Method and device for determining running state of coal mill and electronic equipment

Abstract

The invention discloses a method and device for determining the running state of a coal mill and electronic equipment. Relates to the big data field. The method comprises the steps that M first feature values are obtained by obtaining the feature value of each first feature when a target coal mill runs, the first features are determined from multiple initial features when the target coal mill runs, and M is a positive integer; the M first feature values are input into a first prediction model, a first prediction result is obtained, the first prediction result is used for representing the target output quantity of the target coal mill, and the first prediction model is obtained by taking the first historical feature value of each first feature and the first historical input quantity of the target coal mill as samples for training; and determining the operation state of the target coal mill according to the first prediction result and the expected output quantity of the target coal mill. According to the invention, the problem that the quantity of coal as fired output by the coal mill cannot be directly measured by traditional measuring equipment in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of big data, and more specifically, to a method, device and electronic equipment for determining the operating status of a coal mill. Background Art

[0002] In the power generation industry, the double-inlet and double-outlet ball mill is one of the key production equipment, and its operating status is directly related to production efficiency, energy consumption control and safe operation. The operating status of the double-inlet and double-outlet ball mill is often closely related to a variety of factors, among which the output coal volume is a crucial indicator. The output coal volume not only reflects the processing capacity of the double-inlet and double-outlet ball mill, but is also directly related to the smoothness of the subsequent process flow.

[0003] However, in the actual production process, since a large amount of coal (powder) is stored in the cylinder of the double-inlet and double-outlet ball mill, the amount of coal entering the double-inlet and double-outlet ball mill under dynamic conditions is not equal to the amount of coal entering the furnace at the outlet of the double-inlet and double-outlet ball mill. Traditional measuring equipment cannot accurately measure the amount of coal powder in the gas-solid two-phase flow state at the outlet of the double-inlet and double-outlet ball mill, and thus cannot accurately determine the operating status of the double-inlet and double-outlet ball mill and affect the subsequent boiler load control.

[0004] With regard to the problem in the related art that the amount of coal fed into the mill cannot be directly measured by traditional measuring equipment, no effective solution has been proposed so far. Summary of the invention

[0005] The present application provides a method, device and electronic device for determining the operating status of a coal mill, so as to solve the problem in the related art that the amount of coal fed into the furnace outputted by the coal mill cannot be directly measured by traditional measuring equipment.

[0006] According to one aspect of the present application, a method for determining the operating state of a coal mill is provided. The method includes: obtaining the characteristic value of each first feature when the target coal mill is running, and obtaining M first characteristic values, wherein the first feature is determined from multiple initial features when the target coal mill is running, and M is a positive integer; inputting the M first characteristic values ​​into a first prediction model, and obtaining a first prediction result, wherein the first prediction result is used to characterize the target output of the target coal mill, and the first prediction model is obtained by training the first historical characteristic value of each first feature and the first historical input of the target coal mill as samples; and determining the operating state of the target coal mill according to the first prediction result and the expected output of the target coal mill.

[0007] Optionally, obtaining the characteristic value of each first characteristic when the target coal mill is running to obtain M first characteristic values ​​includes: when the target coal mill is running, obtaining the initial characteristic value of each initial characteristic of the target coal mill to obtain Q groups of initial characteristic values, wherein each group of characteristic values ​​corresponds to an acquisition period; preprocessing the Q groups of initial characteristic values ​​to obtain Q groups of processed initial characteristic values; performing principal component analysis on the Q groups of processed initial characteristic values ​​to obtain M first characteristic values, and determining the initial features corresponding to the M first characteristic values ​​as the first features.

[0008] Optionally, the first prediction model is trained in the following manner: obtaining the first historical characteristic value of the first characteristic of the target coal mill in each sampling period to obtain N groups of first historical characteristic values, wherein the first characteristic includes at least one of the following: coal mill inlet wind pressure, capacity air volume, and material level difference; obtaining the input quantity of the target coal mill in each sampling period to obtain N first historical input quantities, where N is a positive integer; associating a group of first historical characteristic values ​​and the first historical input quantity in the same sampling period to obtain N groups of first sample data; using the N groups of first sample data to train the initial prediction model, and adjusting the parameters of the initial prediction model until the prediction accuracy of the initial prediction model is greater than the preset accuracy to obtain the first prediction model.

[0009] Optionally, determining the operating state of the target coal mill according to the first prediction result and the expected output of the target coal mill includes: calculating a first error rate between the first prediction result and the expected output, and determining whether the first error rate is greater than a preset error rate; when the first error rate is greater than the preset error rate, determining a second prediction result of the target coal mill through a second prediction model, and determining the operating state of the target coal mill through the second prediction result, wherein the second prediction model is obtained by training historical feature values ​​of multiple second features and historical input amounts of the target coal mill as samples, the multiple second features include a second target feature, the M first features include the first target feature, there is a correlation between the second target feature and the first target feature, and the accuracy of measuring the feature value of the second target feature is greater than the accuracy of measuring the feature value of the first target feature; when the first error rate is less than or equal to the preset error rate, determining that the operating state of the target coal mill is normal.

[0010] Optionally, determining a second prediction result of a target coal mill through a second prediction model, and determining the operating state of the target coal mill through the second prediction result includes: inputting characteristic values ​​of multiple second features into the second prediction model to obtain a second prediction result; calculating a second error rate between the second prediction result and the expected output, and determining whether the second error rate is greater than a preset error rate; when the second error rate is greater than the preset error rate, determining that the operating state of the target coal mill is abnormal; when the second error rate is less than or equal to the preset error rate, determining that the operating state of the target coal mill is normal.

