An air compressor control method and system

Abstract

The present invention discloses an air compressor control method and system, which includes: acquiring historical output pressure data and historical rotational speed data of the air compressor, and preprocessing the two data; analyzing the correlation relationship between the two preprocessed data, and constructing a relationship model between pressure and rotational speed based on the two data and the correlation relationship; acquiring the required output pressure, and setting a rotational speed control strategy based on it and the relationship model; operating for a preset time period based on the rotational speed control strategy, and acquiring the current real-time output pressure data; judging the difference between the real-time output pressure data and the required output pressure, and determining an optimization adjustment strategy according to the difference; adjusting and optimizing the rotational speed control strategy based on the optimization adjustment strategy. The present invention combines machine learning and optimization strategies to achieve intelligent control and optimization. Through continuous learning and adjustment, the air compressor can adapt to different working conditions and requirements, automatically adjust the rotational speed control strategy to meet the requirements of the air compressor for output pressure.

Description

Technical Field

[0001] The present invention relates to the technical field of air compressor control, and particularly to an air compressor control method and system. Background Art

[0002] Air compressors are devices widely used in industrial and commercial fields to compress air into high-pressure gas. To ensure the normal operation of air compressors and meet specific process requirements, appropriate control methods are needed to regulate and optimize their performance. One of the control objectives of air compressors is to meet specific output pressure requirements, and different applications may have different requirements for output pressure, such as the pressure requirements for supplying process equipment, the working pressure requirements for pneumatic equipment, etc. To ensure the stability of the air compressor output pressure and adjust the working state of the compressor when needed to meet the requirements.

[0003] However, traditional control methods usually control based on fixed logic and preset rules. However, this method lacks flexibility and adaptability and cannot be intelligently adjusted according to the actual working conditions of the air compressor, resulting in low energy efficiency under different working conditions, causing energy consumption waste, and unable to achieve the balance of the best performance and energy consumption. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides an air compressor control method and system, including:

[0005] Obtain the historical output pressure data and historical speed data of the air compressor in the past, and preprocess the historical output pressure data and historical speed data;

[0006] Analyze the correlation relationship between the preprocessed historical output pressure data and historical speed data, and construct a relationship model between pressure and speed according to the historical output pressure data, historical speed data and their correlation relationship;

[0007] Obtain the output pressure requirement of the air compressor, and set the speed control strategy of the air compressor based on the output pressure requirement and the relationship model;

[0008] Run for a preset period based on the speed control strategy, and obtain the current real-time output pressure data of the air compressor;

[0009] Judge the difference between the real-time output pressure data and the output pressure requirement, and determine the optimization adjustment strategy according to the difference;

[0010] Adjust and optimize the speed control strategy of the air compressor based on the optimization adjustment strategy.

[0011] Further, the preprocessing of the historical output pressure data and historical speed data includes:

[0012] Clean the historical output pressure data and historical rotational speed data, removing noise, missing values, and outliers from the data;

[0013] Perform data normalization on the cleaned historical output pressure data and historical rotational speed data.

[0014] Furthermore, analyzing the correlation relationship between the preprocessed historical output pressure data and historical rotational speed data includes:

[0015] Taking the historical rotational speed data as the independent variable and the historical output pressure data as the dependent variable, draw a scatter plot of the output pressure against the rotational speed;

[0016] Analyze the data trend line or the distribution of data points in the scatter plot. If a linear trend is presented in the scatter plot, the correlation relationship is a linear correlation relationship; if a non-linear trend is presented in the scatter plot, the correlation relationship is a non-linear correlation relationship.

[0017] Furthermore, constructing a relationship model between the pressure and the rotational speed based on the historical output pressure data, historical rotational speed data, and their correlation relationship includes:

[0018] Taking the historical rotational speed data as the model input data and the historical rotational speed data as the model output data;

[0019] Based on the model input data, model output data, correlation relationship, and a preset neural network model, construct an initial relationship model;

[0020] Divide multiple sets of model input data and models into a training set and a test set according to a certain ratio, and input the training set and the test set into the initial relationship model to train and test the initial relationship model until the initial relationship model meets the preset convergence conditions, obtaining the relationship model between the output pressure and the rotational speed.

