Control method, system and equipment for air treatment equipment and storage medium

Abstract

The embodiment of the invention provides a control method, system and equipment for air treatment equipment and a storage medium. The method comprises the steps that according to detection data of a sensor in the air treatment equipment, a target air treatment model corresponding to the air treatment equipment is determined; wherein the detection data comprises an inlet air state of the air treatment equipment; on the basis of the air inlet state and the set air outlet state requirement, path searching and optimizing are conducted in the air enthalpy and humidity diagram through the target air treatment model and an optimization algorithm, and an energy-saving air treatment path is obtained; and according to the energy-saving air treatment path, multiple functional sections in the air treatment equipment are controlled, so that the air outlet state of the air treatment equipment is changed to the air state at the end point of the energy-saving air treatment path. According to the control method provided by the embodiment of the invention, the system oscillation and stabilization time of the air treatment equipment can be shortened, so that the energy consumption is reduced.

Description

Technical Field

[0001] This application relates to the technical field of temperature and humidity control, and particularly to a control method, system, device and storage medium for air handling equipment. Background Art

[0002] Air handling equipment is an indispensable part of some industrial production environments, mainly used to control the temperature and humidity of the processing workshop by treating the air. Taking the production of battery cells as an example, a large number of dehumidifiers (a type of air handling equipment) will be arranged in the workshop. By treating the air in the workshop with the dehumidifiers, the temperature and humidity in the workshop can meet the requirements of the battery cell production for the environmental temperature and humidity. During the production process of battery cells, some production processes have high requirements for the temperature and humidity of the workshop. Regardless of the state of the external environment in each season of spring, summer, autumn and winter, the workshop is basically controlled at a certain fixed value point, and a large amount of energy (electricity, gas, hot water, steam, water, etc.) is consumed in each season to control at the fixed point. Constant temperature and humidity are important conditions to ensure the quality of battery cells. Therefore, the allowable window of temperature and humidity specified by battery cell manufacturers is generally small. When in different seasons, it takes a long time to debug and adapt the temperature and humidity of the dehumidifiers in the battery cell workshop, which means more energy consumption and waste. Therefore, it is very important to be able to adapt to different working conditions and quickly and stably make the temperature and humidity reach the steady state. Summary of the Invention

[0003] This application provides a control method for air handling equipment, a control method for dehumidifiers, a system, a device and a storage medium through multiple embodiments to solve the problems that the temperature and humidity debugging of air handling equipment such as dehumidifiers takes a long time to reach the steady state and consumes a large amount of energy.

[0004] Then, in the first embodiment of this application, a control method for air handling equipment is provided. The control method includes:

[0005] Determine the target air handling model corresponding to the air handling equipment according to the detection data of the sensors in the air handling equipment; wherein, the detection data includes the inlet air state of the air handling equipment;

[0006] Based on the inlet air state and the set outlet air state requirements, perform path search and optimization in the air enthalpy-humidity diagram through the target air handling model and the optimization algorithm to obtain an energy-saving air handling path;

[0007] Control multiple functional segments in the air handling equipment according to the energy-saving air handling path, so that the outlet air state of the air handling equipment changes to the air state at the end point of the energy-saving air handling path.

[0008] In the second embodiment of this application, a control method for a dehumidifier is provided. The control method includes:

[0009] Based on the detection data of the sensors in the dehumidifier, determine the target air treatment model corresponding to the dehumidifier; wherein, the detection data includes the inlet air state of the dehumidifier.

[0010] Based on the inlet air state of the dehumidifier and the set outlet air state requirements, perform path search and optimization in the air enthalpy-humidity diagram through the target air treatment model and the optimization algorithm to obtain an energy-saving air treatment path.

[0011] According to the energy-saving air treatment path, control multiple functional segments in the dehumidifier so that the outlet air state of the dehumidifier is the air state at the end point of the most node air treatment path.

[0012] In the third embodiment of this application, a control system is provided, including:

[0013] An air treatment device, including multiple functional segments and sensors;

[0014] A control device, configured to obtain the detection data of the sensors in the air treatment device; wherein, the detection data includes the inlet air state of the air treatment device; based on the detection data, determine the target air treatment model corresponding to the air treatment device; based on the inlet air state and the set outlet air state requirements, perform path search and optimization in the air enthalpy-humidity diagram through the air treatment model and the optimization algorithm to obtain an energy-saving air treatment path; according to the energy-saving air treatment path, control the multiple functional segments so that the outlet air state of the air treatment device is the air state at the end point of the energy-saving air treatment path.

[0015] In the fourth embodiment of this application, an electronic device is provided. The electronic device includes: a memory and a processor. Among them, the memory is used to store a program; the processor is coupled to the memory and is configured to execute the program stored in the memory to implement the steps in the control method provided in each embodiment of this application above.

[0016] In the fifth embodiment of this application, a computer-readable storage medium is provided. A computer program is stored in the computer-readable storage medium; when the computer program is executed by the computer, it can implement the steps in the control method provided in each embodiment of this application above.

[0017] In the technical solution provided by the embodiment of the present application, first, according to the detection data of the sensors in the air treatment device (such as a dehumidifier) (including the inlet air state of the air treatment device), the target air treatment model corresponding to the air treatment device is determined; then, based on the inlet air state and the set outlet air state requirements, through the target air treatment model (a machine learning model) and an optimization algorithm, path search and optimization are performed in the air enthalpy-humidity diagram to obtain an energy-saving air treatment path. Generally, the total path length of the energy-saving air treatment path obtained through optimization is the shortest compared to other paths. The shortest total path length means that when controlling multiple functional segments in the air treatment device according to this energy-saving air treatment path, the corresponding control process is simple. The simplification of the control process enables, under the same conditions (such as the same inlet air state), the outlet air state of the air treatment device to be adjusted and changed to the desired stable air state in a shorter time. This desired stable air state is the air state at the end point of the energy-saving air treatment path. From the above analysis, it can be seen that adopting the solution of the present application can shorten the system stabilization time of the air treatment device, and the length of the stabilization time is related to energy consumption, so energy consumption can be reduced. Taking the battery cell workshop as an example, generally, only after the dehumidifier starts and reaches a stable state can the production of battery cells begin. Therefore, shortening the system stabilization time of the dehumidifier can reduce energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 It is an example diagram of the combined structure of the dehumidifier provided by an embodiment of the present application;

[0020] Figure 2a and Figure 2b It is the air enthalpy-humidity diagram provided by the embodiment of the present application;

[0021] Figure 3 It is an example diagram of setting the air state range provided by an embodiment of the present application;

[0022] Figure 4 It is the schematic diagram of the enthalpy-humidity control principle provided by an embodiment of the present application;

[0023] Figure 5 It is the schematic flow diagram of the control method provided by an embodiment of the present application;

[0024] Figure 6An exemplary diagram of an air treatment path provided by an embodiment of the present application;

[0025] Figure 7 An exemplary diagram of the regional division of the psychrometric chart provided by an embodiment of the present application;

[0026] Figure 8 An exemplary diagram of the comparison result of temperature and humidity control provided by an embodiment of the present application;

[0027] Figure 9 A schematic flowchart of a control method provided by another embodiment of the present application;

[0028] Figure 10 A structural block diagram of a control system provided by an embodiment of the present application;

