Variable air volume adjustable sectional type ventilation control system

Abstract

The invention relates to the technical field of laboratory ventilation, in particular to a variable air volume adjustable sectional type ventilation control system which comprises a central controller used for monitoring the operation state of the system in real time and adjusting execution instructions based on environment parameters of corresponding areas; the distributed control units are distributed in all control areas of the laboratory and used for collecting environment parameters of the areas and adjusting ventilation control parameters of the control areas according to execution instructions of the central controller; and executing mechanisms distributed in each control area of the laboratory and used for executing ventilation control actions based on the ventilation control parameters adjusted by the distributed control unit. According to the variable air volume adjustable sectional type ventilation control system, through cooperative work of the central controller, the distributed control unit, the execution mechanism and the Internet of Things management platform, accurate control over environment parameters of all areas of a laboratory is achieved. The system can monitor and adjust execution instructions in real time, and ensures that the laboratory environment is always in a preset ideal state.

Description

Technical Field

[0001] The invention relates to the technical field of laboratory ventilation, in particular to a variable air volume adjustable segmented ventilation control system. Background Art

[0002] In a modern laboratory environment, the effectiveness and accuracy of the ventilation control system are crucial to ensuring the comfort of experimenters, the stable operation of experimental equipment, and the accuracy of experimental results. Traditional ventilation control systems often use fixed air volume or simple adjustment methods, which are difficult to meet the diverse needs of various areas of the laboratory for environmental parameters (such as temperature, humidity, CO2 concentration, etc.). Especially in large laboratories or complex experimental scenarios, the environmental parameter requirements of different areas vary significantly, and traditional ventilation control methods often lead to problems such as energy waste and poor environmental control effects.

[0003] In order to solve the above problems, a variety of intelligent ventilation control systems have emerged in recent years. These systems usually integrate sensors, controllers and actuators to achieve real-time monitoring and precise control of laboratory environmental parameters. However, these systems still have some shortcomings in practical applications, such as insufficient control accuracy, slow response speed, lack of intelligent prediction and adaptive adjustment capabilities, etc. Summary of the invention

[0004] In view of the technical problems existing in the prior art, the present invention provides a variable air volume adjustable segmented ventilation control system to solve the problems of insufficient control accuracy and slow response speed of the existing ventilation control system.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: a variable air volume adjustable segmented ventilation control system, comprising:

[0006] The central controller is used to monitor the operating status of the system in real time and adjust the execution instructions based on the environmental parameters of the corresponding area;

[0007] Distributed control units distributed in each control area of ​​the laboratory are used to collect environmental parameters of the area and adjust the ventilation control parameters of the control area according to the execution instructions of the central controller;

[0008] The actuators distributed in each control area of ​​the laboratory perform ventilation control actions based on the ventilation control parameters adjusted by the distributed control unit;

[0009] An IoT management platform for connecting the central controller with distributed control units and actuators;

[0010] A control terminal for a user to interact with the ventilation control system.

[0011] Based on the above technical solution, the present invention can also be improved as follows.

[0012] Furthermore, the environmental parameters include at least one of temperature, humidity, CO2 concentration, air flow rate and / or air quality index.

[0013] Furthermore, the distributed control unit also includes a storage module for storing historical environmental parameter data of the control area, and a prediction module for analyzing historical data to predict future environmental parameter change trends.

[0014] Furthermore, the prediction module performs prediction based on a machine learning algorithm or an artificial intelligence model, and the algorithm or model optimizes prediction accuracy by training historical environmental parameter data.

[0015] Furthermore, the prediction module uses a machine learning algorithm or an artificial intelligence model, which is trained and optimized through the following steps to predict future environmental parameter change trends:

[0016] Collect and pre-process historical environmental parameter data;

[0017] The machine learning algorithm or artificial intelligence model includes a long short-term memory network (LSTM) unit, a support vector machine (SVM) unit, a random forest unit or a deep neural network (DNN) unit;

[0018] The preprocessed historical data is divided into a training set for model training and a validation set for model validation in chronological order;

[0019] Use the training set data to train the machine learning algorithm or model and adjust the model parameters to minimize the prediction error;

[0020] Use validation set data to evaluate model performance;

[0021] Iteratively optimize the model based on the evaluation results until the expected prediction performance is achieved;

[0022] The trained model is deployed in the prediction module to predict the future trend of environmental parameters in real time.

