Air compressor connecting device
Through the combination of data detection and strategy setting modules, the k-mean clustering algorithm and load prediction model are used to realize automatic control of the load state of the air compressor unit, solving the stability and efficiency problems of the air compressor unit when the load changes. , improves operating efficiency.
Patent Information
- Application Number
- CN202411050420.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-19
AI Technical Summary
The existing air compressor units are difficult to operate stably when load changes, and their operating efficiency is not high. The number of machines needs to be adjusted manually to cope with changes in gas consumption.
The data detection module is used to obtain the operating data, and the load curve is predicted through the k-mean clustering algorithm and the load prediction model. The strategy setting module automatically adjusts the operating status and target exhaust pressure of the air compressor according to the prediction results, and the pressure setting module adjusts the supply. gas volume to achieve stable operation.
Through load curve prediction and automatic regulation, the air compressor unit is ensured to operate stably under different load states, improve operation efficiency and meet the gas needs in the factory.
Smart Images

Figure CN118981647A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of air compressor control technology, and more specifically, to an air compressor connection device. Background Art
[0002] A compressed air system is a system that compresses atmospheric air for industrial and commercial purposes. The principle is to compress atmospheric air to a set pressure through a compressor and store it in an air storage tank. Compressed air filters can remove impurities and moisture from the air, while pressure regulators are used to control the output pressure of the compressed air. Compressed air systems usually use piston compressors or screw compressors to achieve the compression process.
[0003] In the actual use of the air compressor units in the prior art, the number of units used needs to be continuously adjusted according to the changes in load, and the opening and closing of the air compressors are manually judged to increase or decrease the number of machines. If the gas consumption changes greatly in a day, the factory maintenance personnel need to constantly change the number of air compressors according to the pressure of the gas main, which makes it difficult for the units to operate stably and the operating efficiency is low. Summary of the invention
[0004] The present invention provides an air compressor connection device to solve the technical problems of poor stability and low operating efficiency of air compressor units in the prior art, including:
[0005] A data detection module is used to obtain the current operating data of the air compressor unit and determine the load prediction curve of the air compressor unit according to the current operating data of the air compressor unit;
[0006] A strategy setting module is used to determine the operating status of the air compressor unit according to the load prediction curve and set the air compressor control strategy according to the operating status;
[0007] The pressure setting module is used to determine the target exhaust pressure of each air compressor according to the current air compressor control strategy, determine the air supply volume according to the target exhaust pressure of each air compressor, and adjust the target exhaust pressure setting value of the air compressor group according to the air supply volume.
[0008] Furthermore, the data detection module includes:
[0009] A clustering unit, used for obtaining historical operation data of the air compressor unit, determining a historical load curve according to the historical operation data of the air compressor unit, and clustering the historical load curve based on a k-means clustering algorithm;
[0010] An analysis unit, used to determine the historical load classification according to the clustering results, and determine the key influencing factors of each classification according to the historical load classification;
[0011] Classify the historical load curves, and establish the load forecasting models corresponding to each classification according to the classification of the historical load curves;
[0012] The prediction unit is used to build a load prediction model according to the key influencing factors of each classification, obtain the operating data of the current air compressor unit, and determine the load prediction curve of the current air compressor unit according to the operating data of the current air compressor unit.
[0013] Furthermore, the clustering unit is used for:
[0014] Determine the historical exhaust pressure according to the historical operation data of the air compressor unit, and set the number of clusters k according to the historical exhaust pressure;
[0015] Extracting load curve shape data and average load value of the historical load curve, forming a load curve data set according to the load curve shape data and the average load value, and randomly selecting k cluster centers of the load curve data set;
[0016] Calculate the Euclidean distance between each load curve data set and the initial cluster center, and divide each load curve data set into a corresponding cluster according to the Euclidean distance between each load curve data set and the initial cluster center;
[0017] Calculate the average value of all load curve data sets in each cluster, and update the cluster center according to the average value of all load curve data sets in each cluster;
[0018] Repeat the above steps until the cluster center no longer changes, and obtain k final cluster centers to obtain the clustering results of the historical load curve.
