A coal mill equipment monitoring method and system based on data analysis

Abstract

The application discloses a coal mill equipment monitoring method and system based on data analysis. The application obtains coal block original image data, carries out image recognition and analysis according to the coal block original image data, obtains coal block size distribution information based on image analysis, and further obtains targeted preset coal mill operation parameter information through model analysis, so that the production efficiency of the coal mill is improved. In addition, the application obtains parameter correction information by comparing actual monitoring data with preset monitoring data, further improves the abnormal situation resistance of the coal mill, reduces the consumption of human resources, and finally realizes the purpose of improving the production economic benefits.

Description

Technical Field

[0001] This invention relates to the field of data analysis, and more specifically, to a method and system for monitoring coal mill equipment based on data analysis. Background Technology

[0002] A coal mill is a machine that grinds coal into pulverized coal. It is an important auxiliary equipment for pulverized coal boilers. Coal grinding is the process by which coal is pulverized, and its surface area continuously increases. To increase the surface area, the binding forces between solid molecules need to be overcome, thus consuming energy. Coal is ground into pulverized coal in a coal mill, mainly through processes such as crushing, pulverizing, and grinding.

[0003] During the operation of a coal mill, problems such as uneven particle size of the finished product and coal blockage often occur due to technical reasons. Manually inspecting the machine is time-consuming and labor-intensive. Therefore, there is an urgent need for a method to monitor coal mill equipment and improve production efficiency. Summary of the Invention

[0004] To address at least one of the aforementioned technical problems, this invention proposes a data analysis-based method for monitoring coal mill equipment.

[0005] The first aspect of this invention provides a data analysis-based method for monitoring coal mill equipment, comprising:

[0006] Obtain raw image data of coal blocks, perform image recognition and analysis based on the raw image data of coal blocks, and obtain coal block size distribution information based on image analysis;

[0007] The coal block size distribution information is imported into the coal mill operation simulation model for analysis to obtain the preset coal mill operation parameter information and preset coal mill monitoring data.

[0008] The coal mill is operated according to the preset coal mill operating parameters, and the coal mill operation monitoring data is acquired in real time.

[0009] By comparing and analyzing the coal mill operation monitoring data with the preset coal mill monitoring data, abnormal deviation data are obtained.

[0010] Simulation analysis is performed based on abnormal deviation data to obtain parameter correction information, and the operating parameters of the coal mill are corrected based on the parameter correction information.

[0011] In this solution, the acquisition of original coal block image data, and the subsequent image recognition and analysis based on the original coal block image data to obtain coal block size distribution information based on image analysis, specifically involves:

[0012] Acquire raw image data of the coal block;

[0013] The original image data is smoothed, denoised, and converted to grayscale to obtain enhanced image data;

[0014] Enhanced image data is used for coal block contour feature recognition and relative size analysis to obtain information on the size range and quantity distribution of coal blocks based on image analysis.

[0015] The coal block size distribution information is obtained by integrating the information on the range of coal block sizes with the information on the distribution of coal block quantities.

[0016] In this scheme, the step of importing coal block size distribution information into the coal mill operation simulation model for analysis to obtain preset coal mill operation parameter information and preset coal mill monitoring data includes:

[0017] Construct a simulation model of coal mill operation;

[0018] Obtain historical operation monitoring data and corresponding historical operation parameter data of the coal mill;

[0019] Import historical operation monitoring data and historical operation parameter data into the coal mill operation simulation model for dataset training;

[0020] After appropriate training, historical operation monitoring data and corresponding historical operation parameter data are used as a two-way test set to obtain a pre-set standard coal mill operation simulation model.

[0021] In this scheme, the process of importing coal block size distribution information into the coal mill operation simulation model for analysis to obtain preset coal mill operation parameters and preset coal mill monitoring data specifically involves:

[0022] The coal block size distribution information is imported into the coal mill operation simulation model to predict simulation parameters and obtain test parameter information within the prediction range;

[0023] Based on the test parameter information, the parameter range is divided to obtain N test coal mill operating parameter information;

[0024] The test coal mill operating parameter information is imported into the coal mill operation simulation model for operation simulation analysis to obtain the corresponding N coal mill monitoring data;

[0025] The monitoring data of N coal mills are compared with historical stable detection data, and the optimal coal mill monitoring data is selected to obtain the preset coal mill monitoring data. The corresponding coal mill operating parameter information is then used as the preset coal mill operating parameter information.