[0023] Further, the pre-processed historical environmental parameter data includes temperature, humidity, CO2 concentration, air velocity and / or air quality index, and the process of collecting and pre-processing the historical environmental parameter data includes:

[0024] Use the normalization formula to normalize the data:

[0025] The normalization formula is:

[0026]

[0027] Among them, X is the original data, X norm is the normalized data, X min and X max are the minimum and maximum values ​​in the data set, respectively.

[0028] Further, the long short-term memory network (LSTM) unit is selected as a prediction model for training, and state update and hidden state calculation are performed according to the LSTM unit. The LSTM unit update formula includes:

[0029] Forget gate: f t =σ(W f ·[h t-1 , x t ]+b f );

[0030] Input gate: i t =σ(W i ·[h t-1 , x t ]+b i );

[0031] Output gate: o t =σ(W o ·[h t-1 , x t ]+b o );

[0032] Cell state update: C t =f t *C t-1 +i t *tanh(w c ·[h t-1 , x t ]+b c );

[0033] Hidden state: h t =o t *tanh(C t );

[0034] Where σ is the sigmoid function, W f , W i , W o 、w c is the weight matrix; b f 、b i 、b o 、b c is the offset top; h t-1 is the hidden state of the previous moment; the x t The input at the current moment.

[0035] Further, the prediction accuracy and mean square error of the model are evaluated based on the model evaluation formula, and the model evaluation formula includes:

[0036] Forecast accuracy formula:

[0037] Among them, TP is true positive (correctly predicted as a positive example), TN is true negative (correctly predicted as a negative example), FP is false positive (incorrectly predicted as a positive example), and FN is false negative (incorrectly predicted as a negative example);

[0038] Mean square error formula:

[0039] Among them, y i is the true value, is the predicted value, and n is the number of samples.

[0040] Further, the actuator includes a variable air volume damper, a fan, a heating / cooling element and / or a humidifier / dehumidifier for adjusting the ventilation volume, temperature and humidity according to the ventilation control parameters;

[0041] The Internet of Things management platform supports wired and / or wireless communication technology to achieve data exchange and control instruction transmission between the central controller and the distributed control units and actuators.

[0042] The Internet of Things management platform also includes functional modules for remote monitoring, fault diagnosis and / or system upgrade.

[0043] Further, the control terminal is a smart phone, tablet computer, personal computer or dedicated control panel, which is used to display system status, receive user input and send control instructions to the central controller;

[0044] The control terminal also includes an application for setting environmental parameter thresholds, receiving alarm notifications and / or viewing historical data.

[0045] The system also includes a sensor for detecting the status of the actuator, and a maintenance management module for generating maintenance or replacement recommendations based on the sensor data.

[0046] The beneficial effects of the present invention are:

[0047] 1) The variable air volume adjustable segmented ventilation control system of the present invention realizes precise control of environmental parameters in each area of ​​the laboratory through the collaborative work of the central controller, distributed control unit, actuator and Internet of Things management platform. The system can monitor and adjust the execution instructions in real time to ensure that the laboratory environment is always in the preset ideal state. This precise control not only improves the comfort of the experimenters, but also ensures the stable operation of the experimental equipment and the accuracy of the experimental results.

[0048] 2) The present invention adds a storage module and a prediction module to the distributed control unit, and uses a machine learning algorithm or an artificial intelligence model to train historical environmental parameter data to predict the changing trend of future environmental parameters. This intelligent prediction capability enables the system to adjust the ventilation control parameters in advance and effectively respond to changes in environmental parameters, further improving the control accuracy and response speed of the system. At the same time, the application of the prediction module also reduces unnecessary energy waste and improves the overall energy efficiency of the system.

[0049] 3) The Internet of Things management platform of the present invention integrates the functional modules of remote monitoring, fault diagnosis and system upgrade, so that managers can view the operating status of the system in real time and promptly discover and handle abnormal situations. In addition, the system also includes sensors for detecting the status of actuators and maintenance management modules, which can monitor the working status of actuators in real time, generate maintenance or replacement suggestions, and notify users through control terminals. This comprehensive system monitoring and maintenance management not only ensures the stable operation of the system, but also extends the service life of the actuators and reduces maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a control principle block diagram of the variable air volume adjustable segmented ventilation control system of the present invention;

