Method and device for controlling air pressure of material grinding machine and electronic equipment

Abstract

The application discloses a kind of material grinder wind pressure control method, device and electronic equipment.It relates to big data field.The method comprises the following steps: obtaining the characteristic value of M target characteristics of material grinder and the preset value of capacity damper baffle opening of material grinder;The characteristic value of M target characteristics and the preset value of capacity damper baffle opening are input into target prediction model, and target prediction result is obtained;According to target prediction result, determine the primary air main pipe pressure value of material grinder, and control the main pipe pressure value of material grinder according to primary air main pipe pressure value.Through the present application, it solves the problem that the adjustment range of coal quantity is small in the related art by adjusting the capacity damper baffle opening.

Description

Technical Field

[0001] This application relates to the field of big data, and more specifically, to a method, apparatus, and electronic device for controlling the air pressure of a material grinding mill. Background Technology

[0002] In the field of existing coal processing technology, adjusting the coal output of the coal mill has become a critical operation. Its efficiency and accuracy directly affect the amount of coal entering the boiler, thus influencing the boiler's output load. To ensure that the coal mill can accurately adjust the output coal quantity according to the boiler's output load and reduce labor costs, the industry widely adopts the method of automatically controlling the opening of the capacity damper to achieve automated adjustment of the coal output. This technological innovation not only significantly reduces the frequency and intensity of manual intervention but also ensures the stability of the coal output by precisely controlling the damper opening.

[0003] However, while the method of automatically controlling the opening of capacity dampers performs well in most cases, it also faces limitations that cannot be ignored. Specifically, when the damper opening reaches its physical or design limit, the system loses its ability to make further adjustments and cannot respond immediately to sudden changes in coal output or special needs. This situation undoubtedly limits the system's flexibility and response speed, making it difficult to quickly and accurately adjust the coal output in emergency or special operating conditions, which may adversely affect production efficiency and product quality.

[0004] There is currently no effective solution to the problem that the adjustment range of the coal output is small when the capacity damper opening is adjusted in related technologies. Summary of the Invention

[0005] This application provides a method, device, and electronic equipment for controlling the air pressure of a material grinding mill, in order to solve the problem that the adjustment range of the coal output is small when automatically adjusting the opening of the capacity damper in related technologies.

[0006] According to one aspect of this application, a method for controlling the air pressure of a material grinding mill is provided. The method includes: acquiring feature values ​​of M target features of the material grinding mill and a preset value of the opening degree of the capacity damper of the material grinding mill, where M is a positive integer; inputting the feature values ​​of the M target features and the preset value of the capacity damper opening into a target prediction model to obtain a target prediction result; determining the primary air header pressure value of the material grinding mill based on the target prediction result, and controlling the header pressure value of the material grinding mill based on the primary air header pressure value.

[0007] Optionally, before obtaining the feature values ​​of the M target features, the method further includes: obtaining multiple initial features with operating parameters in the material grinding mill while the material grinding mill is in operation; determining the target features from the multiple initial features to obtain the M target features.

[0008] Optionally, determining the target features from multiple initial features to obtain M target features includes: acquiring the initial feature values ​​of each initial feature of the material grinder during operation to obtain Q sets of initial feature values, where each set of feature values ​​corresponds to a collection period and Q is a positive integer; preprocessing the Q sets of initial feature values ​​to obtain Q sets of processed initial feature values; performing principal component analysis on the Q sets of processed initial feature values ​​based on the boiler's steam flow rate, obtaining M target feature values ​​from multiple initial features based on the analysis results, and determining the initial features corresponding to the M target feature values ​​as the target features.

[0009] Optionally, the target prediction model is trained as follows: Historical feature values ​​of the target features of the material grinder are obtained for each sampling period, resulting in N sets of historical feature values. The target features include at least one of the following: the primary air header pressure of the material grinder, the number of material grinders, and the steam flow rate of the boiler; the capacity damper opening of the material grinder is obtained for each sampling period, resulting in N historical damper openings, where N is a positive integer; a set of historical feature values ​​and historical input quantities from the same sampling period are correlated to obtain N sets of sample data; the initial prediction model is trained using the N sets of sample data, and the parameters of the initial prediction model are adjusted until the prediction accuracy of the initial prediction model is greater than the preset accuracy, thus obtaining the target prediction model.

[0010] Optionally, determining the primary air header pressure value of the material grinder based on the target prediction result includes: determining the current pressure value of the primary air header of the material grinder; calculating the difference between the current pressure value and the target prediction result; determining the configuration method of the primary air header pressure value of the material grinder based on the difference, and configuring the primary air header pressure value of the material grinder according to the configuration method.

[0011] Optionally, the configuration method for determining the primary air header pressure value of the material grinder based on the degree of difference includes: determining whether the degree of difference between the current pressure value and the target prediction result is greater than or equal to a preset degree of difference; if the degree of difference is less than the preset degree of difference, determining the configuration method as the first configuration method, wherein the first configuration method refers to changing the primary air header pressure value from the current pressure value to the predicted pressure value in the target prediction result; if the degree of difference is greater than or equal to the preset degree of difference, determining the configuration method as the second configuration method, wherein the second configuration method refers to generating a pressure value change curve based on the current pressure value and the predicted pressure value, and changing the primary air header pressure value from the current pressure value to the predicted pressure value in the target prediction result based on the pressure value change curve.