[0021] Furthermore, obtaining the output pressure requirement of the air compressor and setting the rotational speed control strategy of the air compressor based on the output pressure requirement and the relationship model includes:

[0022] Taking the output pressure requirement as the model input data and inputting it into the relationship model, and outputting through the relationship model to obtain rotational speed prediction data;

[0023] Set the rotational speed control strategy of the air compressor according to the rotational speed prediction data.

[0024] Furthermore, judging the difference between the real-time output pressure data and the output pressure requirement includes:

[0025] Obtain the real-time output pressure data of the air compressor and the output pressure requirement, and calculate the difference between the real-time output pressure data and the output pressure requirement;

[0026] Calculate the degree of difference of the difference according to the difference, where the expression of the degree of difference is:

[0027]

[0028] Among them, η1 is the degree of difference, and λ n is the weight coefficient of the difference between the real-time output pressure data and the required output pressure at the nth time point, and t n is the real-time output pressure data at the nth time point, and t is the required output pressure.

[0029] Furthermore, determining the optimization adjustment strategy according to the difference includes:

[0030] Judge the degree of difference of the difference. If the degree of difference = 0, continue to control the speed of the air compressor based on the current speed control strategy;

[0031] If the degree of difference > 0, determine the optimization adjustment strategy according to the degree of difference;

[0032] There are several pre-set corresponding relationships between the optimization adjustment strategy and the degree-of-difference interval. For each optimization adjustment strategy interval of the heating system, several degrees of difference are associated;

[0033] Judge the degree-of-difference interval where the degree of difference is located, and determine the optimization adjustment strategy according to the mapping relationship in the several corresponding relationships between the optimization adjustment strategy and the degree-of-difference interval.

[0034] The present invention also provides an air compressor control system, including:

[0035] An acquisition module, configured to acquire the historical output pressure data and historical speed data of the air compressor in the past, and preprocess the historical output pressure data and historical speed data;

[0036] A modeling module, configured to analyze the correlation relationship between the preprocessed historical output pressure data and historical speed data, and construct a relationship model between pressure and speed according to the historical output pressure data, historical speed data and their correlation relationship;

[0037] A setting module, configured to acquire the required output pressure of the air compressor, and set the speed control strategy of the air compressor based on the required output pressure and the relationship model;

[0038] An operation module, configured to operate for a preset time period based on the speed control strategy, and acquire the current real-time output pressure data of the air compressor;

[0039] A determination module, configured to judge the difference between the real-time output pressure data and the required output pressure, and determine the optimization adjustment strategy according to the difference;

[0040] An optimization module for adjusting and optimizing the rotational speed control strategy of an air compressor based on an optimization adjustment strategy.

[0041] Compared with the prior art, the beneficial effects of the air compressor control method and system according to the embodiments of the present invention are as follows:

[0042] By analyzing historical data and constructing a relationship model, the present invention can determine the relationship between the optimal output pressure and rotational speed, thereby optimizing the rotational speed control strategy, helping the air compressor achieve the best efficiency under different working conditions, reducing energy consumption, and lowering production costs.

[0043] Based on the relationship model and real-time data, the present invention can dynamically adjust the rotational speed control strategy, enabling the air compressor to maintain a stable output pressure under different loads and working conditions, improving the performance and stability of the system, and ensuring product quality and production efficiency.

[0044] The present invention combines machine learning and optimization strategies to achieve intelligent control and optimization. Through continuous learning and adjustment, the air compressor can adapt to different working conditions and requirements, automatically adjust the rotational speed control strategy to meet the requirements of the air compressor for output pressure. Brief Description of the Drawings

[0045] Figure 1 is a schematic flow structure diagram of the air compressor control method in the embodiments of the present invention;

[0046] Figure 2 is a schematic composition diagram of the air compressor control system in the embodiments of the present invention. Detailed Embodiments

[0047] The following further describes in detail the specific embodiments of the present application in conjunction with the drawings and embodiments. The following embodiments are used to illustrate the present invention but are not used to limit the scope of the present invention.

[0048] In the description of the present application, it should be understood that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the platform or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present application.