[0051] Figure 2 A flow chart of the training and optimization of the present invention to predict future environmental parameter change trends. DETAILED DESCRIPTION

[0052] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0053] In recent years, a variety of intelligent ventilation control systems have emerged. These systems achieve real-time monitoring and precise control of laboratory environmental parameters by integrating advanced equipment such as sensors, controllers and actuators. However, although these systems have made certain progress in intelligence and automation, there are still some shortcomings in practical applications. For example, the control accuracy and response speed of some systems still need to be improved; some systems lack intelligent prediction and adaptive adjustment capabilities and cannot respond to changes in environmental parameters in advance; and some systems have hidden dangers in stability and reliability, which may affect the normal operation of the laboratory.

[0054] In view of these problems existing in traditional ventilation systems and existing intelligent ventilation systems, the demand for new ventilation control systems is becoming increasingly urgent. The new ventilation control system needs to have higher control accuracy and response speed, and can accurately meet the diverse needs of various areas of the laboratory for environmental parameters; at the same time, it also needs to have intelligent prediction and adaptive adjustment capabilities, and can adjust ventilation control parameters in advance to effectively respond to changes in environmental parameters; in addition, the new system also needs to have higher stability and reliability to ensure the normal operation of the laboratory and the accuracy of experimental results.

[0055] It is in this context that we proposed a variable air volume adjustable segmented ventilation control system. Through the collaborative work of the central controller, distributed control unit, actuator, Internet of Things management platform and control terminal, the system realizes the precise control and intelligent management of the environmental parameters of each area of ​​the laboratory. Compared with traditional ventilation systems and existing intelligent ventilation systems, this system has significantly improved control accuracy, response speed, intelligent prediction and adaptive adjustment capabilities.

[0056] like Figure 1 As shown, an embodiment of the present invention provides a variable air volume adjustable segmented ventilation control system, comprising:

[0057] The central controller is used to monitor the operating status of the system in real time and adjust the execution instructions based on the environmental parameters of the corresponding area;

[0058] Distributed control units distributed in each control area of ​​the laboratory are used to collect environmental parameters of the area and adjust the ventilation control parameters of the control area according to the execution instructions of the central controller;

[0059] The actuators distributed in each control area of ​​the laboratory perform ventilation control actions based on the ventilation control parameters adjusted by the distributed control unit;

[0060] An IoT management platform for connecting the central controller with distributed control units and actuators;

[0061] A control terminal for a user to interact with the ventilation control system.

[0062] The central controller monitors and adjusts the execution instructions in real time, the distributed control unit collects environmental parameters and adjusts ventilation parameters, the actuator performs ventilation actions, the Internet of Things management platform realizes connection and data transmission, and the control terminal is provided for user interaction to achieve precise control of environmental parameters in various areas of the laboratory.

[0063] In addition, the environmental parameters include at least one of temperature, humidity, CO2 concentration, air flow rate and / or air quality index to ensure comprehensive optimization and precise control of the laboratory environment.

[0064] As an implementation mode, the distributed control unit further includes a storage module for storing historical environmental parameter data of the control area, and a prediction module for analyzing historical data to predict future environmental parameter change trends.

[0065] Specifically, the prediction module performs prediction based on a machine learning algorithm or an artificial intelligence model, and the algorithm or model optimizes prediction accuracy by training historical environmental parameter data.

[0066] like Figure 2 As shown, in this embodiment, the prediction module adopts a machine learning algorithm or an artificial intelligence model, and the algorithm or model is trained and optimized through the following steps to predict the future trend of environmental parameter changes:

[0067] Collect and pre-process historical environmental parameter data;

[0068] The machine learning algorithm or artificial intelligence model includes a long short-term memory network (LSTM) unit, a support vector machine (SVM) unit, a random forest unit or a deep neural network (DNN) unit;

[0069] The preprocessed historical data is divided into a training set for model training and a validation set for model validation in chronological order;

[0070] Use the training set data to train the machine learning algorithm or model and adjust the model parameters to minimize the prediction error;

[0071] Use validation set data to evaluate model performance, including prediction accuracy, stability, and generalization ability;

[0072] Iteratively optimize the model based on the evaluation results until the expected prediction performance is achieved;

[0073] The trained model is deployed in the prediction module to predict the future trend of environmental parameters in real time.