[0011] Optionally, the second prediction model is trained in the following manner: obtaining the second historical characteristic value of the second characteristic of the target coal mill in each sampling period to obtain P groups of second historical characteristic values, wherein the second characteristic includes at least one of the following: coal mill inlet wind pressure, capacity door damper opening, material level difference, and P is a positive integer; obtaining the input quantity of the target coal mill in each sampling period to obtain P second historical input quantities; associating a group of second historical characteristic values ​​and the second historical input quantity in the same sampling period to obtain P groups of second sample data; using the P groups of second sample data to train the initial prediction model, and adjusting the parameters of the initial prediction model until the prediction accuracy of the initial prediction model is greater than the preset accuracy to obtain the second prediction model.

[0012] Optionally, after determining the operating state of the target coal mill based on the first prediction result and the expected output of the target coal mill, the method also includes: when the operating state of the target coal mill is abnormal, obtaining the expected value of each first feature, and comparing the characteristic value of each first feature with the expected value to obtain M comparison results; obtaining a target comparison result from the M comparison results, wherein the difference between the characteristic value corresponding to the target comparison result and the expected value is greater than the target difference; determining the first feature corresponding to the target comparison result as an abnormal feature, and generating an alarm message based on the abnormal feature, wherein the alarm message indicates that the abnormal feature needs to be processed.

[0013] According to another aspect of the present application, a device for determining the operating state of a coal mill is provided. The device includes: a first acquisition unit, used to acquire the characteristic value of each first feature when the target coal mill is running, and obtain M first characteristic values, wherein the first feature is determined from multiple initial features when the target coal mill is running, and M is a positive integer; a prediction unit, used to input the M first characteristic values ​​into a first prediction model, and obtain a first prediction result, wherein the first prediction result is used to characterize the target output of the target coal mill, and the first prediction model is obtained by training the first historical characteristic values ​​of each first feature and the first historical input of the target coal mill as samples; a first determination unit, used to determine the operating state of the target coal mill according to the first prediction result and the expected output of the target coal mill.

[0014] According to another aspect of the present invention, a computer program product is provided, including a computer program, which, when executed by a processor, implements a method for determining the operating status of a coal mill provided in the aforementioned embodiment of the present application.

[0015] According to another aspect of the present invention, there is also provided an electronic device 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 when the computer-readable instructions are executed, a method for determining the operating status of a coal mill provided in the aforementioned embodiment is executed.

[0016] Through this application, the following steps are adopted: obtain the characteristic value of each first feature when the target coal mill is running, and obtain M first characteristic values, wherein the first feature is determined from multiple initial features when the target coal mill is running, and M is a positive integer; input the M first characteristic values ​​into the first prediction model to obtain the first prediction result, wherein the first prediction result is used to characterize the target output of the target coal mill, and the first prediction model is obtained by training the first historical characteristic value of each first feature and the first historical input of the target coal mill as samples; determine the operating state of the target coal mill according to the first prediction result and the expected output of the target coal mill, solving the problem that the traditional measuring equipment cannot be used to directly measure the amount of coal entering the furnace output by the coal mill in the related technology. By analyzing multiple characteristic values ​​when the target coal mill is running, the first characteristic of the target coal mill is determined, and the output of the target coal mill is predicted according to the characteristic values ​​of each first feature when the target coal mill is running and the first prediction model, so that the operating state of the target coal mill can be determined according to the prediction result, thereby achieving the technical effect of improving the accuracy of identifying the operating state of the target coal mill. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a flow chart of a method for determining the operating status of a coal mill provided in an embodiment of the present application;

[0019] Figure 2 is a flowchart of an optional process for selecting a principal component feature according to an embodiment of the present application;

[0020] Figure 3 is a schematic diagram of a device for determining the operating state of a coal mill provided in an embodiment of the present application;

[0021] Figure 4 It is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work 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 and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] It should be noted that the method, device and electronic equipment for determining the operating status of a coal mill determined in the present disclosure can be used in the field of big data, and can also be used in any field except the field of big data. The application field of the method, device and electronic equipment for determining the operating status of a coal mill determined in the present disclosure is not limited.

[0026] It should be noted that the collected 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, displayed data, etc.) used in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with the relevant laws, regulations and standards of the relevant regions, necessary confidentiality measures are taken, and public order and good customs are not violated. Corresponding operation portals are provided for users to choose to authorize or refuse to use. For example, an interface is set up between this system and relevant users or organizations. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0027] The embodiments or examples of the present disclosure are not exhaustive, but are only illustrative of some embodiments or examples, and are not intended to be specific limitations on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment or example can be implemented as an independent example, and the steps can be combined arbitrarily. For example, the scheme after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be combined arbitrarily; in addition, the various embodiments or examples can be combined arbitrarily, for example, some or all steps of different embodiments or examples can be combined arbitrarily, and a certain embodiment or example can be combined arbitrarily with the optional methods or optional examples of other embodiments or examples.

[0028] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0029] Principal component analysis: It is a commonly used method for data dimensionality reduction and feature extraction. It maps the original data to a new coordinate system through linear transformation, so that the variance of the data in the new coordinate system is maximized. This can retain the most important information while reducing the dimension of the data, facilitating subsequent data analysis and processing.

[0030] The air pressure at the coal mill inlet is the air pressure value before entering the coal mill. It is an important parameter in the operation of the coal mill. In a thermal power plant, a suitable air pressure at the coal mill inlet can improve the fluidity of the coal powder in the coal mill, promote the collision and friction between materials, and thus improve the coal grinding efficiency. Changes in the air pressure at the inlet will affect the fineness of the coal powder and the conveying capacity of the coal powder.

[0031] Capacity air volume refers to the air volume that enters the coal mill through the capacity air door of the coal mill. During the operation of the coal mill, the size of the capacity air volume directly affects the grinding effect of coal powder and the output of the coal mill.

[0032] The coal mill material level differential pressure refers to the differential pressure value obtained when the material height or density in the coal mill cylinder is measured by a differential pressure sensor.