[0029] Figure 11 A structural block diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0030] Cell manufacturing is the core process in the lithium battery industry. During the production process, high requirements are imposed on environmental parameters such as temperature and humidity (i.e., temperature and humidity) and cleanliness in the workshop. For some production processes, the humidity requirement can even reach -45°C dew point, that is, the air contains almost no moisture. For example, the production processes of cells mainly include the following processes: raw material preparation, positive and negative electrode paste mixing, coating, drying, and winding. The general relative humidity requirement for the front processes represented by mixing / coating is 10% - 40%, while the temperature requirement for the coating drying process is as low as -45°C dew point. The quality fluctuation of cell production is mainly disturbed by the external environment, mainly affected by the changes in outdoor temperature, sunlight, and air moisture content. If the environment gets out of control, it may cause the cell materials to be affected by moisture and fail, thus directly affecting the cell quality. To ensure the quality of cell production, a large number of dehumidifiers are arranged in the cell production workshop. By treating the air with dehumidifiers, the temperature and humidity in the workshop are controlled to meet certain temperature and humidity requirements. Specifically, regardless of the external environment in each season of spring, summer, autumn, and winter, the temperature and humidity in the workshop are basically fixed and controlled at a certain value point through dehumidifiers, and a large amount of energy (electricity, gas, hot water, steam, water, etc.) is consumed in each season to control at the fixed point. Constant temperature and humidity are important conditions to ensure the quality of cells. Therefore, the allowable window of temperature and humidity specified by cell manufacturers is generally small. Due to the large space and high temperature and humidity requirements in the cell workshop, the overall energy consumption of the dehumidifiers in the cell workshop accounts for more than 40% of the production energy consumption of the cell workshop. It can be seen that the energy consumption of dehumidifiers is an important part affecting the production energy consumption of cells.

[0031] Traditional temperature and humidity control mainly relies on PID (Proportion Integration Differentiation) regulation. For a system like a dehumidifier with large lag, multiple variations, and multiple couplings, the control effect of this method highly depends on the experience of the debugging personnel. Moreover, the control switching during seasonal changes in the system is rather cumbersome, easily causing excessive system fluctuations and affecting the quality of the battery cells. The traditional control methods usually have a relatively long debugging cycle, require a long time for debugging and adaptation to different seasons, and the stabilization time within the control system is also long. As a major energy consumer in the battery cell workshop, the dehumidifier system consumes a large amount of steam, cold water, hot water, etc. A long debugging time means more energy consumption and waste. Therefore, it is very important to be able to adapt to different working conditions and quickly and stably bring the temperature and humidity to a steady state. Effectively improving the working efficiency of the dehumidifier, reducing the idling time of the dehumidifier, etc., to quickly and stably bring the temperature and humidity to a steady state can bring obvious economic benefits to battery cell manufacturers, especially in terms of energy.

[0032] It should be noted that the different working conditions (multiple working conditions) described in the application refer to different external environments. Specifically, it refers to the changes in air temperature and humidity caused by seasonal changes.

[0033] In response to the above problems, the basic design idea of this application for realizing the temperature and humidity control in the battery cell workshop is as follows: Use the psychrometric chart to characterize the relationship between air temperature and humidity in different seasons, and based on this, propose a multi-condition zoning control strategy; in addition, under different working conditions, based on the HVAC process, establish an HVAC optimization model for the temperature and humidity set values in different working condition zones (working areas) (that is, establish a temperature and humidity influence model under different working conditions), and establish a prediction model (that is, a control model) corresponding to each functional section of the dehumidifier. Thus, use the above models to determine the control quantities of each functional section under different working conditions, and send the control quantities to the actuators corresponding to the respective functional sections to complete the control of the dehumidifier and achieve the adjustment of the temperature and humidity in the battery cell workshop. Among them, the actuator corresponding to the functional section is, for example, an MPC (Model Predictive Control, an advanced control technology) execution controller.

[0034] Based on the above basic design idea, this application provides a control method for air handling equipment, a control method for a dehumidifier, a system, an electronic device, and a computer-readable storage medium.

[0035] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of this application.

[0036] In addition, in some processes described in the specification, claims, and the above-mentioned accompanying drawings of this application, there are multiple operations that appear in a specific order. These operations may not be executed in the order in which they appear in this text or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any processing order. Additionally, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first", "second", etc. in this text are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types. And the term "or / and" in this application is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A or / and B means that A can exist alone, A and B can exist simultaneously, and B can exist alone. The character " / " in this application generally represents an "or" relationship between the preceding and following associated objects. It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a commodity or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such a commodity or system. Without further limitations, the element defined by the statement "including one..." does not exclude the existence of additional identical elements in the commodity or system including the said element. In addition, the following embodiments are only a part of the embodiments of this application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of this application.

[0037] Before introducing the technical solutions provided by this application, take a dehumidifier as an example to roughly introduce the control process of the solution of this application. Specifically, the general control process of the solution of this application is as follows:

[0038] 1) Send the ambient temperature and humidity data of the dehumidifier system (i.e., the inlet air temperature and humidity data of the dehumidifier) to a certain industrial brain intelligent manufacturing platform (AICS). Use the data learning and training platform established on the AICS in advance to analyze and process the ambient temperature and humidity data to establish a heating, ventilation, and air conditioning (HVAC) optimization model (i.e., a temperature and humidity impact model, which is called an air handling model when describing the method embodiments provided in this application below).

[0039] Among them, when establishing the HVAC optimization model, other data of the dehumidifier can also be combined, such as the medium flow rate information, temperature information (such as supply temperature, return temperature) of the medium used to process air in each functional section, and the outlet air temperature and humidity of the dehumidifier. All the data used when establishing the above HVAC optimization model can be detected by sensors arranged in the dehumidifier. Thus, the HVAC optimization model can be established by analyzing and processing the detection data of the sensors in the dehumidifier.

[0040] Specifically, the modeling process is as follows:

[0041] (a) Before modeling, first preprocess various detection data of the sensors (such as data cleaning, data conversion (such as normalization / standardization), etc.), and then use the preprocessed detection data to train an initial HVAC model established based on HVAC technology (which is a data learning model (i.e., a machine learning model)) to obtain the HVAC optimization model;

[0042] (b) After the HVAC optimization model is established, it will periodically correct and update the established HVAC optimization model according to the real-time detection data of the sensors.

[0043] 2) Based on the HVAC optimization model and combined with the corresponding optimization algorithm, realize the search for the shortest air handling path. Among them, the search is carried out starting from the inlet air temperature and humidity of the dehumidifier as the search starting point and with the set outlet air temperature and humidity requirements (such as the set outlet air temperature and humidity range) as the search end point, in combination with the psychrometric chart; the shortest air handling path obtained through the search is the most energy-efficient air handling path (i.e., the energy-saving air handling path described in the method embodiments below), and the end point of the shortest air handling path corresponds to the most energy-efficient outlet air temperature and humidity control point;

[0044] 3) Establish a control model for each functional section in the dehumidifier. Based on the control model and using the actuator corresponding to the functional section, implement the control of the dehumidifier according to the shortest air handling path obtained in step 2) above.

