Control method of rotating wheel dehumidification air conditioning system

Abstract

The invention relates to a control method of a rotating wheel dehumidification air-conditioning system. The control method comprises the following steps: acquiring a state variable, a controllable variable, a target variable and a relationship model satisfied by the variables according to typical working conditions; constructing a control model, generating a training set and a verification set by using the relation model, and training and verifying the control model by using the training set and the verification set to obtain an optimal control model; adjusting the controllable variable by taking the minimum target variable as an optimization target, and updating parameters in the optimal control model according to a predicted target variable obtained by inputting the adjusted controllable variable and the state variable into the optimal control model and the minimum target variable to obtain a final control model; and the state variables and the controllable variables in the multiple to-be-controlled working conditions are input into the final control model, the minimum value is selected from the target variables corresponding to all the to-be-controlled working conditions, and the controllable variable corresponding to the minimum value is used for controlling the rotating wheel dehumidification air conditioner system. The control method can reduce energy consumption.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning systems, and in particular to a control method for a rotary dehumidification air conditioning system. Background Art

[0002] With the continuous growth of global energy demand and the increase of environmental pressure, energy conservation and emission reduction have become the common goals of all industries. As the core component of new energy vehicles, the production process of lithium batteries has extremely stringent requirements on environmental conditions. In particular, humidity control is crucial to the production quality and safety of lithium batteries; excessive humidity will cause battery materials to absorb moisture, which will affect the electrochemical performance of the battery and may even cause safety accidents. Therefore, in certain key processes of lithium battery production, the environmental humidity must be strictly controlled to ensure that the produced batteries have high capacity, high stability and long life.

[0003] There are many traditional dehumidification technologies, such as refrigeration dehumidification and direct expansion heat pump dehumidification, but traditional dehumidification technologies are often unable to meet extremely low humidity requirements. The existing rotary dehumidification technology has gradually become the mainstream dehumidification solution for lithium battery production workshops because it can process air humidity to a dew point temperature below -60°C. However, the high energy consumption problem of the rotary dehumidification system has also become prominent. How to reduce energy consumption while ensuring humidity control accuracy has become a problem that the industry needs to solve urgently.

[0004] Traditional dehumidification system control methods mostly rely on preset parameters based on experience and rules. Although this method is simple and direct, it lacks the ability to flexibly respond to the actual operating environment. In actual applications, the production environment is ever-changing, making it difficult for traditional methods to adapt to complex working conditions, resulting in low system operating efficiency and high energy consumption. Especially in the scenario of lithium battery production, which requires extremely high humidity control accuracy, the limitations of traditional control methods are more obvious. For this reason, further improvements to the existing technology are needed. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a control method for a rotary wet air conditioning system which can reduce energy consumption in view of the above-mentioned prior art.

[0006] The technical solution adopted by the present invention to solve the above technical problems is: a control method for a rotary dehumidification air conditioning system, characterized by comprising the following steps:

[0007] Step 1: Collect the working environment parameters of the rotary dehumidification air conditioning system, and pre-process the collected data to form a data set;

[0008] Step 2: Perform cluster analysis on the data set to obtain typical operating conditions of the rotary dehumidification air conditioning system;

[0009] Step 3, extract and classify parameters of the typical working conditions of the rotary dehumidification air conditioning system in step 2 to obtain the state variable x, the controllable variable μ and the target variable y;

[0010] Step 4: Analyze the state variable x, the controllable variable μ and the target variable y to obtain the relationship model satisfied by the state variable x, the controllable variable μ and the target variable y;

[0011] Step 5: construct a control model for the rotary dehumidification air conditioning system, use the relational model to generate a sample set, the sample set consists of multiple different working conditions, divide the sample set into a training set and a verification set, use the training set to train the constructed control model to obtain the trained control model, and use the verification set to verify the trained control model to obtain the optimal control model;

[0012] Step 6: When the state variable x meets the requirements, the controllable variable μ is adjusted with the objective variable of minimizing the rotary dehumidification air conditioning system as the optimization objective, and the adjusted controllable variable μ and the state variable x are input into the optimal control model to obtain the predicted objective variable, and the parameters in the optimal control model are updated according to the difference between the predicted objective variable and the minimized objective variable to obtain the final control model;

[0013] Step 7: Input the state variables x and controllable variables μ in multiple working conditions to be controlled into the final control model to obtain the target variable corresponding to each working condition to be controlled, and select the minimum value among the target variables corresponding to all working conditions to be controlled. Then, use the controllable variable μ corresponding to the minimum value to control the rotary dehumidification air-conditioning system.