[0012] Optionally, the method further includes: obtaining the opening degree of the capacity damper of the material grinder and determining whether the opening degree of the capacity damper is within a preset opening degree range; if the opening degree of the capacity damper is not within the preset opening degree range, performing the step of obtaining the feature values ​​of M target features of the material grinder and the preset value of the opening degree of the capacity damper of the material grinder; if the opening degree of the capacity damper is within the preset opening degree range, keeping the pressure value of the primary air header of the material grinder unchanged.

[0013] According to another aspect of this application, a control device for the air pressure of a material grinding mill is provided. The device includes: a first acquisition unit, configured to acquire feature values ​​of M target features of the material grinding mill and a preset value of the opening degree of the capacity damper of the material grinding mill, wherein M is a positive integer; a prediction unit, configured to input the feature values ​​of the M target features and the preset value of the capacity damper opening into a target prediction model to obtain a target prediction result; and a first determination unit, configured to determine the primary air header pressure value of the material grinding mill based on the target prediction result, and control the header pressure value of the material grinding mill based on the primary air header pressure value.

[0014] According to another aspect of the present invention, a computer program product is also provided, comprising a computer program that, when executed by a processor, implements a method for controlling the air pressure of a material grinding mill provided in the foregoing embodiments of the present application.

[0015] According to another aspect of the present invention, an electronic device is also provided, comprising one or more processors and a memory; the memory stores computer-readable instructions, and the processor is used to execute the computer-readable instructions, wherein the computer-readable instructions, when executed, perform a method for controlling the air pressure of a material grinding mill provided in the foregoing embodiments.

[0016] This application employs the following steps: obtaining the feature values ​​of M target features of the material grinder and the preset value of the capacity damper opening of the material grinder, where M is a positive integer; inputting the feature values ​​of the M target features and the preset value of the capacity damper opening into the target prediction model to obtain the target prediction result; determining the primary air header pressure value of the material grinder based on the target prediction result, and controlling the header pressure value of the material grinder based on the primary air header pressure value. This solves the problem of a small adjustment range for automatically adjusting the coal output by adjusting the capacity damper opening in related technologies. By determining the required primary air header pressure value of the coal mill based on the preset value of the capacity damper opening and the target features of the material grinder, the capacity damper opening is maintained near the preset value by adjusting the primary air header pressure value. This ensures that in the event of a sudden change in coal output, the capacity damper opening can quickly adjust to the demand for coal output, and the capacity damper opening is stabilized at the preset value by adjusting the primary air header pressure value. This achieves the effect of ensuring the accuracy and stability of coal output while keeping the opening of the capacity damper at a preset value. Attached Figure Description

[0017] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 This is a flowchart of a method for controlling the air pressure of a material grinding mill according to an embodiment of this application;

[0019] Figure 2 This is a flowchart of the selection process for optional principal features provided in the embodiments of this application;

[0020] Figure 3 This is a schematic diagram of a control device for the air pressure of a material grinding mill according to an embodiment of this application;

[0021] Figure 4 This is a schematic diagram of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0022] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] It should be noted that the material grinding mill air pressure control method, device and electronic equipment as defined in this disclosure can be used in the field of big data, or in any field other than big data. The application field of the material grinding mill air pressure control method, device and electronic equipment as defined in this disclosure is not limited.

[0026] It should be noted that all information, user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, and displayed data) used in this application are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant regions, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose whether to authorize or refuse use. For example, this system has interfaces with relevant users or organizations. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained only after receiving consent from the aforementioned user or organization.

[0027] The embodiments or examples disclosed herein are not exhaustive, but merely illustrative of some embodiments or examples, and are not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment or example can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment or example can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment or example can be arbitrarily interchanged. Furthermore, optional methods or examples in a particular embodiment or example can be arbitrarily combined; moreover, embodiments or examples can be arbitrarily combined. For example, some or all steps of different embodiments or examples can be arbitrarily combined, and a particular embodiment or example can be arbitrarily combined with optional methods or examples of other embodiments or examples.

[0028] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application:

[0029] Principal Component Analysis (PCA) is a widely used statistical method, primarily used for data dimensionality reduction, feature extraction, and data compression.

[0030] Capacity damper opening: Capacity damper opening refers to the degree of opening of dampers used to regulate the flow rate of media (such as air, flue gas, etc.) in boilers or related industrial equipment. This opening is usually expressed as a percentage, ranging from 0% (fully closed) to 100% (fully open).

[0031] Coal mill: A coal mill is a mechanical device that crushes coal lumps and grinds them into coal powder. It is an important auxiliary device for pulverized coal boilers.

[0032] Primary air header pressure: The primary air header pressure of a coal mill refers to the gas pressure within the primary air header of the coal mill system. This pressure value is a crucial parameter during coal mill operation, directly affecting the mill's performance, pulverized coal conveying, and combustion efficiency.