[0045] Among the above, a dehumidifier is also known as a moisture extractor, a dryer, etc. It is generally divided into two categories: household dehumidifiers and industrial dehumidifiers, and belongs to a part of the air-conditioning family. The dehumidifier described in this application is an industrial dehumidifier, which usually includes: an air inlet of the machine body, an air outlet of the machine body, and a plurality of functional sections located between the air inlet of the machine body and the air outlet of the machine body; among them, the functional section can be specifically referred to as an air treatment functional section. The plurality of functional sections may include: a preheating section, a surface cooling section, a heating section, a humidifying section, and so on. In different dehumidifiers, due to different process requirements for treating air, the combination method and combination order of the functional sections often vary. For example: in a dehumidifier, between the air inlet of the machine body and the air outlet of the machine body, from front to back in sequence are: a preheating section, a surface cooling section, a heating section, a humidifying section; in another dehumidifier, between the air inlet of the machine body and the air outlet of the machine body, from front to back in sequence are: a preheating section, a humidifying section, a surface cooling section, a heating section. Each functional section can only achieve one air treatment method, for example: one of heating, surface cooling, and humidifying.

[0046] Figure 1 It is an example diagram of the combined structure of a dehumidifier given in this application.

[0047] Figure 2a and Figure 2b It shows the psychrometric chart provided by an embodiment of this application. The psychrometric chart, which can be simply referred to as the h-d chart, represents the relationship between various parameters of moist air with line graphs and is often applied in the field of industrial air-conditioning temperature and humidity control. It includes a moist air system with a certain mass of dry air and may also have changes in steam content. It has one more degree of freedom for state change than a simple compressible system. Therefore, the state of moist air is determined by 3 independent parameters. There are only 2 independent parameters for the state point on the plane graph. So the humidity chart is often made with 2 independent parameters selected as coordinates under a certain total pressure (generally standard atmospheric pressure). The isopleths in the psychrometric chart include: constant enthalpy lines, constant humidity lines, constant relative humidity lines, and constant temperature lines. Constant enthalpy lines: The enthalpy value H on the line is the same, and its parallel lines are also constant enthalpy lines. For the same enthalpy value, as the air temperature rises, the moisture content decreases. Constant humidity lines: The humidity on the line is the same, and its parallel lines are also constant humidity lines. For the same moisture content, the lower the air temperature, the lower the enthalpy value (energy). Constant relative humidity lines: The relative humidity RH on the line is the same, and its parallel lines are also constant relative humidity lines. For the same relative humidity, the higher the air temperature, the higher the enthalpy value (energy). Constant temperature lines: The temperature on the line is the same, and its parallel lines are also constant temperature lines. For the same temperature, the greater the moisture content of the air, the greater the relative humidity and the enthalpy value.

[0048] For example: a certain battery cell workshop requires a temperature of 21 - 24 °C and a relative humidity of 10 - 20%. Draw the air state region (or range) enclosed by two isothermal lines and two constant relative humidity lines on the psychrometric chart, such as Figure 3As shown by the dashed line, it can be found that it is close to a quadrilateral, which is composed of four boundary points. That is to say, as long as the air state entering the battery cell workshop is within this range, the temperature and humidity conditions of the battery cell production process can be guaranteed.

[0049] Figure 4 This is the enthalpy-humidity control principle of different functional segments provided by an embodiment of the present application. As Figure 4 shown, the different functional segments (heating, surface cooling and humidification) of the dehumidifier have different enthalpy-humidity control principles as follows:

[0050] (1) Heating process:

[0051] In the air enthalpy-humidity diagram, during the heating process, the air temperature rises, the enthalpy value rises, the relative humidity decreases, and the moisture content remains unchanged, that is, Figure 4 the process from A to B in

[0052] (2) Surface cooling process:

[0053] In the air enthalpy-humidity diagram, within a certain range, during the surface cooling process, the air temperature decreases, the enthalpy value decreases, the relative humidity increases, and the moisture content remains unchanged, that is, Figure 4 the process from A to B1 in

[0054] When the surface cooling reaches the dew point temperature of the current temperature, from B1 to C1, the relative humidity reaches 100%. If cooling continues, liquid water will be precipitated. At this time, the relative humidity continues to maintain 100%, the temperature decreases, the enthalpy value decreases, and the moisture content decreases, that is, Figure 4 the process from C1 to D1 in

[0055] (3) Humidification process:

[0056] In the air enthalpy-humidity diagram, during the humidification process, the air temperature decreases, the enthalpy value remains unchanged, the relative humidity increases, and the moisture content increases, that is, Figure 4 the process from A to B2 in

[0057] When continuous humidification is carried out, that is, Figure 4 the process from B2 to C2 in

[0058] The method embodiments provided by the present application will be introduced in detail below. The execution subject of each method provided below can be a client or a server. Among them, the client can be a hardware with an embedded program integrated on the terminal, an application software installed in the terminal, or a tool software embedded in the terminal operating system, etc. The embodiments of the present application do not make any limitations in this regard. The terminal can be any terminal device including a mobile phone, a tablet computer, an air-conditioning control device, etc. Among them, the server can be a common server, a cloud, a virtual server, etc. The embodiments of the present application do not make specific limitations in this regard.

[0059] Figure 5 The flowchart of the control method for an air handling device provided by an embodiment of the present application is shown. The air handling device includes: a plurality of functional sections located between the device air inlet and the device air outlet of the air handling device. Among them, the air handling device is an air conditioner, specifically, it can be a dehumidifier, and the dehumidifier is an industrial dehumidifier. For the detailed description of the structure and corresponding functions of the air handling device, reference can be made to the relevant content of the dehumidifier described in other embodiments above.

[0060] As Figure 5 shown, the control method for the air handling device includes the following steps:

[0061] 101. Determine the target air handling model corresponding to the air handling device according to the detection data of the sensors in the air handling device; wherein, the detection data includes the inlet air state of the air handling device.

[0062] 102. Based on the inlet air state and the set outlet air state requirements, perform path search and optimization in the air enthalpy-humidity diagram through the target air handling model and the optimization algorithm to obtain an energy-saving air handling path.

[0063] 103. Control the plurality of functional sections in the air handling device according to the energy-saving air handling path, so that the outlet air state of the air handling device changes to the air state at the end point of the energy-saving air handling path.

[0064] In practical applications, various sensors such as air state sensors (e.g., air temperature and humidity sensors) and medium state sensors (e.g., medium flow sensors, medium temperature sensors) can be arranged in air treatment equipment to detect corresponding data. The above-mentioned air state sensors can be arranged at the equipment air inlet and outlet of the air treatment equipment, as well as at the entrances and exits of each functional section in the air treatment equipment. The medium state sensors can be arranged in each functional section to detect the medium state information (such as flow information, temperature information) of the medium used to treat air in the corresponding functional section. Among them, the medium used by the functional section to treat air can be water or a mixed medium of ethylene glycol and water, etc. For example, if the functional section is a chilled water coil section, the medium used by the chilled water coil section to treat air can be a mixed medium of ethylene glycol and water.

[0065] Based on the above, in the above 101, the detected data may include but is not limited to: the inlet air state of the air treatment equipment (i.e., the air state at the equipment air inlet) and the outlet air state (i.e., the air state at the equipment air outlet), and the operating parameters of each of the multiple functional sections in the air treatment equipment; among them, the operating parameters include: the air state at the entrance and the air state at the exit of the functional section, and the medium state information of the medium used by the functional section to treat air (such as hot water flow, hot water supply temperature, hot water return temperature, cold water flow, cold water supply temperature, cold water return temperature, steam temperature, etc.). Among them, the multiple functional sections are connected in sequence, and the outlet of the previous functional section is also the inlet of the next functional section. Thus, the air state at the outlet of the previous functional section is also the air state at the inlet of the next functional section; the air state at each part of the air treatment equipment can be air temperature and humidity. The sensors in the air treatment equipment can collect data according to their sampling periods (sampling times) to obtain corresponding detected data. For example, the sampling period can be 2 seconds, 5 seconds, etc., and no specific limitation is made here. Using the detected data collected by the sensors in the current period, the previously established air treatment model can be corrected and updated, and the corrected and updated air treatment model can be determined as the target air treatment model corresponding to the air treatment equipment currently. Thus, in one implementable technical solution, the above 101 "determine the target air treatment model corresponding to the air treatment equipment according to the detected data of the sensors in the air treatment equipment" can specifically include:

[0066] 1011. Periodically obtain the detected data of the sensors in the air treatment equipment;

[0067] 1012. Use the detected data obtained in the current period to correct and update the previously established air treatment model to obtain the corrected and updated air treatment model;

[0068] 1013. Determine the corrected and updated air treatment model as the target air treatment model.