[0019] Furthermore, the analysis unit is used for:
[0020] Classify the historical load curves corresponding to each load curve data set according to the clustering results to obtain the historical load classification;
[0021] Obtain multiple influencing factors corresponding to each historical load curve classification, and calculate the correlation between the influencing factors and the historical load curve;
[0022] The influencing factors in each category are sorted according to the correlation between the influencing factors and the historical load curve. The influencing factors with the top three correlations in each category are screened out according to the sorting results, and the influencing factors with the top three correlations in the category are set as the key influencing factors of the corresponding category.
[0023] Furthermore, the prediction unit is used for:
[0024] Establish a data set based on the time point data of the key influencing factors of each classification and the time point data of the corresponding historical load curve, and establish an initial load forecasting model based on the data set;
[0025] The initial load forecasting model is trained according to the data set to obtain the final load forecasting model;
[0026] The key influencing factors of the corresponding classification of the current exhaust pressure are obtained, and the key influencing factors of the corresponding classification of the current exhaust pressure are input into the load prediction model to obtain the load prediction curve of the current air compressor unit.
[0027] Furthermore, the policy setting module includes a state unit, and the state unit is used to:
[0028] Obtain a preset sliding time window, and divide the load prediction curve of the air compressor unit into a plurality of sub-load curves according to the preset sliding time window;
[0029] Calculate the average load value of each sub-load curve according to the sub-load curve, screen out the sub-load curve whose average load value exceeds the first preset threshold, and count the number of sub-load curves whose average load value exceeds the first preset threshold;
[0030] Obtaining a preset load threshold, if the number of sub-load curves whose average load value exceeds the first preset threshold is greater than the preset load threshold, determining that the current operating state of the air compressor unit is an overload state;
[0031] If the number of sub-load curves whose average load values exceed the first preset threshold is less than or equal to the preset load threshold, a load fluctuation curve is drawn according to the average load value of each sub-load curve in the load forecast curve, a preset rolling time window is obtained, several absolute values of the slopes of the load fluctuation curve in the preset rolling window are calculated, and the number of rolling time windows whose absolute values of the slopes are greater than the second preset threshold is counted;
[0032] If the number of rolling time windows whose slope absolute value is greater than the second preset threshold is greater than the preset fluctuation threshold, it is determined that the current operating state of the air compressor unit is a load fluctuation state;
[0033] If the number of rolling time windows whose slope absolute values are greater than the second preset threshold is less than or equal to the preset fluctuation threshold, it is determined that the current operating state of the air compressor unit is a low-load state.
[0034] Furthermore, the strategy setting module further includes a strategy unit, and the strategy unit is used to:
[0035] If the current operating state of the air compressor unit is overloaded, it will enter the pre-addition delay time. After the delay time ends, an additional air compressor will be added.
[0036] If the current operating state of the air compressor unit is load fluctuation state, it will enter the pre-addition delay. After the delay time ends, if the exhaust pressure of the air compressor unit decreases, an additional air compressor will be added;
[0037] If the current operating state of the air compressor unit is a low-load state, the pre-reduction delay is entered. After the delay timing ends, if the exhaust pressure of the air compressor unit is greater than the third preset threshold, one air compressor is shut down.
[0038] Furthermore, the pressure setting module includes a setting unit, and the setting unit is used to:
[0039] Obtain the operating time of each air compressor in the air compressor group that is in the turned-on state, and set the exhaust pressure weight of the air compressor according to the operating time of each air compressor;
[0040] The target exhaust pressure setting value of the air compressor group is obtained, and the target exhaust pressure of each air compressor is determined according to the target exhaust pressure setting value of the air compressor group based on the exhaust pressure weight, so that the exhaust pressure of the air compressor group reaches the target exhaust pressure.