[0033] According to an embodiment of this application, a method for controlling the air pressure of a material grinding mill is provided.

[0034] Figure 1 This is a flowchart of a method for controlling the air pressure of a material grinding mill according to an embodiment of this application. For example... Figure 1 As shown, the method includes the following steps:

[0035] Step S101: Obtain the feature values ​​of M target features of the material grinder and the preset value of the capacity damper opening of the material grinder, where M is a positive integer.

[0036] Specifically, the material grinding mill can be a coal mill, such as a double-inlet, double-outlet ball mill. The coal output from the coal mill is fed into the boiler, ensuring the boiler can operate normally and guarantee normal steam output. Target characteristics can include information related to the coal mill, such as the boiler's steam flow rate and the number of coal mills.

[0037] Furthermore, when the boiler's output load changes, in order to ensure that the opening of the capacity damper of the material grinder remains at the preset value, the pressure value of the primary air header needs to be adjusted. This ensures that the opening of the capacity damper of the material grinder remains at the preset value while the boiler's output load meets the user's requirements.

[0038] It should be noted that when the capacity damper opening is maintained at a preset value, the capacity damper opening of the material grinder will be adjusted first when the boiler output load changes. However, if the capacity damper opening of the material grinder is too large, it may become impossible to adjust. Therefore, to avoid this situation, it is necessary to obtain the characteristic values ​​of M target features of the material grinder and the preset value of the capacity damper opening. Then, the primary air header pressure value is calculated based on the obtained characteristic values ​​of the M target features of the material grinder and the preset value of the capacity damper opening. Finally, the capacity damper opening is maintained at the preset value by adjusting the primary air header pressure value.

[0039] Step S102: Input the feature values ​​of the M target features and the preset value of the capacity damper opening into the target prediction model to obtain the target prediction result.

[0040] Specifically, after obtaining the feature values ​​and preset values, since the target prediction model contains a fitting equation for calculating the pressure value of the primary air main pipe, the feature values ​​of the M target features and the preset value of the capacity damper opening can be input into the target prediction model. The target prediction model then calculates the feature values ​​and preset values ​​to obtain the prediction result. The prediction result is also the set value of the pressure value of the primary air main pipe calculated by the model based on the feature values ​​of the M target features and the preset value of the capacity damper opening.

[0041] It should be noted that the model formula in the target prediction model can be as shown in Formula 1:

[0042] P s =a0+a1D+a2N+a3O+a4D 2 +a5N 2 +a6O 2 (1)

[0043] Among them, P sThe setpoint for the primary air header pressure is given by , D is the steam flow rate, N is the number of coal mills in operation, and O is the average opening value of the capacity damper.

[0044] Step S103: Determine the primary air main pipe pressure value of the material grinder based on the target prediction result, and control the main pipe pressure value of the material grinder based on the primary air main pipe pressure value.

[0045] Specifically, after obtaining the target prediction result through the target prediction model, the pressure value contained in the target prediction result can be determined as the pressure value of the primary air header of the material grinder at the current moment. Based on this pressure value, the pressure value of the header of the material grinder is set, thereby ensuring that under this pressure setting value, the coal mill can ensure that the boiler output load can meet the user's setting requirements when the average opening value of the capacity damper is the preset value. This ensures the normal operation of the boiler when the average opening value of the capacity damper of the coal mill is the preset value. At the same time, when it is necessary to increase or decrease the output load of the boiler, the boiler output load can be changed in a timely manner by immediately modifying the average opening value of the capacity damper.

[0046] The method for controlling the air pressure of a material grinding mill provided in this application involves acquiring the feature values ​​of M target features of the material grinding mill and a preset value for the opening of the capacity damper of the material grinding mill, where M is a positive integer; inputting the feature values ​​of the M target features and the preset value for the opening of the capacity damper into a target prediction model to obtain the target prediction result; determining the primary air header pressure value of the material grinding mill based on the target prediction result; and controlling the header pressure value of the material grinding mill based on the primary air header pressure value. This solves the problem of a small adjustment range for automatically adjusting the coal output by adjusting the opening of the capacity damper in related technologies. By determining the current required primary air header pressure value of the coal mill based on the preset value of the capacity damper opening and the target features of the material grinding mill, the method maintains the capacity damper opening near the preset value by adjusting the primary air header pressure value, thereby ensuring that the capacity damper opening can quickly adjust to the coal output demand in the event of a sudden change in coal output, and stabilizing the capacity damper opening at the preset value by adjusting the primary air header pressure value. This achieves the effect of ensuring the accuracy and stability of coal output while keeping the opening of the capacity damper at a preset value.

[0047] To reduce the number of features that need to be analyzed, optionally, in the material grinding mill air pressure control method provided in the embodiments of this application, before obtaining the feature values ​​of M target features, the method further includes: when the material grinding mill is in operation, obtaining multiple initial features with operating parameters in the material grinding mill; determining target features from the multiple initial features to obtain M target features.