[0049] The terms "first", "second" are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second" may explicitly or implicitly include one or more of such features. In the description of this application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0050] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected to" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0051] As Figure 1 shown, in the embodiments of this application, an air compressor control method is provided, including: S100: Obtain the historical output pressure data and historical speed data of the air compressor in the past, and preprocess the historical output pressure data and historical speed data; S200: Analyze the correlation relationship between the preprocessed historical output pressure data and historical speed data, and construct a relationship model between pressure and speed based on the historical output pressure data, historical speed data and their correlation relationship; S300: Obtain the output pressure requirement of the air compressor, and set the speed control strategy of the air compressor based on the output pressure requirement and the relationship model; S400: Run for a preset period based on the speed control strategy, and obtain the current real-time output pressure data of the air compressor; S500: Judge the difference between the real-time output pressure data and the output pressure requirement, and determine the optimization adjustment strategy according to the difference; S600: Adjust and optimize the speed control strategy of the air compressor based on the optimization adjustment strategy.

[0052] Furthermore, by analyzing historical data and constructing a relationship model, the present invention can determine the optimal relationship between output pressure and speed, thereby optimizing the speed control strategy, helping the air compressor achieve the best efficiency under different working conditions, reducing energy consumption, and lowering production costs; based on the relationship model and real-time data, the present invention can dynamically adjust the speed control strategy, enabling the air compressor to maintain a stable output pressure under different loads and working conditions, improving the performance and stability of the system, and ensuring product quality and production efficiency; the present invention combines machine learning and optimization strategies to achieve intelligent control and optimization. By continuously learning and adjusting, the air compressor can adapt to different working conditions and requirements, and automatically adjust the speed control strategy to meet the requirements of the air compressor for output pressure.

[0053] In an embodiment of the present application, an air compressor control method is provided. The preprocessing of historical output pressure data and historical rotational speed data includes: performing data cleaning on the historical output pressure data and historical rotational speed data to remove noise, missing values, and outliers in the data; performing data normalization processing on the cleaned historical output pressure data and historical rotational speed data.

[0054] Specifically, for data cleaning of historical output pressure data and historical rotational speed data, duplicate data is removed by checking for duplicate data points in the historical data and removing them to ensure data uniqueness. Noise is removed using filtering techniques or smoothing algorithms to reduce the impact of random errors on data analysis. Missing values are processed by checking for missing values in the historical data and removing the data points where the missing values are located to ensure data integrity and continuity. Outliers are processed by detecting and handling outliers in the historical data, using statistical methods (such as the 3σ principle) or domain knowledge to identify outliers and making corrections or removals. An appropriate normalization method is selected to scale the data to a specified range so that the data has similar scales and ranges. By performing data cleaning and normalization processing, noise, missing values, and outliers in the data can be eliminated, improving the quality and accuracy of the data and providing a reliable data basis for subsequent data analysis and modeling.

[0055] In an embodiment of the present application, an air compressor control method is provided. The analysis of the correlation relationship between the preprocessed historical output pressure data and historical rotational speed data includes: taking the historical rotational speed data as the independent variable and the historical output pressure data as the dependent variable, and plotting a scatter plot of output pressure versus rotational speed; analyzing the data trend line or the distribution of data points in the scatter plot. If a linear trend is presented in the scatter plot, the correlation relationship is a linear correlation relationship; if a non-linear trend is presented in the scatter plot, the correlation relationship is a non-linear correlation relationship.

[0056] Specifically, taking the historical rotational speed data as the independent variable and the historical output pressure data as the dependent variable, a scatter plot is plotted with the rotational speed on the x-axis and the output pressure on the y-axis, and each data point represents a sample. Observe the trend line or the distribution of data points in the scatter plot. If the scatter plot shows a linear trend and the data points are distributed near a straight line, a linear regression method can be selected. If the scatter plot shows a non-linear trend and the data points are not distributed on a straight line, a polynomial regression or other non-linear regression methods may be required. Among them, linear regression estimates a straight line through the least squares method to represent the linear relationship between rotational speed and output pressure. After fitting, a regression equation and related regression coefficients can be obtained for predicting the output pressure. Polynomial regression can approximately describe the non-linear relationship between rotational speed and output pressure by fitting a polynomial function, and an appropriate polynomial order can be selected for fitting according to the distribution of data points.