[0026] In this solution, the step of comparing and analyzing the coal mill operation monitoring data with the preset coal mill monitoring data to obtain abnormal deviation data is as follows:

[0027] Obtain the actual vibration frequency and actual amplitude range from the coal mill operation monitoring data;

[0028] Obtain the preset vibration frequency and preset amplitude range from the preset coal mill monitoring data;

[0029] The actual vibration frequency and amplitude range are compared and analyzed with the preset vibration frequency and amplitude range respectively;

[0030] If the actual vibration frequency is higher than the preset vibration frequency and the actual amplitude range is greater than the preset amplitude range, then the deviation between the vibration frequency and the amplitude range is calculated to obtain the vibration frequency deviation data and the amplitude range deviation data.

[0031] Abnormal deviation data are obtained by processing the vibration frequency deviation data and amplitude range deviation data.

[0032] In this scheme, the step of performing simulation analysis based on abnormal deviation data to obtain parameter correction information, and then correcting the operating parameters of the coal mill based on the parameter correction information, specifically involves:

[0033] The abnormal deviation data and preset parameter information are imported into the coal mill operation simulation model for deviation analysis to obtain parameter correction information and preset correction time.

[0034] The preset parameter information is corrected based on the parameter correction information, and the corrected preset parameter information is used as the operating parameters of the coal mill.

[0035] In this scheme, the step of performing simulation analysis based on abnormal deviation data to obtain parameter correction information, and then correcting the operating parameters of the coal mill based on the parameter correction information, specifically involves:

[0036] Real-time acquisition of coal mill correction operation monitoring data;

[0037] Anomaly monitoring analysis was performed between the corrected operation monitoring data of the coal mill and the preset coal mill monitoring data to obtain the duration of the abnormal data deviation.

[0038] Compare the duration of abnormal data deviation with the preset correction time;

[0039] If the duration of abnormal data deviation exceeds the preset correction time, the corrected coal mill operation monitoring data and the preset coal mill monitoring data will be compared to perform a monitoring data deviation early warning analysis to obtain equipment operation early warning information.

[0040] A second aspect of the present invention also provides a coal mill equipment monitoring system based on data analysis. The system includes a memory and a processor. The memory includes a coal mill equipment monitoring method program based on data analysis. When executed by the processor, the coal mill equipment monitoring method program based on data analysis performs the following steps:

[0041] Obtain raw image data of coal blocks, perform image recognition and analysis based on the raw image data of coal blocks, and obtain coal block size distribution information based on image analysis;

[0042] The coal block size distribution information is imported into the coal mill operation simulation model for analysis to obtain the preset coal mill operation parameter information and preset coal mill monitoring data.

[0043] The coal mill is operated according to the preset coal mill operating parameters, and the coal mill operation monitoring data is acquired in real time.

[0044] By comparing and analyzing the coal mill operation monitoring data with the preset coal mill monitoring data, abnormal deviation data are obtained.

[0045] Simulation analysis is performed based on abnormal deviation data to obtain parameter correction information, and the operating parameters of the coal mill are corrected based on the parameter correction information.

[0046] In this solution, the acquisition of original coal block image data, and the subsequent image recognition and analysis based on the original coal block image data to obtain coal block size distribution information based on image analysis, specifically involves:

[0047] Acquire raw image data of the coal block;

[0048] The original image data is smoothed, denoised, and converted to grayscale to obtain enhanced image data;

[0049] Enhanced image data is used for coal block contour feature recognition and relative size analysis to obtain information on the size range and quantity distribution of coal blocks based on image analysis.

[0050] The coal block size distribution information is obtained by integrating the information on the range of coal block sizes with the information on the distribution of coal block quantities.

[0051] In this scheme, the step of importing coal block size distribution information into the coal mill operation simulation model for analysis to obtain preset coal mill operation parameter information and preset coal mill monitoring data includes:

[0052] Construct a simulation model of coal mill operation;

[0053] Obtain historical operation monitoring data and corresponding historical operation parameter data of the coal mill;

[0054] Import historical operation monitoring data and historical operation parameter data into the coal mill operation simulation model for dataset training;

[0055] After appropriate training, historical operation monitoring data and corresponding historical operation parameter data are used as a two-way test set to obtain a pre-set standard coal mill operation simulation model.

