Control method and device of air purification system, storage medium and equipment

Abstract

The invention is applicable to the technical field of gas treatment, and provides a control method and device of an air purification system, a storage medium and equipment, and the method comprises the following steps: acquiring real-time monitoring data of an outdoor environment, real-time monitoring data of an indoor environment and forecast data of the outdoor environment; acquiring an environment prediction adjustment network; acquiring the change control quantity; and based on the change control quantity, the real-time working state of the air purification system is dynamically adjusted and controlled. The method has the advantages that system parameters can be changed in advance before the external environment changes, and the indoor environment is actively regulated, controlled and changed in a prediction mode so as to adapt to future environment changes. Moreover, according to the scheme, the environment state regulated and controlled by the system can directly point to the preset comfort level interval, excessive work of an air purification module, a temperature control module and the like can be effectively avoided, the overall energy efficiency ratio is increased, and energy waste is further reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of gas treatment, and particularly relates to a control method, device, storage medium and equipment for an air purification system. Background Art

[0002] An air purification system is a system that removes pollutants such as particulate matter, harmful gases, and microorganisms in the air through technologies such as filtration, adsorption, and sterilization. At present, the air purification system can reduce pollution and at the same time be responsible for integrating a temperature and humidity control system, and adjust parameters such as temperature, humidity, and oxygen content in the environmental space to improve indoor air quality.

[0003] For large places such as commercial complexes, medical institutions, and industries, air purification is very important. Therefore, large central fresh air systems are mostly used to adjust indoor air quality, temperature, and humidity. Its core goal is to reduce the impact of pollutants on human health and the environment and improve the comfort of the place. In general commercial buildings, the energy consumption of the central air circulation system often accounts for more than half of the total building electricity consumption, and the annual electricity consumption per unit area reaches 100-300 degrees per square meter, which is 10-20 times that of ordinary residential buildings. Therefore, intelligence and energy conservation are crucial for air purification systems.

[0004] At present, there are already some air circulation systems integrated with intelligent control. These systems use neural networks such as LSTM and GRU, or model predictive control and reinforcement learning algorithms to dynamically adjust parameters such as fan speed, fresh air mixing ratio, and filter activation level to achieve the purpose of reducing energy consumption.

[0005] However, these above methods often predict pollutant content and temperature and humidity based on historical data in the venue to adjust the energy consumption level of the system, and do not fully combine the possible future environmental states of the venue location for predictive adjustment. Therefore, when the external environment suddenly changes, the control system adjustment inside the building has a delay and no predictability, which makes the indoor environmental perception worse. Therefore, the overall control accuracy of the system needs to be improved. Summary of the Invention

[0006] The purpose of the embodiments of the present application is to provide a control method for an air purification system, aiming to solve the problem that when the external environment suddenly changes, the control system adjustment inside the building has a delay and no predictability, which makes the indoor environmental perception worse.

[0007] The embodiments of the present application are implemented as follows. A control method for an air purification system is provided, and the method includes: Obtain real-time monitoring data of the outdoor environment and real-time monitoring data of the indoor environment and the forecast data of the outdoor environment after k unit time intervals ; Obtain an environmental prediction and adjustment network, and input the monitoring data , monitoring data , forecast data and the target regulation value of the indoor environment after k unit time intervals into the environmental prediction and adjustment network. The output value of the environmental prediction and adjustment network is a change control amount; the change control amount is set to: make the predicted value of the indoor environmental data after k unit time intervals fit with the target regulation value; Obtain the change control amount, and based on the change control amount, dynamically adjust and control the real-time working state of the air purification system.

[0008] Another object of the embodiments of the present application is to provide a control device for an air purification system. The control device for the air purification system includes: A basic data acquisition unit, configured to acquire the real-time monitoring data of the outdoor environment , the real-time monitoring data of the indoor environment and the forecast data of the outdoor environment after k unit time intervals ; A prediction and adjustment unit, configured to obtain an environmental prediction and adjustment network, and input the monitoring data , monitoring data , forecast data and the target regulation value of the indoor environment after k unit time intervals into the environmental prediction and adjustment network. The output value of the environmental prediction and adjustment network is a change control amount; the change control amount is set to: make the predicted value of the indoor environmental data after k unit time intervals fit with the target regulation value; A dynamic adjustment and control unit, configured to obtain the change control amount, and based on the change control amount, dynamically adjust and control the real-time working state of the air purification system.