[0057] In an embodiment of the present application, an air compressor control method is provided. The method for constructing a relationship model between pressure and speed based on historical output pressure data, historical speed data, and their correlation relationships includes: using the historical speed data as model input data and the historical output pressure data as model output data; constructing an initial relationship model based on the model input data, model output data, correlation relationships, and a preset neural network model; dividing multiple sets of model input data and models into a training set and a test set according to a certain ratio, and inputting the training set and the test set into the initial relationship model to train and test the initial relationship model until the initial relationship model meets the preset convergence conditions, thereby obtaining a relationship model between output pressure and speed.

[0058] Specifically, use the historical speed data as the input data of the model and the historical output pressure data as the output data of the model; select a suitable neural network model to construct the relationship model, such as using a Feedforward Neural Network or other suitable model structures, and determine hyperparameters such as the number of layers of the neural network and the number of neurons in each layer according to the characteristics of the data and the requirements of the problem; divide the data set into a training set and a test set according to a certain ratio. The training set is used for parameter training and optimization of the model, and the test set is used to evaluate the performance and generalization ability of the model. Divide the data set into a training set according to a ratio of 70 - 80%, and the remaining 20 - 30% is used as the test set; input the training set into the initial relationship model and perform training and optimization of the model through the backpropagation algorithm. During the training process, perform iterative training according to the preset convergence conditions (such as the convergence of the loss function) until the model meets the convergence conditions.

[0059] In an embodiment of the present application, an air compressor control method is provided. The method for obtaining the output pressure requirement of the air compressor and setting the speed control strategy of the air compressor based on the output pressure requirement and the relationship model includes: using the output pressure requirement as model input data and inputting it into the relationship model, and obtaining speed prediction data through the output of the relationship model; setting the speed control strategy of the air compressor according to the speed prediction data.

[0060] Specifically, use the output pressure requirement as the input data of the model and the historical speed data as the output data of the model; input the output pressure requirement into the model and obtain speed prediction data through prediction by the model; set the speed control strategy of the air compressor according to the speed prediction data. The speed control strategy includes, for example, adjusting the speed of the compressor, setting a speed threshold, etc.

[0061] In an embodiment of the present application, a method for controlling an air compressor is provided. The determination of the difference between the real-time output pressure data and the required output pressure includes: obtaining the real-time output pressure data and the required output pressure of the air compressor, and calculating the difference between the real-time output pressure data and the required output pressure; calculating the degree of difference of the difference according to the difference, where the expression of the degree of difference is:

[0062]

[0063] where η1 is the degree of difference, and λ n is the weight coefficient of the difference between the real-time output pressure data and the required output pressure at the nth time point, t n is the real-time output pressure data at the nth time point, and t is the required output pressure.

[0064] Specifically, obtain the real-time output pressure data and the required output pressure data of the air compressor, perform a subtraction operation on the real-time output pressure data and the required output pressure data to obtain a difference value, and the difference value represents the floating difference between the actual output pressure data and the required output pressure; calculate the degree of difference of the difference according to the floating difference.

[0065] In an embodiment of the present application, a method for controlling an air compressor is provided. The determination of the optimization adjustment strategy according to the difference includes: judging the degree of difference of the difference. If the degree of difference = 0, continue to control the speed of the air compressor based on the current speed control strategy; if the degree of difference > 0, determine the optimization adjustment strategy according to the degree of difference; there are several preset corresponding relationships between the optimization adjustment strategy and the degree of difference interval. For each optimization adjustment strategy interval of the heating system, several degrees of difference are associated; judge the degree of difference interval where the degree of difference is located, and determine the optimization adjustment strategy according to the mapping relationship in the several corresponding relationships between the optimization adjustment strategy and the degree of difference interval.

[0066] Specifically, set several degree of difference intervals and associate them with the corresponding optimization adjustment strategies, divide the degree of difference into multiple intervals, and set the corresponding optimization adjustment strategies for each interval; determine the corresponding optimization adjustment strategy according to the interval where the degree of difference is located, map the degree of difference to the corresponding optimization adjustment strategy according to the preset corresponding relationship between the optimization adjustment strategy and the degree of difference interval; perform corresponding optimization adjustment on the speed of the air compressor according to the determined optimization adjustment strategy, and adjust the speed, speed threshold, and speed increment or decrement, etc. according to the specific strategy.