[0041] Furthermore, the setting unit sets the exhaust pressure weight of the air compressor according to the operation time of each air compressor, including:
[0042] The exhaust pressure weight of the air compressor is determined according to the exhaust pressure weight calculation formula. The exhaust pressure weight calculation formula is as follows:
[0043]
[0044] Among them, q is the exhaust pressure weight of the air compressor, α is the preset exhaust pressure weight mean, t c is the running time of the air compressor, t s is the running time tolerance, and exp represents the natural exponential function.
[0045] Furthermore, the pressure setting module further includes an adjustment unit, and the adjustment unit is used to:
[0046] Obtain the current air supply of the air compressor unit, calculate the difference between the target air supply and the current air supply of the air compressor unit, and obtain the air supply deviation of the current air compressor unit;
[0047] Obtaining a preset air supply volume deviation allowable value, calculating a ratio of a current air supply volume deviation to the air supply volume deviation allowable value, normalizing the ratio of the current air supply volume deviation to the air supply volume deviation allowable value, and obtaining an exhaust pressure adjustment coefficient;
[0048] The target exhaust pressure setting value is adjusted by multiplying the exhaust pressure adjustment coefficient by the target exhaust pressure setting value.
[0049] The beneficial effects of the present invention are:
[0050] By applying the above technical scheme, the present invention can accurately predict the operating status of the air compressor unit by predicting the load curve of the air compressor unit, and automatically add or subtract the air compressor unit to enable the unit to operate stably. By adjusting the target exhaust pressure setting value, it is ensured that the unit can always meet the gas demand in the factory, thereby greatly improving the operating efficiency of the unit. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0052] Figure 1 The figure shows the overall structure of an air compressor connection device proposed in an embodiment of the present invention. DETAILED DESCRIPTION
[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0054] The present application embodiment provides an air compressor connection device, such as Figure 1 As shown, including:
[0055] The data detection module is used to obtain the operating data of the current air compressor unit and determine the load prediction curve of the air compressor unit based on the operating data of the current air compressor unit; the strategy setting module is used to determine the operating status of the air compressor unit based on the load prediction curve and set the air compressor control strategy according to the operating status; the pressure setting module is used to determine the target exhaust pressure of each air compressor according to the current air compressor control strategy, determine the air supply according to the target exhaust pressure of each air compressor, and adjust the target exhaust pressure setting value of the air compressor unit according to the air supply.
[0056] In this embodiment, by connecting all the air compressors in the air compressor unit, the control of the air compressor adder and subtractor and the target exhaust pressure setting value is realized, the load curve of the air compressor unit is predicted by the data detection module, and the operating status of the air compressor unit is predicted by the strategy setting module, so as to set the air compressor control strategy, and the target exhaust pressure of each air compressor and the target exhaust pressure setting value of the unit are set by the pressure setting module to achieve stable operation of the air compressor unit.
[0057] In some embodiments of the present application, the data detection module includes: a clustering unit, which is used to obtain historical operating data of the air compressor unit, determine the historical load curve based on the historical operating data of the air compressor unit, and cluster the historical load curve based on the k-means clustering algorithm; an analysis unit, which is used to determine the historical load classification based on the clustering results, and determine the key influencing factors of each classification based on the historical load classification; classify the historical load curves, and establish a load prediction model corresponding to each classification based on the classification of the historical load curves; a prediction unit, which is used to construct a load prediction model based on the key influencing factors of each classification, obtain the operating data of the current air compressor unit, and determine the load prediction curve of the current air compressor unit based on the operating data of the current air compressor unit.
[0058] In this embodiment, the historical load curves are classified by the clustering unit, a load prediction model is established for the key influencing factors of each classification by the analysis unit, and the load curve of the current air compressor unit is predicted by the load prediction model.
