation model, simulate the wind pressure change under different working conditions and verify the effectiveness of the control strategy;

[0066] S24. Based on the adaptive learning mechanism, continuously optimize the control parameters according to the operation data, and conduct regular pressure balance tests to evaluate the system performance.

[0067] The working principle of the above technical solution is as follows: Based on the collected environmental data (such as temperature, humidity, wind speed, etc.), a fluid dynamics model is used to calculate the current air volume values of the supply air duct and the return air duct. The fluid dynamics model takes into account factors such as the unit friction air volume of the air duct, the air duct length, and the ratio of the local air volume to the friction air volume loss, and can accurately calculate the air volume value in the air duct; through the PID (Proportional-Integral-Derivative) control algorithm, according to the calculated air volume value, the fan speed and the inverter output are dynamically adjusted. The PID control algorithm can monitor the change of the air volume in real time and make precise adjustments according to the set target value to achieve the balance of the supply air and return air volumes; a pressure sensor is used to monitor the pressure change in the mixing chamber in real time to ensure that the pressure in the mixing chamber remains within the set range; according to the change of the pressure in the mixing chamber, a fuzzy control strategy or a neural network control strategy is adopted to dynamically adjust the ratio of fresh air to return air. The fuzzy control strategy can handle complex non-linear relationships and improve the accuracy of working condition identification; while the neural network control strategy has the ability of self-learning and self-adaptation and can continuously optimize the control strategy according to historical data; moreover, when the air volume of the air system is adjusted, the built-in water system of the system can also synchronously adjust the water volume according to the change of the air volume. For example, when the opening degree of the air valve in a certain area increases and the supply air volume increases, the water system automatically increases the opening degree of the water valve of the corresponding air handling unit to ensure that the increased air volume can carry enough cooling or heating capacity to meet the temperature requirements of the area. Through the air volume-water volume matching model, according to the load changes in different seasons and different time periods, as well as the temperature feedback of each area, the operating parameters of the air system and the water system are dynamically adjusted to keep the two in the best matching state all the time and improve the energy utilization efficiency; after implementing the air volume balance energy-saving measures, the output frequency of the air handling unit decreases, and the water system is adjusted accordingly. As the air volume of the air handling unit decreases, the water system reduces the frequencies of the chilled water pump and the cooling water pump, reduces the opening degree of the water valve, reduces the production and transportation of cooling capacity, and avoids energy waste. According to the change of the water temperature at the outlet of the main unit, the operating parameters of the air system, the air valve opening degree, and the water system are coordinated and adjusted. When the water temperature at the outlet of the main unit is raised, the air system appropriately adjusts the supply air volume, and the water system further optimizes the flow rate and temperature of the chilled water to ensure that while saving energy, the temperature control effect of each area is not affected. Based on the pressure balance simulation model, the pressure changes under different working conditions are simulated. This model can consider the influence of various factors (such as air duct air volume, fan speed, inverter output, etc.) on the wind pressure, so as to simulate the wind pressure changes under different working conditions; through the simulation model, the effectiveness of the proposed control strategy is verified. By comparing the simulation results with the actual operation results, the advantages and disadvantages of the control strategy can be evaluated, and necessary adjustments and optimizations can be made; based on the adaptive learning mechanism, the control parameters are continuously optimized according to the operation data. This mechanism can monitor the operation state of the system in real time and automatically adjust the control parameters according to the change of the operation state to improve the accuracy and response speed of the air balance adjustment; regular pressure balance tests are implemented to evaluate the system performance.Through testing, problems existing in the system can be discovered and solved in a timely manner, ensuring the continuous stability of the air balance state. At the same time, the test data can also provide important references for subsequent optimization and improvement.

[0068] The effects of the above technical solutions are as follows: By calculating the current air volume values of the supply air duct and the return air duct using a fluid dynamics model based on the collected environmental data, the air volume status of the air system can be accurately grasped. Combining with the PID control algorithm, the fan speed and the output of the frequency converter are dynamically adjusted to achieve the balance of the supply air and return air volumes, effectively avoiding problems such as uneven air volume distribution and increased energy consumption caused by air volume imbalance; The pressure in the mixing chamber is monitored in real time, and a fuzzy control strategy or a neural network control strategy is adopted to dynamically adjust the ratio of fresh air to return air according to the pressure change. This intelligent control method can quickly respond to environmental changes and load requirements, ensuring a reasonable ratio of fresh air to return air, improving the indoor air quality while also optimizing energy utilization; Based on the pressure balance simulation model, the pressure changes under different working conditions are simulated, and the effectiveness of the control strategy is verified. This step helps to discover and solve potential problems during the design stage, ensuring that the control strategy can achieve the expected effect in actual applications. At the same time, the control strategy can be optimized through simulation verification to improve its adaptability and robustness; Based on the adaptive learning mechanism, the control parameters are continuously optimized according to the operation data, which can further improve the accuracy and response speed of air balance adjustment. This continuous optimization process helps to maintain the best operating state of the system and improve the overall performance of the system. At the same time, regular pressure balance tests are carried out to evaluate the system performance, and potential problems can be discovered and solved in a timely manner to ensure the continuous stability of the air balance state; Through the comprehensive application of the above technical solutions, precise control and continuous optimization of the air balance state of the air conditioning system can be achieved, thereby improving the overall energy efficiency and reducing the operating cost. This not only helps to improve the economic benefits of the enterprise but also conforms to the current social development trend of energy conservation and emission reduction. The above formula can accurately calculate the current air volume values in the supply air duct and the return air duct through the given pressure loss formula. This is crucial for optimizing the air conditioning system, reducing energy consumption, and improving comfort; With the help of the PID control algorithm, the fan speed and the output of the frequency converter can be dynamically adjusted in real time according to the calculated air volume values. This helps to achieve the balance of the supply air and return air volumes and ensure the stable and efficient operation of the system; The calculation formula of the friction factor f takes into account different ranges of the Reynolds number Re, enabling the air volume calculation to be applicable to pipe conditions with different roughnesses and different flow velocities. This enhances the generality and practicality of the formula; Through real-time monitoring and dynamic adjustment, the system can quickly respond to environmental changes such as pipe blockage and flow rate changes, thereby maintaining the stability and efficiency of the air conditioning system.

[0069] In an embodiment of the present invention, the S22 includes:

[0070] S221. Monitor the pressure change in the air mixing chamber in real time through the pressure sensor installed in the air mixing chamber, calibrate the collected pressure data, and identify and eliminate outliers;

[0071] S222. Use time series analysis technology to analyze the change trend of the pressure in the air mixing chamber and identify the laws and characteristics of the pressure fluctuations;

[0072] S223. Evaluate the applicability of the fuzzy control strategy and the neural network control strategy according to the change characteristics and control requirements of the pressure in the air mixing chamber, and select the optimal control strategy;

[0073] S224. Initialize the parameters of the selected control strategy, and verify the adaptability and stability of the control strategy under different working conditions through simulation;

[0074] S225. Calculate the optimal ratio of fresh air to return air by using the control strategy according to the change of the pressure in the air mixing chamber, and convert the calculated ratio of fresh air to return air into the control command of the actuator. The optimal ratio is calculated by the following formula:

[0075]

[0076] where e represents the error between the current pressure and the target pressure in the air mixing chamber; Δe represents the change rate of the pressure error; A min and A max represent the minimum and maximum values of the fresh air ratio respectively; K P and K d represent the proportional and derivative gains of the fuzzy controller; K I represents the integral gain; A base represents the basic fresh air ratio when there is no pressure error; ΔA fuzzy is the additional adjustment amount provided by the fuzzy logic controller, which is calculated through the fuzzy rule base, that is , and F total represents the comprehensive fuzzy logic function;

[0077] where and represent the fuzzy logic functions, which map the pressure error and the error change rate to the adjustment amount of the fresh air ratio. These functions are usually defined through the fuzzy rule base as follows:

[0078]

[0079] where NB, NM, NS, ZE, PS, PM, PB represent Negative Big, Negative Medium, Negative Small, Zero, Positive Small, Positive Medium, Positive Big respectively; It mainly reflects the influence of the current magnitude of the error on the control quantity, similar to the proportional (P) link in traditional PID control, but realizes non-linear adjustment through fuzzy logic; for example, when the error e is large, a relatively large adjustment quantity will be output to quickly respond to the deviation; It mainly reflects the influence of the change trend of the error on the control quantity, similar to the derivative (D) link in PID control; for example, when the error change rate is negative large (NB), it indicates that the error is rapidly decreasing, and the adjustment quantity may be reduced to avoid system overshoot; the function is used to convert the accurate input value into a fuzzy set, and then calculate the optimal ratio of fresh air to return air with the help of the fuzzy rule base.