[0067] Such as Figure 2As shown in the figure, in an embodiment of the present application, an air compressor control system is provided, including: an acquisition module, configured to acquire historical output pressure data and historical rotational speed data of the air compressor in the past, and preprocess the historical output pressure data and the historical rotational speed data; a modeling module, configured to analyze the correlation relationship between the preprocessed historical output pressure data and historical rotational speed data, and construct a relationship model between pressure and rotational speed according to the historical output pressure data, the historical rotational speed data and their correlation relationship; a setting module, configured to acquire the output pressure requirement of the air compressor, and set a rotational speed control strategy for the air compressor based on the output pressure requirement and the relationship model; an operation module, configured to operate for a preset period based on the rotational speed control strategy, and acquire the current real-time output pressure data of the air compressor; a determination module, configured to judge the difference between the real-time output pressure data and the output pressure requirement, and determine an optimization adjustment strategy according to the difference; an optimization module, configured to adjust and optimize the rotational speed control strategy of the air compressor based on the optimization adjustment strategy.

[0068] In summary, an embodiment of the present invention provides an air compressor control method and system, which includes: acquiring historical output pressure data and historical rotational speed data of the air compressor, and preprocessing the two data; analyzing the correlation relationship between the two preprocessed data, and constructing a relationship model between pressure and rotational speed according to the two data and the correlation relationship; acquiring the output pressure requirement, and setting a rotational speed control strategy based on it and the relationship model; operating for a preset period based on the rotational speed control strategy, and acquiring the current real-time output pressure data; judging the difference between the real-time output pressure data and the output pressure requirement, and determining an optimization adjustment strategy according to the difference; adjusting and optimizing the rotational speed control strategy based on the optimization adjustment strategy. The present invention combines machine learning and optimization strategies to achieve intelligent control and optimization. Through continuous learning and adjustment, the air compressor can adapt to different working conditions and requirements, and automatically adjust the rotational speed control strategy to meet the requirements of the air compressor for output pressure.

[0069] Finally, it should be noted that: Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

[0070] The above is only one embodiment of the present invention, but the scope of the present invention cannot be limited thereby. Any structural changes made based on the present invention, as long as they do not deviate from the essence of the present invention, should be considered as falling within the protection scope of the present invention and being restricted. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process and related descriptions of the above-described platform can refer to the corresponding process in the foregoing platform embodiment, and will not be repeated here.

[0071] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, platform, article, or apparatus / platform that comprises a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to those processes, platforms, articles, or apparatus / platforms.

[0072] So far, the technical solutions of the present invention have been described in connection with the further embodiments shown in the accompanying drawings. However, it is easily understood by those skilled in the art that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

[0073] The above is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. An air compressor control method, characterized in that, Including: Obtain the historical output pressure data and historical rotational speed data of the air compressor in the past, and preprocess the historical output pressure data and historical rotational speed data; Analyze the correlation relationship between the preprocessed historical output pressure data and historical rotational speed data, and construct a relationship model between pressure and rotational speed based on the historical output pressure data, historical rotational speed data and their correlation relationship; Obtain the output pressure requirement of the air compressor, and set the rotational speed control strategy of the air compressor based on the output pressure requirement and the relationship model; Operate for a preset time period based on the rotational speed control strategy, and obtain the current real-time output pressure data of the air compressor; Judge the difference between the real-time output pressure data and the output pressure requirement, and determine the optimization and adjustment strategy according to the difference; Adjust and optimize the rotational speed control strategy of the air compressor based on the optimization and adjustment strategy; The preprocessing of the historical output pressure data and historical rotational speed data includes: Perform data cleaning on the historical output pressure data and historical rotational speed data to remove noise, missing values and outliers in the data; Perform data normalization processing on the cleaned historical output pressure data and historical rotational speed data; The analysis of the correlation relationship between the preprocessed historical output pressure data and historical rotational speed data includes: Take the historical rotational speed data as the independent variable and the historical output pressure data as the dependent variable, and draw a scatter plot of the output pressure and rotational speed; Analyze the data trend line or the distribution of data points in the scatter plot. If a linear trend appears in the scatter plot, the correlation relationship is a linear correlation relationship. If a non-linear trend appears in the scatter plot, the correlation relationship is a non-linear correlation relationship; The construction of the relationship model between pressure and rotational speed based on the historical output pressure data, historical rotational speed data and their correlation relationship includes: Take the historical rotational speed data as the model input data and the historical rotational speed data as the model output data; Based on the model input data, model output data, correlation relationship and a preset neural network model, construct an initial relationship model; Divide multiple groups of model input data and models into a training set and a test set according to a certain ratio, and input the training set and the test set into the initial relationship model to train and test the initial relationship model until the initial relationship model meets the preset convergence condition, and obtain the relationship model between the output pressure and the rotational speed.