[0059] In some embodiments of the present application, the clustering unit is used to: determine the historical exhaust pressure based on the historical operation data of the air compressor unit, and set the number of clusters k based on the historical exhaust pressure; extract the load curve morphology data and the average load value of the historical load curve, form a load curve data set based on the load curve morphology data and the average load value, and randomly select k clustering centers of the load curve data set; calculate the Euclidean distance of each load curve data set to the initial clustering center, and divide each load curve data set into a corresponding cluster according to the Euclidean distance of each load curve data set to the initial clustering center; calculate the average value of all load curve data sets in each cluster, and update the clustering center according to the average value of all load curve data sets in each cluster; repeat the above steps until the clustering center no longer changes, obtain k final clustering centers, and obtain the clustering result of the historical load curve.
[0060] In this embodiment, the number of clusters k is set by the difference between the maximum and minimum values of the historical exhaust pressure. The larger the difference, the larger the set k value is, and the more classification results for the historical load curve are. The curve morphology data and the average load value of the historical load curve are clustered based on the k-means clustering algorithm, and the clustering results are divided into k exhaust pressure intervals.
[0061] In some embodiments of the present application, the analysis unit is used to: classify the historical load curves corresponding to each load curve data set according to the clustering results to obtain the historical load classification; obtain multiple influencing factors corresponding to each historical load curve classification, and calculate the correlation between the influencing factors and the historical load curve; sort the influencing factors in each classification according to the correlation between the influencing factors and the historical load curve, and screen out the influencing factors with the top three correlations in each classification according to the sorting results, and set the influencing factors with the top three correlations in the classification as the key influencing factors of the corresponding classification.
[0062] In this embodiment, the influencing factors in the load curve classification may include: target exhaust pressure, environmental stability, machine efficiency, cooling efficiency, power supply voltage, etc. The correlation between the influencing factors and the historical load curve is obtained by calculating the Pearson correlation coefficient between each influencing factor in the classification and the load curve, and three key influencing factors are screened out according to the sorting results.
[0063] In some embodiments of the present application, the prediction unit is used to: establish a data set based on the time point data of the key influencing factors of each classification and the time point data of the corresponding historical load curve, and establish an initial load prediction model based on the data set; train the initial load prediction model based on the data set to obtain the final load prediction model; obtain the key influencing factors of the classification corresponding to the current exhaust pressure, input the key influencing factors of the classification corresponding to the current exhaust pressure into the load prediction model, and obtain the load prediction curve of the current air compressor unit.
[0064] In this embodiment, a load prediction model is established based on a neural network. A data set is established by extracting the key influencing factors at each time point and the load data at the corresponding time point, and the initial load prediction model is trained to achieve the establishment of the load prediction model. The type of the current air compressor unit is determined by the target exhaust pressure range in which the current air compressor unit is located. After extracting the key influencing factors corresponding to the current type, the load curve of the current air compressor unit is predicted through the load prediction model.
[0065] In some embodiments of the present application, the strategy setting module includes a state unit, which is used to: obtain a preset sliding time window, and divide the load prediction curve of the air compressor unit into a number of sub-load curves according to the preset sliding time window; calculate the average load value of each sub-load curve according to the sub-load curve, screen out the sub-load curves whose average load values exceed the first preset threshold, and count the number of sub-load curves whose average load values exceed the first preset threshold; obtain the preset load threshold, and if the number of sub-load curves whose average load values exceed the first preset threshold is greater than the preset load threshold, determine that the current operating state of the air compressor unit is an overload state; if the average load value exceeds the first preset threshold If the number of sub-load curves is less than or equal to the preset load threshold, a load fluctuation curve is drawn according to the average load value of each sub-load curve in the load forecast curve, the preset rolling time window is obtained, several absolute values of the slopes of the load fluctuation curve in the preset rolling window are calculated, and the number of rolling time windows with absolute slope values greater than the second preset threshold is counted; if the number of rolling time windows with absolute slope values greater than the second preset threshold is greater than the preset fluctuation threshold, it is determined that the current operating state of the air compressor unit is a load fluctuation state; if the number of rolling time windows with absolute slope values greater than the second preset threshold is less than or equal to the preset fluctuation threshold, it is determined that the current operating state of the air compressor unit is a low load state.