[0009] Another object of the embodiments of the present application is to provide a computer-readable storage medium. A computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the processor is caused to execute the steps of the control method of the air purification system as described above.

[0010] Another object of the embodiments of the present application is to provide an air purification device, including a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of the control method of the air purification system as described above.

[0011] The control method of the air purification system provided by the embodiments of the present application has prominent advantages in that it can change the system parameters in advance before the external environment changes, and actively regulate and control the indoor environment in a predictive manner to adapt to future environmental changes. Moreover, this solution can directly direct the environmental state after system regulation into the preset comfort range, effectively avoiding the overwork of modules such as air purification and temperature control, improving the overall energy efficiency ratio, and further reducing energy waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is an application environment diagram of the control method of the air purification system provided by the embodiments of the present application; Figure 2 It is a flowchart of the control method of the air purification system provided by the embodiments of the present application; Figure 3 It is a schematic diagram of the control method of the air purification system provided by the embodiments of the present application; Figure 4 It is a structural diagram of the environmental prediction and adjustment network provided by the embodiments of the present application; Figure 5 It is a structural block diagram of the control device of the air purification system provided by the embodiments of the present application; Figure 6 It is an internal structural block diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

[0014] It can be understood that the terms "first", "second", etc. used in the present application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish one unit or module from another. For example, without departing from the scope of the present application, the first script may be referred to as the second script, and similarly, the second script may be referred to as the first script.

[0015] Figure 1 It is an application environment diagram of the control method of the air purification system provided by the embodiments of the present application, as Figure 1As shown, in this application environment, it includes a terminal 110 and a computer device 120.

[0016] The computer device 120 can be an independent physical server or terminal, or a server cluster composed of multiple physical servers. It can be a cloud server providing basic cloud computing services such as cloud servers, or a tablet computer, a notebook computer, a desktop computer, etc.

[0017] The terminal 110 can be an air purification system, an air conditioner or a purification device with a temperature and humidity adjustment function, but is not limited thereto. The terminal 110 and the computer device 120 can be connected through a network, and this application does not make any restrictions here.

[0018] As Figure 2 shown, in one embodiment, a control method for an air purification system is proposed. The adjustment schematic diagram of this method can be as Figure 3 shown. In this embodiment, it is mainly illustrated by applying this method to the computer device 120 in the above Figure 1 . A control method for an air purification system may specifically include the following steps: Step S10: Obtain the real-time monitoring data of the outdoor environment , the real-time monitoring data of the indoor environment and the forecast data of the outdoor environment after k unit times .

[0019] In this embodiment, considering that factors such as the temperature outside the venue, the temperature difference between the inside and outside of the venue, the humidity outside the venue, and the degree of environmental pollution will significantly affect the environment inside the venue. Therefore, in order to improve the accuracy of automatic adjustment, while considering the preset adjustment target inside the venue, the external environmental change factors need to be added to the decision-making elements of the intelligent control system.

[0020] Step S20: Obtain an environmental prediction and adjustment network, and input the monitoring data , the monitoring data , the forecast data and the target regulation value of the indoor environment after k unit times into the environmental prediction and adjustment network. The output value of the environmental prediction and adjustment network is a change control amount; the change control amount is set to: make the predicted value of the indoor environment data after k unit times fit the target regulation value .

[0021] In this embodiment, the target regulation value of the indoor environment after k unit times It can be obtained by means such as looking up a table or online query. Since there are often preset values of comfortable temperature and humidity on different dates and at different time periods, this value may be different at different query times. It can be understood that a query can be made every several unit times, and continuous uninterrupted query is not necessary. The query step size can be selected and set according to requirements. The environmental prediction and adjustment network can be a prediction model based on a neural network, which is used to predict how the air purification system changes the control quantity so that even if the future external environment changes drastically, the indoor environment can reach the preset standard, so that the indoor environment can adaptively change in advance before the external weather conditions and other changes.