2. The air compressor control method according to claim 1, wherein The obtaining of the output pressure requirement of the air compressor and the setting of the rotational speed control strategy of the air compressor based on the output pressure requirement and the relationship model includes: Take the output pressure requirement as the model input data and input it into the relationship model, and perform output through the relationship model to obtain rotational speed prediction data; Set the rotational speed control strategy of the air compressor according to the rotational speed prediction data.

3. The air compressor control method according to claim 2, wherein, The judgment of the difference between the real-time output pressure data and the output pressure requirement includes: Obtain the real-time output pressure data and the output pressure requirement of the air compressor, and calculate the difference between the real-time output pressure data and the output pressure requirement; Calculate the degree of difference of the difference according to the difference, and the expression of the degree of difference is: Among them, η1 is the degree of difference, and λ n is the weight coefficient of the difference between the real-time output pressure data and the required output pressure at the nth time point, t n is the real-time output pressure data at the nth time point, and t is the required output pressure.

4. The air compressor control method according to claim 3, characterized in that, The determination of the optimization and adjustment strategy according to the difference includes: Judge the degree of difference of the difference. If the degree of difference = 0, continue to control the rotational speed of the air compressor based on the current rotational speed control strategy; If the degree of difference > 0, determine the optimization and adjustment strategy according to the degree of difference; There are several preset optimization and adjustment strategy - degree of difference interval correspondences. For each optimization and adjustment strategy interval of the heating system, several degrees of difference are associated; Judge the degree of difference interval where the degree of difference is located, and determine the optimization and adjustment strategy according to the mapping relationship in the several optimization and adjustment strategy - degree of difference interval correspondences.

5. An air compressor control system, characterized in that, It includes: An acquisition module, which is used to acquire the historical output pressure data and historical rotation speed data of the air compressor in the past, and preprocess the historical output pressure data and historical rotation speed data; A modeling module, which is used to analyze the correlation relationship between the preprocessed historical output pressure data and historical rotation speed data, and construct a relationship model between pressure and rotation speed according to the historical output pressure data, historical rotation speed data and their correlation relationship; A setting module, which is used to acquire the output pressure requirement of the air compressor, and set the rotation speed control strategy of the air compressor based on the output pressure requirement and the relationship model; An operation module, which is used to operate for a preset time period based on the rotation speed control strategy, and acquire the current real-time output pressure data of the air compressor; A determination module, which is used to judge the difference between the real-time output pressure data and the output pressure requirement, and determine the optimization and adjustment strategy according to the difference; An optimization module, which is used to adjust and optimize the rotation speed control strategy of the air compressor based on the optimization and adjustment strategy; The preprocessing of the historical output pressure data and historical rotation speed data includes: Clean the historical output pressure data and historical rotation speed data to remove noise, missing values and outliers in the data; Perform data normalization processing on the cleaned historical output pressure data and historical rotation speed data; The analysis of the correlation relationship between the preprocessed historical output pressure data and historical rotation speed data includes: Take the historical rotation speed data as the independent variable and the historical output pressure data as the dependent variable, and draw a scatter plot of output pressure and rotation speed; Analyze the data trend line or the distribution of data points in the scatter plot. If a linear trend appears in the scatter plot, the correlation relationship is a linear correlation relationship. If a non-linear trend appears in the scatter plot, the correlation relationship is a non-linear correlation relationship; The construction of the relationship model between pressure and rotation speed according to the historical output pressure data, historical rotation speed data and their correlation relationship includes: Take the historical rotation speed data as the model input data and the historical rotation speed data as the model output data; Based on the model input data, model output data, correlation relationship and a preset neural network model, construct an initial relationship model; Divide multiple groups of model input data and models into a training set and a test set according to a certain ratio, and input the training set and the test set into the initial relationship model to train and test the initial relationship model until the initial relationship model meets the preset convergence condition, and obtain the relationship model between output pressure and rotation speed.

Images