[0033] According to an embodiment of the present application, a method for determining the operating status of a coal mill is provided.

[0034] Figure 1 1 is a flow chart of a method for determining the operating status of a coal mill according to an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0035] Step S101, obtaining a characteristic value of each first characteristic when the target coal mill is running, and obtaining M first characteristic values, wherein the first characteristic is determined from a plurality of initial characteristics when the target coal mill is running, and M is a positive integer.

[0036] Specifically, the target coal mill can be a double-inlet and double-outlet ball mill. When the coal mill is running, multiple characteristic values ​​of the coal mill can be detected, such as the primary air pressure at the coal mill inlet, the capacity air volume (or the capacity door damper opening), the coal mill material level differential pressure, and other operating characteristic values. At this time, since there are many characteristics of the coal mill during operation, resulting in the characteristic dimension angle, therefore, in order to improve the prediction accuracy of the coal mill output, the features can be screened to obtain multiple first features, so that when the coal mill is running, only the characteristic value of the first feature can be collected, and the characteristic value of the first feature can be analyzed to obtain the predicted output coal.

[0037] Step S102, inputting M first characteristic values ​​into the first prediction model to obtain a first prediction result, wherein the first prediction result is used to characterize the target output of the target coal mill, and the first prediction model is obtained by training the first historical characteristic values ​​of each first characteristic and the first historical input of the target coal mill as samples.

[0038] Specifically, after obtaining the eigenvalue of the first feature, it is necessary to input the M first eigenvalues ​​into the first prediction model, and predict the target output of the target coal mill through the first prediction model to obtain a first prediction result, wherein the target output may be the output coal of the coal mill.

[0039] It should be noted that the model formula in the first prediction model can be shown as Formula 1:

[0040]

[0041] Among them, B i is the amount of coal fed into the furnace, p i is the air pressure at the coal mill inlet, f i is the volumetric air volume, Δp hi It is the material level differential pressure of coal mill.

[0042] It should be noted that since the output coal amount cannot be accurately measured, and under steady-state conditions (the material level in the pulverizer remains unchanged), the amount of coal entering the furnace is equal to the output coal amount. Therefore, when training the model, the amount of coal entering the furnace can be used as the output coal amount to train the model, thereby obtaining the first prediction model.

[0043] Step S103: determining the operating state of the target coal mill according to the first prediction result and the expected output of the target coal mill.

[0044] Specifically, after inputting each first characteristic value under the current operating conditions into the trained first prediction model to obtain the prediction result, the predicted output of the target coal mill under the current conditions is determined. At this time, the expected output of the target coal mill can be set according to the production plan, product quality requirements or historical experience. This expected output can be a specific value (such as output, particle size distribution, etc.), or a range or threshold.

[0045] Furthermore, after obtaining the expected output, a comparative analysis can be performed, that is, the predicted result can be compared with the expected output. If the predicted result is close to or reaches the expected output, the coal mill is considered to be in normal or good operating condition. If there is a deviation between the predicted result and the expected output, the cause and extent of the deviation need to be further analyzed. The deviation may be caused by a variety of factors, such as raw material changes, equipment wear, improper operation, etc.

[0046] For example, when the predicted result is basically consistent with the expected output, it is determined that the target coal mill is operating in a normal state and no special intervention is required. When there is a small deviation between the predicted result and the expected output, it is determined that the target coal mill is operating in a warning state. At this time, although the target coal mill is abnormal, it is within an acceptable range. The operation status of the coal mill can be closely monitored and necessary adjustment measures can be taken. When there is a significant deviation between the predicted result and the expected output, it is determined that the target coal mill is operating in an abnormal state. At this time, it is necessary to immediately check the operation status of the coal mill, find the cause of the problem, and take corresponding corrective measures. Among them, corresponding countermeasures can be formulated according to the operation status evaluation results. For example, in the warning state, the raw material ratio or coal mill parameters can be adjusted; in the abnormal state, it is necessary to shut down for inspection, maintenance or replacement of faulty parts, and after implementing the countermeasures, continue to monitor the operation status of the coal mill to ensure that the problem is effectively solved, thereby ensuring the normal operation of the coal mill.

[0047] The method for determining the operating state of a coal mill provided in the embodiment of the present application obtains M first characteristic values ​​by obtaining the characteristic value of each first characteristic when the target coal mill is running, wherein the first characteristic is determined from multiple initial characteristics when the target coal mill is running, and M is a positive integer; the M first characteristic values ​​are input into the first prediction model to obtain the first prediction result, wherein the first prediction result is used to characterize the target output of the target coal mill, and the first prediction model is obtained by training the first historical characteristic value of each first characteristic and the first historical input of the target coal mill as samples; the operating state of the target coal mill is determined according to the first prediction result and the expected output of the target coal mill, which solves the problem that the amount of coal entering the furnace output by the coal mill cannot be directly measured by traditional measuring equipment in the related art. By analyzing multiple characteristic values ​​when the target coal mill is running, the first characteristic of the target coal mill is determined, and the output of the target coal mill is predicted according to the characteristic values ​​of each first characteristic when the target coal mill is running and the first prediction model, the operating state of the target coal mill can be determined according to the prediction result, thereby achieving the technical effect of improving the accuracy of identifying the operating state of the target coal mill.

[0048] In order to ensure the accuracy of the features used to predict the output coal quantity, optionally, Figure 2 is a flowchart of an optional process for selecting a principal component feature according to an embodiment of the present application, such as Figure 2 As shown, in the method for determining the operating state of a coal mill provided in an embodiment of the present application, the characteristic value of each first characteristic when the target coal mill is running is obtained, and the M first characteristic values ​​obtained include:

[0049] Step S201, when the target coal mill is running, the initial characteristic value of each initial characteristic of the target coal mill is obtained to obtain Q groups of initial characteristic values, wherein each group of characteristic values ​​corresponds to a collection period.