[0022] Step S30, obtain the change control quantity, and based on the change control quantity, dynamically adjust and control the real-time working state of the air purification system.

[0023] In this embodiment, the system can control and adjust multiple output dimensions of the air circulation and purification system through the above change control quantity. For example, based on this data, the temperature, humidity of the gas output by the system, and the treatment rates for physical particle pollutants and chemical pollutants are adjusted in real time, so as to cope with the estimated future weather changes.

[0024] In the traditional method, the air purification system often adjusts the working parameters of the air purification system in real time based on the current indoor environment, or parameters such as the difference between the current indoor environment and the outdoor environment, without considering that the outdoor environment may change suddenly at a certain future moment. This application takes into account that since the change of indoor air conditions is a gradual process and cannot change suddenly like the outdoor environment, for large venues such as stadiums, the time required for environmental change is longer. Therefore, the system should make adaptive changes in advance to cope with future sudden changes. Compared with the existing adjustment methods, the advantage of this application is that it can change the system parameters in advance before the external environment changes, and actively regulate and change the indoor environment in a predictive manner to adapt to future environmental changes. Moreover, this solution can make the environmental state after system regulation directly point to the preset comfort interval, effectively avoid the overwork of modules such as air purification and temperature control, improve the overall energy efficiency ratio, and further reduce energy waste.

[0025] In a preferred embodiment, the obtained real-time monitoring data of the outdoor environment, real-time monitoring data of the indoor environment, forecast data of the outdoor environment, and change control quantity are all data containing four dimensions: Physical particle pollutant concentration, chemical pollutant concentration, temperature data, and humidity data.

[0026] In this embodiment, considering that the temperature and humidity of the environment will affect the settlement of solid particulate matter in the environment and the growth rate of chemical bacteria, and traditional single-parameter PID control is prone to cause system oscillation, a temperature-humidity-pollutant joint regulation matrix is constructed, and the prediction error is mapped to the coordinated adjustment of multi-dimensional control variables through a fully connected network. This application simultaneously controls particulate matter, chemical pollutants, temperature, and humidity, which enables the system to fully cover the composite objectives of air purification and comfort adjustment. Adjusting the temperature, humidity, and pollutant treatment rate simultaneously can avoid system oscillation caused by single-parameter adjustment.

[0027] Among them, the data containing four dimensions means that the data can be an array formed by splicing 4-dimensional numerical values. For example, the variable control quantity is: Among them, represents the change in the output gas temperature, represents the change in the output gas humidity, represents the change in the physical particulate pollutant treatment rate, represents the change in the chemical pollutant treatment rate.

[0028] The real-time monitoring data of the outdoor environment is: Among them, represents the concentration of outdoor physical particulate pollutants, represents the concentration of outdoor chemical pollutants, represents the outdoor temperature data, represents the outdoor humidity data.

[0029] Similarly, the real-time monitoring data of the indoor environment and the forecast data of the outdoor environment can be represented in the same way as above.

[0030] In this embodiment, the concentration of physical particulate pollutants can refer to particulate matter such as physical dust, for example, PM2.5, PM10 concentration, etc., and chemical pollutants can refer to pollutants such as HCHO formaldehyde, total volatile organic compounds TVOCs, etc., which are common in newly renovated venues or cleaners using specific chemical substances, and can also refer to pollutants such as bacteria, viruses, and mold spores that are prone to grow in crowded and poorly ventilated situations. The air treatment system contains specific units or modules that can handle these specific pollutants.

[0031] When specific processing is required, the purification system will enable these processing modules to filter the air or perform corresponding levels of dehumidification / humidification to reduce the possibility of bacteria breeding in the air. Since the throughput rates of physical filtration and chemical filtration are adjustable, different throughputs correspond to different energy consumptions, different amounts of treatment agents used, and different consumption amounts of disposable filtration consumables. Therefore, precise adjustment will significantly help reduce the costs of system maintenance and use.