[0048] Specifically, during continuous operation, material grinding mills involve a series of operating and configuration parameters that directly reflect the equipment's operating status, performance, and configuration information. To obtain operating characteristics highly correlated with boiler load, it is first necessary to acquire initial data for these parameters. These initial characteristics include, but are not limited to, motor current and speed, grinding chamber temperature and pressure, distribution and movement of grinding media, material flow rate and particle size changes, number of coal mills, and coal mill operating time. High-precision sensors and real-time data acquisition systems can accurately capture these initial characteristics, providing a solid foundation for subsequent data analysis, feature extraction, and optimized control.

[0049] Furthermore, after determining the initial characteristics of the coal mill, the characteristic values ​​corresponding to each initial characteristic can be obtained by querying the configuration information table and measuring the operating parameters. Then, based on the characteristic values ​​of each characteristic at different operating times, the characteristic with the greatest impact on the boiler output power can be determined, thereby identifying the target characteristic from multiple initial characteristics. Finally, the output load of the boiler can be determined based on the characteristic value of the target characteristic.

[0050] To ensure the accuracy of the selected target features, optionally, Figure 2 This is a flowchart of the selection process for optional principal features provided in the embodiments of this application, such as... Figure 2 As shown, in the material grinding mill air pressure control method provided in this application embodiment, target features are determined from multiple initial features to obtain M target features, including:

[0051] Step S201: When the material grinder is running, the initial feature value of each initial feature of the material grinder is obtained to obtain Q sets of initial feature values, where each set of feature values ​​corresponds to a collection period, and Q is a positive integer.

[0052] Step S202: Preprocess the initial feature values ​​of group Q to obtain the processed initial feature values ​​of group Q.

[0053] Step S203: Perform principal component analysis on the initial feature values ​​of group Q after processing based on the steam flow rate of the boiler. Based on the analysis results, obtain M target feature values ​​from multiple initial features, and determine the initial features corresponding to the M target feature values ​​as target features.

[0054] It should be noted that in industrial production, the boiler's output load is affected by multiple initial characteristics, the most important of which is the coal output of the coal mill. The coal output of the coal mill is also influenced by multiple initial characteristics (such as raw material type, raw material moisture content, grinding time, mill temperature, and motor current). Therefore, to ensure the accuracy of the boiler's output load, it is necessary to select the target characteristics that significantly affect the output from among the numerous initial characteristics. This embodiment will detail how to determine the target characteristics from the multiple initial characteristics during coal mill operation.

[0055] Specifically, firstly, when the coal mill is running, it is necessary to install and use sensors, instruments and other equipment in the coal mill, or to acquire the initial feature value of each initial feature in real time in the control equipment of the coal mill, and divide the collected data into Q collection periods according to the time sequence, with each period corresponding to a set of initial feature values, for a total of Q sets of initial feature values.

[0056] Furthermore, the initial feature values ​​of the Q group need to be cleaned to remove missing values, outliers, and other data that do not meet the requirements. Non-numerical features need to be encoded, and numerical features need to be standardized or normalized to eliminate the influence of different feature units, thereby obtaining the processed initial feature values ​​of the Q group.

[0057] Furthermore, after obtaining the initial eigenvalues ​​after processing the Q groups, principal component analysis (PCA) needs to be performed on these initial eigenvalues ​​to map the high-dimensional data to a low-dimensional space while preserving the main information of the data. During PCA, the covariance matrix of the initial eigenvalues ​​after processing the Q groups needs to be calculated, and the eigenvalues ​​and eigenvectors of this matrix need to be solved. Based on the magnitude of the eigenvalues, the top M most important eigenvectors (i.e., principal components) are selected. The initial features corresponding to these eigenvectors are the target features. The magnitude of the eigenvalues ​​during PCA reflects the importance of the eigenvectors in the data.

[0058] Finally, based on the results of principal component analysis, the initial features corresponding to the M target feature values ​​are determined as target features, thereby obtaining the key features affecting the boiler's output load.

[0059] It should be noted that in this technical solution, after obtaining the target features, the feature with the largest adjustable range, such as the primary air main pipe pressure value of the material grinding mill, can be selected as the final predicted value. By adjusting this feature, it can be ensured that after the user sets the output load of the boiler, the actual output load of the boiler can be adjusted to the user's set value by adjusting the feature value.

[0060] This embodiment effectively identifies target features from multiple initial features during the operation of a material grinding mill by employing principal component analysis, providing strong support for subsequent prediction and evaluation work.

[0061] Optionally, in the material grinding mill air pressure control method provided in this application embodiment, the target prediction model is trained as follows: Historical feature values ​​of the target features of the material grinding mill are obtained for each sampling period, resulting in N sets of historical feature values. The target features include at least one of the following: the primary air header pressure of the material grinding mill, the number of material grinding mills, and the steam flow rate of the boiler; the capacity damper opening of the material grinding mill is obtained for each sampling period, resulting in N historical damper openings, where N is a positive integer; a set of historical feature values ​​and historical input quantities from the same sampling period are correlated to obtain N sets of sample data; the initial prediction model is trained using the N sets of sample data, and the parameters of the initial prediction model are adjusted until the prediction accuracy of the initial prediction model is greater than a preset accuracy, thus obtaining the target prediction model.