[0014] Preferably, the data collected in step 1 includes at least one or more of the humidity of the place where the rotary dehumidification air-conditioning system is located, the temperature outside the place, the dew point temperature outside the place, the freezing water temperature, the steam flow, the cooling capacity, the steam temperature and the energy consumption.

[0015] In order to eliminate abnormal data caused by data collection failure or external interference, the preprocessing process in step 1 includes one or more of outlier detection, missing value filling, data smoothing and standardization.

[0016] In order to ensure the scientificity and practicality of the lithium battery production process condition analysis, the specific process of obtaining the typical working condition of the rotary dehumidification air conditioning system in step 2 is as follows:

[0017] Select at least two clustering methods to perform cluster analysis on the data set respectively, compare the clustering results of each clustering method, select the clustering result with better performance as the final analysis result, and delete the outliers in the final analysis result, that is, obtain the typical working conditions of the rotary dehumidification air-conditioning system.

[0018] Preferably, there are two clustering methods, namely, K-means clustering method and DBSCAN clustering method.

[0019] Preferably, the specific process in step 3 is: extracting all parameters related to the time period corresponding to each cluster of typical working conditions; and dividing all the extracted parameters into three categories according to their functions, namely obtaining state variables x, controllable variables and target variables y.

[0020] In the above scheme, in step 4, the generalized additive model is used to analyze the state variable x, the controllable variable μ and the target variable y to obtain the fitted generalized additive model;

[0021] Determine whether the result of the fitted generalized additive model is valid. If so, use the fitted generalized additive model as the relationship model satisfied by the state variable x, the controllable variable μ and the target variable y; if not, use the regression analysis method to analyze the state variable x, the controllable variable μ and the target variable y to obtain the relationship model satisfied by the state variable x, the controllable variable μ and the target variable y.

[0022] Preferably, the specific process of using the regression analysis method to analyze the state variable x, the controllable variable μ and the target variable y is:

[0023] If the state variable x, the controllable variable μ and the target variable y show a linear relationship, the multivariate linear regression method is used to analyze the state variable x, the controllable variable μ and the target variable y;

[0024] If the state variable x, the controllable variable μ and the target variable y present a nonlinear relationship, the multivariate nonlinear regression method or the support vector machine regression method is used to analyze the state variable x, the controllable variable μ and the target variable y.

[0025] Preferably, the control model in step 5 adopts a neural network or a multivariate regression model.

[0026] Compared with the prior art, the advantages of the present invention are: by deeply mining the collected data, the rules and patterns hidden in the data can be discovered, that is: the relationship model satisfied by the state variable x, the controllable variable μ and the target variable y is obtained, so as to extract the key factors affecting the performance of the rotary dehumidification air-conditioning system, and establish a control model of the rotary dehumidification air-conditioning system, and then optimize the control model according to the operating conditions of the rotary dehumidification air-conditioning system to achieve energy saving and consumption reduction of the rotary dehumidification air-conditioning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 Flow chart of a typical working condition acquisition method in an embodiment of the present invention;

[0028] Figure 2 The figure is a flow chart of a method for acquiring a relationship model in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The present invention is further described in detail below with reference to the accompanying drawings.

[0030] The control method of the rotary dehumidification air conditioning system in this embodiment includes the following steps:

[0031] Step 1: Collect the working environment parameters of the rotary dehumidification air conditioning system, and pre-process the collected data to form a data set;

[0032] The collected data includes at least one or more of the humidity of the place where the rotary dehumidification air conditioning system is located, the temperature outside the place, the dew point temperature outside the place, the freezing water temperature, the steam flow, the cooling capacity, the steam temperature and the energy consumption;

[0033] The rotary dehumidification air conditioning system in this embodiment is installed in a lithium battery production workshop. The data collected in this embodiment include but are not limited to the humidity, outdoor temperature, outdoor dew point temperature, frozen water temperature, steam flow, cooling capacity, steam temperature and energy consumption data of the lithium battery production workshop; the collected data can be recorded frequently and continuously through the sensor network and the industrial Internet of Things system to ensure the timeliness and integrity of the data;

[0034] The preprocessing process in this embodiment includes one or more of outlier detection, missing value filling, data smoothing and standardization processing;

[0035] Step 2: Perform cluster analysis on the data set to obtain typical operating conditions of the rotary dehumidification air conditioning system;