[0050] Step S202, preprocessing the Q groups of initial eigenvalues ​​to obtain the Q groups of processed initial eigenvalues.

[0051] Step S203, performing principal component analysis on the Q groups of processed initial eigenvalues ​​to obtain M first eigenvalues, and determining the initial features corresponding to the M first eigenvalues ​​as the first features.

[0052] It should be noted that in industrial production, the operating state of the target coal mill is jointly affected by multiple initial features (such as raw material type, raw material humidity, coal mill temperature, motor current, etc.). In order to effectively predict and evaluate the output and performance of the coal mill, it is necessary to screen out the first feature that has a significant impact on the output from many initial features. This embodiment will explain in detail how to obtain the characteristic value of each first feature when the target coal mill is running, and obtain M first characteristic values.

[0053] Specifically, first, when the target coal mill is running, it is necessary to set up sensors, instruments and other equipment in the target coal mill, or to obtain the initial characteristic value of each initial characteristic in real time in the control device of the target coal mill, and divide the collected data into Q collection time periods in chronological order, each time period corresponds to a group of initial characteristic values, and a total of Q groups of initial characteristic values ​​are obtained.

[0054] Furthermore, it is necessary to clean the initial eigenvalues ​​of group Q, remove missing values, outliers and other data that do not meet the requirements, encode non-numerical features, and standardize or normalize numerical features to eliminate the influence of different feature dimensions, so as to obtain the initial eigenvalues ​​of group Q after processing.

[0055] Furthermore, after obtaining the initial eigenvalues ​​after the Q groups are processed, it is necessary to perform principal component analysis on the initial eigenvalues ​​after the Q groups are processed, so as to map the high-dimensional data to a low-dimensional space while retaining the main information of the data. In the principal component analysis process, it is necessary to calculate the covariance matrix of the initial eigenvalues ​​after the Q groups are processed, and solve the eigenvalues ​​and eigenvectors of the matrix, and select the first M most important eigenvectors (i.e., principal components) according to the size of the eigenvalues. The initial features corresponding to these eigenvectors are the first features, wherein the size of the eigenvalues ​​in the principal component analysis process reflects the importance of the eigenvectors in the data.

[0056] Finally, according to the results of principal component analysis, the initial features corresponding to the M first eigenvalues ​​are determined as the first features, thereby obtaining the key features that affect the output and performance of the target coal mill.

[0057] This embodiment uses principal component analysis to effectively determine the first feature from multiple initial features of the target coal mill during operation, providing strong support for subsequent prediction and evaluation work.

[0058] In order to improve the prediction accuracy of the first prediction model, optionally, in the method for determining the operating status of a coal mill provided in an embodiment of the present application, the first prediction model is trained in the following manner: obtaining the first historical characteristic value of the first characteristic of the target coal mill in each sampling period to obtain N groups of first historical characteristic values, wherein the first characteristic includes at least one of the following: coal mill inlet wind pressure, volumetric air volume, and material level difference; obtaining the input amount of the target coal mill in each sampling period to obtain N first historical input amounts, where N is a positive integer; associating a group of first historical characteristic values ​​and the first historical input amount in the same sampling period to obtain N groups of first sample data; using the N groups of first sample data to train the initial prediction model, and adjusting the parameters of the initial prediction model until the prediction accuracy of the initial prediction model is greater than the preset accuracy to obtain the first prediction model.

[0059] It should be noted that the sampling period can be any period when the coal mill is in operation. The characteristic value corresponding to the first characteristic and the input coal amount in this period are obtained in this sampling period, and the average value of each first characteristic value in the sampling period is calculated to obtain the operating data, and generate sample data based on the operating data.

[0060] Specifically, when training the first prediction model, the operating data of the target coal mill can be obtained from the historical database, including the first characteristic values ​​of each operation (such as coal mill inlet wind pressure, capacity air volume, material level difference) and the corresponding input coal quantity, to obtain multiple sets of historical data, and remove missing values, outliers and other data that do not meet the requirements from the historical data to ensure data quality, and encode non-numerical features according to business needs and model characteristics to ensure that the model can read historical data, thereby obtaining multiple sets of first sample data.

[0061] It should be noted that although some data are not missing, they are erroneous values ​​and may not be identified, resulting in errors in the model prediction values. In this case, after obtaining the eigenvalues ​​of each feature, the erroneous values ​​in the eigenvalues ​​can be determined based on the change dimensions and change rules between the eigenvalues, thereby ensuring the accuracy of the eigenvalues.

[0062] Furthermore, after obtaining multiple sets of first sample data, the multiple sets of first sample data can be divided into training sets, validation sets and test sets, usually in a ratio of 7:2:1 or adjusted according to specific circumstances, and a suitable prediction model is selected according to the nature of the problem and the characteristics of the data, such as linear regression, decision tree, random forest, gradient boosting tree, neural network, etc., so as to train the selected model using the training set data, optimize the model performance by adjusting the model parameters (such as learning rate, number of trees, depth of trees, etc.), and further evaluate the trained model using the validation set, and evaluate the model performance by calculating the prediction error (such as mean square error, mean absolute error, etc.). If the model performance does not meet the requirements, return to the model training step for adjustment, so as to obtain a model with a more accurate prediction value, and obtain the first prediction model.

[0063] This embodiment achieves the technical effect of improving the prediction accuracy of the model by acquiring the operating data in the historical operating period and then training the model based on the sample data obtained from the operating data.