[0069] In specific implementation, the above-mentioned pre-established air treatment model can be obtained by training an initial HVAC model constructed based on HVAC technology using the detection data obtained in the historical period. The initial HVAC model can be a machine learning model, and the machine learning model can be, but is not limited to, a deep learning model. Before model training, the detection data can be preprocessed first to improve the quality and usability of the data and prepare for subsequent model training. Based on this, the above-mentioned pre-established air treatment model can be obtained by training a machine learning model. Training the machine learning model includes the following steps:

[0070] S11. Preprocess the detection data obtained in the historical period to obtain the preprocessed detection data;

[0071] S12. Use the preprocessed detection data as training data to train the machine learning model;

[0072] Among them, the preprocessing includes, but is not limited to, at least one of the following: data cleaning, data transformation. Data cleaning includes: handling missing values, identifying and handling outliers. For example, when handling missing values, they can be filled with the mean, median, mode, or the missing values can be predicted using a model, or simply delete the rows / columns containing missing values, and so on. When identifying and handling outliers, statistical methods (such as IQR (data dispersion degree)) can be used to identify outliers and determine whether to correct, delete, or retain them. Data transformation includes: data standardization ( / normalization). By data standardization, the data value features of the detection data can be scaled to a standard range, such as within the range of [0, 1] or with unit variance.

[0073] The training data used for training the machine learning model includes training samples and corresponding training labels. After preprocessing, the inlet air state (such as inlet air temperature and humidity) included in the preprocessed detection data, and the medium state information (medium supply temperature, medium return temperature, medium flow rate) of the medium used to process air in each functional section (such as heating section, surface cooling section, humidifying section) can be used as training samples, and the corresponding outlet air state (such as outlet air temperature and humidity, also known as supply air temperature and humidity) in the detection data can be used as training labels. Then, the machine learning model is trained using the training samples and the training labels corresponding to the training samples to optimize the model parameters in the machine learning model.

[0074] In the above 102, setting the air state requirement refers to the requirement set for the air state of the air outlet of the air treatment equipment, that is, the air state requirement of the workshop set to meet the production process requirements of a certain product (such as a battery cell). The setting of the air state requirement includes: setting the air state value or setting the air state range. In this embodiment, preferably, the setting of the air state requirement includes setting the air state range, and the setting of the air state range includes the temperature range and the humidity range. Refer to Figure 6 a nearly quadrilateral area composed of four points A, B, C, and D shown in

[0075] Taking the air state of the air inlet of the air treatment equipment as the search starting point and setting the air state requirement of the air outlet as the search end point, based on the principle of minimum energy consumption, the determined target air treatment model can be used and the corresponding optimization algorithm can be adopted to search for the optimal path in the air enthalpy-humidity diagram, so as to search for the shortest air treatment path through optimization. This shortest air treatment path is the energy-saving air treatment path. Correspondingly, the air state at the end point of the energy-saving air treatment path is the energy-saving air outlet air state value (i.e., the most energy-saving point).

[0076] The above optimization algorithm can be the gray wolf optimization algorithm, the particle swarm optimization algorithm, the whale optimization algorithm, the ant colony optimization algorithm, the genetic algorithm, etc., which are not limited here. After inputting the air inlet air state and the set air outlet state requirement into the target air treatment module, taking the air enthalpy-humidity diagram as the path optimization space, the optimization algorithm can be used to perform path optimization iteration and solution on the target air treatment model, and when the iteration termination condition is reached, the iteration stops. The path solution obtained when the iteration stops is the optimal air treatment path (the air treatment path with the shortest total path length, simply referred to as the shortest air treatment path), and this optimal air treatment path is the finally obtained energy-saving air treatment path.

[0077] Specifically, the above path optimization iteration and solution process is roughly as follows:

[0078] Step 1: Take the air inlet air state as the starting point of the path solution and the set air outlet air state requirement as the end point requirement of the path solution;

[0079] Step 2: Set the first path solution S1 (as the initial path solution) and set the iteration parameters;

[0080] Step 3: Randomly generate the second path solution S2;

[0081] Step 4: According to the total path length of the first path solution S1 and the total path length of the second path solution S2, select the path solution with the shorter total path length from the first path solution S1 and the second path solution S2 as the preferred path solution S0;

[0082] Step 5: Update the iteration parameter, and determine whether the iteration termination requirement is met according to the updated iteration parameter;

[0083] Step 6: When the iteration termination requirement is not met, randomly generate a second path solution S2 again, and select the path with a shorter total path length between the total path length of the regenerated second path solution S2 and the total path length of the optimal path solution S0 to update the optimal path solution S0;

[0084] Step 7: When the iteration termination requirement is met, output the optimal path solution; where the output optimal path solution is the energy-saving air treatment path.

[0085] When using different optimization algorithms to perform path optimization iterative solution on the target air treatment model, the specific implementation of the iterative solution process of the above steps 1 to 7 will be different.

[0086] Taking the genetic algorithm as an example of the optimization algorithm, the above iteration parameter can be the preset maximum number of iterations, and each time the iteration parameter is updated, it is decremented by one. When the updated iteration parameter is less than or equal to the set threshold (such as zero), the iteration termination requirement is met. When the updated iteration parameter is greater than the set threshold, the iteration termination requirement is not met. Specifically, if the preferred algorithm is the genetic algorithm, the specific implementation process of the above steps 1 to 7 can be simply described as follows:

[0087] A11: Set the initial constraint conditions of the air treatment path, that is, the relevant parameters of the genetic algorithm: Let the starting point of the path be the coordinates corresponding to the incoming air state in the air enthalpy-humidity diagram (such as Figure 6 the coordinates of point M shown in the figure), the ending point of the path be any coordinate within the coordinate range corresponding to the set outgoing air state requirement in the air enthalpy-humidity diagram, take the preset maximum number of iterations as the initial iteration parameter, and network the air enthalpy-humidity diagram so that each grid is a gene of the genetic algorithm to represent the path through gene combination, as well as the initial population of the genetic algorithm (which can be understood as the initial path solution), coding length, crossover probability, crossover constant, mutation probability, mutation constant, etc.;

[0088] A22: Define a fitness function to evaluate the quality of each individual (path). This fitness function can be defined according to actual needs, such as path length, time, etc. In this embodiment, it is defined according to the path length. For example, after randomly generating a second path solution S2 through gene combination, the defined fitness function can be used to evaluate which of the second path solution S2 and the set first path solution S1 has a better path (that is, a shorter total path length), and thus according to this evaluation result, the path solution with a better path can be used as the optimal path solution.