[0056] This invention discloses a data analysis-based method and system for monitoring coal mill equipment. The invention acquires raw image data of coal blocks, performs image recognition and analysis based on this data to obtain coal block size distribution information, and further analyzes the data through a model to obtain targeted preset operating parameters for the coal mill, thereby improving the mill's production efficiency. Furthermore, by comparing actual monitoring data with preset monitoring data, the invention obtains parameter correction information, further enhancing the mill's ability to respond to abnormal situations, thus reducing manpower consumption and ultimately improving economic efficiency. Attached Figure Description

[0057] Figure 1 A flowchart of a data analysis-based coal mill equipment monitoring method according to the present invention is shown;

[0058] Figure 2 A flowchart illustrating the process of obtaining coal block size distribution information according to the present invention is shown.

[0059] Figure 3 The flowchart of the present invention for constructing a coal mill operation simulation model is shown;

[0060] Figure 4 A block diagram of a coal mill equipment monitoring system based on data analysis according to the present invention is shown. Detailed Implementation

[0061] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0062] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0063] Figure 1 A flowchart of a data analysis-based coal mill equipment monitoring method according to the present invention is shown.

[0064] like Figure 1 As shown, the first aspect of the present invention provides a data analysis-based method for monitoring coal mill equipment, comprising:

[0065] S102, acquire the original image data of the coal block, perform image recognition and analysis based on the original image data of the coal block, and obtain the coal block size distribution information based on image analysis;

[0066] S104. Import the coal block size distribution information into the coal mill operation simulation model for analysis to obtain the preset coal mill operation parameter information and preset coal mill monitoring data.

[0067] S106, performs coal mill operation according to preset coal mill operating parameter information, and acquires coal mill operation monitoring data in real time;

[0068] S108, compare and analyze the coal mill operation monitoring data with the preset coal mill monitoring data to obtain abnormal deviation data;

[0069] S110: Based on the abnormal deviation data, simulation analysis is performed to obtain parameter correction information, and the operating parameters of the coal mill are corrected based on the parameter correction information.

[0070] Figure 2 A flowchart illustrating the process of obtaining coal block size distribution information according to the present invention is shown.

[0071] According to an embodiment of the present invention, the step of acquiring original image data of coal blocks, and performing image recognition and analysis based on the original image data of coal blocks to obtain coal block size distribution information based on image analysis specifically includes:

[0072] S202, Obtain raw image data of the coal block;

[0073] S204 performs smoothing, noise reduction, and grayscale conversion on the original image data to obtain enhanced image data;

[0074] S206, perform coal block contour feature recognition and relative size analysis on the enhanced image data to obtain coal block size range information and coal block quantity distribution information based on image analysis;

[0075] S208, integrate the information on the range of coal block sizes with the information on the distribution of coal block quantities to obtain the coal block size distribution information.

[0076] It should be noted that the process of identifying coal block contour features and analyzing relative sizes from enhanced image data specifically involves identifying coal block contour features in the image data and performing area ratio analysis between the contour range and the entire image to obtain coal block size range information. Furthermore, by comprehensively analyzing and statistically processing multiple original image datasets, coal block quantity distribution information can be obtained. This coal block quantity distribution information includes quantity information corresponding to different coal block size ranges.

[0077] It is worth mentioning that the size distribution of coal lumps in the same batch is relatively consistent. Through image recognition analysis, the size distribution of coal lumps in the current batch can be obtained, providing a precise data basis for adjusting the parameters of the coal mill. In the subsequent analysis process, targeted preset parameters for the equipment can be obtained for the current batch of coal lumps.

[0078] Figure 3 The flowchart of the present invention for constructing a coal mill operation simulation model is shown.

[0079] According to an embodiment of the present invention, the step of importing coal block size distribution information into a coal mill operation simulation model for analysis to obtain preset coal mill operation parameter information and preset coal mill monitoring data includes:

[0080] S302, Construct a simulation model for coal mill operation;

[0081] S304, Obtain historical operation monitoring data and corresponding historical operation parameter data of the coal mill;

[0082] S306, import historical operation monitoring data and historical operation parameter data into the coal mill operation simulation model for dataset training;

[0083] After appropriate training, S308 uses historical operation monitoring data and corresponding historical operation parameter data as a two-way test set to obtain a pre-set standard coal mill operation simulation model.

[0084] It should be noted that the historical operation monitoring data and operation parameter data include monitoring the coal mill's inlet air temperature, outlet temperature, operating power, vibration frequency and amplitude range, etc., while the operation parameter data include inlet air volume, loading force, coal feed rate, coal feed rate, separator speed, etc.