[0064] In order to ensure the operating efficiency and product quality of the target coal mill, optionally, in the method for determining the operating state of the coal mill provided in the embodiment of the present application, determining the operating state of the target coal mill according to the first prediction result and the expected output of the target coal mill includes: calculating a first error rate between the first prediction result and the expected output, and judging whether the first error rate is greater than a preset error rate; when the first error rate is greater than the preset error rate, determining a second prediction result of the target coal mill through a second prediction model, and determining the operating state of the target coal mill through the second prediction result, wherein the second prediction model is obtained by training historical feature values ​​of multiple second features and historical input amounts of the target coal mill as samples, the multiple second features include a second target feature, the M first features include the first target feature, there is a correlation between the second target feature and the first target feature, and the accuracy of determining the feature value of the second target feature is greater than the accuracy of determining the feature value of the first target feature; when the first error rate is less than or equal to the preset error rate, determining that the operating state of the target coal mill is normal.

[0065] It should be noted that in order to ensure the operating efficiency and product quality of the target coal mill, its operating status needs to be monitored in real time. The output of the target coal mill can be predicted by the prediction model and compared with the expected output to determine its operating status.

[0066] Specifically, after obtaining the first prediction result of the first prediction model, a first error rate between the first prediction result and the expected output can be calculated. The error rate calculation can be performed using methods such as an absolute error rate and a relative error rate to obtain the error rate. For example, the first prediction result and the expected output are subtracted to obtain a difference, and the absolute value of the difference is divided by the expected output to obtain the first error rate.

[0067] Furthermore, after obtaining the first error rate, it is necessary to determine whether the first error rate is greater than a preset error rate. Among them, the preset error rate is a threshold set according to actual production needs and tolerance. If the first error rate is greater than the preset error rate, it indicates that the first prediction result is significantly different from the expected output and further inspection is required. At this time, the second prediction model can be used for prediction. The second prediction model is obtained based on the historical characteristic values ​​of multiple second features (including the second target feature) and the historical input of the target coal mill as sample training. Among them, the second target feature is associated with the first target feature in the first prediction model, but the accuracy of determining the characteristic value of the second target feature is higher.

[0068] It should be noted that the model formula in the second prediction model is shown in Formula 2:

[0069]

[0070] Among them, Bi is the amount of coal fed into the furnace, p i is the coal mill inlet air pressure, o i is the capacity door damper opening, It is the material level differential pressure of coal mill.

[0071] It should be noted that the first target feature is the capacity air volume, and the second target feature is the capacity door damper opening. Since errors may occur when measuring the capacity air volume, resulting in inaccurate capacity air volume, the capacity door damper opening associated with the capacity air volume can be used as the first feature to train the model to obtain a second prediction model with higher accuracy. The output coal volume is predicted by the second prediction model to obtain the operation result of the coal mill.

[0072] It should be noted that if the first error rate is less than or equal to the preset error rate, it indicates that the difference between the first prediction result and the expected output is within an acceptable range, and the target coal mill is in good operating condition. The target coal mill is determined to be in normal operating condition, and the current production operation can continue.

[0073] This embodiment calculates the first error rate between the first prediction result and the expected output, and determines the operating state of the coal mill according to the first error rate, so as to more accurately judge the operating state of the target coal mill and ensure the normal operation of the coal mill.

[0074] Optionally, in the method for determining the operating status of a coal mill provided in an embodiment of the present application, a second prediction result of a target coal mill is determined by a second prediction model, and determining the operating status of the target coal mill by the second prediction result includes: inputting characteristic values ​​of multiple second characteristics into the second prediction model to obtain a second prediction result; calculating a second error rate between the second prediction result and the expected output, and determining whether the second error rate is greater than a preset error rate; when the second error rate is greater than the preset error rate, determining that the operating status of the target coal mill is abnormal; when the second error rate is less than or equal to the preset error rate, determining that the operating status of the target coal mill is normal.

[0075] It should be noted that when the prediction result of the first prediction model is significantly different from the expected output, in order to more accurately judge the operating status of the target coal mill, a second prediction model can be introduced for further analysis. The second prediction model is trained based on different feature sets to improve the accuracy of the prediction.

[0076] Specifically, since the input data of the second prediction model and the first prediction model are different, when using the second prediction model to predict the output coal volume, it is necessary to collect the characteristic values ​​of multiple second characteristics of the target coal mill at the current moment, and use the collected characteristic values ​​of the multiple second characteristics as input data and input them into the trained second prediction model to obtain a second prediction result.

[0077] Furthermore, the second prediction model performs calculations based on the input characteristic values, outputs a second prediction result of the target coal mill, and calculates a second error rate between the second prediction result and the expected output, wherein the calculation method of the error rate may be the same as that of the first error rate to ensure consistency of the evaluation criteria.

[0078] Furthermore, after obtaining the second error rate, it is necessary to compare the second error rate with the preset error rate. If the second error rate is greater than the preset error rate, it means that even if a more accurate second prediction model is used, the prediction result is still significantly different from the expected output. At this time, it can be determined that the operating state of the target coal mill is abnormal, and it may be necessary to shut down for inspection, maintenance, or parameter adjustment. When the second error rate is less than or equal to the preset error rate, it means that the second prediction result is basically consistent with the expected output, and the operating state of the target coal mill is normal. The current production operation can be continued, and the operating state can be continuously monitored, so that the operating state of the coal mill can be accurately determined according to the second prediction result, ensuring accurate monitoring of the operating state of the coal mill and the normal operation of the coal mill.

[0079] This embodiment determines the operating state of the target coal mill through a more accurate second prediction model, and takes corresponding measures in time, thereby ensuring the normal operation of the coal mill.

[0080] In order to improve the accuracy of the second prediction model, optionally, in the method for determining the operating status of a coal mill provided in an embodiment of the present application, the second prediction model is trained in the following manner: obtaining a second historical characteristic value of a second characteristic of a target coal mill in each sampling period to obtain P groups of second historical characteristic values, wherein the second characteristic includes at least one of the following: coal mill inlet wind pressure, capacity door damper opening, material level difference, and P is a positive integer; obtaining the input of the target coal mill in each sampling period to obtain P second historical inputs; associating a group of second historical characteristic values ​​and the second historical input in the same sampling period to obtain P groups of second sample data; using the P groups of second sample data to train an initial prediction model, and adjusting the parameters of the initial prediction model until the prediction accuracy of the initial prediction model is greater than the preset accuracy to obtain a second prediction model.