[0089] Iterate the population through genetic operations such as selection, crossover, and mutation. Each iteration generates a new population (i.e., generates a new path solution), and then evaluate the new population. After each iteration, decrement the iteration parameter by one until the iteration termination condition is met (e.g., the iteration parameter is zero), and end the path search optimization. The path solution output at the end is the optimal path solution, that is, the energy-saving air treatment path with the shortest total path length.

[0090] For the energy-saving air treatment path obtained through the above step 102, refer to Figure 6 the path M→O→P→C shown in

[0091] Combined with Figure 6 , taking the battery cell workshop as an example, traditionally, different outlet air state values (such as the S point shown in Figure 6 ) are set for the workshop in different seasons. Regardless of the ambient temperature and humidity, it will be fixed at the set outlet air state value, and then the outlet air state of the dehumidifier is adjusted to the set outlet air state value. In the above mode, although the output temperature and humidity of the dehumidifier can be kept stable at a certain set value all the time, it ignores the impact of energy consumption; moreover, the state of the external environment is not applied in real time, and there is often over-regulation, and a lot of energy needs to be wasted to reach the expected set value. In this application, an effective connection is established between the temperature and humidity values output by the dehumidifier and the ambient temperature and humidity. The temperature and humidity output by the dehumidifier are no longer fixed set values, but the most energy-saving point (such as the C point shown in Figure 6 ) is matched within the set air state range by detecting the ambient temperature and humidity in real time. The parameter setting is improved from a constant value to automatically match the most energy-saving point within the process control range (which refers to the temperature and humidity fluctuation range that does not affect the quality of the battery cells, that is, the set air state range), and the temperature and humidity control mode is as shown in Figure 6 . For example, refer to Figure 6 , assuming that the external environment (the external air state, which is the inlet air state of the dehumidifier) is at point M. If the single set value S point is adopted, then the most ideal control process is M→O→P→Q→S; if the process range (or process control range) is adopted, according to the solution provided in the embodiment of this application, the current most energy-saving set value can be identified in real time as point C, and the most ideal control process (i.e., the energy-saving air treatment path) is M→O→P→C, where the enthalpy difference between P→Q is the saved refrigeration energy consumption; the enthalpy difference between Q→S and P→C is the saved heating energy consumption.

[0092] Therefore, in order to reduce the energy consumption of the dehumidifier, the above air state requirements can specifically be the set air state range, for example: temperature 21~24℃, relative humidity 10~20%.

[0093] Further, based on the energy-saving air treatment path obtained above, it is possible to determine the target functional segments that need to be used. Then, in combination with the control models of each functional segment established in advance, the control quantities of the target functional segments can be determined, and thus the control quantities are sent to the actuators of the target functional segments to achieve the control of the target functional segments. Therefore, in one feasible solution, the above "controlling the multiple functional segments according to the energy-saving air treatment path" in 103 may include:

[0094] 1031. According to the energy-saving air treatment path, determine at least one target functional segment that needs to be used among the multiple functional segments and the control quantities of each functional segment;

[0095] 1032. Control each target functional segment according to the control quantities of each target functional segment.

[0096] In this embodiment, based on the set air state range described above, the air enthalpy-humidity diagram is divided into multiple state regions (i.e., multi-condition zoning of the air enthalpy-humidity diagram), and each air state region corresponds to a corresponding air treatment strategy. The air treatment strategy includes at least one air treatment method (such as heating, surface cooling), and one air treatment method corresponds to one functional segment. For example, the heating air treatment method is implemented by the heating functional segment, that is, the heating treatment method corresponds to the heating functional segment. Therefore, when determining the target functional segments that need to be used, it can be determined based on the air treatment strategy corresponding to the air state region to which the energy-saving air treatment path belongs (specifically, the air treatment methods included in the air treatment strategy).

[0097] That is, in a specific implementation technical solution, the above 1031 "determine at least one target functional segment that needs to be used among the multiple functional segments according to the energy-saving air treatment path" can be implemented by the following steps:

[0098] 10311. Determine the air state region to which the energy-saving air treatment path belongs;

[0099] 10312. According to the air treatment strategy corresponding to the air state region to which the energy-saving air treatment path belongs, determine at least one target functional segment that needs to be used;

[0100] Among them, the air state region to which the energy-saving air treatment path belongs is one of the multiple air state regions included in the air enthalpy-humidity diagram. The multiple air state regions are divided according to the set outlet air state requirements. Different air state regions correspond to different air treatment strategies. The air treatment strategy includes at least one air treatment method, and one air treatment method corresponds to one functional segment. In addition to the air treatment methods, the air treatment strategy may also include the treatment sequence of the air treatment methods.

[0101] Taking the set air state requirement as Figure 6 the set air state range shown in Figure 7 as an example, then: Refer to Figure 7 , the psychrometric chart is divided into the following several air state regions: Region I, Region II, Region III, Region IV, and Region V. The air treatment strategies adopted for any air state change to the set air state range in each air state region are the same.

[0102] Among them, the air treatment methods included in the air treatment strategy corresponding to Region I are heating and humidification, and heating precedes humidification. That is to say, the air treatment methods involved in the energy-saving air treatment path for any air state in Region I to change to the set air state range are heating and humidification, and heating precedes humidification. Among them, the energy-saving air treatment path for any air state A11 in Region I to change to the set air state range is: A11 - A12 - A13. The air treatment method involved in A11 - A12 is heating, the air treatment method involved in A12 - A13 is humidification, and A12 is located on the boundary line between Region I and Region II.

[0103] The air treatment method included in the air treatment strategy corresponding to Region II is humidification. That is to say, the air treatment method involved in the energy-saving treatment path for any air state in Region II to change to the set air state range is humidification. Among them, the energy-saving air treatment path for any air state A21 in Region II to change to the set air state range is: A21 - A22. The air treatment method involved in A21 - A22 is humidification.

[0104] The air treatment methods included in the air treatment strategy corresponding to Region III are cooling coil and humidification, and cooling coil precedes humidification. That is to say, the air treatment methods involved in the energy-saving air treatment path for any air state in Region III to change to the set air state range are: cooling coil and humidification, and cooling coil precedes humidification. Among them, the energy-saving air treatment path required for any air state A31 in Region III to change to the set air state range is: A31 - A32 - A33. The air treatment method involved in A31 - A32 is cooling coil, the air treatment method involved in A32 - A33 is humidification, and A32 is located on the boundary line between Region II and Region III.

[0105] The air treatment methods included in the air treatment strategy corresponding to Zone Ⅳ are chilled water cooling and heating, and chilled water cooling precedes heating. That is to say, the air treatment methods involved in the energy-saving air treatment path corresponding to any air state in Zone Ⅳ changing to the set air state range are: chilled water cooling and heating, and chilled water cooling precedes heating. Among them, the energy-saving air treatment path corresponding to any air state A41 in Zone Ⅳ changing to the set air state range is: A41 - A42 - A43 - A44. The air treatment methods involved in A41 - A42 - A43 are chilled water cooling, and the air treatment method involved in A43 - A44 is heating. A42 is on the 100% relative humidity line, and A43 is on the boundary line between Zone Ⅳ and Zone Ⅴ.

[0106] The air treatment method included in the air treatment strategy corresponding to Zone Ⅴ is heating. That is to say, the air treatment method involved in the energy-saving air treatment path corresponding to any air state in Zone Ⅴ changing to the set air state range is: heating. Among them, the energy-saving air treatment path corresponding to any air state A51 in Zone Ⅴ changing to the set air state range is: A51 - A52.