[0085] Furthermore, the step of using historical operation monitoring data and corresponding historical operation parameter data as a bidirectional test set specifically involves importing the historical monitoring data and historical operation parameter data as test data into the coal mill operation simulation model for bidirectional testing, and obtaining corresponding test result data. The test result data includes both historical operation parameter data and historical operation monitoring data. The preset standard specifically requires that the coal mill operation simulation model can perform simulation analysis based on the historical monitoring data or historical operation parameter data to obtain correct historical operation parameter data or historical operation monitoring data.

[0086] According to an embodiment of the present invention, the step of importing coal block size distribution information into a coal mill operation simulation model for analysis to obtain preset coal mill operation parameter information and preset coal mill monitoring data specifically includes:

[0087] The coal block size distribution information is imported into the coal mill operation simulation model to predict simulation parameters and obtain test parameter information within the prediction range;

[0088] Based on the test parameter information, the parameter range is divided to obtain N test coal mill operating parameter information;

[0089] The test coal mill operating parameter information is imported into the coal mill operation simulation model for operation simulation analysis to obtain the corresponding N coal mill monitoring data;

[0090] The monitoring data of N coal mills are compared with historical stable detection data, and the optimal coal mill monitoring data is selected to obtain the preset coal mill monitoring data. The corresponding coal mill operating parameter information is then used as the preset coal mill operating parameter information.

[0091] It should be noted that, in the process of importing the coal block size distribution information into the coal mill operation simulation model for simulation parameter prediction, and obtaining test parameter information within the prediction range, the coal mill operation simulation model will estimate the reasonable parameter range of the coal mill based on the coal block size distribution information, thus obtaining test parameter information within the prediction range. Furthermore, the coal mill operation parameters corresponding to coal grinding operations for different coal block sizes will also be different. In the N test coal mill operation parameter information, the value of N is determined by the size of the prediction range, specifically the reasonable parameter prediction range; the larger the range, the larger N. The historical stable detection data specifically refers to the detection data during stable operation of the coal mill.

[0092] According to an embodiment of the present invention, the step of comparing and analyzing the coal mill operation monitoring data with preset coal mill monitoring data to obtain abnormal deviation data specifically involves:

[0093] Obtain the actual vibration frequency and actual amplitude range from the coal mill operation monitoring data;

[0094] Obtain the preset vibration frequency and preset amplitude range from the preset coal mill monitoring data;

[0095] The actual vibration frequency and amplitude range are compared and analyzed with the preset vibration frequency and amplitude range respectively;

[0096] If the actual vibration frequency is higher than the preset vibration frequency and the actual amplitude range is greater than the preset amplitude range, then the deviation between the vibration frequency and the amplitude range is calculated to obtain the vibration frequency deviation data and the amplitude range deviation data.

[0097] Abnormal deviation data are obtained by processing the vibration frequency deviation data and amplitude range deviation data.

[0098] It should be noted that the deviation calculation of vibration frequency and amplitude range specifically involves calculating the difference between the actual vibration frequency and the preset vibration frequency, and calculating the data range difference between the actual amplitude range and the preset amplitude range.

[0099] According to an embodiment of the present invention, the step of performing simulation analysis based on abnormal deviation data to obtain parameter correction information, and then correcting the operating parameters of the coal mill based on the parameter correction information, specifically includes:

[0100] The abnormal deviation data and preset parameter information are imported into the coal mill operation simulation model for deviation analysis to obtain parameter correction information and preset correction time.

[0101] The preset parameter information is corrected based on the parameter correction information, and the corrected preset parameter information is used as the operating parameters of the coal mill.

[0102] It should be noted that during the production operation of a coal mill, problems such as sluggish operation and large vibration amplitude often occur due to foreign objects or coal blockage. This invention monitors and analyzes the vibration frequency and amplitude range of the coal mill equipment to obtain corresponding parameter correction information, thereby solving the problems encountered by the coal mill in the production process more efficiently and accurately, reducing the consumption of human resources, and greatly improving production efficiency.

[0103] According to an embodiment of the present invention, the step of performing simulation analysis based on abnormal deviation data to obtain parameter correction information, and then correcting the operating parameters of the coal mill based on the parameter correction information, specifically includes:

[0104] Real-time acquisition of coal mill correction operation monitoring data;

[0105] Anomaly monitoring analysis was performed between the corrected operation monitoring data of the coal mill and the preset coal mill monitoring data to obtain the duration of the abnormal data deviation.