[0081] It should be noted that in order to build a second prediction model that can accurately predict the operating status of the target coal mill, it is necessary to collect and process a large amount of historical data, and train the model through machine learning or statistical methods so that it can learn and identify the output patterns of the coal mill under different operating conditions.

[0082] Specifically, it is first necessary to collect historical data on the second characteristics of the target coal mill in multiple sampling time periods. These second characteristics include but are not limited to coal mill inlet wind pressure, capacity door damper opening, material level difference, etc., so as to obtain the second historical characteristic value of group P. At the same time, it is necessary to obtain the input coal amount of the target coal mill in each sampling time period, and each input coal amount corresponds to the second historical characteristic value of group P respectively.

[0083] Furthermore, after obtaining P groups of second historical characteristic values ​​and P second historical input quantities, it is necessary to group the second historical characteristic values ​​and second historical input quantities with the same sampling period into a group to obtain P groups of data, and clean the P groups of data to remove outliers, missing values ​​or unreasonable data points and perform other preprocessing to obtain P groups of second sample data.

[0084] Furthermore, after determining the second sample data, it is necessary to select a suitable initial prediction model and initialize the parameters of the model. The above parameters will be adjusted during the training process, wherein the initial prediction model can be a statistical-based regression model (such as linear regression, polynomial regression), a machine learning model (such as decision trees, random forests, neural networks, etc.) or a deep learning model.

[0085] After the initial prediction model is determined, the initial prediction model can be trained using the P group of second sample data. During the training process, the model will try to learn the relationship between the feature value and the input quantity, and how they jointly affect the output of the coal mill. The parameters of the model are adjusted through iterative optimization algorithms (such as gradient descent method, Newton method, etc.) to minimize the error between the predicted value and the true value. During the training process, the prediction performance of the model is evaluated through methods such as cross-validation to prevent overfitting or underfitting, thereby obtaining the second prediction model.

[0086] This embodiment achieves the technical effect of improving the prediction accuracy of the model by acquiring the operating data in the historical operating period and then training the model based on the sample data obtained from the operating data.

[0087] Optionally, in the method for determining the operating state of a coal mill provided in an embodiment of the present application, after determining the operating state of the target coal mill based on the first prediction result and the expected output of the target coal mill, the method further includes: when the operating state of the target coal mill is abnormal, obtaining the expected value of each first feature, and comparing the characteristic value of each first feature with the expected value to obtain M comparison results; obtaining a target comparison result from the M comparison results, wherein the difference between the characteristic value corresponding to the target comparison result and the expected value is greater than the target difference; determining the first feature corresponding to the target comparison result as an abnormal feature, and generating an alarm message based on the abnormal feature, wherein the alarm message indicates that the abnormal feature needs to be processed.

[0088] Specifically, when it is detected that the operating state of the target coal mill is abnormal, it is necessary to determine the cause of the abnormality of the target coal mill. At this time, since the first feature is the main feature that affects the operation of the coal mill, the expected value of each first feature can be obtained, and the feature value of each first feature is compared with the expected value to obtain M comparison results, and the target difference is obtained, wherein the target difference is a preset difference value. When the difference between the feature value and the expected value is greater than the target difference, the difference between the expected value and the feature value obtained by measurement is large. At this time, it can be determined that the feature to which the feature value belongs is an abnormal feature, thereby determining the first feature of the abnormality based on the comparison result, and generating an alarm message based on the abnormal feature and sending it to the operation and maintenance personnel, so that the equipment position indicated by the abnormal feature can be processed in time, so that the coal mill can resume normal operation as soon as possible.

[0089] This embodiment compares the characteristic value of each first characteristic with the expected value, thereby determining the abnormal cause of the coal mill according to the comparison result, thereby achieving the technical effect of ensuring the normal operation of the coal mill.

[0090] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0091] The embodiment of the present application also provides a device for determining the operating state of a coal mill. It should be noted that the device for determining the operating state of a coal mill in the embodiment of the present application can be used to execute the method for determining the operating state of a coal mill provided in the embodiment of the present application. The device for determining the operating state of a coal mill provided in the embodiment of the present application is introduced below.

[0092] Figure 3 Schematic diagram of a device for determining the operating status of a coal mill according to an embodiment of the present application. Figure 3 As shown, the device includes: a first acquisition unit 31, a prediction unit 32, and a first determination unit 33.

[0093] The first acquisition unit 31 is used to acquire the characteristic value of each first feature when the target coal mill is running, and obtain M first characteristic values, wherein the first feature is determined from multiple initial features when the target coal mill is running, and M is a positive integer.

[0094] The prediction unit 32 is used to input M first characteristic values ​​into the first prediction model to obtain a first prediction result, wherein the first prediction result is used to characterize the target output of the target coal mill, and the first prediction model is obtained by training the first historical characteristic values ​​of each first characteristic and the first historical input of the target coal mill as samples.

[0095] The first determination unit 33 is used to determine the operating state of the target coal mill according to the first prediction result and the expected output of the target coal mill.