[0062] It should be noted that the sampling period can be any period during the operation of the coal mill. During this sampling period, the feature values ​​corresponding to the target features (including the opening degree of the capacity damper) and the steam flow rate of the boiler under each sampling period are obtained. Thus, the primary air header pressure value of the material grinding mill, the number of material grinding mills, the steam flow rate of the boiler and the capacity damper opening degree are used as variables for model training, thereby obtaining a target prediction model that predicts the primary air header pressure value of the material grinding mill using the number of material grinding mills, the steam flow rate of the boiler and the capacity damper opening degree.

[0063] Specifically, when training the target prediction model, the operating data of the coal mill can be obtained from the historical database, including various feature values ​​for each operation (such as the primary air header pressure of the coal mill, the number of coal mills, the steam flow rate of the boiler, and the opening of the capacity damper). Multiple sets of historical data are obtained, and the historical data is processed to remove missing values, outliers, and other data that do not meet the requirements, thereby ensuring data quality. Based on business needs and model characteristics, non-numerical features are encoded to ensure that the model can read historical data, thus obtaining multiple sets of sample data.

[0064] It should be noted that some data, although not missing, may contain erroneous values ​​that may not be identified, leading to errors in the model's predictions. In such cases, after obtaining the feature values ​​of each feature, the erroneous values ​​can be identified based on the dimension and pattern of change between the feature values, thereby ensuring the accuracy of the feature values.

[0065] Furthermore, after obtaining multiple sets of sample data, these sets can be divided into training, validation, and test sets, typically in a 7:2:1 ratio or adjusted according to specific circumstances. A suitable prediction model, such as linear regression, decision trees, random forests, gradient boosting trees, or neural networks, is selected based on the nature of the problem and the characteristics of the data. The selected model is then trained using the training set data. Model performance is optimized by adjusting model parameters (such as learning rate, number of trees, and tree depth). The trained model is further evaluated using the validation set by calculating prediction errors (such as mean squared error and mean absolute error). If the model performance does not meet the requirements, the process returns to the model training step for further adjustments, resulting in a model with more accurate predictions, thus obtaining the target prediction model.

[0066] This embodiment achieves the technical effect of improving the model's prediction accuracy by acquiring running data from historical running periods and then training the model with sample data obtained from the running data.

[0067] To ensure the normal operation of the coal mill, optionally, in the material grinding mill air pressure control method provided in this application embodiment, determining the primary air header pressure value of the material grinding mill based on the target prediction result includes: determining the current pressure value of the primary air header of the material grinding mill; calculating the difference between the current pressure value and the target prediction result; determining the configuration method of the primary air header pressure value of the material grinding mill based on the difference, and configuring the primary air header pressure value of the material grinding mill according to the configuration method.

[0068] Specifically, after obtaining the target prediction result, since the target prediction result includes the primary air header pressure value required to maintain the capacity damper opening at the preset value, the primary air header pressure value may have a difference from the currently set primary air header pressure value. When adjusting the primary air header pressure value, it is necessary to determine the configuration method of the pressure value according to the difference between the current pressure value and the target prediction result, so as to avoid abnormalities in the coal mill equipment due to excessive changes in the primary air header pressure value.

[0069] To accurately determine the configuration method for the primary air header pressure value, optionally, in the material grinding mill air pressure control method provided in this application embodiment, determining the configuration method for the primary air header pressure value of the material grinding mill based on the degree of difference includes: determining whether the degree of difference between the current pressure value and the target prediction result is greater than or equal to a preset degree of difference; if the degree of difference is less than the preset degree of difference, determining the configuration method as a first configuration method, wherein the first configuration method refers to changing the primary air header pressure value from the current pressure value to the predicted pressure value in the target prediction result; if the degree of difference is greater than or equal to the preset degree of difference, determining the configuration method as a second configuration method, wherein the second configuration method refers to generating a pressure value change curve based on the current pressure value and the predicted pressure value, and changing the primary air header pressure value from the current pressure value to the predicted pressure value in the target prediction result based on the pressure value change curve.

[0070] It should be noted that in this technical solution, the difference between the current pressure value and the target prediction result needs to be calculated first. This difference can be calculated through the following steps: First, obtain the real-time current pressure value of the primary air main pipe, which reflects the actual operating status of the system. Next, obtain the predicted pressure value from the target prediction result from the prediction model or algorithm. Then, calculate the difference between the current pressure value and the predicted pressure value using a preset calculation method (such as absolute difference, squared difference, percentage difference, etc.).

[0071] Furthermore, after calculating the difference degree, it is necessary to determine whether the difference between the current pressure value and the target prediction result is greater than or equal to the preset difference degree, so as to determine the way to configure the pressure value based on the difference degree, thereby ensuring the normal operation of the coal mill.