[0066] In this embodiment, the sub-load curve is divided by a sliding time window, and whether the unit operation state is an overload state is determined by calculating the number of average load values in the sub-load curve that exceed the first preset threshold value. If the current unit is not in an overload state, the average load value of the load prediction curve is further connected to form a load fluctuation curve, and the absolute value of the slope is used to determine whether the current unit is in a load fluctuation state. If the current unit is not in a load fluctuation state, the unit is determined to be in a low load state.
[0067] In some embodiments of the present application, the strategy setting module also includes a strategy unit, which is used to: if the current operating state of the air compressor unit is an overload state, it enters a pre-addition delay, and after the delay timing ends, an additional air compressor is added; if the current operating state of the air compressor unit is a load fluctuation state, it enters a pre-addition delay, and after the delay timing ends, if the exhaust pressure of the air compressor unit decreases, an additional air compressor is added; if the current operating state of the air compressor unit is a low load state, it enters a pre-reduction delay, and after the delay timing ends, if the exhaust pressure of the air compressor unit is greater than a third preset threshold, an air compressor is shut down.
[0068] In this embodiment, the air compressor unit is automatically added or subtracted by detecting the operating status of the air compressor unit. When the unit is in a load fluctuation state, timing starts from the detection of the load fluctuation state. When the exhaust pressure of the unit after the timing is over is lower than the exhaust pressure when the timing starts, an additional air compressor is added. When the unit is in a low load state, the third preset threshold is set to 1.5 times the target exhaust pressure setting value. When the exhaust pressure of the unit after the timing is over is greater than 1.5 times the target exhaust pressure setting value, an air compressor is closed.
[0069] In some embodiments of the present application, the pressure setting module includes a setting unit, which is used to: obtain the operating time of each air compressor in the air compressor group that is in an open state, and set the exhaust pressure weight of the air compressor according to the operating time of each air compressor; obtain the target exhaust pressure setting value of the air compressor group, and determine the target exhaust pressure of each air compressor based on the exhaust pressure weight according to the target exhaust pressure setting value of the air compressor group, so that the exhaust pressure of the air compressor group reaches the target exhaust pressure.
[0070] In some embodiments of the present application, the setting unit sets the exhaust pressure weight of the air compressor according to the running time of each air compressor, including: determining the exhaust pressure weight of the air compressor according to the exhaust pressure weight calculation formula, and the exhaust pressure weight calculation formula is specifically,
[0071]
[0072] Among them, q is the exhaust pressure weight of the air compressor, α is the preset exhaust pressure weight mean, t c is the running time of the air compressor, t s is the running time tolerance, and exp represents the natural exponential function.
[0073] In this embodiment, the target exhaust pressure of each air compressor in the open state is first divided evenly, and then the target exhaust pressure is weighted based on the operating time of the air compressor to prevent the air compressor from being overloaded due to long operating time, thereby effectively improving the stability of the unit.
[0074] In some embodiments of the present application, the pressure setting module also includes an adjustment unit, which is used to: obtain the current air supply of the air compressor unit, calculate the difference between the target air supply and the current air supply of the air compressor unit, and obtain the air supply deviation of the current air compressor unit; obtain a preset air supply deviation allowable value, calculate the ratio of the current air supply deviation to the air supply deviation allowable value, normalize the ratio of the current air supply deviation to the air supply deviation allowable value, and obtain an exhaust pressure adjustment coefficient; multiply the exhaust pressure adjustment coefficient by the target exhaust pressure setting value, and adjust the target exhaust pressure setting value.
[0075] In this embodiment, the target exhaust pressure setting value is adjusted by calculating the ratio of the current air supply deviation to the allowable air supply deviation, and converting the interval of the ratio of the current air supply deviation to the allowable air supply deviation to [0, 2] through a normalization processing formula.