[0080] S226. Real-time monitor the pressure of the mixing chamber after adjustment, evaluate the adjustment effect, and if the expected target is not achieved, perform iterative adjustment until the pressure is stable.

[0081] The working principle of the above technical solution is as follows: Install a high-precision pressure sensor in the air mixing chamber to monitor the pressure changes in the air mixing chamber in real time; the sensor transmits the collected pressure data to the central control system through a signal; the central control system verifies the received pressure data to check the integrity and accuracy of the data; identifies and eliminates outliers caused by sensor failures, data transmission errors, etc. to ensure the accuracy of subsequent analysis; uses time series analysis technology to statistically analyze the historical data of the air mixing chamber pressure to identify the trends and periodicities of pressure changes; analyzes the laws and characteristics of pressure fluctuations, such as the fluctuation amplitude, frequency, etc., to provide a basis for formulating subsequent control strategies; evaluates the applicability of fuzzy control strategies and neural network control strategies according to the change characteristics and control requirements of the air mixing chamber pressure; considers factors such as the real-time performance, stability, and robustness of the system to select the optimal control strategy; initializes the parameters of the selected control strategy, including the membership function and rule base of the fuzzy controller, or the structure and learning rate of the neural network, etc.; the settings of these parameters will directly affect the performance and effect of the control strategy; uses simulation software to verify the adaptability and stability of the control strategy under different working conditions; adjusts the parameters of the control strategy according to the simulation results until the best control effect is achieved; calculates the optimal ratio of fresh air to return air using the control strategy according to the change of the air mixing chamber pressure; this ratio will ensure that the pressure in the air mixing chamber is stable within the set range; converts the calculated ratio of fresh air to return air into control instructions for the actuator, such as adjusting the opening degrees of the fresh air valve and the return air valve; these instructions will directly control the flow rates of fresh air and return air to achieve dynamic adjustment of the ratio; monitors the pressure of the adjusted air mixing chamber in real time to evaluate the adjustment effect; if the adjusted pressure is stable and meets the expected target, the control strategy is effective; if the adjusted pressure does not reach the expected target, iterative adjustment is performed; adjusts the parameters of the control strategy or reselects the control strategy according to the real-time monitored pressure data; repeats the above steps until the pressure is stable and meets the expected target.

[0082] The effects of the above technical solution are as follows: By installing high-precision pressure sensors to monitor the pressure changes in the air mixing chamber in real time and verifying and eliminating outliers from the collected data, the accuracy and reliability of the data are ensured. This provides accurate data support for basic pressure control, enabling the control strategy to more accurately reflect the actual situation of the air mixing chamber pressure, thereby improving the control accuracy; Using time series analysis technology to analyze the change trend of the air mixing chamber pressure, identifying the laws and characteristics of pressure fluctuations, and providing a scientific basis for the formulation of control strategies. According to the change characteristics and control requirements of the air mixing chamber pressure, the optimal control strategy (fuzzy control or neural network control) is selected and its parameters are initialized, and its adaptability and stability under different working conditions are verified through simulation. This refined control strategy can more accurately calculate the optimal ratio of fresh air to return air, realize the dynamic adjustment of the ratio, thereby optimizing the indoor air quality and meeting people's needs for a comfortable environment; By initializing the parameters of the control strategy and verifying through simulation, it can be ensured that the control strategy has good adaptability and stability in practical applications. This helps to reduce system fluctuations and instability caused by improper control strategies, and improve the overall stability and robustness of the system. At the same time, the pressure of the air mixing chamber after adjustment is monitored in real time to evaluate the adjustment effect. If the expected target is not achieved, iterative adjustment is performed until the pressure is stable. This iterative adjustment mechanism can ensure that the system can quickly adjust and maintain stability in the face of different working conditions and load changes; By precisely controlling the ratio of fresh air to return air, the accurate adjustment of the air supply volume of the air conditioning system can be realized, thus avoiding unnecessary energy waste. At the same time, the optimized control strategy can also reduce the energy consumption increase caused by system fluctuations and instability, and further improve the energy utilization efficiency. This helps to reduce the operating costs of enterprises and improve economic benefits; The technical solution adopts a modular design, and each step and component are relatively independent, which is convenient for maintenance and expansion. When it is necessary to update or improve the control strategy, only the corresponding module needs to be adjusted and optimized, without the need to make large-scale changes to the entire system. This reduces the difficulty and cost of system maintenance and upgrade, and improves the flexibility and scalability of the system. The above optimal ratio formula can calculate the optimal ratio of fresh air to return air in real time according to the error (e) between the current pressure and the target pressure of the air mixing chamber and its change rate (Δe), thereby realizing the precise control of the air mixing chamber pressure; Through the additional adjustment amount provided by the fuzzy logic controller (FLC), the system can further adapt to complex and changeable operating environments, and improve the robustness and flexibility of control.By precisely controlling the ratio of fresh air to return air, the system can maximize the utilization of return air while ensuring the stable pressure in the mixing chamber, reducing the consumption of fresh air, and thus lowering energy consumption. Especially in cases where outdoor air quality is poor or fresh air supply is tight, this optimized ratio is particularly important. The stable pressure in the mixing chamber helps maintain the comfort of the indoor environment and avoid problems such as air flow disorder and increased noise caused by pressure fluctuations. By precisely controlling the fresh air ratio, it is also possible to ensure that the indoor air quality meets the standards and provide a good breathing environment for users. The integral term in the formula helps eliminate the static error in the system and improve the steady-state accuracy of the system. The proportional term and the derivative term are respectively used to improve the response speed and stability of the system and prevent the system from overshooting or oscillating. The parameters and fuzzy rule base in the formula can be adjusted and optimized according to the actual situation to make the system more in line with the actual application requirements.

[0083] In one embodiment of the present invention, the S222 includes:

[0084] Using time series decomposition techniques, such as the STL method, decompose the mixing chamber pressure time series into a trend term, a seasonal term, and a residual term, and identify the long-term trend and seasonal fluctuations of the pressure change;

[0085] Using statistical tools such as the autocorrelation function (ACF) and the partial autocorrelation function (PACF), identify the periodic components in the mixing chamber pressure time series, such as daily cycles, weekly cycles, etc., and analyze their cycle lengths and fluctuation amplitudes;

[0086] Based on time series anomaly detection algorithms, such as statistic-based methods, machine learning-based methods, etc., identify the outliers or mutation points in the mixing chamber pressure time series;

[0087] According to the results of the time series analysis, identify the typical patterns of the mixing chamber pressure fluctuations and analyze the reasons for their occurrence;

[0088] Extract key features from the mixing chamber pressure time series. According to the characteristics of the mixing chamber pressure time series, select a suitable prediction model, such as the ARIMA model, the LSTM neural network, etc., for preliminary modeling;

[0089] Use historical data to train the prediction model, and verify the trained prediction model by the holdout method to evaluate the prediction accuracy and generalization ability of the model; according to the verification results, optimize the model.