[0072] When the calculated difference is less than the preset difference threshold, it indicates that the current pressure value is close to the target prediction result, and the pressure value is within a relatively stable or acceptable fluctuation range. In this case, the first configuration method is selected: the pressure value of the primary air header is directly changed from the current pressure value to the predicted pressure value in the target prediction result. This configuration method is simple and direct, and can quickly respond to the prediction results. By directly setting the predicted pressure value, the system can maintain stable operation for a period of time in the future, reducing unnecessary fluctuations and adjustment costs.

[0073] When the calculated difference is greater than or equal to the preset difference threshold, it means there is a significant gap between the current pressure value and the target prediction result. A more refined and gradual adjustment strategy may be needed to ensure a smooth system transition. In this case, the second configuration method is selected: First, a pressure value change curve is generated based on the current and predicted pressure values. This curve should transition smoothly to avoid abrupt pressure changes impacting the system. Then, based on this curve, the pressure value of the primary air header is gradually adjusted from the current value to the predicted value. This method allows the system to maintain a certain degree of stability and controllability during the adjustment process, reducing the risks that may arise from sudden changes. By precisely controlling the rate and path of pressure value change, the system can better adapt to dynamic changes, ensuring stability and efficiency throughout the adjustment process.

[0074] This embodiment determines the pressure value configuration based on the pressure difference, thereby ensuring the normal operation of the coal mill.

[0075] Optionally, in the material grinding mill air pressure control method provided in the embodiments of this application, the method further includes: obtaining the opening degree of the capacity damper of the material grinding mill, and determining whether the opening degree of the capacity damper is within a preset opening degree range; if the opening degree of the capacity damper is not within the preset opening degree range, performing the step of obtaining the feature values ​​of M target features of the material grinding mill and the preset value of the opening degree of the capacity damper of the material grinding mill; if the opening degree of the capacity damper is within the preset opening degree range, keeping the primary air main pipe pressure value of the material grinding mill unchanged.

[0076] Specifically, before changing the pressure value of the primary air header, it is necessary to determine whether the pressure value of the primary air header needs to be changed. Therefore, it is necessary to obtain the opening degree of the capacity damper of the material grinder and determine whether the opening degree of the capacity damper of the material grinder is within the preset opening degree range. If the opening degree of the capacity damper is within the preset opening degree range, it indicates that the opening degree of the capacity damper is in a suitable position. At this time, it is not necessary to adjust the pressure value of the primary air header of the material grinder, and the pressure value of the primary air header of the material grinder can be kept unchanged.

[0077] Furthermore, if the opening of the capacity damper is not within the preset opening range, it indicates that the opening of the capacity damper needs to be changed to the preset opening range by changing the pressure value of the primary air header of the material grinder. This ensures that the capacity damper can be adjusted accordingly when the boiler's output load changes, thus ensuring the accuracy of the boiler's output load.

[0078] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0079] This application also provides a control device for the air pressure of a material grinding mill. It should be noted that the control device for the air pressure of a material grinding mill in this application can be used to execute the control method for the air pressure of a material grinding mill provided in this application. The following describes the control device for the air pressure of a material grinding mill provided in this application.

[0080] Figure 3 This is a schematic diagram of a control device for the air pressure of a material grinding mill according to an embodiment of this application. Figure 3 As shown, the device includes: a first acquisition unit 31, a prediction unit 32, and a first determination unit 33.

[0081] The first acquisition unit 31 is used to acquire the feature values ​​of M target features of the material grinder and the preset value of the capacity damper opening of the material grinder, where M is a positive integer.

[0082] The prediction unit 32 is used to input the feature values ​​of M target features and the preset value of the capacity damper opening into the target prediction model to obtain the target prediction result.

[0083] The first determining unit 33 is used to determine the primary air main pipe pressure value of the material grinder based on the target prediction result, and to control the main pipe pressure value of the material grinder based on the primary air main pipe pressure value.

[0084] The material grinding mill air pressure control device provided in this application embodiment acquires the feature values ​​of M target features of the material grinding mill and the preset value of the capacity damper opening of the material grinding mill through the first acquisition unit 31, where M is a positive integer; the prediction unit 32 inputs the feature values ​​of the M target features and the preset value of the capacity damper opening into the target prediction model to obtain the target prediction result; the first determination unit 33 determines the primary air main pipe pressure value of the material grinding mill according to the target prediction result, and controls the main pipe pressure value of the material grinding mill according to the primary air main pipe pressure value. This invention solves the problem of limited adjustment range in related technologies that automatically adjust coal output by adjusting the opening of the capacity damper. It determines the required primary air header pressure value for the coal mill based on the preset value of the capacity damper opening and the target characteristics of the material grinding mill. By adjusting the primary air header pressure, the capacity damper opening is maintained near the preset value. This ensures that even with sudden changes in coal output, the capacity damper opening can quickly adjust to the demand and stabilize at the preset value by adjusting the primary air header pressure. Thus, it achieves the effect of ensuring the accuracy and stability of coal output while maintaining the capacity damper opening at the preset value.

[0085] Optionally, in the material grinding mill air pressure control device provided in the embodiments of this application, before acquiring the feature values ​​of M target features, the device further includes: a second acquisition unit, used to acquire multiple initial features with operating parameters in the material grinding mill when the material grinding mill is in operation; and a second determination unit, used to determine the target features from the multiple initial features to obtain M target features.