[0036] The specific process of obtaining the typical working conditions of the rotary dehumidification air conditioning system is as follows:

[0037] Select at least two clustering methods to perform cluster analysis on the data set respectively, compare the clustering results of each clustering method, select the clustering result with better performance as the final analysis result, and delete the outliers in the final analysis result, that is, obtain the typical working condition of the rotary dehumidification air-conditioning system;

[0038] like Figure 1 As shown, there are two clustering methods in this embodiment, namely, K-means clustering method and DBSCAN clustering method; K-means clustering method divides data into several clusters by minimizing the distance from the sample to the cluster center, each cluster represents a typical working condition, and the objective function of K-means clustering is:

[0039]

[0040] Among them, Ci is the i-th cluster, μ i is the centroid of the cluster, and x is the sample point of the cluster. In order to determine the optimal number of clusters k in K-means clustering, the Elbow Method is used. By observing the change of the sum of squared errors under different numbers of clusters, the number of clusters at the inflection point is selected as the optimal number of clusters.

[0041] As a density-based clustering method, DBSCAN clustering method can effectively process noisy data and identify clusters of any shape. DBSCAN does not need to pre-specify the number of clusters, but automatically divides the high-density areas into clusters by setting the radius and minimum number of points, and marks the low-density points as noise. The formula for the noise point condition is:

[0042] Noise point condition = {x1|MinPts(x1)<∈}

[0043] Among them, x1 represents a specific data point in the data set, ∈ represents the neighborhood radius of a given point x1. Within this radius, the algorithm will check how many other data points fall within this range. MinPts represents the minimum number of data points required within the neighborhood radius ∈. If the number of points in this range is less than MinPts, then the point x1 is marked as a noise point.

[0044] By comparing the clustering results of the K-means clustering method and the DBSCAN clustering method, we can evaluate the performance of the two methods in dealing with data noise and identifying typical working conditions. The K-means clustering method performs well in dealing with large-scale data and can quickly process and generate multiple clusters, but it is slightly insufficient in dealing with noisy data; on the contrary, the DBSCAN clustering method has obvious advantages in dealing with noise and identifying complex cluster shapes. Finally, based on the stability and accuracy of the clustering results and the representative analysis of the working conditions, the clustering result with better performance can be selected as the final analysis result;

[0045] Step 3, extract and classify parameters of the typical working conditions of the rotary dehumidification air conditioning system in step 2 to obtain the state variable x, the controllable variable μ and the target variable y;

[0046] like Figure 2As shown, the specific process is as follows: for the clustered typical working conditions, firstly, a detailed analysis is performed to check whether there are abnormal values ​​in various typical working conditions; the identified abnormal values ​​should be removed and deleted, and then the final multiple typical working conditions are obtained; after obtaining the cleaned typical working conditions, all relevant data are extracted one by one according to the time period corresponding to each cluster of typical working conditions; specifically, it is necessary to extract all other parameters related to it from the time period corresponding to each cluster, including outdoor temperature, outdoor dew point temperature, freezing water temperature, freezing water side power consumption, steam temperature, cooling capacity and steam flow, etc.; and all the extracted parameters are divided into three categories according to their functions, that is, the state variable x, the controllable variable μ and the target variable y are obtained; the state variable x in this embodiment includes the outdoor temperature and the outdoor dew point temperature, the controllable variable μ includes the freezing water temperature, cooling capacity and steam temperature; the target variable y includes the freezing water side power consumption and steam flow;

[0047] Step 4: Analyze the state variable x, the controllable variable μ and the target variable y to obtain the relationship model satisfied by the state variable x, the controllable variable μ and the target variable y;

[0048] In this embodiment, a generalized additive model is used to analyze the state variable x, the controllable variable μ and the target variable y to obtain a fitted generalized additive model;

[0049] Determine whether the result of the fitted generalized additive model is valid. If so, use the fitted generalized additive model as the relationship model satisfied by the state variable x, the controllable variable μ and the target variable y; if not, use the regression analysis method to analyze the state variable x, the controllable variable μ and the target variable y to obtain the relationship model satisfied by the state variable x, the controllable variable μ and the target variable y;

[0050] The generalized additive model in this embodiment is a prior art and will not be elaborated here. The generalized additive model can capture both linear and nonlinear relationships without pre-assuming the relationship form of the data. Therefore, the generalized additive model is an ideal choice for preliminary analysis. If the analysis results show a good fit, the results can be directly used to explain the relationship between the variables. However, if the results are not ideal and cannot accurately capture the pattern in the data, it is necessary to further select a suitable analysis method based on the relationship of the data (linear or nonlinear);