[0090] The working principle of the above technical solution is as follows: Using the STL method, the pressure time series of the mixing air chamber is decomposed into a trend term, a seasonal term, and a residual term. The trend term reflects the long-term change trend of the time series, the seasonal term reflects the seasonal fluctuations, and the residual term contains other changes except for trends and seasons. For example, assume that in the pressure time series of the mixing air chamber, due to seasonal changes (such as the increase in pressure caused by the rise in temperature in summer), there is an obvious seasonal fluctuation. Through STL decomposition, we can separate this seasonal fluctuation from the original time series, and at the same time obtain the long-term trend of pressure change (such as rising or falling year by year) and the residual term (such as short-term fluctuations caused by random factors). Using statistical tools such as the autocorrelation function (ACF) and the partial autocorrelation function (PACF), identify the periodic components in the pressure time series of the mixing air chamber, such as daily cycles, weekly cycles, etc., and analyze their cycle lengths and fluctuation amplitudes. For example, if there is a daily periodic fluctuation (such as pressure changes in the morning and evening every day) in the pressure time series of the mixing air chamber, the ACF graph will show a high autocorrelation at the corresponding lag order. The PACF graph can be used to further confirm the existence of this periodic fluctuation and determine its cycle length (such as 24 hours). At the same time, by analyzing the fluctuation amplitudes of the ACF and PACF, we can understand the intensity of the periodic fluctuation. Based on time series anomaly detection algorithms, such as statistic-based methods (such as the 3σ principle), machine learning-based methods (such as Isolation Forest), etc., identify the outliers or mutation points in the pressure time series of the mixing air chamber. For example, assume that the pressure value at a certain moment in the pressure time series of the mixing air chamber suddenly increases or decreases, showing a significant difference from the values at the previous and subsequent moments. Through the statistic-based method (such as the 3σ principle), we can calculate the mean and standard deviation of the time series and regard the values exceeding 3 times the standard deviation as outliers. Or, through the machine learning-based method (such as Isolation Forest), we can train a model to identify the abnormal patterns in the time series and mark the outliers or mutation points. According to the results of time series analysis, identify the typical patterns of the mixing air chamber pressure fluctuation, such as periodic fluctuations, trend changes, random fluctuations, etc., and analyze the reasons for their occurrence. For example, if there are obvious periodic fluctuations in the pressure time series of the mixing air chamber and this fluctuation is closely related to the changes in external environmental factors (such as temperature, humidity), it can be inferred that this periodic fluctuation is caused by external environmental factors. In addition, if there is a trend change (such as rising or falling year by year) in the time series, it may be related to factors such as the aging of the air conditioning system and insufficient maintenance. Extract key features (such as fluctuation amplitude, cycle length, trend slope, etc.) from the pressure time series of the mixing air chamber, and select a suitable prediction model for preliminary modeling according to the characteristics of the time series. Commonly used prediction models include the ARIMA model, LSTM neural network, etc. For example, if the pressure time series of the mixing air chamber has stable periodicity and trend changes and no obvious non-linear characteristics, the ARIMA model can be selected for modeling.If there are complex non-linear relationships and long-term dependencies in the time series, an LSTM neural network can be selected for modeling. In the initial modeling stage, the parameters and structure of the model need to be set according to the characteristics of the time series and the extracted features. The prediction model is trained using historical data, and the trained model is verified through the hold-out method (i.e., dividing the dataset into a training set and a test set). The prediction accuracy and generalization ability of the model are evaluated, and the model is optimized according to the verification results. For example, the historical data of the mixing chamber pressure time series is divided into a training set and a test set, where the training set is used to train the prediction model, and the test set is used to verify the prediction effect of the model. The prediction accuracy of the model is evaluated by calculating the error (such as the mean squared error MSE) between the predicted value and the actual value on the test set. If the prediction error is large, the model needs to be optimized, such as adding features, adjusting the model structure or parameters, etc., to improve the prediction ability and generalization ability of the model.

[0091] The effects of the above technical solutions are as follows: Through time series decomposition techniques (such as the STL method), the mixing chamber pressure time series is decomposed into a trend term, a seasonal term, and a residual term, which can clearly identify the long-term trend, seasonal fluctuations, and random perturbations of the pressure change, helping to deeply understand the dynamic characteristics of the mixing chamber pressure; Using statistical tools such as the autocorrelation function (ACF) and partial autocorrelation function (PACF), the periodic components in the mixing chamber pressure time series, such as daily cycles, weekly cycles, etc., can be accurately identified, and their cycle lengths and fluctuation amplitudes can be analyzed, providing an important basis for the construction of subsequent prediction models; The anomaly detection algorithm based on time series can accurately identify the outliers or mutation points in the mixing chamber pressure time series. These outliers may be caused by factors such as system failures and external disturbances. By detecting and processing these outliers in a timely manner, the accuracy and robustness of the prediction model can be improved; According to the results of time series analysis, the typical patterns of the mixing chamber pressure fluctuations, such as periodic fluctuations, trend changes, random fluctuations, etc., can be identified, and the reasons for their occurrence can be analyzed, which helps to formulate targeted control strategies and prediction models; Key features are extracted from the mixing chamber pressure time series, and a suitable prediction model is selected for initial modeling according to its characteristics. Then, the model is trained and verified using historical data, and the prediction accuracy and generalization ability of the model are evaluated. The model is optimized according to the verification results, which can further improve the prediction performance of the model; Through the above technical solutions, a more accurate and reliable mixing chamber pressure prediction model can be constructed, providing strong support for the control and regulation of the mixing chamber pressure. This helps to maintain the stability of the mixing chamber pressure, improve the comfort and energy efficiency level of the indoor environment; The results of the prediction model can provide guidance for the actual control of the mixing chamber pressure, such as providing decision-making basis for adjusting the ratio of fresh air to return air and regulating the valve opening, etc., so as to optimize the control system of the mixing chamber pressure.

[0092] In one embodiment of the present invention, S3 includes:

[0093] S31. Regularly read various technical parameters of the refrigeration unit through the Modbus network protocol, and clean and format the read data;

[0094] S32. Analyze the relationship between technical parameters and energy consumption through data mining techniques (such as association analysis, classification algorithms) to identify key factors affecting refrigeration efficiency;

[0095] S33. Adopt an extremum search algorithm combined with historical operation data and current environmental load to dynamically adjust the operation strategy of the refrigeration unit to maximize the overall COP (coefficient of performance);

[0096] S34. According to the predicted cooling capacity demand, use the predictive control algorithm to intelligently control the operation of adding or removing machines of the main unit, implement the preventive maintenance strategy of the refrigeration unit, predict the fault risk based on data analysis, and perform maintenance in advance.

[0097] The working principle of the above technical solution is as follows: Through the Modbus network protocol, various technical parameters are regularly read from the refrigeration unit. These parameters include, but are not limited to, refrigerating capacity, power consumption, compressor status, condenser pressure, evaporator pressure, etc. The Modbus protocol is a serial communication-based protocol widely used in industrial control systems. It defines a communication mode between master and slave devices, allowing the master device (such as a computer or PLC) to communicate with slave devices (such as sensors, actuators, etc.). Clean the read data, including removing duplicate data, filling in missing data, etc.; format the data to meet the requirements of subsequent analysis. This may include data standardization, that is, converting data with different dimensions into a unified dimension for comparison and analysis. Apply data mining techniques, such as association analysis, classification algorithms, etc., to deeply analyze the relationship between technical parameters and energy consumption; association analysis can reveal potential connections between technical parameters, such as the relationship between refrigerating capacity and power consumption; classification algorithms can classify the status of the refrigeration unit into different categories, such as normal, faulty, etc., for subsequent analysis and processing. Through data mining techniques, identify the key factors affecting refrigeration efficiency; these factors may include compressor status, condenser pressure, evaporator pressure, etc.; focus on monitoring and optimizing these key factors can improve the coefficient of performance (COP) of the refrigeration unit; adopt the extremum seeking algorithm, combined with historical operation data and current environmental load, to dynamically adjust the operation strategy of the refrigeration unit; the extremum seeking algorithm is an adaptive control algorithm that can search for the control variable that makes the system output reach the maximum or minimum value without knowing the specific form of the loss function; according to the results of the extremum seeking algorithm, adjust the operation parameters of the refrigeration unit, such as compressor speed, condenser fan speed, etc.; the goal is to maximize the coefficient of performance (COP) of the refrigeration unit while meeting the current cooling capacity demand; use the model predictive control algorithm to predict the future cooling capacity demand based on historical data and current environmental load; this helps to adjust the operation strategy of the refrigeration unit in advance to avoid energy consumption waste caused by over-cooling or under-cooling; according to the prediction result of the cooling capacity demand, intelligently control the addition and removal of units by the host; when it is predicted that the cooling capacity demand increases, start the standby unit in advance; when it is predicted that the cooling capacity demand decreases, appropriately shut down some units; based on data analysis, predict the fault risk and perform maintenance in advance; this includes monitoring and predicting the wear degree of key components, and regularly checking and replacing aging parts; through the preventive maintenance strategy, the efficient and stable operation of the refrigeration unit can be ensured, and its service life can be extended.

[0098] The effects of the above technical solution are as follows: By regularly reading various technical parameters of the refrigeration unit through the Modbus network protocol, the timeliness and accuracy of the data are ensured. The read data is cleaned and formatted, including data deduplication, data filling, data standardization, etc., improving the quality and usability of the data; Applying data mining techniques (such as association analysis, classification algorithms) to deeply analyze the relationship between technical parameters and energy consumption, and identifying the key factors affecting refrigeration efficiency; This helps to optimize the refrigeration unit targeted, thereby improving its coefficient of performance (COP); Using the extremum search algorithm combined with historical operation data and current environmental load to dynamically adjust the operation strategy of the refrigeration unit; This dynamic adjustment can ensure that the refrigeration unit maintains a high COP under different working conditions, thereby reducing energy consumption; According to the prediction of cooling capacity demand, using the predictive control algorithm to intelligently control the operation of adding or removing units of the main unit; This can avoid energy consumption waste caused by over-cooling or under-cooling, and realize the intelligent scheduling and optimized operation of the refrigeration unit; Based on data analysis to predict the fault risk and perform maintenance in advance; This can significantly reduce the failure rate of the refrigeration unit, extend its service life, and reduce the downtime and maintenance costs caused by faults; Through the above technical solution, the COP of the refrigeration unit is significantly improved and the energy consumption is effectively reduced; This helps to reduce the operating costs of enterprises and improve the overall operating efficiency; The implementation of the preventive maintenance strategy can reduce the failure rate and downtime of the refrigeration unit; This helps to ensure the stable operation of the refrigeration system and improve the reliability and stability of the system; Through intelligent data reading, processing and analysis means, remote monitoring and intelligent management of the refrigeration unit can be realized; This helps to improve the management efficiency of enterprises and reduce labor costs.