[0032] In a preferred embodiment, as Figure 4 shown, the environmental prediction and adjustment network includes an environmental prediction network and a control optimization network; The input of the environmental prediction network is the monitoring data and monitoring data , and the forecast data , and the output is the predicted value ; the environmental prediction network is composed of a long short-term memory network layer for capturing the temporal dependence relationship of the input data and an attention layer for obtaining data weighted information; The control optimization network is a fully connected network, and the input of the fully connected network is the predicted value and the target regulation value , and the output is the change control amount.

[0033] In the embodiments of the present application, in order to further improve the prediction accuracy and control stability, in this embodiment, through the designed joint neural network structure, the environmental prediction and control optimization are decoupled into two cooperative sub-networks, and the output of the environmental prediction network is the input of the control optimization network. Compared with a single network, the present application has higher prediction and control accuracy. Among them, the environmental prediction network combines a long short-term memory network and an attention mechanism, making the system more suitable for capturing temporal dependence relationships, such as the correlation between historical pollution changes and future forecasts, so as to obtain more accurate predictions. The control optimization network based on a fully connected network is suitable for quickly mapping prediction errors to control quantities to meet real-time requirements.

[0034] In a preferred embodiment, the method for obtaining the predicted value is as follows: Obtain the temporal dependence relationship obtained by the long short-term memory network layer: Based on the temporal dependence relationship, obtain the predicted value : Among them, represents the hidden state at time t, represents the cell state at time t, represents the hidden state at the previous measurement moment of time t represents the cell state at the previous measurement moment of time t represents obtaining the time-sequence dependence calculation is the output weight matrix is the attention weight matrix, and ⊙ represents element-wise multiplication () represents passing through the function to obtain the data weight at time t .

[0035] In the embodiment of the present application, the advantage of the above method is that this network construction method enables the system to simultaneously consider modeling short-term emergencies and periodic laws, and the combined attention mechanism can automatically enhance the influence of key time steps, thereby improving the system control accuracy.

[0036] In a preferred embodiment, the method for obtaining the change control amount is as follows: wherein, is the change control amount and are weight matrices and are bias terms is the activation function

[0037] In the embodiment of the present application, the fully connected network can convert the prediction error into a change in the control amount through non-linear mapping. The activation function is used to introduce non-linear expression ability, and for example, ReLU or Tanh can be selected. By restricting the output range, sudden changes in the control amount are avoided. The bias term is used to adjust the output reference, and the weight matrix is used to learn the mapping relationship from the prediction error to the control amount.

[0038] The activation function set in this embodiment restricts the change amplitude of the control amount, avoids frequent start and stop of the actuator, and also improves the control accuracy by directly minimizing the difference between the predicted value and the target value.

[0039] In a preferred embodiment, the prediction loss error of the environmental prediction adjustment network is: The training objective of the environmental prediction adjustment network is to minimize the value of the loss error .

[0040] In the embodiment of the present application, the output of the network is forced to approach the comfort interval set by the user through the loss error.

[0041] In a preferred embodiment, the system can query weather data every fixed query step and then make an adjustment to the system. However, researchers noticed in the simulation experiment that if a fixed query interval is adopted, when the environmental change rate is large, for example, the sudden high humidity and low temperature brought by a typhoon, or when the query step of the system is set improperly, the system may have overshoot or excessive adjustment, which may instead cause the environmental parameters to exceed the comfort zone value and result in energy waste. Therefore, preferably here, a dynamic step size is adopted: Let the current time be t. First, obtain the change rate of the outdoor environmental parameters within the most recent preset τ time windows , and construct a dynamic step size mapping function: where is the adjustment step size in the dynamic adjustment state, is the upper limit of the step size, is the lower limit of the step size. For example, the lower limit and the upper limit are set to 3 minutes and 20 minutes respectively, is the rate threshold determined through historical data, is the adjustment slope.

[0042] When the change rate exceeds the preset activation threshold, the above-mentioned dynamic adjustment mechanism is triggered. When the change rate returns within the activation threshold and does not exceed the activation threshold again within the buffer time , the system resumes to the default power-saving mode.