[0074] The prediction module works as follows:

[0075] Data collection and preprocessing: First, historical environmental parameter data such as temperature, humidity, CO2 concentration, air velocity and / or air quality index are collected from the storage module, and these data are standardized using the normalization processing formula to ensure that the data are on a uniform scale to facilitate subsequent model training.

[0076] Model selection and training: Among various machine learning algorithms or artificial intelligence models, the long short-term memory network (LSTM) is selected as the prediction model because it is particularly suitable for processing time series data. The pre-processed historical data is divided into a training set and a validation set in chronological order, and then the training set data is used to train the LSTM model, and the prediction error is minimized by adjusting the model parameters (such as weight matrix and bias term).

[0077] Model evaluation and optimization: The trained model is evaluated using validation set data, with evaluation metrics including prediction accuracy and mean square error. Prediction accuracy is determined by calculating true positives, true negatives, false positives, and false negatives, while mean square error measures the difference between the predicted value and the true value. Based on the evaluation results, the model is iteratively optimized until the expected prediction performance is achieved.

[0078] Model deployment and prediction: The trained and optimized LSTM model is deployed in the prediction module, which can receive new environmental parameter data in real time and make predictions based on the model to derive the changing trend of future environmental parameters.

[0079] Preferably, the pre-processed historical environmental parameter data includes temperature, humidity, CO2 concentration, air velocity and / or air quality index, and the process of collecting and pre-processing the historical environmental parameter data includes:

[0080] Use the normalization formula to normalize the data:

[0081] The normalization formula is:

[0082]

[0083] Among them, X is the original data, X norm is the normalized data, X min and X max are the minimum and maximum values ​​in the data set, respectively.

[0084] Preferably, the long short-term memory network (LSTM) unit is selected as the prediction model for training, and state update and hidden state calculation are performed according to the LSTM unit, and the LSTM unit update formula includes:

[0085] Forget gate: f t =σ(W f ·[h t-1 , x t ]+b f );

[0086] Input gate: i t =σ(W i ·[h t-1 , xt ]+b i );

[0087] Output gate: o t =σ(W o ·[h t-1 , x t ]+b o );

[0088] Cell state update: C t =f t *C t-1 +i t *tanh(w c ·[h t-1 , x t ]+b c );

[0089] Hidden state: h t =o t *tanh(C t );

[0090] Where σ is the sigmoid function, W f , W i , W o 、w c is the weight matrix; b f 、b i 、b o 、b c is the offset top; h t-1 is the hidden state of the previous moment; the x t The input at the current moment.

[0091] Preferably, the prediction accuracy and mean square error of the model are evaluated based on a model evaluation formula, wherein the model evaluation formula comprises:

[0092] Forecast accuracy formula:

[0093] Among them, TP is true positive (correctly predicted as a positive example), TN is true negative (correctly predicted as a negative example), FP is false positive (incorrectly predicted as a positive example), and FN is false negative (incorrectly predicted as a negative example);

[0094] Mean square error formula:

[0095] Among them, y i is the true value, is the predicted value, and n is the number of samples.

[0096] In this embodiment, the distributed control unit is not only responsible for collecting environmental parameters (such as temperature, humidity, CO2 concentration, air flow rate and / or air quality index) of each control area, but also adds a storage module and a prediction module. The storage module is used to save the historical environmental parameter data of the control area to provide a training basis for the subsequent machine learning algorithm. The prediction module is based on the machine learning algorithm or artificial intelligence model, and uses the stored historical data for training to predict the changing trend of future environmental parameters.

[0097] Machine learning algorithms and model training can be summarized as follows:

[0098] Data collection and preprocessing:

[0099] Collect historical environmental parameter data from the storage module.

[0100] Preprocess the data, including data cleaning, missing value filling and normalization.

[0101] Model selection and training:

[0102] The long short-term memory network (LSTM) is selected as the prediction model because it is good at processing time series data and can capture the changes of environmental parameters over time.

[0103] The LSTM unit update formula includes the forget gate, input gate, output gate, cell state update, and hidden state calculation, which together determine the output and internal state update of the LSTM unit.

[0104] Data partitioning and model evaluation:

[0105] The preprocessed historical data is divided into a training set and a validation set in chronological order.

[0106] The LSTM model is trained using the training set data, and the model parameters (such as the weight matrix and bias term) are adjusted to minimize the prediction error.

[0107] The validation set data was used to evaluate the model performance, including prediction accuracy (calculated using TP, TN, FP, FN) and mean square error (MSE).