[0099] In one embodiment of the present invention, the S33 includes:

[0100] S331. Select the extremum search algorithm according to the characteristics of the refrigeration unit and initialize the algorithm parameters;

[0101] S332. Define an objective function with the maximization of the overall COP as the goal, and use historical operation data to continuously find the combination of refrigeration unit operation parameters that makes the objective function reach the optimal value, such as the condenser fan speed and the evaporator water pump flow rate, through iterative calculation;

[0102] S334. Evaluate the performance of the extremum search algorithm through cross-validation and optimize the algorithm according to the evaluation results;

[0103] S335. Perform preprocessing operations on the historical operation data, extract key features from the preprocessed historical operation data, and use feature selection methods to screen out the features that have the greatest impact on the overall COP;

[0104] S336. Group the historical operation data using a clustering algorithm, identify the operation modes under different working conditions, monitor the environmental parameters in real time, and predict the cooling load for a period of time in the future using time series analysis;

[0105] S337. Set a warning threshold according to the load prediction result. When the predicted load exceeds or is lower than a certain range, trigger the corresponding warning mechanism;

[0106] S338. Based on the optimization result of the extremum search algorithm, the analysis result of the historical operation data, and the prediction result of the current environmental load, formulate an adjustment plan for the operation strategy of the refrigeration unit;

[0107] Convert the formulated operation strategy into a control command, and send it to the refrigeration unit in real time through the Modbus network protocol. Monitor the operation parameters and the overall COP of the adjusted refrigeration unit in real time, evaluate the adjustment effect. If the expected goal is not achieved, perform iterative adjustment according to the feedback information until the optimal operation state is reached.

[0108] The working principle of the above technical solution is as follows: According to the characteristics and requirements of the refrigeration unit, select a suitable extremum search algorithm. These algorithms may include gradient ascent / descent method, genetic algorithm, particle swarm optimization algorithm, etc. Each algorithm has its unique advantages and applicable scenarios, and needs to be selected according to the actual situation; Initialize the parameters of the selected algorithm. For example, for the gradient ascent / descent method, the learning rate needs to be set; for the genetic algorithm, the population size, crossover probability, mutation probability, etc. need to be set; for the particle swarm optimization algorithm, the number of particles, inertia weight, learning factor, etc. need to be set. The setting of these parameters will directly affect the performance and convergence speed of the algorithm; Define an objective function aiming at maximizing the overall COP. This function takes the operating parameters of the refrigeration unit (such as condenser fan speed, evaporator water pump flow rate, etc.) as inputs and outputs the overall COP; Utilize historical operating data and continuously find the combination of refrigeration unit operating parameters that makes the objective function reach the optimal value through iterative calculation. In each iteration, the algorithm calculates the objective function value according to the current parameter combination and updates the parameter combination according to the algorithm rules until the optimal solution is found or the iteration times limit is reached; Evaluate the performance of the extremum search algorithm through cross-validation. This includes indicators such as the convergence speed, search accuracy, and robustness of the algorithm. The evaluation results will be used as the basis for algorithm tuning; Tune the algorithm according to the evaluation results. This may include adjusting algorithm parameters, improving algorithm structure, or introducing new algorithm strategies, etc. The purpose of tuning is to improve the performance and search efficiency of the algorithm; Perform preprocessing operations on historical operating data, including steps such as data cleaning, denoising, and normalization. These operations aim to improve the quality and usability of the data; Adopt feature selection methods (such as mutual information, recursive feature elimination, etc.) to screen out the features that have the greatest impact on the overall COP from the preprocessed historical operating data. These features will serve as the basis for subsequent analysis and optimization; Use clustering algorithms to group historical operating data and identify the operating modes under different working conditions. These modes will help the system better understand the operating laws and characteristics of the refrigeration unit; Real-time monitor environmental parameters (such as ambient temperature, humidity, etc.) and use time series analysis to predict the refrigeration load for a period of time in the future. This helps the system make adjustments in advance to cope with possible load changes; Set warning thresholds according to the load prediction results. When the predicted load exceeds or is lower than a certain range, trigger the corresponding warning mechanism; When the predicted load exceeds or is lower than a certain range, trigger the corresponding warning mechanism; For example, assume that the rated load of a certain refrigeration unit is 1000 kW, and the historical data shows that the load mean is 800 kW and the standard deviation is 100 kW; Considering the comprehensive design parameters and historical statistics, the warning threshold range is set to 600 kW (800 kW - 2×100 kW) to 1000 kW (rated load); Trigger a high-load warning when the predicted load exceeds 1000 kW and a low-load warning when it is lower than 600 kW.This helps the system to detect potential problems in a timely manner and take corresponding countermeasures; based on the optimization results of the extremum search algorithm, the analysis results of historical operation data, and the prediction results of the current environmental load, formulate adjustment plans for the operation strategy of the refrigeration unit. These plans include compressor start-stop strategies, condenser fan speed adjustment strategies, evaporator water pump flow adjustment strategies, etc.; convert the formulated operation strategy into control instructions and send them to the refrigeration unit in real time through the Modbus network protocol. This ensures that the system can respond and adjust the operation state of the refrigeration unit in a timely manner; monitor the operation parameters and overall COP of the adjusted refrigeration unit in real time, and evaluate the adjustment effect. If the expected goal is not achieved, perform iterative adjustment according to the feedback information until the optimal operation state is reached. This process is a closed-loop feedback system that can continuously optimize and improve the operation efficiency and energy efficiency ratio of the refrigeration unit.

[0109] The effects of the above technical solutions are as follows: Through the application of the extremum search algorithm, this technical solution can accurately find the combination of refrigeration unit operation parameters that maximizes the overall COP. This refined adjustment method can significantly improve the energy efficiency ratio of the refrigeration unit compared with traditional fixed-parameter operation or simple manual adjustment, thereby reducing energy consumption and improving energy utilization efficiency. The clustering algorithm in the technical solution can identify the operation modes under different working conditions, which enables the system to automatically adjust the operation strategy according to different working conditions. This adaptive ability enhances the stability and reliability of the system and reduces the system fluctuations and failure risks caused by changes in working conditions; predict the future refrigeration load through time series analysis and set warning thresholds. When the predicted load exceeds or is lower than a certain range, trigger the corresponding warning mechanism. This intelligent warning function can detect potential load changes in advance, providing sufficient time for system maintenance personnel to conduct fault troubleshooting and preventive maintenance, and avoiding downtime and maintenance costs caused by faults; the control instructions in the technical solution are sent to the refrigeration unit in real time through the Modbus network protocol, realizing remote monitoring and intelligent management of the refrigeration unit. This management method not only improves management efficiency, reduces labor costs, but also enhances the automation level of the system, enabling the system to respond more quickly to environmental changes and user needs; through accurate load prediction and optimized operation strategies, this technical solution can reasonably allocate refrigeration resources according to actual load demands, avoiding energy consumption waste caused by over-cooling or under-cooling. This resource optimization allocation method not only helps to save energy and reduce emissions, but also reduces the operating costs of enterprises and improves economic benefits; this technical solution integrates various advanced technologies such as extremum search algorithm, data mining technology, and time series analysis, promoting technological innovation and industrial upgrading in the refrigeration industry. This innovation not only improves the performance and energy efficiency ratio of the refrigeration unit, but also provides useful references for the intelligent management and energy conservation and emission reduction of other industries.

[0110] An embodiment of the present invention, said S4 includes:

[0111] S41. According to the cooling water temperature difference, the real-time air-conditioning load, and the outdoor wet-bulb temperature, use an intelligent algorithm (such as a fuzzy control algorithm or a neural network algorithm) to calculate the optimal air volume and the number of operating units of the cooling tower fan; the optimal air volume is calculated by the following formula:

[0112]

[0113] The number of operating units is obtained by the following formula:

[0114]

[0115] where k1, k2, and k3 are coefficients determined based on system characteristics and experience; T in represents the inlet temperature of the cooling water; T out represents the outlet temperature of the cooling water; T wb represents the outdoor wet-bulb temperature; N max represents the maximum number of fans that the cooling tower can operate; Q max represents the maximum air volume of a single fan; L represents the real-time air-conditioning load; represents rounding up;

[0116] S42. Through variable frequency speed control, dynamically adjust the fan speed; and monitor the operating state of the fan.