[0096] The device for determining the operating state of a coal mill provided in an embodiment of the present application obtains the characteristic value of each first feature when the target coal mill is operating through the first acquisition unit 31, and obtains M first characteristic values, wherein the first feature is determined from multiple initial features when the target coal mill is operating, and M is a positive integer. The prediction unit 32 inputs the M first characteristic values ​​into the first prediction model to obtain a first prediction result, wherein the first prediction result is used to characterize the target output of the target coal mill, and the first prediction model is obtained by training the first historical characteristic values ​​of each first feature and the first historical input of the target coal mill as samples. The first determination unit 33 determines the operating state of the target coal mill based on the first prediction result and the expected output of the target coal mill. This solves the problem in the related art that it is impossible to use traditional measuring equipment to directly measure the amount of coal entering the furnace output by the coal mill. By analyzing multiple characteristic values ​​of the target coal mill during operation, the first characteristic of the target coal mill is determined, and the output of the target coal mill is predicted based on the characteristic values ​​of each first characteristic when the target coal mill is running and the first prediction model. The operating state of the target coal mill can be determined based on the prediction result, thereby achieving the technical effect of improving the accuracy of identifying the operating state of the target coal mill.

[0097] Optionally, in the device for determining the operating status of a coal mill provided in an embodiment of the present application, the first acquisition unit 31 includes: an acquisition module, used to acquire the initial characteristic value of each initial characteristic of the target coal mill when the target coal mill is running, and obtain Q groups of initial characteristic values, wherein each group of characteristic values ​​corresponds to an acquisition period; a processing module, used to preprocess the Q groups of initial characteristic values, and obtain the Q groups of processed initial characteristic values; an analysis module, used to perform principal component analysis on the Q groups of processed initial characteristic values, and obtain M first characteristic values, and determine the initial characteristics corresponding to the M first characteristic values ​​as the first characteristics.

[0098] Optionally, in the device for determining the operating status of a coal mill provided in an embodiment of the present application, the first prediction model is trained in the following manner: a second acquisition unit is used to acquire the first historical characteristic value of the first characteristic of the target coal mill in each sampling period, and obtain N groups of first historical characteristic values, wherein the first characteristic includes at least one of the following: coal mill inlet wind pressure, volumetric air volume, and material level difference; a third acquisition unit is used to acquire the input quantity of the target coal mill in each sampling period, and obtain N first historical input quantities, where N is a positive integer; a first association unit is used to associate a group of first historical characteristic values ​​and the first historical input quantity in the same sampling period, and obtain N groups of first sample data; a first training unit is used to train the initial prediction model using the N groups of first 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 the first prediction model is obtained.

[0099] Optionally, in the device for determining the operating state of a coal mill provided in an embodiment of the present application, the first determination unit 33 includes: a calculation module, used to calculate a first error rate between a first prediction result and an expected output, and to determine whether the first error rate is greater than a preset error rate; a first determination module, used to determine a second prediction result of a target coal mill through a second prediction model when the first error rate is greater than the preset error rate, and to determine the operating state of the target coal mill through the second prediction result, wherein the second prediction model is obtained by training with historical feature values ​​of multiple second features and historical inputs of the target coal mill as samples, the multiple second features include a second target feature, the M first features include a first target feature, there is a correlation between the second target feature and the first target feature, and the accuracy of determining the feature value of the second target feature is greater than the accuracy of determining the feature value of the first target feature; a second determination module, used to determine that the operating state of the target coal mill is normal when the first error rate is less than or equal to the preset error rate.

[0100] Optionally, in the device for determining the operating status of a coal mill provided in an embodiment of the present application, a first determination module includes: an input submodule, used to input characteristic values ​​of multiple second characteristics into a second prediction model to obtain a second prediction result; a calculation submodule, used to calculate a second error rate between the second prediction result and the expected output, and to determine whether the second error rate is greater than a preset error rate; a first determination submodule, used to determine that the operating status of the target coal mill is abnormal when the second error rate is greater than the preset error rate; and a second determination submodule, used to determine that the operating status of the target coal mill is normal when the second error rate is less than or equal to the preset error rate.

[0101] Optionally, in the device for determining the operating status of a coal mill provided in an embodiment of the present application, the second prediction model is trained in the following manner: a fourth acquisition unit is used to obtain a second historical characteristic value of a second characteristic of the target coal mill in each sampling period, and obtain P groups of second historical characteristic values, wherein the second characteristic includes at least one of the following: coal mill inlet wind pressure, capacity door damper opening, material level difference, and P is a positive integer; a fifth acquisition unit is used to obtain the input quantity of the target coal mill in each sampling period, and obtain P second historical input quantities; a second association unit is used to associate a group of second historical characteristic values ​​and the second historical input quantity in the same sampling period, and obtain P groups of second sample data; a second training unit is used to train the initial prediction model using the P groups of second 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 second prediction model.

[0102] Optionally, in the device for determining the operating state of a coal mill provided in an embodiment of the present application, after determining the operating state of the target coal mill based on the first prediction result and the expected output of the target coal mill, the device also includes: a comparison unit, for obtaining the expected value of each first feature when the operating state of the target coal mill is abnormal, and comparing the characteristic value of each first feature with the expected value to obtain M comparison results; a sixth acquisition unit, for obtaining a target comparison result from the M comparison results, wherein the difference between the characteristic value corresponding to the target comparison result and the expected value is greater than the target difference; a second determination unit, for determining the first feature corresponding to the target comparison result as an abnormal feature, and generating an alarm message based on the abnormal feature, wherein the alarm message indicates that the abnormal feature needs to be processed.

[0103] The above-mentioned device for determining the operating status of the coal mill includes a processor and a memory. The above-mentioned 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 above-mentioned program units stored in the memory to realize corresponding functions.

[0104] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the problem that the amount of coal fed into the coal mill output by traditional measuring equipment cannot be directly measured in the related art by adjusting the kernel parameters is solved.

[0105] The memory may include non-permanent memory in a computer-readable medium, 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.

[0106] An embodiment of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, the method for determining the operating state of the coal mill is implemented.

[0107] An embodiment of the present invention provides a processor, which is used to run a program, wherein the program executes the above-mentioned method for determining the operating status of the coal mill when it is running.