[0086] Optionally, in the control device for the air pressure of the material grinder provided in this application embodiment, the second determining unit includes: an acquisition module, used to acquire the initial feature value of each initial feature of the material grinder during operation, to obtain Q sets of initial feature values, wherein each set of feature values ​​corresponds to a collection period, and Q is a positive integer; a processing module, used to preprocess the Q sets of initial feature values ​​to obtain Q sets of processed initial feature values; and an analysis module, used to perform principal component analysis on the Q sets of processed initial feature values ​​based on the steam flow rate of the boiler, to obtain M target feature values ​​from multiple initial features based on the analysis results, and to determine the initial features corresponding to the M target feature values ​​as target features.

[0087] Optionally, in the material grinding mill air pressure control device provided in this application embodiment, the target prediction model is trained in the following manner: a third acquisition unit is used to acquire historical feature values ​​of the target features of the material grinding mill under each sampling period, and obtain N sets of historical feature values, wherein the target features include at least one of the following: the primary air header pressure value of the material grinding mill, the number of material grinding mills, and the steam flow rate of the boiler; a fourth acquisition unit is used to acquire the capacity damper opening degree of the material grinding mill under each sampling period, and obtain N historical damper opening degrees, where N is a positive integer; an association unit is used to associate a set of historical feature values ​​and historical input quantities under the same sampling period, and obtain N sets of sample data; a training unit is used to train the initial prediction model using the N sets of sample data, and adjust the parameters of the initial prediction model until the prediction accuracy of the initial prediction model is greater than the preset accuracy, and obtain the target prediction model.

[0088] Optionally, in the material grinding mill air pressure control device provided in the embodiments of this application, the first determining unit 33 includes: a determining module, used to determine the current pressure value of the primary air header of the material grinding mill; a calculation module, used to calculate the difference between the current pressure value and the target prediction result; and a configuration module, used to determine the configuration method of the primary air header pressure value of the material grinding mill according to the difference, and configure the primary air header pressure value of the material grinding mill according to the configuration method.

[0089] Optionally, in the material grinding mill air pressure control device provided in this application embodiment, the configuration module includes: a judgment submodule, used to judge whether the difference between the current pressure value and the target prediction result is greater than or equal to a preset difference; a first determination submodule, used to determine the configuration method as a first configuration method when the difference is less than the preset difference, wherein the first configuration method refers to changing the primary air header pressure value from the current pressure value to the predicted pressure value in the target prediction result; and a second determination submodule, used to determine the configuration method as a second configuration method when the difference is greater than or equal to the preset difference, wherein the second configuration method refers to generating a pressure value change curve based on the current pressure value and the predicted pressure value, and changing the primary air header pressure value from the current pressure value to the predicted pressure value in the target prediction result based on the pressure value change curve.

[0090] Optionally, in the material grinding mill air pressure control device provided in this application embodiment, the device further includes: a judgment unit, used to obtain the opening degree of the capacity damper of the material grinding mill and determine whether the opening degree of the capacity damper is within a preset opening degree range; an execution unit, used to execute the step of obtaining the feature values ​​of M target features of the material grinding mill and the preset value of the opening degree of the capacity damper of the material grinding mill when the opening degree of the capacity damper is not within the preset opening degree range; and a holding unit, used to keep the primary air header pressure value of the material grinding mill unchanged when the opening degree of the capacity damper is within the preset opening degree range.

[0091] The aforementioned control device for the air pressure of the material grinding mill includes a processor and a memory. The aforementioned first acquisition unit 31, prediction unit 32, first determination unit 33, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0092] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured. By adjusting the kernel parameters, the problem of limited adjustment range for automatically adjusting coal output by adjusting the opening of the capacity damper in related technologies is solved.

[0093] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0094] This invention provides a computer-readable storage medium storing a program thereon, which, when executed by a processor, implements a method for controlling the air pressure of a material grinding mill.

[0095] This invention provides a processor for running a program, wherein the program executes a method for controlling the air pressure of a material grinding mill.

[0096] Figure 4 This is a schematic diagram of an electronic device provided according to an embodiment of this application, such as... Figure 4 As shown, this embodiment of the invention provides an electronic device 40, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the above-described method for controlling the air pressure of a material grinding mill. The device described herein can be a server, PC, PAD, mobile phone, etc.

[0097] This application also provides a computer program product that, when executed on a data processing device, is adapted to perform the steps of initializing the control method for the air pressure of the material grinding mill described above.