[0117] S43. Based on the Internet of Things technology, remotely monitor and fault warn the cooling tower fan, and in combination with the load status of the fresh air unit, adjust the cold and heat source supply in real time.

[0118] S44. Based on parameters such as outdoor temperature and humidity changes and on-site temperature, establish a supply air temperature prediction model, and use a predictive control algorithm to dynamically adjust the supply air temperature.

[0119] The working principle of the above technical solution is as follows: calculating the optimal air volume and the number of operating units of the cooling tower fan; input parameters including the cooling water temperature difference, the real-time load of the air conditioner, and the outdoor wet-bulb temperature. Intelligent algorithms (such as fuzzy control algorithms and neural network algorithms) are used to analyze and process the input parameters. The output result calculates the optimal air volume and the number of operating units of the cooling tower fan. Through variable frequency speed control, the fan speed is dynamically adjusted to adapt to different cooling requirements. When the cooling demand increases, the fan speed is increased to enhance the cooling effect. When the cooling demand decreases, the fan speed is decreased to reduce energy consumption. The operating status of the fan is monitored in real time, including parameters such as speed, vibration, and temperature. Through data analysis, potential fault risks are detected in a timely manner to prevent faults from occurring. Based on the Internet of Things technology, remote monitoring and fault warning of the cooling tower fan are carried out; through sensors and communication devices, the operating status and environmental parameters of the fan are collected in real time; the data is transmitted to the cloud platform for analysis and processing to achieve remote monitoring and fault warning; combined with the load status of the fresh air unit, the cold and heat source supply is adjusted in real time; when the load of the fresh air unit increases, the cold and heat source supply is increased to meet the demand; when the load of the fresh air unit decreases, the cold and heat source supply is reduced to save energy; through the coordinated control of air and water, the efficient and stable operation of the air conditioning system is ensured. When the temperature sensor in the strong cooling area detects that the temperature is higher than the preset value, in terms of the air system, the control system increases the opening degree of the electric proportional integral regulating air valve in the corresponding area to increase the air supply volume; at the same time, in the water system, the frequency of the chilled water pump is increased to increase the flow rate of the chilled water, and the opening degree of the air handling unit water valve is increased to transfer more cooling capacity to the air to quickly reduce the temperature in the strong cooling area. When the temperature reaches the preset value, the air system and the water system fine-tune the operating parameters according to the temperature fluctuations to maintain temperature stability. For the weak cooling area, when the temperature rises, the air system appropriately increases the opening degree of the air valve, but the increase amplitude is smaller than that in the strong cooling area, and the temperature is adjusted by increasing the air volume slightly; the water system correspondingly moderately increases the frequency of the chilled water pump and the opening degree of the water valve to provide an appropriate amount of cooling capacity. Similarly, when the temperature reaches the set value, fine-tuning is carried out. The comfort area has higher requirements for temperature stability. When the temperature deviates from the preset value, the air system, the opening degree of the air valve, and the frequency of the chilled water pump and the opening degree of the water valve in the water system are all adjusted slightly to avoid excessive temperature fluctuations affecting the comfort of passengers and staff. Based on parameters such as outdoor temperature and humidity changes and on-site temperature, a supply air temperature prediction model is established; by analyzing historical data and real-time data, a prediction model is established; the model can predict the change trend of the supply air temperature in the future for a period of time; the predictive control algorithm is used to dynamically adjust the supply air temperature; according to the results of the prediction model, the supply air temperature is adjusted in advance to adapt to environmental changes; by optimizing the supply air temperature, the comfort of passengers and the energy-saving effect are improved.

[0120] The effects of the above technical solutions are as follows: By adopting intelligent algorithms such as fuzzy control algorithms and neural network algorithms, and based on parameters such as the cooling water temperature difference, the real-time load of the air conditioner, and the outdoor wet-bulb temperature, the optimal air volume and the number of operating units of the cooling tower fan are accurately calculated. This refined adjustment method avoids the energy consumption waste caused by traditional fixed-parameter operation, and significantly improves the energy efficiency ratio of the system; Through the variable-frequency speed regulation technology, the fan speed is dynamically adjusted to adapt to different cooling requirements. This adjustment method not only maintains the efficient operation of the cooling tower, but also significantly reduces energy consumption and water consumption, achieving the goal of energy conservation and consumption reduction; The operating status of the fan is monitored in real time, including key parameters such as speed, vibration, and temperature, to timely detect potential fault risks and prevent faults from occurring. This preventive maintenance method improves the stability and reliability of the system, and reduces the downtime and maintenance costs caused by faults; Based on the Internet of Things technology, the cooling tower fan is remotely monitored and fault warnings are issued. This remote management method enables the operation and maintenance personnel to master the operating status of the system in real time, respond to and handle abnormal situations in a timely manner, and further enhance the stability and reliability of the system; Combining with the load status of the fresh air unit, the cold and heat sources are supplied in real time to achieve the coordinated control of air and water. This control method enables the air conditioning system to perform intelligent adjustment according to actual needs, avoids the energy consumption waste caused by excessive cooling or heating, and improves the overall energy efficiency of the system; Through the application of the Internet of Things technology and intelligent algorithms, the intelligent management of the cooling tower fan and the air conditioning system is realized. This management method not only improves the automation level of the system, but also reduces the labor cost, making the operation and maintenance work more efficient and convenient; Based on parameters such as outdoor temperature and humidity changes and on-site temperature, a supply air temperature prediction model is established. This model can predict the change trend of the supply air temperature in the next period of time, providing a scientific basis for system adjustment; The predictive control algorithm is used to dynamically adjust the supply air temperature to adapt to environmental changes. This adjustment method not only improves the comfort of passengers, but also maximizes the energy-saving effect. By accurately controlling the supply air temperature, the energy consumption waste and passenger discomfort caused by temperature fluctuations are avoided. The above optimal air volume calculation formula comprehensively considers multiple factors such as the cooling water temperature difference, the real-time load of the air conditioner, and the outdoor wet-bulb temperature. This formula can calculate the optimal air volume that better meets the actual needs, thereby improving the cooling efficiency of the cooling tower; Precise air volume control helps to avoid the situation of excessive or insufficient operation of the fan, thereby reducing energy consumption and operating costs. The above operating unit calculation formula can calculate the minimum number of operating units required according to the optimal air volume and the maximum air volume of a single fan, so as to ensure that the cooling tower maintains a high operating efficiency while meeting the cooling requirements. By limiting the maximum value of the number of operating units, this formula can prevent too many fans from operating simultaneously, thereby avoiding resource waste and increased energy consumption.

[0121] In one embodiment of the present invention, the S44 includes:

[0122] Collect historical data of key parameters such as outdoor temperature and humidity, on-site temperature, and supply air temperature, and perform preprocessing operations. Using feature selection methods such as mutual information and recursive feature elimination, screen out the features that have the greatest impact on the prediction of supply air temperature; at the same time, use data mining techniques to explore the potential relationships between features;

[0123] According to the characteristics of the data and the prediction requirements, select a prediction model and use the preprocessed data to train the model;

[0124] Verify the trained prediction model through cross-validation, and evaluate the prediction performance and generalization ability of the model; according to the verification results, optimize the model;

[0125] Based on the supply air temperature prediction model, design a predictive control algorithm, use real-time data to predict the supply air temperature, and calculate the optimal supply air temperature set value according to the prediction results and the control algorithm. Then, use the control system to adjust the supply air temperature of the air conditioning system in real time;

[0126] Monitor the adjusted supply air temperature and the passenger comfort feedback in real time, and evaluate the adjustment effect; if the expected goal is not achieved, perform iterative adjustment according to the feedback information to optimize the predictive control algorithm and the supply air temperature set value;

[0127] Collect passengers' comfort feedback on the air conditioning system, including perception evaluations of temperature, humidity, wind speed, etc. Based on the passenger comfort evaluation results, formulate optimization strategies.