[0107] Based on the above content, in the above 10311 - 10312, specifically, the air state region to which the air state at the starting point of the energy-saving air treatment path (i.e., the incoming air state of the air treatment equipment) belongs can be directly determined as the air state region to which this energy-saving air treatment path belongs. For example, the energy-saving air treatment path obtained through path search is Figure 6 The control process shown: M → O → P → C, where M is the starting point of this energy-saving air treatment path, and the air state region to which the air state at the starting point belongs is Zone Ⅳ. Therefore, it can be determined that the air state region to which this energy-saving air treatment path belongs is Zone Ⅳ. Further, the air treatment methods included in the air treatment strategy corresponding to Zone Ⅳ are chilled water cooling and heating, and chilled water cooling precedes heating. Chilled water cooling and heating are respectively implemented by the chilled water cooling section and the heating section. Therefore, it can be determined that the target functional sections to be used are: the chilled water cooling section and the heating section, and the chilled water cooling section is used before the heating section.

[0108] Further, if the first functional section is one of at least one target functional section determined to be used, then in the above 1031, "determining the control quantity of the first functional section" may include:

[0109] 10313. Determining the air treatment path segment that the first functional section needs to be responsible for from the most energy-saving air treatment path.

[0110] 10314. Determining the air state at the starting point and the air state at the ending point of the air treatment path segment that needs to be responsible for as the air state at the entrance and the desired air state at the exit of the first functional section respectively;

[0111] 10315. Use the flow rate information of the medium for processing air in the first functional section and the air state at the inlet of the first functional section as the input of the first air model corresponding to the first functional section, and use the desired air state at the outlet of the first functional section as the output of the first control model. Execute the first control model to obtain the control quantity of the first functional section.

[0112] Among them, a mapping relationship is established in the first control model among the air state at the inlet of the first functional section, the medium flow rate information of the medium for processing air, the air state at the outlet, and the control quantity.

[0113] In specific implementation, the first control model is established in advance. The form of the first control model can be a transfer function, a state-space equation, a difference equation, an impulse response, a step response model, etc. In the process of establishing the first control model, based on the medium state information (such as medium flow rate information) of the medium for processing air in the first functional section obtained historically, the air state at the inlet of the first functional section, the air state at the outlet, the valve opening degree and pump frequency corresponding to the first functional section, etc., the model parameters of the initial prediction model constructed for the first functional section can be deduced and calculated, so as to establish the first control model.

[0114] After inputting the currently obtained medium flow rate information of the medium for processing air in the first functional section, the air state at the inlet of the first functional section, and the desired air state at the outlet into the first control model, the first control model can determine the target medium flow rate required to adjust the air state at the inlet of the first functional section to the desired air state at the outlet of the first functional section, and then determine the control quantity that needs to be increased or decreased to adjust the current medium flow rate in the first functional section to the target medium flow rate. Then, the determined control quantity that needs to be increased or decreased is sent to the actuator corresponding to the first functional section for execution, so as to realize the control of the first functional section. Among them, the control quantity can be the valve opening degree, pump frequency, etc. of the first functional section. For example, if it is determined that the valve opening degree of the first functional section needs to be increased by Δα, after sending the Δα to the valve actuator corresponding to the first functional section, the valve actuator will control the current valve opening degree α of the first functional section 当前 to increase by Δα to change to α 当前+ Δα.

[0115] Regarding the determination of the control quantity of other functional sections except the first functional section in at least one target functional section and the control implementation, reference can be made to the determination and control implementation of the control quantity of the first functional section described above.

[0116] In summary, for the technical solution provided in this embodiment, first, based on the detection data of the sensors in the air treatment device (including the inlet air state of the air treatment device), the target air treatment model corresponding to the air treatment device is determined; then, based on the inlet air state and the set outlet air state requirements, an energy-saving air treatment path is obtained through path search in the air enthalpy-humidity diagram using the target air treatment model and the optimization algorithm. Furthermore, according to the energy-saving air treatment path, multiple functional segments in the air treatment device are controlled, so that the outlet air state of the air treatment device changes to the air state at the end point of the most energy-saving air treatment path. The solution of this application controls the air treatment device according to the energy-saving air treatment path determined by the corresponding air treatment model (a machine learning model), which can reduce the system oscillation of the air treatment device and shorten the system stabilization time of the air treatment device, thereby reducing energy consumption. Taking the battery cell workshop as an example, generally, only after the dehumidifier starts and reaches a stable state can the production of battery cells begin. Therefore, shortening the system stabilization time of the dehumidifier can reduce energy consumption.

[0117] The air state described in the solution of this application can be the air temperature and humidity. Figure 8 It shows the comparison of the temperature and humidity control results corresponding to the same target set values (temperature set value, humidity set value) when the air treatment device is controlled by using the traditional PID control method and the control method provided in the solution of this application (a machine learning control method) respectively for the air temperature and humidity. From Figure 8 It can be easily seen that, compared with the traditional PID control method, the control method provided in the solution of this application can reach the stable range quickly both in terms of temperature and humidity, and has a smaller overshoot. In summary, obviously, compared with the traditional PID control method, the control method provided in the solution of this application can automatically adjust the air treatment device according to different working conditions to meet the control requirements, and can greatly shorten the time for the system to reach the stable state.

[0118] Optionally, the following steps may further be included in step 103 above:

[0119] 1033. Determine at least one unused functional segment among the multiple functional segments according to the at least one target functional segment.

[0120] 1034. Control the actuators of the at least one functional segment to perform a closing operation.

[0121] During specific implementation, a closing control signal can be sent to the actuators of the at least one unused functional segment. After receiving the closing control signal, the actuators close the corresponding valves.

[0122] Optionally, the method provided in this embodiment may further include:

[0123] 104. Display the air enthalpy-humidity diagram;

[0124] 105. Display the set outlet air state requirement and the energy-saving air treatment path in the air enthalpy-humidity diagram.

[0125] In the air enthalpy-humidity diagram, different highlighting methods can be used to display the set outlet air state requirement and the energy-saving air treatment path. The display of the energy-saving air treatment path enables relevant staff to visually and directly understand the air treatment process of the air treatment equipment for the incoming air and the final output air state, facilitating the staff to know the working condition of the air treatment equipment.

[0126] Figure 9 The flowchart of the control method for a dehumidifier provided by another embodiment of the present application. The dehumidifier can be an industrial dehumidifier. As Figure 9 shown, the control method provided in this embodiment includes the following steps:

[0127] 201. Determine the target air treatment model corresponding to the dehumidifier according to the detection data of the sensors in the dehumidifier; wherein, the detection data includes the inlet air state of the dehumidifier;

[0128] 202. Based on the inlet air state of the dehumidifier and the set outlet air state requirement, perform path search and optimization in the air enthalpy-humidity diagram through the target air treatment model and the optimization algorithm to obtain the energy-saving air treatment path;

[0129] 203. Control multiple functional segments in the dehumidifier according to the energy-saving air treatment path so that the outlet air state of the dehumidifier is the air state at the end point of the energy-saving air treatment path.

[0130] Further, the above control method may further include:

[0131] 204. Display the air enthalpy-humidity diagram;

[0132] 205. Display the set outlet air state requirement and the energy-saving air treatment path in the air enthalpy-humidity diagram.

[0133] The above-mentioned dehumidifier can be used in food processing workshops, electronic production workshops, etc. In this embodiment, preferably, the dehumidifier is used in a battery cell workshop.