[0098] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0099] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0100] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0101] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0102] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0103] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0104] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0105] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0106] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for controlling the air pressure of a material grinding mill, characterized in that, include: Obtain the feature values ​​of M target features of the material grinder and the preset value of the capacity damper opening of the material grinder, wherein the target features include at least one of the following: the primary air header pressure of the material grinder, the number of material grinders, and the steam flow rate of the boiler, where M is a positive integer; The feature values ​​of the M target features and the preset value of the capacity damper opening are input into the target prediction model to obtain the target prediction result. The target prediction model includes a fitting equation for calculating the pressure value of the primary air main pipe. The primary air main pipe pressure value of the material grinder is determined based on the target prediction result, and the main pipe pressure value of the material grinder is controlled based on the primary air main pipe pressure value. Before obtaining the feature values ​​of the M target features of the material grinding mill, the method further includes: when the material grinding mill is in operation, obtaining a plurality of initial features with operating parameters in the material grinding mill; determining target features from the plurality of initial features to obtain the M target features; The process of determining the target features from the plurality of initial features to obtain the M target features includes: acquiring the initial feature value of each initial feature of the material grinding mill during operation to obtain Q sets of initial feature values, wherein each set of feature values ​​corresponds to a collection period and Q is a positive integer; preprocessing the Q sets of initial feature values ​​to obtain Q sets of processed initial feature values; performing principal component analysis on the Q sets of processed initial feature values ​​based on the steam flow rate of the boiler, obtaining M target feature values ​​from the plurality of initial features based on the analysis results, and determining the initial features corresponding to the M target feature values ​​as the target features.

2. The method according to claim 1, characterized in that, The target prediction model is trained in the following manner: Obtain historical feature values ​​of the target features of the material grinding mill under each sampling period to obtain N sets of historical feature values; Obtain the capacity damper opening of the material grinder during each sampling period to obtain N historical damper openings, where N is a positive integer; By associating a set of historical feature values ​​and historical baffle openings within the same sampling period, N sets of sample data are obtained. The initial prediction model is trained using the N sets of sample data, and the parameters of the initial prediction model are adjusted until the prediction accuracy of the initial prediction model is greater than the preset accuracy, thereby obtaining the target prediction model.

3. The method according to claim 1, characterized in that, The primary air header pressure value of the material grinding mill is determined based on the target prediction results, including: Determine the current pressure value of the primary air header of the material grinder; Calculate the degree of difference between the current pressure value and the target prediction result; The configuration method of the primary air main pipe pressure value of the material grinder is determined based on the difference, and the primary air main pipe pressure value of the material grinder is configured according to the configuration method.

4. The method according to claim 3, characterized in that, The configuration method for determining the primary air header pressure value of the material grinder based on the aforementioned difference includes: Determine whether the difference between the current pressure value and the target prediction result is greater than or equal to a preset difference. If the difference is less than the preset difference, the configuration method is determined to be the first configuration method, wherein the first configuration method refers to changing the pressure value of the primary air main pipe from the current pressure value to the predicted pressure value in the target prediction result; If the difference is greater than or equal to the preset difference, the configuration method is determined to be the second configuration method. The second configuration method refers to generating a pressure value change curve based on the current pressure value and the predicted pressure value, and changing the pressure value of the primary air main pipe from the current pressure value to the predicted pressure value in the target prediction result according to the pressure value change curve.

5. The method according to claim 1, characterized in that, The method further includes: Obtain the opening degree of the capacity damper of the material grinding mill, and determine whether the opening degree of the capacity damper is within the preset opening degree range; If the opening degree of the capacity damper is not within the preset opening degree range, the step of obtaining the feature values ​​of the M target features of the material grinder and the preset value of the opening degree of the capacity damper of the material grinder is performed. When the opening degree of the capacity damper is within the preset opening degree range, the pressure value of the primary air main pipe of the material grinder remains unchanged.

6. A control device for the air pressure of a material grinding mill, characterized in that, include: The first acquisition unit is used to acquire the feature values ​​of M target features of the material grinder and the preset value of the capacity damper opening of the material grinder, wherein the target features include at least one of the following: the primary air header pressure of the material grinder, the number of the material grinders, and the steam flow rate of the boiler, where M is a positive integer; The prediction unit is used to input the feature values ​​of the M target features and the preset value of the capacity damper opening into the target prediction model to obtain the target prediction result. The target prediction model includes a fitting equation for calculating the pressure value of the primary air header. The first determining unit is used to determine the primary air main pipe pressure value of the material grinder based on the target prediction result, and to control the main pipe pressure value of the material grinder based on the primary air main pipe pressure value. Before acquiring the feature values ​​of the M target features of the material grinding mill, the device further includes: a second acquisition unit, configured to acquire multiple initial features with operating parameters in the material grinding mill when the material grinding mill is in operation; and a second determination unit, configured to determine the target features from the multiple initial features to obtain the M target features. The second determining unit includes: an acquisition module, used to acquire the initial feature value of each initial feature of the material grinding mill during operation, to obtain Q sets of initial feature values, wherein each set of feature values ​​corresponds to a collection period, and Q is a positive integer; a processing module, used to preprocess the Q sets of initial feature values ​​to obtain Q sets of processed initial feature values; and an analysis module, used to perform principal component analysis on the Q sets of processed initial feature values ​​based on the steam flow rate of the boiler, to obtain M target feature values ​​from the plurality of initial features based on the analysis results, and to determine the initial features corresponding to the M target feature values ​​as the target features.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for controlling the air pressure of the material grinding mill as described in any one of claims 1 to 5.

8. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the material grinding mill air pressure control method according to any one of claims 1 to 5.

Images