[0128] The working principle of the above technical solution is as follows: collect historical data of key parameters such as outdoor temperature and humidity, on-site temperature, and supply air temperature; perform preprocessing operations on the collected data, including data cleaning, missing value handling, outlier detection, etc.; use feature selection methods (such as mutual information, recursive feature elimination, etc.) to screen out the features that have the greatest impact on the supply air temperature prediction; explore the potential relationships between features to provide a basis for subsequent modeling; select a suitable prediction model according to the characteristics of the data and the prediction requirements. For example, for time series data, models such as ARIMA and LSTM can be selected; for complex non-linear relationships, machine learning models such as support vector machines and random forests, or deep learning models such as convolutional neural networks and recurrent neural networks can be selected; use the preprocessed data to train the selected model to obtain a preliminary prediction model; verify the trained prediction model through methods such as cross-validation, and evaluate the prediction performance and generalization ability of the model; according to the verification results, optimize the model to improve the prediction accuracy and stability; based on the supply air temperature prediction model, design prediction control algorithms, such as MPC (Model Predictive Control) algorithm, adaptive control algorithm, etc.; the algorithm should consider multiple factors such as changes in outdoor temperature and humidity, on-site temperature changes, and passenger comfort requirements, and dynamically adjust the supply air temperature set value; use real-time data to predict the supply air temperature, and calculate the optimal supply air temperature set value according to the prediction results and the control algorithm, and adjust the supply air temperature of the air conditioning system in real time through the control system; monitor the adjusted supply air temperature and passenger comfort feedback in real time; evaluate the adjustment effect, if the expected goal is not achieved, perform iterative adjustment according to the feedback information to optimize the prediction control algorithm and the supply air temperature set value; collect passenger comfort feedback on the air conditioning system, including perception evaluations of temperature, humidity, wind speed, etc.; based on the passenger comfort evaluation results, formulate optimization strategies, such as adjusting the supply air temperature range, optimizing the supply air method (such as up and down air supply, side air supply, etc.), increasing humidity control, etc.; integrate the optimization strategy into the prediction control algorithm to further improve passenger comfort and energy-saving effects.

[0129] The effects of the above technical solutions are as follows: By using feature selection methods such as mutual information and recursive feature elimination, the features that have the greatest impact on the supply air temperature prediction are screened out. At the same time, data mining techniques are used to explore the potential relationships between features, which helps to improve the accuracy and robustness of the prediction model; According to the characteristics of the data and the prediction requirements, a suitable prediction model is selected for training. Whether it is a time series analysis model (such as ARIMA, LSTM), a machine learning model (such as support vector machine, random forest) or a deep learning model (such as convolutional neural network, recurrent neural network), the prediction accuracy can be improved to a certain extent. Through cross-validation and model tuning, the prediction performance and generalization ability of the model can be further ensured; Based on the supply air temperature prediction model, a prediction control algorithm (such as MPC algorithm, adaptive control algorithm, etc.) is designed, which can comprehensively consider multiple factors such as outdoor temperature and humidity changes, on-site temperature changes, and passenger comfort requirements, and dynamically adjust the supply air temperature set value. This intelligent control method can achieve precise control of the air conditioning system, avoid over-cooling or over-heating, and thus significantly reduce energy consumption; By real-time monitoring the adjusted supply air temperature and passenger comfort feedback, the adjustment effect is evaluated, and the prediction control algorithm and the supply air temperature set value are iteratively adjusted and optimized according to the feedback information. This real-time feedback mechanism can ensure that the operation of the air conditioning system always remains in the optimal state and further improve the energy-saving effect; Collecting passengers' comfort feedback on the air conditioning system, including perception evaluations of temperature, humidity, wind speed, etc., helps to understand the actual needs of passengers; Based on the passenger comfort evaluation results, optimization strategies are formulated, such as adjusting the supply air temperature range, optimizing the air supply mode (such as up-down air supply, side air supply, etc.), and increasing humidity control. These optimization strategies can further improve the comfort of passengers and increase passenger satisfaction; Through the prediction control algorithm and the real-time monitoring system, the automatic control of the air conditioning system is realized. This automatic control method reduces manual intervention and improves the operation efficiency and stability of the system; Combining advanced technologies such as data mining, machine learning / deep learning, the intelligent management of the air conditioning system is realized. This intelligent management method can achieve real-time monitoring and early warning of the system status, discover potential problems in advance and take corresponding measures to ensure the safe and stable operation of the system.

[0130] In one embodiment of the present invention, step S5 includes:

[0131] S51. Calculate the optimal damper opening through an intelligent algorithm according to the changes in the indoor and outdoor environments;

[0132] S52. Adjust the damper opening based on a damper adjustment strategy that combines remote control and local control, and real-time monitor the operation status of the damper through Internet of Things technology;

[0133] S53. Through the centralized intelligent management system of central air-conditioning equipment, the equipment status is monitored in real time, fault early warning is carried out, and remote operation and maintenance are performed.

[0134] The working principle of the above technical solution is as follows: First, the system monitors the changes in the indoor and outdoor environment in real time through the sensor network, including key parameters such as temperature, humidity, and CO2 concentration; uses intelligent optimization algorithms such as genetic algorithms and particle swarm algorithms to calculate the optimal damper opening under the current environment according to the real-time monitored environmental parameters; these algorithms find the best damper opening configuration that can balance the indoor and outdoor air circulation and maintain the air quality in the subway station through iterative search; the calculated optimal damper opening will be used as the basis for subsequent damper adjustment; the system adopts a damper adjustment strategy that combines remote control and local control; remote control allows the operation and maintenance personnel to remotely adjust the damper through the central management system, improving the flexibility and response speed of adjustment; local control ensures that when the remote control fails, the damper can still be basically adjusted through the local controller, ensuring the reliability of the system; using the Internet of Things technology, the system can monitor the operation status of the damper in real time, including key parameters such as opening, rotation speed, and power consumption; through data analysis, the system can timely detect abnormal situations in the damper operation and prevent faults from occurring; through the centralized intelligent management system, the system can monitor the operation status of the central air-conditioning equipment in real time, including the working conditions of key components such as compressors, condensers, and evaporators; the system can give early warnings of equipment failures based on real-time monitored data and notify the operation and maintenance personnel to handle them in advance; the operation and maintenance personnel can remotely debug, maintain, and troubleshoot the equipment through the remote operation and maintenance platform, reducing the number of on-site repairs and improving the operation and maintenance efficiency.

[0135] The effects of the above technical solutions are as follows: Through intelligent algorithms such as genetic algorithms and particle swarm algorithms, the optimal damper opening is calculated in real time according to changes in indoor and outdoor environments (such as temperature, humidity, CO2 concentration, etc.); this intelligent adjustment method can accurately control the damper opening, thereby effectively balancing indoor and outdoor air circulation and avoiding situations of over-ventilation or insufficient ventilation. By optimizing air circulation, the freshness and quality of the air in the subway station can be maintained, providing a more comfortable environment for passengers; balanced air circulation helps reduce the concentration of pollutants in the subway station, such as harmful gases like CO2 and formaldehyde; maintaining good air quality in the subway station helps improve passengers' comfort and satisfaction, and also contributes to the operational safety and health of the subway station. Adopting a damper adjustment strategy that combines remote control and local control improves the flexibility of damper adjustment; remote control allows maintenance personnel to remotely adjust the damper through the central management system without having to go to the site for operation, improving work efficiency; local control serves as a backup solution to ensure that the damper can still be basically adjusted through the local controller in case of remote control failure, ensuring the reliability of the system. Through the Internet of Things technology, the operating status of the damper can be monitored in real time, including key parameters such as opening, rotation speed, and power consumption; this real-time monitoring method helps to promptly detect abnormal situations during the operation of the damper, such as blockages and faults, so as to take preventive or repair measures in advance; through the application of the Internet of Things technology, the reliability and safety of damper adjustment are improved; through the centralized intelligent management system of central air-conditioning equipment, real-time monitoring of equipment status, fault warning, and remote operation and maintenance are realized; this centralized management method helps maintenance personnel comprehensively understand the operating status of the equipment and promptly detect and handle potential faults; through the remote operation and maintenance function, maintenance personnel can debug, maintain, and troubleshoot faults of the equipment without going to the site, reducing operation and maintenance costs and time costs; by real-time monitoring the equipment status and giving warnings and performing operation and maintenance, it helps to promptly detect and handle potential problems of the equipment, thereby extending the service life of the equipment; at the same time, the intelligent management system also helps to optimize the operating parameters of the equipment, improving the operating efficiency and energy-saving performance of the equipment; through the centralized intelligent management system, operation and maintenance costs and time costs can be reduced.

[0136] An embodiment of the present invention, as Figure 2 shown, is a full-link energy-saving system for central air-conditioning in a subway station based on air balance. The system includes:

[0137] Data acquisition module: It collects environmental data (such as temperature, humidity, and passenger flow) inside and outside the subway station in real time through a sensor network and uploads the collected environmental data to the full-link energy-saving control platform for central air-conditioning.