[0108] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application, such as Figure 4 As shown, an embodiment of the present invention provides an electronic device, the electronic device 40 includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the steps of the above-mentioned method for determining the operating state of the coal mill when executing the program. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0109] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the steps of the above-mentioned method for determining the operating status of a coal mill.

[0110] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0111] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0112] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0114] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0115] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0116] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules 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 technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0117] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0118] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining the operating state of a coal mill, characterized in that: include: Obtain a characteristic value of each first characteristic when the target coal mill is running, and obtain M first characteristic values, wherein the first characteristic is determined from a plurality of initial characteristics when the target coal mill is running, and M is a positive integer; Inputting the M first characteristic values ​​into a first prediction model to obtain a first prediction result, wherein the first prediction result is used to characterize a target output of the target coal mill, and the first prediction model is obtained by training with the first historical characteristic values ​​of each first characteristic and the first historical input of the target coal mill as samples; The operating state of the target coal mill is determined according to the first prediction result and the expected output of the target coal mill.

2. The method according to claim 1, characterized in that Obtain the characteristic value of each first characteristic when the target coal mill is running, and obtain M first characteristic values ​​including: When the target coal mill is running, an initial characteristic value of each initial characteristic of the target coal mill is obtained to obtain Q groups of initial characteristic values, wherein each group of characteristic values ​​corresponds to a collection period; Preprocessing the Q groups of initial eigenvalues ​​to obtain Q groups of processed initial eigenvalues; Principal component analysis is performed on the Q groups of processed initial eigenvalues ​​to obtain M first eigenvalues, and initial features corresponding to the M first eigenvalues ​​are determined as the first features.

3. The method according to claim 1, characterized in that The first prediction model is trained in the following way: Obtaining a first historical characteristic value of a first characteristic of the target coal mill in each sampling period to obtain N groups of first historical characteristic values, wherein the first characteristic includes at least one of the following: coal mill inlet air pressure, volumetric air volume, and material level difference; Obtaining the input amount of the target coal mill in each sampling period to obtain N first historical input amounts, where N is a positive integer; Associating a group of first historical characteristic values ​​and a first historical input quantity in the same sampling period to obtain N groups of first sample data; The initial prediction model is trained using the N groups of first 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, thereby obtaining the first prediction model.

4. The method according to claim 1, characterized in that Determining the operating state of the target coal mill according to the first prediction result and the expected output of the target coal mill includes: Calculating a first error rate between the first prediction result and the expected output, and determining whether the first error rate is greater than a preset error rate; In the case where the first error rate is greater than the preset error rate, a second prediction result of the target coal mill is determined by a second prediction model, and the operating state of the target coal mill is determined by the second prediction result, wherein the second prediction model is obtained by training with historical feature values ​​of multiple second features and historical input amounts of the target coal mill as samples, the multiple second features include a second target feature, the M first features include a first target feature, there is a correlation between the second target feature and the first target feature, and the accuracy of determining the feature value of the second target feature is greater than the accuracy of determining the feature value of the first target feature; When the first error rate is less than or equal to the preset error rate, it is determined that the operating state of the target coal mill is normal.

5. The method according to claim 4, characterized in that Determining a second prediction result of the target coal mill by using a second prediction model, and determining the operating state of the target coal mill by using the second prediction result includes: Inputting the feature values ​​of the plurality of second features into the second prediction model to obtain a second prediction result; Calculating a second error rate between the second prediction result and the expected output, and determining whether the second error rate is greater than a preset error rate; When the second error rate is greater than the preset error rate, determining that the operating state of the target coal mill is abnormal; When the second error rate is less than or equal to the preset error rate, it is determined that the operating state of the target coal mill is normal.

6. The method according to claim 4, characterized in that The second prediction model is trained in the following way: Obtaining the second historical characteristic value of the second characteristic of the target coal mill in each sampling period, and obtaining P groups of second historical characteristic values, wherein the second characteristic includes at least one of the following: coal mill inlet wind pressure, capacity door damper opening, material level difference, and P is a positive integer; Obtaining the input amount of the target coal mill in each sampling period to obtain P second historical input amounts; Associating a group of second historical characteristic values ​​and a second historical input quantity in the same sampling period to obtain P groups of second sample data; The initial prediction model is trained using the P groups of second 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, thereby obtaining the second prediction model.

7. The method according to claim 1, characterized in that After determining the operating state of the target coal mill according to the first prediction result and the expected output of the target coal mill, the method further includes: When the operating state of the target coal mill is abnormal, obtaining expected values ​​of each first feature, and comparing the characteristic value of each first feature with the expected value to obtain M comparison results; Obtaining a target comparison result from the M comparison results, wherein the difference between the characteristic value corresponding to the target comparison result and the expected value is greater than the target difference; A first feature corresponding to the target comparison result is determined as an abnormal feature, and an alarm message is generated according to the abnormal feature, wherein the alarm message indicates that the abnormal feature needs to be processed.

8. A device for determining the operating state of a coal mill, characterized in that: include: A first acquisition unit is used to acquire a characteristic value of each first characteristic when the target coal mill is running, and obtain M first characteristic values, wherein the first characteristic is determined from a plurality of initial characteristics when the target coal mill is running, and M is a positive integer; A prediction unit, used for inputting the M first characteristic values ​​into a first prediction model to obtain a first prediction result, wherein the first prediction result is used to characterize a target output of the target coal mill, and the first prediction model is obtained by training with first historical characteristic values ​​of each first characteristic and a first historical input of the target coal mill as samples; The first determination unit is used to determine the operating state of the target coal mill according to the first prediction result and the expected output of the target coal mill.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for determining the operating status of a coal mill as described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: It comprises one or more processors and a memory, wherein the memory is 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 implement the method for determining the operating status of a coal mill as described in any one of claims 1 to 7.

Images