[0076] By applying the above technical scheme, the present invention includes a data detection module, which is used to obtain the operating data of the current air compressor unit, and determine the load prediction curve of the air compressor unit according to the operating data of the current air compressor unit; a strategy setting module, which is used to determine the operating state of the air compressor unit according to the load prediction curve, and set the air compressor control strategy according to the operating state; a pressure setting module, which is used to determine the target exhaust pressure of each air compressor according to the current air compressor control strategy, determine the air supply according to the target exhaust pressure of each air compressor, and adjust the target exhaust pressure setting value of the air compressor unit according to the air supply. The present invention predicts the load curve of the air compressor unit, thereby controlling each air compressor in the unit, and adjusts the exhaust pressure setting value at the same time, which can effectively reduce the load fluctuation of the air compressor unit and achieve stable operation of the air compressor unit.
[0077] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.
[0078] Those skilled in the art will appreciate that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more devices different from the implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.
[0079] 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 it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. An air compressor connection device, characterized in that: include: A data detection module is used to obtain the current operating data of the air compressor unit and determine the load prediction curve of the air compressor unit according to the current operating data of the air compressor unit; A strategy setting module is used to determine the operating status of the air compressor unit according to the load prediction curve and set the air compressor control strategy according to the operating status; The pressure setting module is used to determine the target exhaust pressure of each air compressor according to the current air compressor control strategy, determine the air supply volume according to the target exhaust pressure of each air compressor, and adjust the target exhaust pressure setting value of the air compressor group according to the air supply volume.
2. The air compressor connection device according to claim 1, characterized in that: The data detection module comprises: A clustering unit, used for obtaining historical operation data of the air compressor unit, determining a historical load curve according to the historical operation data of the air compressor unit, and clustering the historical load curve based on a k-means clustering algorithm; An analysis unit, used to determine the historical load classification according to the clustering results, and determine the key influencing factors of each classification according to the historical load classification; Classify the historical load curves, and establish the load forecasting models corresponding to each classification according to the classification of the historical load curves; The prediction unit is used to build a load prediction model according to the key influencing factors of each classification, obtain the operating data of the current air compressor unit, and determine the load prediction curve of the current air compressor unit according to the operating data of the current air compressor unit.
3. The air compressor connection device according to claim 2, characterized in that: The clustering unit is used for: Determine the historical exhaust pressure according to the historical operation data of the air compressor unit, and set the number of clusters k according to the historical exhaust pressure; Extracting load curve shape data and average load value of the historical load curve, forming a load curve data set according to the load curve shape data and the average load value, and randomly selecting k cluster centers of the load curve data set; Calculate the Euclidean distance between each load curve data set and the initial cluster center, and divide each load curve data set into a corresponding cluster according to the Euclidean distance between each load curve data set and the initial cluster center; Calculate the average value of all load curve data sets in each cluster, and update the cluster center according to the average value of all load curve data sets in each cluster; Repeat the above steps until the cluster center no longer changes, and obtain k final cluster centers to obtain the clustering results of the historical load curve.
4. The air compressor connection device according to claim 3, characterized in that: The analysis unit is used for: Classify the historical load curves corresponding to each load curve data set according to the clustering results to obtain the historical load classification; Obtain multiple influencing factors corresponding to each historical load curve classification, and calculate the correlation between the influencing factors and the historical load curve; The influencing factors in each category are sorted according to the correlation between the influencing factors and the historical load curve. The influencing factors with the top three correlations in each category are screened out according to the sorting results, and the influencing factors with the top three correlations in the category are set as the key influencing factors of the corresponding category.
5. The air compressor connection device according to claim 4, characterized in that: The prediction unit is used to: Establish a data set based on the time point data of the key influencing factors of each classification and the time point data of the corresponding historical load curve, and establish an initial load forecasting model based on the data set; The initial load forecasting model is trained according to the data set to obtain the final load forecasting model; The key influencing factors of the corresponding classification of the current exhaust pressure are obtained, and the key influencing factors of the corresponding classification of the current exhaust pressure are input into the load prediction model to obtain the load prediction curve of the current air compressor unit.