[0138] Dynamic adjustment module: The full-link energy-saving control platform for central air-conditioning dynamically adjusts the air volume of the supply air duct and the return air duct through fan control according to the collected data.

[0139] Parameter reading module: Reads all technical parameters of the refrigeration unit through the Modbus network protocol, optimizes the overall COP of the central air conditioner using the extremum search algorithm, and controls the addition and subtraction of the main unit according to the cooling capacity demand;

[0140] Supply regulation module: Adjusts the air volume and number of units of the cooling tower fan according to the cooling water temperature difference, real-time load of the air conditioner, outdoor wet bulb temperature, etc., and adjusts the cold and heat source supply in real time according to the load status of the fresh air unit, conducts joint regulation of air and water, and adjusts the supply air temperature according to the changes in outdoor temperature and humidity and corresponding parameters such as on-site temperature;

[0141] Opening adjustment module: Adjusts the opening of the air valve according to the changes in the indoor and outdoor environment, and conducts centralized intelligent management of central air conditioning equipment;

[0142] Angle adjustment module: Adjusts the opening angle of the electric proportional integral regulating air valve in the corresponding area through the signals fed back by the high-precision temperature sensors set in different areas of the platform layer.

[0143] The working principle of the above technical solution is as follows: A dense sensor network is deployed inside and outside the subway station. These sensors can capture key environmental data such as temperature, humidity, and passenger flow inside and outside the subway station in real time. This data is uploaded to the central air-conditioning full-link energy-saving control platform in real time through a high-speed communication network. The control platform is a central system integrating advanced algorithms and data processing capabilities, capable of quickly analyzing and processing massive amounts of data; the central air-conditioning full-link energy-saving control platform dynamically adjusts the air volume of the supply air duct and the return air duct according to the collected environmental data, including fine-tuning parameters such as the fan speed and damper opening. By avoiding excessive fresh air intake or excessive return air discharge, it can ensure that the air circulation in the subway station meets the comfort requirements of passengers and maximizes energy utilization; through the Modbus network protocol, the central air-conditioning full-link energy-saving control platform can read all technical parameters of the refrigeration unit, including operating status, energy consumption, refrigeration efficiency, etc. Using the extremum search algorithm, the platform can optimize the overall COP (coefficient of performance) of the central air-conditioning. According to the actual cooling capacity demand of the subway station, the platform can intelligently control the operation of adding and subtracting units of the main engine to ensure that the refrigeration efficiency is always in the optimal state; the cooling tower is an important part of the subway station central air-conditioning system, and its operating efficiency directly affects the energy consumption of the entire system. The central air-conditioning full-link energy-saving control platform intelligently adjusts the air volume and number of units of the cooling tower fan according to relevant conditions such as the cooling water temperature difference, the real-time load of the air-conditioning, and the outdoor wet-bulb temperature. At the same time, the platform also adjusts the cold and heat source supply in real time according to the load status of the fresh air unit to achieve joint adjustment of air and water. In addition, the platform can also finely adjust the supply air temperature according to the changes in outdoor temperature and humidity and corresponding parameters such as the on-site temperature to ensure that the air environment in the subway station is always in the best state; according to the changes in the indoor and outdoor environment, the central air-conditioning full-link energy-saving control platform can intelligently adjust the opening of the air valve. By installing an electric proportional-integral regulating air valve at the air outlet position of each air valve and setting high-precision temperature sensors in different areas such as the strong cooling area, weak cooling area, and comfort area on the platform layer. These temperature sensors can monitor the temperature changes in the area in real time and accurately and feedback the data to the control system. The control system accurately adjusts the opening angle of the electric proportional-integral regulating air valve in the corresponding area according to the signals feedback by these temperature sensors and the preset temperature values in different areas, so as to effectively control the temperature in different areas. When the air outlet is close to the air handling unit, due to the large air volume, the temperature in this area is more likely to reach the set temperature. At this time, the system automatically reduces the opening angle of the electric regulating air valve to enable the excess air volume to be transported to the area of the farther air outlet, thereby ensuring that the temperature in the area of the farther air outlet can also reach the set value. At the same time, a lower temperature value is set for the strong cooling area. When the temperature sensor in the strong cooling area feedbacks that the temperature does not meet the standard, the system appropriately increases the opening of the air valve in this area; for the weak cooling area and the comfort area, the opening of the air valve is adjusted according to their respective preset temperatures.This can not only ensure that the air circulation in the subway station meets the comfort requirements of passengers, but also achieve the maximum utilization of energy. At the same time, the platform also conducts centralized intelligent management of the central air-conditioning equipment, including the monitoring of the equipment operation status, fault warning, and remote control, etc. Through centralized management, the global optimization and energy conservation and consumption reduction of the central air-conditioning system in the subway station can be realized.

[0144] The effects of the above technical solution are as follows: The environmental data inside and outside the subway station are collected in real time through the sensor network and uploaded to the energy-saving control platform, enabling the system to make precise adjustments according to the actual situation; The dynamic adjustment of the fan control ensures the pressure balance in the mixing chamber, avoiding excessive entry of fresh air or excessive discharge of return air, thus reducing energy waste; The overall COP of the central air-conditioning is optimized by using the extremum search algorithm, making the operation of the refrigeration unit more efficient and further improving the energy utilization efficiency; Due to the improvement of the energy utilization efficiency, the energy consumption of the central air-conditioning system in the subway station is significantly reduced, thereby reducing the operation cost; The centralized intelligent management makes the operation of the equipment more stable, reducing the downtime and maintenance cost caused by equipment failures; By precisely adjusting the supply air temperature and volume, the air environment in the subway station is made more comfortable, meeting the needs of passengers; The coordinated adjustment of water and air ensures that the supply of cold and heat sources matches the changes in the internal and external environment of the subway station, further enhancing the comfort of passengers; This technical solution contributes to energy conservation and emission reduction by improving the energy utilization efficiency and reducing energy consumption; The reduced energy consumption means less consumption of fossil fuels and greenhouse gas emissions, which is beneficial to environmental protection and sustainable development; The centralized intelligent management makes the operation of the central air-conditioning system in the subway station more intelligent and automated, reducing manual intervention and operation difficulty; The real-time monitoring and warning function enables the management personnel to discover and solve problems in a timely manner, improving the management efficiency; Measures such as the dynamic adjustment of the fan control, the optimization of the refrigeration unit, and the coordinated adjustment of water and air make the operation of the central air-conditioning system in the subway station more stable and reliable; It reduces the downtime caused by equipment failures and the impact on subway operations.

[0145] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A full-link energy-saving method for the central air-conditioning system in a subway station based on wind balance, characterized in that, The method comprises: S1. Collect environmental data inside and outside the subway station in real time through the sensor network, and upload the collected environmental data to the central air-conditioning full-link energy-saving control platform; S2. The central air conditioning full-link energy-saving control platform dynamically adjusts the air volume of the supply and return air ducts through fan control based on the collected data; S3, read all technical parameters of the refrigeration unit through the modbus network protocol, use the extreme value search algorithm to optimize the overall COP of the central air conditioner, and control the host addition and subtraction according to the cooling demand; S4. According to relevant conditions, adjust the air volume and number of cooling tower fans, adjust the supply of cold and hot sources in real time according to the load status of the fresh air unit, conduct wind and water joint adjustment, and adjust the supply air temperature according to the corresponding parameters; S5. Adjust the air valve opening according to the changes in the indoor and outdoor environment, and conduct centralized intelligent management of central air-conditioning equipment; S6. Adjust the opening angle of the electric proportional integral regulating air valve in the corresponding area through the feedback signal from the high-precision temperature sensors installed in different areas of the platform layer; The S4 comprises: S41. Calculate the optimal air volume and number of cooling tower fans using an intelligent algorithm based on the cooling water temperature difference, the real-time air conditioning load, and the outdoor wet-bulb temperature; S42, dynamically adjust the fan speed through frequency conversion speed control, and monitor the fan operation status; S43. Remotely monitor and warn of faults of cooling tower fans based on the Internet of Things technology, and adjust the supply of cold and heat sources in real time in combination with the load status of the fresh air unit; S44. Based on the outdoor temperature and humidity changes and the on-site temperature, a supply air temperature prediction model is established, and a prediction control algorithm is used to dynamically adjust the supply air temperature; The S44 comprises: Collect historical data of key parameters, perform preprocessing, and use feature selection methods to screen out the features that have the greatest impact on the supply air temperature prediction; at the same time, use data mining technology to explore the potential relationship between features; Select a prediction model based on the characteristics of the data and prediction requirements, and use the preprocessed data to train the model; Verify the trained prediction model through cross-validation to evaluate the prediction performance and generalization ability of the model; optimize the model based on the verification results; Based on the supply air temperature prediction model, a predictive control algorithm is designed to predict the supply air temperature using real-time data. Based on the prediction results and the optimal supply air temperature setting value calculated by the control algorithm, the supply air temperature of the air conditioning system is adjusted in real time through the control system. Monitor the adjusted air supply temperature and passenger comfort feedback in real time to evaluate the adjustment effect; if the expected target is not achieved, make iterative adjustments based on the feedback information to optimize the predictive control algorithm and air supply temperature setting value; Collect passenger comfort feedback on the air conditioning system and develop optimization strategies based on passenger comfort evaluation results.