[0043] It can be understood that the change rate can refer to any one of the outdoor temperature and humidity change or the pollutant change rate. Based on the above method, the balance between energy consumption saving and smooth adjustment can be achieved.

[0044] As Figure 5 shown, in one embodiment, a control device for an air purification system is provided. The control device of the air purification system can be integrated into the above-mentioned computer device 120 and specifically can include: A basic data acquisition unit 510, configured to acquire real-time monitoring data of the outdoor environment , real-time monitoring data of the indoor environment and forecast data of the outdoor environment after k unit times ; A prediction adjustment unit 520, configured to acquire an environmental prediction adjustment network and use the monitoring data , monitoring data , forecast data and the target regulation value of the indoor environment after k unit times Input into the environmental prediction and adjustment network, and the output value of the environmental prediction and adjustment network is the change control amount; the change control amount is set to: make the predicted value of the indoor environmental data after k unit time and the target regulation value fit; The dynamic adjustment control unit 530 is configured to obtain the change control amount, and based on the change control amount, perform dynamic adjustment control on the real-time working state of the air purification system.

[0045] In the embodiments of the present application, the explanations and descriptions of the control device of the above air purification system can refer to the explanations and descriptions of the corresponding methods above. For the description of the control method of the above air purification system, please refer to the above, and details are not described herein again.

[0046] In the embodiments of the present application, the advantage of this device is that it can change the system parameters in advance before the external environment changes, and actively regulate and change the indoor environment in a predictive manner to adapt to future environmental changes. Moreover, this solution can directly direct the environmental state after system regulation to the preset comfort range, effectively avoid the overwork of modules such as air purification and temperature control, improve the overall energy efficiency ratio, and further reduce energy waste.

[0047] Figure 6 The internal structure diagram of a computer device in an embodiment is shown. The computer device can specifically be Figure 1 the computer device 120 therein. The computer device can be integrated inside the air purification device or be a part of the air purification device.

[0048] As Figure 6 shown, the computer device includes a processor, a memory, a network interface, an input device, and a display screen connected through a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and can also store a computer program. When the computer program is executed by the processor, the processor can implement the control method of the air purification system. The internal memory can also store a computer program. When the computer program is executed by the processor, the processor can execute the control method of the air purification system. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0049] Those skilled in the art can understand, Figure 6The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0050] In one embodiment, the control device of the air purification system provided by this application can be implemented in the form of a computer program, and the computer program can run on a computer device as shown in Figure 6 The memory of the computer device can store each program module that constitutes the control device of the air purification system. For example, Figure 5 the basic data acquisition unit 510, the prediction adjustment unit 520, and the dynamic adjustment control unit 530 shown in the figure. The computer program composed of each program module enables the processor to execute the steps in the control method of the air purification system in each embodiment of this application described in this specification.

[0051] For example, Figure 6 the computer device shown can execute step S10 through the basic data acquisition unit 510 in the control device of the air purification system as shown in Figure 5 the figure. The computer device can execute step S20 through the prediction adjustment unit 520. And so on.

[0052] In one embodiment, an air purification device is proposed. The air purification device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the processor executes the steps of the control method of the air purification system as described above.

[0053] In the embodiments of this application, for the description of the control method of the above air purification system, please refer to the above, and details will not be repeated here.

[0054] In the embodiments of this application, the prominent advantage of this device is that it can change the system parameters in advance before the external environment changes, and actively regulate and control the indoor environment in a predictive manner to adapt to future environmental changes. Moreover, this solution can make the environmental state after system regulation directly point to the preset comfort range, effectively avoid the overwork of modules such as air purification and temperature control, improve the overall energy efficiency ratio, and further reduce energy waste.

[0055] In one embodiment, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor, the processor executes the steps of the control method of the air purification system as described above.

[0056] In the embodiments of the present application, for the description of the control method of the above air purification system, please refer to the above text and will not be elaborated here.