[0108] Model optimization and deployment:

[0109] The LSTM model is iteratively optimized according to the evaluation results until the expected prediction performance is achieved.

[0110] The trained model is deployed in the prediction module to predict the future trend of environmental parameters in real time.

[0111] As an embodiment, the actuator includes a variable air volume damper, a fan, a heating / cooling element and / or a humidifier / dehumidifier, which is used to adjust the ventilation volume, temperature and humidity according to the ventilation control parameters;

[0112] Specifically, variable air volume dampers and fans are responsible for regulating ventilation, heating / cooling elements are used to adjust temperature, and humidifiers / dehumidifiers focus on humidity management. In this way, the system can ensure that the laboratory environment is always in the preset ideal state.

[0113] The IoT management platform supports wired and / or wireless communication technologies to achieve data exchange and control command transmission between the central controller and the distributed control units and actuators. In this way, the system can ensure that the laboratory environment is always in the preset ideal state. It enables the central controller to efficiently and reliably exchange data and transmit control commands with the distributed control units and actuators. This not only ensures the real-time nature of information, but also greatly improves the response speed and overall performance of the system.

[0114] The IoT management platform also includes functional modules for remote monitoring, fault diagnosis and / or system upgrades, which enables the central controller to efficiently and reliably exchange data and transmit control instructions with the distributed control units and actuators. This not only ensures the real-time nature of information, but also greatly improves the response speed and overall performance of the system.

[0115] What is more advanced is that the IoT management platform also integrates the functional modules of remote monitoring, fault diagnosis and system upgrade. The remote monitoring function allows managers to view the operating status of the system in real time at any location to ensure the stable operation of the system. The fault diagnosis module can intelligently identify and locate possible faults in the system, provide accurate information to maintenance personnel, and thus greatly shorten the troubleshooting time. The system upgrade function ensures that the system can be continuously optimized with the continuous advancement of technology, maintaining its advancedness and competitiveness.

[0116] As an implementation mode, the control terminal is a smart phone, a tablet computer, a personal computer or a dedicated control panel, which is used to display the system status, receive user input and send control instructions to the central controller; these terminals can not only display the current status of the system in real time, such as the environmental parameters of each control area, the working status of the actuator, etc., but also receive user input, such as the setting of environmental parameter thresholds, the sending of control instructions, etc.

[0117] The control terminal also includes an application for setting environmental parameter thresholds, receiving alarm notifications and / or viewing historical data.

[0118] The program not only provides the function of setting environmental parameter thresholds, allowing users to customize the ideal laboratory environment according to their own needs, but also has the ability to receive alarm notifications and view historical data. When the system detects that the environmental parameters exceed the preset thresholds or the actuator fails, the application will immediately send an alarm notification to the user to ensure that the user can understand and deal with the abnormal situation in a timely manner. At the same time, users can also view the system's historical data through the application, such as the changing trends of environmental parameters, the operating records of the actuator, etc., to provide strong support for system optimization and decision-making.

[0119] The system also includes sensors for detecting actuator status (such as failure, maintenance requirements, etc.), and a maintenance management module for generating maintenance or replacement recommendations based on sensor data.

[0120] Sensors can monitor the working status of the actuator in real time, such as temperature, vibration, current, etc., and feed this data back to the maintenance management module. The maintenance management module uses advanced algorithms to process and analyze sensor data to identify possible faults or maintenance needs of the actuator. Once an abnormal situation is detected, the maintenance management module will immediately generate maintenance or replacement suggestions and notify the user through the control terminal. These suggestions not only include specific maintenance measures and replacement plans, but also provide corresponding priority and time suggestions to help users arrange maintenance plans reasonably and ensure the continuous and stable operation of the system.

[0121] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0122] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0123] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A variable air volume adjustable segmented ventilation control system, characterized in that: include: The central controller is used to monitor the operating status of the system in real time and adjust the execution instructions based on the environmental parameters of the corresponding area; Distributed control units distributed in each control area of ​​the laboratory are used to collect environmental parameters of the area and adjust the ventilation control parameters of the control area according to the execution instructions of the central controller; The actuators distributed in each control area of ​​the laboratory perform ventilation control actions based on the ventilation control parameters adjusted by the distributed control unit; An IoT management platform for connecting the central controller with distributed control units and actuators; A control terminal for a user to interact with the ventilation control system.