[0051] The specific process of using regression analysis method to analyze state variable x, controllable variable μ and target variable y is as follows:

[0052] If the state variable x, the controllable variable μ and the target variable y show a linear relationship, the multivariate linear regression method is used to analyze the state variable x, the controllable variable μ and the target variable y;

[0053] If the state variable x, the controllable variable μ and the target variable y present a nonlinear relationship, the multivariate nonlinear regression method or the support vector machine regression method is used to analyze the state variable x, the controllable variable μ and the target variable y;

[0054] This step-by-step analysis method ensures a comprehensive understanding of the relationship between variables. By first using the generalized additive model to explore possible forms of relationships and then selecting other methods based on data characteristics, the complex relationship between x-μ-y can be more effectively captured and explained, thus providing a solid theoretical basis for optimizing production processes and formulating control strategies.

[0055] Step 5: construct a control model for the rotary dehumidification air conditioning system, use the relational model to generate a sample set, the sample set consists of multiple different working conditions, divide the sample set into a training set and a verification set, use the training set to train the constructed control model to obtain the trained control model, and use the verification set to verify the trained control model to obtain the optimal control model;

[0056] In this embodiment, the state variables and control variables under different typical working conditions are parameterized and adjusted, so as to obtain the changes of target variables under specific environmental and control conditions, such as energy consumption and humidity control effects; for each typical working condition, the control model can accurately reproduce the energy consumption-control-environment interaction relationship in a specific season and time, and reflect the energy consumption change law of the system under different conditions; the control model not only has strong robustness, can adapt to different working conditions, maintain stable prediction accuracy, but also can realize effective energy consumption optimization and regulation in the production process; for each working condition, the control model adopts a neural network or a multivariate regression model; the input variables include state variables (outdoor temperature and outdoor dew point temperature) and controllable variables (chilled water temperature, cooling capacity and steam temperature), and the output variables are target variables (chilled water side power consumption and steam flow);

[0057] The constructed control model is trained and verified through training sets and validation sets. The control model can accurately predict the energy consumption under various working conditions. During further optimization, Bayesian optimization, genetic algorithm and other technologies can be used for parameter tuning to improve the generalization ability of the control model and the prediction accuracy under various working conditions.

[0058] Step 6: When the state variable x meets the requirements, the controllable variable μ is adjusted with the objective variable of minimizing the rotary dehumidification air conditioning system as the optimization objective, and the adjusted controllable variable μ and the state variable x are input into the optimal control model to obtain the predicted objective variable, and the parameters in the optimal control model are updated according to the difference between the predicted objective variable and the minimized objective variable to obtain the final control model;

[0059] The optimization goal in this embodiment is:

[0060]

[0061] T chill is the freezing water temperature, T steam is the steam temperature; E(T chill ,T steam ) represents the power consumption of the rotary dehumidification air conditioning system under the setting conditions of chilled water temperature and steam temperature;

[0062] Constraints:

[0063] H indoor =H(T chill ,T steam ,x)

[0064] H indoor ≤H min

[0065] Where x is the outdoor temperature, H(T chill ,T lteam , x) represents the indoor relative humidity under the setting conditions of outdoor temperature, freezing water temperature and steam temperature; H min Indicates the target humidity of the lithium battery production workshop in the target scenario;

[0066] When the controllable variable μ is adjusted, the above constraints need to be met; in actual operation, the balance point between energy consumption and humidity control effect is found through multi-objective optimization algorithm or heuristic search method; since the humidity control effect is closely related to the adjustment of chilled water temperature and steam temperature, and the adjustment of these parameters directly affects the energy consumption of the rotary dehumidification air-conditioning system, it is necessary to continuously try to adjust the chilled water temperature and steam temperature of different parameters through the control model, and gradually approach the optimal balance point between energy consumption and humidity control in the target scenario;

[0067] Step 7: Input the state variables x and controllable variables μ in multiple working conditions to be controlled into the final control model to obtain the target variable corresponding to each working condition to be controlled, and select the minimum value among the target variables corresponding to all working conditions to be controlled. Then, use the controllable variable μ corresponding to the minimum value to control the rotary dehumidification air-conditioning system.