6. The air compressor connection device according to claim 1, characterized in that: The policy setting module includes a state unit, and the state unit is used to: Obtain a preset sliding time window, and divide the load prediction curve of the air compressor unit into a plurality of sub-load curves according to the preset sliding time window; Calculate the average load value of each sub-load curve according to the sub-load curve, screen out the sub-load curve whose average load value exceeds the first preset threshold, and count the number of sub-load curves whose average load value exceeds the first preset threshold; Obtaining a preset load threshold, if the number of sub-load curves whose average load value exceeds the first preset threshold is greater than the preset load threshold, determining that the current operating state of the air compressor unit is an overload state; If the number of sub-load curves whose average load values exceed the first preset threshold is less than or equal to the preset load threshold, a load fluctuation curve is drawn according to the average load value of each sub-load curve in the load forecast curve, a preset rolling time window is obtained, several absolute values of the slopes of the load fluctuation curve in the preset rolling window are calculated, and the number of rolling time windows whose absolute values of the slopes are greater than the second preset threshold is counted; If the number of rolling time windows whose slope absolute value is greater than the second preset threshold is greater than the preset fluctuation threshold, it is determined that the current operating state of the air compressor unit is a load fluctuation state; If the number of rolling time windows whose slope absolute values are greater than the second preset threshold is less than or equal to the preset fluctuation threshold, it is determined that the current operating state of the air compressor unit is a low-load state.
7. The air compressor connection device according to claim 6, characterized in that: The strategy setting module further includes a strategy unit, which is used to: If the current operating state of the air compressor unit is overloaded, it will enter the pre-addition delay time. After the delay time ends, an additional air compressor will be added. If the current operating state of the air compressor unit is load fluctuation state, it will enter the pre-addition delay. After the delay time ends, if the exhaust pressure of the air compressor unit decreases, an additional air compressor will be added; If the current operating state of the air compressor unit is a low-load state, the pre-reduction delay is entered. After the delay timing ends, if the exhaust pressure of the air compressor unit is greater than the third preset threshold, one air compressor is shut down.
8. The air compressor connection device according to claim 1, characterized in that: The pressure setting module comprises a setting unit, and the setting unit is used to: Obtain the operating time of each air compressor in the air compressor group that is in the turned-on state, and set the exhaust pressure weight of the air compressor according to the operating time of each air compressor; The target exhaust pressure setting value of the air compressor group is obtained, and the target exhaust pressure of each air compressor is determined according to the target exhaust pressure setting value of the air compressor group based on the exhaust pressure weight, so that the exhaust pressure of the air compressor group reaches the target exhaust pressure.
9. The air compressor connection device according to claim 8, characterized in that: The setting unit sets the exhaust pressure weight of the air compressor according to the running time of each air compressor, including: The exhaust pressure weight of the air compressor is determined according to the exhaust pressure weight calculation formula. The exhaust pressure weight calculation formula is as follows: Among them, q is the exhaust pressure weight of the air compressor, α is the preset exhaust pressure weight mean, t c is the running time of the air compressor, t s is the running time tolerance, and exp represents the natural exponential function.
10. The air compressor connection device according to claim 8, characterized in that: The pressure setting module further includes an adjustment unit, which is used to: Obtain the current air supply of the air compressor unit, calculate the difference between the target air supply and the current air supply of the air compressor unit, and obtain the air supply deviation of the current air compressor unit; Obtaining a preset air supply volume deviation allowable value, calculating a ratio of a current air supply volume deviation to the air supply volume deviation allowable value, normalizing the ratio of the current air supply volume deviation to the air supply volume deviation allowable value, and obtaining an exhaust pressure adjustment coefficient; The target exhaust pressure setting value is adjusted by multiplying the exhaust pressure adjustment coefficient by the target exhaust pressure setting value.