2. The variable air volume adjustable segmented ventilation control system according to claim 1 is characterized in that: The environmental parameters include at least one of temperature, humidity, CO2 concentration, air flow rate and / or air quality index.

3. The variable air volume adjustable segmented ventilation control system according to claim 1 is characterized in that: The distributed control unit also includes a storage module for storing historical environmental parameter data of the control area, and a prediction module for analyzing historical data to predict future environmental parameter change trends.

4. The variable air volume adjustable segmented ventilation control system according to claim 3 is characterized in that: The prediction module performs prediction based on a machine learning algorithm or an artificial intelligence model, and the algorithm or model optimizes prediction accuracy by training historical environmental parameter data.

5. The variable air volume adjustable segmented ventilation control system according to claim 4 is characterized in that: The prediction module uses a machine learning algorithm or an artificial intelligence model, which is trained and optimized through the following steps to predict future environmental parameter change trends: Collect and pre-process historical environmental parameter data; The machine learning algorithm or artificial intelligence model includes a long short-term memory network (LSTM) unit, a support vector machine (SVM) unit, a random forest unit or a deep neural network (DNN) unit; The preprocessed historical data is divided into a training set for model training and a validation set for model validation in chronological order; Use the training set data to train the machine learning algorithm or model and adjust the model parameters to minimize the prediction error; Use validation set data to evaluate model performance; Iteratively optimize the model based on the evaluation results until the expected prediction performance is achieved; The trained model is deployed in the prediction module to predict the future trend of environmental parameters in real time.

6. The variable air volume adjustable segmented ventilation control system according to claim 5 is characterized in that: The pre-processed historical environmental parameter data includes temperature, humidity, CO2 concentration, air velocity and / or air quality index. The process of collecting and pre-processing the historical environmental parameter data includes: Use the normalization formula to normalize the data: The normalization formula is: Among them, X is the original data, X norm is the normalized data, X min and X max are the minimum and maximum values ​​in the data set, respectively.

7. The variable air volume adjustable segmented ventilation control system according to claim 6, characterized in that: The long short-term memory network (LSTM) unit is selected as a prediction model for training, and state update and hidden state calculation are performed according to the LSTM unit. The LSTM unit update formula includes: Forget gate: f t =σ(W f ·[h t-1 , x t ]+b f ); Input gate: i t =σ(W i ·[h t-1 , x t ]+b i ); Output gate: o t =σ(W o ·[h t-1 , x t ]+b o ); Cell state update: C t =f t *C t-1 +i t *tanh(w c ·[h t-1 , x t ]+b c ); Hidden state: h t =o t *tanh(C t ); Among them, σ is the sigmoid function, W f , W i , W o 、w c is the weight matrix; b f , b i , b o , b c is the offset top; h t-1 is the hidden state of the previous moment; the x t The input at the current moment.

8. The variable air volume adjustable segmented ventilation control system according to claim 7, characterized in that: The prediction accuracy and mean square error of the model are evaluated based on the model evaluation formula, which includes: Forecast accuracy formula: Among them, TP is true positive (correctly predicted as a positive example), TN is true negative (correctly predicted as a negative example), FP is false positive (incorrectly predicted as a positive example), and FN is false negative (incorrectly predicted as a negative example); Mean square error formula: Among them, y i is the true value, is the predicted value, and n is the number of samples.

9. The variable air volume adjustable segmented ventilation control system according to claim 1, characterized in that: The actuator includes a variable air volume damper, a fan, a heating / cooling element and / or a humidifier / dehumidifier, which is used to adjust the ventilation volume, temperature and humidity according to the ventilation control parameters; The Internet of Things management platform supports wired and / or wireless communication technology to achieve data exchange and control instruction transmission between the central controller and the distributed control units and actuators. The Internet of Things management platform also includes functional modules for remote monitoring, fault diagnosis and / or system upgrade.

10. The variable air volume adjustable segmented ventilation control system according to claim 1, characterized in that: The control terminal is a smart phone, tablet computer, personal computer or dedicated control panel, which is used to display system status, receive user input and send control instructions to the central controller; The control terminal also includes an application for setting environmental parameter thresholds, receiving alarm notifications and / or viewing historical data. The system also includes a sensor for detecting the status of the actuator, and a maintenance management module for generating maintenance or replacement recommendations based on the sensor data.

Images