[0134] After the dehumidifier is started, the Figure 9 corresponding control method can be executed, for example: execute the Figure 9 corresponding control method every preset time interval.

[0135] For the content not elaborated in each step of the method provided in this embodiment, reference may be made to the corresponding content in other embodiments of this application, which will not be elaborated here. In addition, in the method provided in this embodiment, in addition to the above steps, it may also include some or all of the steps in other embodiments. Specifically, reference may be made to the corresponding content in the above other embodiments.

[0136] Figure 10 shows a structural block diagram of a control system provided by an embodiment of this application. As Figure 10 , the control system includes:

[0137] An air handling device 31, including multiple functional sections and sensors;

[0138] A control device 32, configured to obtain the detection data of the sensors in the air handling device; wherein, the detection data includes the inlet air state of the air handling device; according to the detection data, determine the target air handling model corresponding to the air handling device; based on the inlet air state and the set outlet air state requirement, perform path search and optimization in the air enthalpy-humidity diagram through the air handling model and an optimization algorithm to obtain an energy-saving air handling path; according to the energy-saving air handling path, control the multiple functional sections so that the outlet air state of the air handling device is the air state at the end point of the energy-saving air handling path.

[0139] For the processing procedures of the above air handling device and control device, reference may be made to the corresponding content in other embodiments of this application, which will not be elaborated here.

[0140] Generally, each functional section in the air handling device corresponds to an actuator. The above control of the multiple functional sections is also to control the actuators corresponding to the respective functional sections. The air handling device may be a dehumidifier and is applied to a battery cell workshop.

[0141] The above control device 32 includes: a data acquisition device 321 and a control device 322; wherein, the data acquisition device 321 is used to acquire the detection data of the sensors in the air handling device, and the detection data includes the inlet air state of the air handling device; the control device 322 includes: a determination module 3221, a search module 3222 and a control module 3223; wherein, the determination module 3221 is used to determine the target air handling model corresponding to the air handling device according to the detection data acquired by the data acquisition device 321; the search module 3222 is used to perform path search and optimization in the air enthalpy-humidity diagram through the air handling model and the optimization algorithm based on the inlet air state and the set outlet air state requirement to obtain an energy-saving air handling path; the control module 3223 is used to control the multiple functional sections according to the energy-saving air handling path so that the outlet air state of the air handling device is the air state at the end point of the energy-saving air handling path.

[0142] Further, when the determination module 3221 is used to determine the target air handling model corresponding to the air handling device according to the detection data of the sensors in the air handling device, it is specifically used to: periodically acquire the detection data of the sensors in the air handling device; use the detection data acquired in the current period to correct and update the pre-established air handling model to obtain the corrected and updated air handling model; and determine the corrected and updated air handling model as the target air handling model.

[0143] Further, the above detection data further includes: the outlet air state of the air handling device, the operating parameters of each functional section in the multiple functional sections; the operating parameters include: the medium state information of the medium used for processing air in the functional section, the inlet air state and the outlet air state at the inlet of the functional section; wherein, the medium state information includes medium flow rate information and medium temperature information.

[0144] Further, the pre-established air handling model above is obtained by training a machine learning model; training the machine learning model includes: preprocessing the detection data acquired in the historical period to obtain the preprocessed detection data; using the preprocessed detection data as training data to train the machine learning model; wherein, the preprocessing includes at least one of the following: data cleaning, data standardization.

[0145] Further, when the control module 3223 is used to control the multiple functional segments according to the energy-saving air treatment path, it is specifically configured to: determine at least one target functional segment to be used among the multiple functional segments and the control amount of each target functional segment according to the energy-saving air treatment path; and control each target functional segment according to the control amount of each target functional segment.

[0146] Further, when the control module 3223 is used to determine at least one target functional segment to be used among the multiple functional segments according to the energy-saving air treatment path, it is specifically configured to: determine the air state region to which the energy-saving air treatment path belongs; determine at least one target functional segment to be used according to the air treatment strategy corresponding to the air state region to which the energy-saving air treatment path belongs; wherein, the air state region to which the energy-saving air treatment path belongs is one of multiple air state regions included in the air enthalpy-humidity diagram, the multiple air state regions are divided according to the set outlet air state requirements, different air state regions correspond to different air treatment strategies, and the air treatment strategy includes at least one air treatment method, and one air treatment method corresponds to one functional segment.

[0147] Further, the first functional segment is one of the at least one target functional segment; and when the control module 3223 is used to determine the control amount of the first functional segment, it is specifically configured to: determine the air treatment path segment that the first functional segment needs to be responsible for from the energy-saving air treatment path; respectively determine the air state at the starting point and the air state at the ending point of the air treatment path segment that needs to be responsible for as the air state at the inlet and the desired air state at the outlet of the first functional segment; use the medium flow rate information of the medium used to treat air in the first functional segment and the air state at the inlet of the first functional segment as the input of the first control model corresponding to the first functional segment, use the desired air state at the outlet of the first functional segment as the output of the first control model, execute the first control model, and obtain the control amount of the first functional segment; a mapping relationship between the air state at the inlet of the first functional segment, the flow rate information of the medium used to treat air, the air state at the outlet, and the control amount is established in the first control model.

[0148] Further, the set outlet air state requirements include: a set outlet air state range.

[0149] For the description of the function implementation of the above modules, reference can be made to the relevant content in other embodiments above.

[0150] In practical applications, the dehumidifier hardware in the battery cell workshop mainly consists of a heating section, a surface cooling section, a humidifying section, a fan section, a multi-stage filtration section, etc. Among them, the heating section, the surface cooling section, the humidifying section and their corresponding PIDs form a stable temperature and humidity control system. This application proposes to use the psychrometric chart to characterize the temperature and humidity relationship in different seasons, and proposes a multi-condition (i.e., different external environments, which in this application refers to the change in air temperature and humidity caused by seasonal changes) zoning air control strategy, and corresponding temperature and temperature control curves are adopted under different conditions. Multi-condition zoning can refer to dividing the psychrometric chart into multiple air state regions based on the air state range (temperature and humidity range) required by the battery cell workshop. Different air state regions correspond to different air control strategies (specifically, the enthalpy-humidity control strategy, which is also the air treatment strategy described in other embodiments above). In this way, under different conditions, the enthalpy value and moisture content of the external environment can be calculated to determine the corresponding air state region, and thus the corresponding air control strategy can be adopted. Therefore, the solution of this application can adopt the corresponding air treatment strategy in different conditions in real time. In addition, an in-machine-based HVAC process optimization method is introduced to process the obtained sensor data, and a temperature and humidity influence model corresponding to different conditions is established, so that a prediction model corresponding to each functional section of the dehumidifier can be established according to different external environments, and then the control quantity can be issued to complete the temperature and humidity control of the dehumidifier system.

[0151] Based on the temperature and humidity control method proposed in this application, a corresponding data learning and training platform is established, and the real-time feedback values of the temperature and humidity in the system environment are transmitted into the data learning and training platform in real time. Among them, the sampling time interval of the temperature and humidity in the system environment can be, for example, 2 seconds. Compared with PID control, the control method proposed in this application can reach the steady state range faster both in terms of temperature and humidity, and has a smaller overshoot, reducing energy consumption.