2. The method for energy saving in the whole link of the central air conditioner in the subway station based on wind balance according to claim 1, wherein, Said S1 comprises: S11, collect environmental data through a high-precision sensor network deployed inside and outside the subway station; S12. Preliminary processing of the collected environmental data is performed through data verification and anomaly detection mechanisms, and outliers are eliminated; S13. Upload the preliminarily processed environmental data to the full-link energy-saving control platform of the central air conditioner through a wired or wireless network; S14. Store the real-time data and historical data respectively through the real-time database and historical database established on the control platform; S15. Mine and analyze the stored data through machine learning algorithms, identify the environmental change trend, and predict the future load demand.

3. The energy-saving method for the whole air-conditioning link of the subway station based on air balance according to claim 2, characterized in that, The said S15 includes: S151. Based on the characteristics of the environmental data, select the features that have an important impact on the load demand prediction; and perform feature extraction, and normalize or standardize the feature data; S152. Select a machine learning algorithm according to the characteristics of the historical data and the prediction requirements; S153. Use the processed stored data to train the selected machine learning model, and verify the trained model through cross-validation to evaluate the generalization ability of the model on unknown data; S154. Use time series analysis or clustering analysis methods to identify the change trend of environmental parameters in the stored data, and predict the load demand in the future period based on the trained machine learning model; S155. Quantitatively evaluate the prediction results, fine-tune the model according to the evaluation results, and formulate an energy-saving strategy based on the prediction results; S156. Real-time feedback the prediction results to the full-link energy-saving control platform of the central air conditioner, and adjust the operating state of the air-conditioning system in real time according to the predicted load demand; S157. According to the actual operating effect of the air-conditioning system, collect feedback data, and continuously optimize and iterate the prediction model.

4. The method for overall-link energy saving of the central air conditioner in the subway station based on air balance according to claim 1, wherein, The said S2 includes: S21. Based on the collected environmental data, use the fluid mechanics model to calculate the current air volume values of the supply air duct and the return air duct; and dynamically adjust the fan speed and the output of the frequency converter through the PID control algorithm; S22. Real-time monitor the pressure in the mixing chamber, and adopt a fuzzy control strategy or a neural network control strategy to dynamically adjust the ratio of fresh air to return air according to the pressure change; S23. Based on the pressure balance simulation model, simulate the wind pressure change under different working conditions, and verify the effectiveness of the control strategy; S24. Based on the adaptive learning mechanism, continuously optimize the control parameters according to the operating data, and conduct regular pressure balance tests to evaluate the system performance.

5. The energy-saving method for the whole-link of the central air-conditioning system in the subway station based on wind balance according to claim 4, characterized in that, The said S22 includes: S221. Real-time monitor the pressure change in the mixing chamber through the pressure sensor installed in the mixing chamber, check the collected pressure data, and identify and eliminate outliers; S222. Use time series analysis technology to analyze the change trend of the pressure in the mixing chamber, and identify the rules and characteristics of the pressure fluctuation; S223. Evaluate the applicability of the fuzzy control strategy and the neural network control strategy according to the change characteristics of the pressure in the mixing chamber and the control requirements, and select the control strategy; S224. Initialize the parameters of the selected control strategy, and verify the adaptability and stability of the control strategy under different working conditions through simulation; S225. According to the change of the pressure in the mixing chamber, calculate the optimal ratio of fresh air to return air by using the control strategy, and convert the calculated ratio of fresh air to return air into the control instruction of the actuator; S226. Monitor the pressure in the air mixing chamber after real-time adjustment, evaluate the adjustment effect. If the expected target is not achieved, perform iterative adjustment until the pressure is stable.

6. The energy-saving method for the whole link of the central air conditioner in the subway station based on wind balance according to claim 1, wherein, The above S3 includes: S31. Regularly read various technical parameters of the refrigeration unit through the Modbus network protocol, and clean and format the read data. S32. Analyze the relationship between technical parameters and energy consumption through data mining technology to identify key factors affecting refrigeration efficiency. S33. Adopt an extremum search algorithm combined with historical operation data and current environmental load to dynamically adjust the operation strategy of the refrigeration unit to maximize the overall COP. S34. According to the prediction of cooling capacity demand, use the predictive control algorithm to intelligently control the operation of adding or removing units of the main unit, implement the preventive maintenance strategy of the refrigeration unit, predict the fault risk based on data analysis, and perform maintenance in advance.

7. The energy-saving method for the whole link of the central air-conditioning system in a subway station based on wind balance according to claim 6, wherein, The above S33 includes: S331. Select an extremum search algorithm according to the characteristics of the refrigeration unit and initialize the algorithm parameters. S332. Define an objective function with the goal of maximizing the overall COP, and use historical operation data to continuously find the combination of refrigeration unit operation parameters that makes the objective function reach the optimal value through iterative calculation. S333. Evaluate the performance of the extremum search algorithm through cross-validation and optimize the algorithm according to the evaluation results. S334. Perform preprocessing operations on historical operation data, extract key features from the preprocessed historical operation data, and use feature selection methods to screen out the features that have the greatest impact on the overall COP. S335. Use the clustering algorithm to group historical operation data, identify the operation modes under different working conditions, monitor environmental parameters in real time, and use time series analysis to predict the refrigeration load in the future for a period of time. S336. Set a warning threshold according to the load prediction result. When the predicted load exceeds or is lower than a certain range, trigger the corresponding warning mechanism. S337. Based on the optimization results of the extremum search algorithm, the analysis results of historical operation data, and the prediction results of the current environmental load, formulate an adjustment plan for the operation strategy of the refrigeration unit. S338. Convert the formulated operation strategy into control instructions, and send them to the refrigeration unit in real time through the Modbus network protocol. Real-time monitor the operation parameters of the refrigeration unit and the overall COP after adjustment, evaluate the adjustment effect. If the expected target is not achieved, perform iterative adjustment according to the feedback information until the optimal operation state is reached.

8. The method for energy conservation in the whole link of the central air conditioner of the subway station based on wind balance according to claim 1, wherein, The above S5 includes: S51. Calculate the optimal damper opening through an intelligent algorithm according to the indoor and outdoor environmental changes. S52. Adjust the damper opening based on the damper adjustment strategy combining remote control and local control, and monitor the operation state of the damper in real time through the Internet of Things technology. S53. Through the centralized intelligent management system of central air-conditioning equipment, monitor the equipment state in real time, give early warning of faults, and perform remote operation and maintenance.

9. A system for implementing the full-link energy-saving method of the central air-conditioning system in a subway station based on wind balance as described in claim 1, characterized in that, The above system includes: Data acquisition module: Real-time collect the environmental data inside and outside the subway station through the sensor network, and upload the collected environmental data to the central air-conditioning full-link energy-saving control platform. Dynamic adjustment module: The central air-conditioning full-link energy-saving control platform dynamically adjusts the air volume of the supply air duct and the return air duct through fan control according to the collected data; Parameter reading module: Reads all technical parameters of the refrigeration unit through the modbus network protocol, optimizes the overall COP of the central air-conditioning using the extremum search algorithm, and controls the addition and subtraction of the main unit according to the cooling capacity demand; Supply adjustment module: Adjusts the air volume and the number of units of the cooling tower fan according to the cooling water temperature difference and related conditions, and adjusts the cold and heat source supply in real time according to the load status of the fresh air unit, conducts joint adjustment of air and water, and adjusts the supply air temperature according to the corresponding parameters; Opening adjustment module: Adjusts the opening of the air valve according to the changes in the indoor and outdoor environment, and conducts centralized intelligent management of central air-conditioning equipment; Angle adjustment module: Adjusts the opening angle of the electric proportional integral regulating air valve in the corresponding area through the signals fed back by the high-precision temperature sensors set in different areas of the platform layer.

Images