[0068] In this embodiment, the control model is used as a virtual test platform to test different control schemes in a simulated environment, thereby reducing the trial and error cost of the actual system, and finding the control combination that meets the humidity requirements and has the lowest energy consumption through iteration; in addition, when the working conditions change, the control model can predict the impact of different environmental and control conditions on humidity control and energy consumption in real time, and automatically adjust the chilled water temperature and steam temperature through dynamic programming and reinforcement learning algorithms to adapt to environmental changes and uncertainties, thereby achieving the optimal dynamic balance between energy consumption and humidity control.

[0069] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A control method for a rotary dehumidification air conditioning system, characterized in that The steps include: Step 1: Collect the working environment parameters of the rotary dehumidification air conditioning system, and pre-process the collected data to form a data set; Step 2: Perform cluster analysis on the data set to obtain typical operating conditions of the rotary dehumidification air conditioning system; Step 3, extract and classify parameters of the typical working conditions of the rotary dehumidification air conditioning system in step 2 to obtain the state variable x, the controllable variable μ and the target variable y; Step 4: Analyze the state variable x, the controllable variable μ and the target variable y to obtain the relationship model satisfied by the state variable x, the controllable variable μ and the target variable y; Step 5: construct a control model for the rotary dehumidification air conditioning system, use the relational model to generate a sample set, the sample set consists of multiple different working conditions, divide the sample set into a training set and a verification set, use the training set to train the constructed control model to obtain the trained control model, and use the verification set to verify the trained control model to obtain the optimal control model; Step 6: When the state variable x meets the requirements, the controllable variable μ is adjusted with the objective variable of minimizing the rotary dehumidification air conditioning system as the optimization objective, and the adjusted controllable variable μ and the state variable x are input into the optimal control model to obtain the predicted objective variable, and the parameters in the optimal control model are updated according to the difference between the predicted objective variable and the minimized objective variable to obtain the final control model; Step 7: Input the state variables x and controllable variables μ in multiple working conditions to be controlled into the final control model to obtain the target variable corresponding to each working condition to be controlled, and select the minimum value among the target variables corresponding to all working conditions to be controlled. Then, use the controllable variable μ corresponding to the minimum value to control the rotary dehumidification air-conditioning system.

2. The control method according to claim 1, characterized in that: The data collected in step 1 includes at least one or more of the humidity of the place where the rotary dehumidification air-conditioning system is located, the temperature outside the place, the dew point temperature outside the place, the freezing water temperature, the steam flow, the cooling capacity, the steam temperature and the energy consumption.

3. The control method according to claim 1, characterized in that: The preprocessing process in step 1 includes one or more of outlier detection, missing value filling, data smoothing and standardization.

4. The control method according to any one of claims 1 to 3, characterized in that: The specific process of obtaining the typical working condition of the rotary dehumidification air conditioning system in step 2 is as follows: Select at least two clustering methods to perform cluster analysis on the data set respectively, compare the clustering results of each clustering method, select the clustering result with better performance as the final analysis result, and delete the outliers in the final analysis result, that is, obtain the typical working conditions of the rotary dehumidification air-conditioning system.

5. The control method according to claim 4, characterized in that: There are two clustering methods, namely K-means clustering method and DBSCAN clustering method.

6. The control method according to claim 4, characterized in that: The specific process in step 3 is: according to the time period corresponding to each cluster of typical working conditions, all parameters related thereto are extracted; and all the extracted parameters are divided into three categories according to their functions, namely, the state variable x, the controllable variable μ and the target variable y are obtained.

7. The control method according to claim 6, characterized in that: In step 4, a generalized additive model is used to analyze the state variable x, the controllable variable μ and the target variable y to obtain a fitted generalized additive model; Determine whether the result of the fitted generalized additive model is valid. If so, use the fitted generalized additive model as the relationship model satisfied by the state variable x, the controllable variable μ and the target variable y; if not, use the regression analysis method to analyze the state variable x, the controllable variable μ and the target variable y to obtain the relationship model satisfied by the state variable x, the controllable variable μ and the target variable y.

8. The control method according to claim 7, characterized in that: The specific process of using regression analysis method to analyze state variable x, controllable variable μ and target variable y is as follows: If the state variable x, the controllable variable μ and the target variable y show a linear relationship, the multivariate linear regression method is used to analyze the state variable x, the controllable variable μ and the target variable y; If the state variable x, the controllable variable μ and the target variable y present a nonlinear relationship, the multivariate nonlinear regression method or the support vector machine regression method is used to analyze the state variable x, the controllable variable μ and the target variable y.

9. The control method according to claim 1, characterized in that: The control model in step 5 adopts a neural network or a multivariate regression model.

Images