[0057] In the embodiments of the present application, the program running based on the method stored in the storage medium of the embodiments of the present application has the prominent advantage that it can change the system parameters in advance before the external environment changes, and actively regulate and control the indoor environment in a predictive manner to adapt to future environmental changes. Moreover, this solution can make the environmental state after system regulation directly point to the preset comfort range, effectively avoid the overwork of modules such as air purification and temperature control, improve the overall energy efficiency ratio, and further reduce energy waste.

[0058] It should be understood that although the steps in the flowcharts of the embodiments of the present application are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0059] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0060] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0061] The above-described embodiments only represent several implementation manners of the present application, and the description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A control method for an air purification system, characterized in that The method includes: Obtain real-time monitoring data of the outdoor environment , real-time monitoring data of the indoor environment and forecast data of the outdoor environment after k unit time intervals ; Obtain an environmental prediction and adjustment network, and input the monitoring data , the monitoring data , the forecast data and the target regulation value of the indoor environment after k unit time intervals into the environmental prediction and adjustment network, and the output value of the environmental prediction and adjustment network is the change control amount; the change control amount is set to: make the predicted value of the indoor environmental data after k unit time intervals fit the target regulation value . Obtaining a change control quantity, and based on the change control quantity, dynamically adjusting and controlling the real-time working state of the air purification system.

2. The control method of an air purification system according to claim 1, characterized in that, The obtained real-time monitoring data of the outdoor environment, real-time monitoring data of the indoor environment, forecast data of the outdoor environment, and the change control quantity all include data in four dimensions: Concentration of physical particulate pollutants, concentration of chemical pollutants, temperature data, and humidity data.

3. The control method of an air purification system according to claim 1, characterized in that The environmental prediction and adjustment network includes an environmental prediction network and a control optimization network; The input of the environmental prediction network is the monitoring data , monitoring data , forecast data , and the output is the predicted value ; the environmental prediction network is composed of a long short-term memory network layer for capturing the temporal dependence of input data and an attention layer for obtaining data weighted information; The control optimization network is a fully connected network, and the input of the fully connected network is the predicted value and the target regulation value , and the output is the change control amount.

4. The control method of an air purification system according to claim 3, wherein The predicted value is obtained by the following method: Obtaining the time series dependence relationship through the long short-term memory network layer: Obtain a predicted value based on the timing dependency relationship : Among them, represents the hidden state at time t, represents the cell state at time t, represents the hidden state at the previous measurement time of time t, represents the cell state at the previous measurement time of time t, represents obtaining sequential dependence calculation, is the output weight matrix, is the attention weight matrix, and ⊙ is element-wise multiplication, () represents passing through the function to obtain the data weight at time t .

5. The control method of an air purification system according to claim 3, characterized in that, The method for obtaining the change control quantity is: Among them, is the change control quantity, and is the weight matrix, and is the bias term, is the activation function.

6. The control method of an air purification system according to claim 1, characterized in that, The prediction loss error of the environmental prediction adjustment network is as follows: The training objective of the environmental prediction adjustment network is to minimize the loss error value.

7. A control device for an air purification system, characterized in that, The control device of the air purification system includes: A basic data acquisition unit for acquiring real-time monitoring data of the outdoor environment , real-time monitoring data of the indoor environment and forecast data of the outdoor environment after k unit time ; A prediction adjustment unit, configured to obtain an environmental prediction adjustment network and input the monitoring data , the monitoring data , the forecast data , and the target regulation value of the indoor environment after k unit time intervals into the environmental prediction adjustment network, and the output value of the environmental prediction adjustment network is a change control amount; the change control amount is set to: make the predicted value of the indoor environmental data after k unit time intervals fit the target regulation value . A dynamic adjustment and control unit, configured to obtain a change control quantity, and based on the change control quantity, dynamically adjust and control the real-time working state of the air purification system.

8. A computer-readable storage medium, characterized in that, A computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the processor is caused to execute the steps of the control method of the air purification system according to any one of claims 1 to 6.

9. An air purification device, characterized in that, It includes a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the processor is caused to execute the steps of the control method of the air purification system according to any one of claims 1 to 6.

Images