[0152] Figure 11 FIG. shows a schematic structural diagram of an electronic device provided by an embodiment of this application. As Figure 11 shown, the electronic device includes a memory 41 and a processor 42. The memory 41 can be configured to store various other data to support operations on the electronic device. Examples of these data include instructions for any application program or method for operating on the electronic device. The memory 41 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0153] The memory 41 is used to store programs;

[0154] The processor 42, which is coupled to the memory 41, is configured to execute the program stored in the memory 41 to implement the methods provided in the above method embodiments.

[0155] Further, as Figure 11 shown, the electronic device further includes: a communication component 43, a display 44, a power supply component 45, an audio component 46, and other components. Figure 11 Only some components are schematically shown, and it does not mean that the electronic device only includes Figure 11 the components shown.

[0156] Correspondingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the steps or functions of the methods provided in the above method embodiments.

[0157] Through the descriptions of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solutions, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0158] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A control method for an air handling device, characterized in that, Including: Determine a target air treatment model corresponding to the air treatment device according to the detection data of sensors in the air treatment device; wherein, the detection data includes the inlet air state of the air treatment device; Based on the inlet air state and the set outlet air state requirements, perform path search and optimization in the air enthalpy-humidity diagram through the target air treatment model and the optimization algorithm to obtain an energy-saving air treatment path; Control multiple functional segments in the air treatment device according to the energy-saving air treatment path, so that the outlet air state of the air treatment device changes to the air state at the end point of the energy-saving air treatment path.

2. The method according to claim 1, wherein Determining a target air treatment model corresponding to the air treatment device according to the detection data of sensors in the air treatment device includes: Periodically obtain the detection data of sensors in the air treatment device; Use the detection data obtained in the current period to correct and update the pre-established air treatment model to obtain the corrected and updated air treatment model; Determine the corrected and updated air treatment model as the target air treatment model.

3. The method according to claim 1, characterized in that The detection data further includes: the outlet air state of the air treatment device, and the operating parameters of each functional segment among the multiple functional segments; The operating parameters include: the medium state information of the medium used to treat air in the functional segment, the air state at the inlet of the functional segment, and the air state at the outlet; wherein, the medium state information includes medium flow information and medium temperature information.

4. The method according to claim 2, wherein The pre-established air treatment model is obtained by training a machine learning model; Training the machine learning model includes: Preprocess the detection data obtained in the historical period to obtain the preprocessed detection data; Use the preprocessed detection data as training data to train the machine learning model; Wherein, the preprocessing includes at least one of the following: data cleaning, data standardization.

5. The method according to any one of claims 1 to 4, characterized in that Controlling the multiple functional segments according to the energy-saving air treatment path includes: Determine at least one target functional segment to be used among the multiple functional segments and the control amount of each target functional segment according to the energy-saving air treatment path; Control each target functional segment according to the control amount of each target functional segment.

6. The method according to claim 5, wherein Determining at least one target functional segment to be used among the multiple functional segments according to the energy-saving air treatment path includes: Determine the air state region to which the energy-saving air treatment path belongs; Determine at least one target functional segment to be used according to the air treatment strategy corresponding to the air state region to which the energy-saving air treatment path belongs; Wherein, the air state region to which the energy-saving air treatment path belongs is one of multiple air state regions included in the air enthalpy-humidity diagram, the multiple air state regions are divided according to the set outlet air state requirements, different air state regions correspond to different air treatment strategies, and the air treatment strategy includes at least one air treatment method, and one air treatment method corresponds to one functional segment.

7. The method according to claim 6, wherein The first functional segment is one of the at least one target functional segment; And Determining the control quantity of the first functional section includes: Determining the air treatment path section that the first functional section needs to be responsible for from the energy-saving air treatment path; Determining the air state at the starting point and the air state at the ending point of the air treatment path section that needs to be responsible for as the air state at the inlet and the desired air state at the outlet of the first functional section respectively; Taking the medium flow rate information of the medium used to treat air in the first functional section and the air state at the inlet of the first functional section as the input of the first control model corresponding to the first functional section, and taking the desired air state at the outlet of the first functional section as the output of the first control model, and executing the first control model to obtain the control quantity of the first functional section; Wherein, a mapping relationship between the air state at the inlet of the first functional section, the medium flow rate information of the medium used to treat air, the air state at the outlet, and the control quantity is established in the first control model.

8. The method according to any one of claims 1 to 4, characterized in that The setting of the required air state of the outlet air includes: setting the range of the outlet air state.

9. The method according to any one of claims 1 to 4, characterized in that, Based on the inlet air state and the setting of the required outlet air state, performing path search and optimization in the air enthalpy-humidity diagram through the target air treatment model and the optimization algorithm to obtain the energy-saving air treatment path, including: After inputting the inlet air state and the setting of the required outlet air state into the target air treatment model, using the air enthalpy-humidity diagram as the path optimization space, and using the optimization algorithm to perform path optimization iterative solution on the target air treatment model to obtain the energy-saving air treatment path; Wherein, the process of path optimization iterative solution is: Taking the inlet air state as the starting point of the path solution and the setting of the required outlet air state as the ending point requirement of the path solution; Setting the first path solution and the iteration parameters; Randomly generating a second path solution; According to the total path length of the first path solution and the total path length of the second path solution, selecting the path solution with the shorter total path length from the first path solution and the second path solution as the preferred path solution; Updating the iteration parameters and determining whether the iteration termination requirement is met according to the updated iteration parameters; When the iteration termination requirement is not met, randomly generating a second path solution again, and selecting the path solution with the shorter total path length from the total path length of the newly generated second path solution and the total path length of the preferred path solution to update the preferred path solution; When the iteration termination requirement is met, outputting the preferred path solution as the energy-saving air treatment path.

10. A control method for a dehumidifier, characterized in that, Including: Determining the target air treatment model corresponding to the dehumidifier according to the detection data of the sensors in the dehumidifier; wherein, the detection data includes the inlet air state of the dehumidifier; Based on the inlet air state of the dehumidifier and the setting of the required outlet air state, performing path search and optimization in the air enthalpy-humidity diagram through the target air treatment model and the optimization algorithm to obtain the energy-saving air treatment path; Controlling multiple functional sections in the dehumidifier according to the energy-saving air treatment path so that the outlet air state of the dehumidifier is the air state at the ending point of the energy-saving air treatment path.

11. The method according to claim 10, wherein Also including: Display the air enthalpy-humidity chart; Show the set outlet air state requirements and the energy-saving air treatment path in the air enthalpy-humidity chart.

12. A control system, characterized in that, Comprising: An air treatment device, including multiple functional sections and sensors; A control device for obtaining the detection data of the sensors in the air treatment device; wherein, the detection data includes the inlet air state of the air treatment device; According to the detection data, determine the target air treatment model corresponding to the air treatment device; based on the inlet air state and the set outlet air state requirements, perform path search and optimization in the air enthalpy-humidity chart through the air treatment model and the optimization algorithm to obtain an energy-saving air treatment path; according to the energy-saving air treatment path, control the multiple functional sections so that the outlet air state of the air treatment device is the air state at the end point of the energy-saving air treatment path.

13. An electronic device, characterized in that, Comprising: A memory and a processor, wherein, The memory is used for storing programs; The processor is coupled to the memory and is used for executing the programs stored in the memory to implement the steps in the control method described in any one of claims 1 to 9 above, or to implement the steps in the control method described in any one of claims 10 to 11 above.

14. 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 the computer, it can implement the steps in the control method described in any one of claims 1 to 9 above, or implement the steps in the control method described in any one of claims 10 to 11 above.

Images