[0106] Compare the duration of abnormal data deviation with the preset correction time;

[0107] If the duration of abnormal data deviation exceeds the preset correction time, the corrected coal mill operation monitoring data and the preset coal mill monitoring data will be compared to perform a monitoring data deviation early warning analysis to obtain equipment operation early warning information.

[0108] It should be noted that the equipment operation early warning information includes early warning level and monitoring deviation information. The early warning level is specifically determined by the degree of deviation between the corrected operating monitoring data of the coal mill and the preset monitoring data; the greater the deviation, the higher the early warning level. Based on the equipment operation early warning information, the current abnormal operating status of the coal mill equipment can be grasped in real time and accurately, thereby enabling safer production.

[0109] According to an embodiment of the present invention, it further includes:

[0110] Acquire coal powder image data after coal mill production operation;

[0111] The coal powder image data is smoothed, denoised, and color-enhanced preprocessed to obtain color-enhanced image data.

[0112] Acquire comparative coal powder image data; perform colorimetric recognition and color distribution analysis on the color-enhanced image data and the comparative coal powder image data to obtain information on the uniformity of coal powder particles and the fineness of coal powder particles;

[0113] The information on the uniformity of coal powder particles and the fineness of coal powder particles are imported into the coal mill operation simulation model for reverse simulation analysis to obtain secondary correction parameter information.

[0114] It should be noted that the comparative coal powder image data specifically refers to historically existing images of qualified coal powder products, which have good comparative reference value. The information on the uniformity and fineness of the coal powder particles can accurately reflect the production and operation effect of the coal mill. Combined with the coal mill operation simulation model, secondary correction parameter information can be obtained, thereby performing secondary parameter correction on the coal mill, achieving precise control of the coal mill equipment, and further improving the production efficiency of the coal mill.

[0115] According to an embodiment of the present invention, it further includes:

[0116] Obtain vibration frequency deviation data and amplitude range deviation data;

[0117] Intelligent analysis of the degree of deviation is performed based on the vibration frequency deviation data and amplitude range deviation data to obtain the degree of damage to the coal mill fault.

[0118] Obtain coal mill structural data;

[0119] The structural data, vibration frequency deviation data, and amplitude range deviation data of the coal mill are imported into a CNN-based fault prediction model, and the fault points of the coal mill are predicted and analyzed to obtain information on the fault damage location.

[0120] Based on the information on the location of the fault damage, the structural range of the coal mill is analyzed to obtain the information on the scope of the fault's impact.

[0121] Fault warning information is generated based on the degree of damage to the coal mill, the location of the damage, and the scope of the impact of the fault.

[0122] It should be noted that in the CNN-based fault prediction model, the CNN specifically refers to a convolutional neural network. Through the prediction algorithm of the convolutional neural network, the fault location of the coal mill can be accurately predicted, thereby generating targeted fault warning information and further improving the efficiency of resolving coal mill faults. The coal mill structural data specifically refers to the three-dimensional structural data of the coal mill.

[0123] Figure 4 A block diagram of a coal mill equipment monitoring system based on data analysis according to the present invention is shown.

[0124] A second aspect of the present invention also provides a coal mill equipment monitoring system 4 based on data analysis. The system includes a memory 41 and a processor 42. The memory includes a coal mill equipment monitoring method program based on data analysis. When the processor executes the coal mill equipment monitoring method program based on data analysis, it performs the following steps:

[0125] Obtain raw image data of coal blocks, perform image recognition and analysis based on the raw image data of coal blocks, and obtain coal block size distribution information based on image analysis;

[0126] The coal block size distribution information is imported into the coal mill operation simulation model for analysis to obtain the preset coal mill operation parameter information and preset coal mill monitoring data.

[0127] The coal mill is operated according to the preset coal mill operating parameters, and the coal mill operation monitoring data is acquired in real time.

[0128] By comparing and analyzing the coal mill operation monitoring data with the preset coal mill monitoring data, abnormal deviation data are obtained.

[0129] Simulation analysis is performed based on abnormal deviation data to obtain parameter correction information, and the operating parameters of the coal mill are corrected based on the parameter correction information.

[0130] According to an embodiment of the present invention, the step of acquiring original image data of coal blocks, and performing image recognition and analysis based on the original image data of coal blocks to obtain coal block size distribution information based on image analysis specifically includes:

[0131] Acquire raw image data of the coal block;

[0132] The original image data is smoothed, denoised, and converted to grayscale to obtain enhanced image data;

[0133] Enhanced image data is used for coal block contour feature recognition and relative size analysis to obtain information on the size range and quantity distribution of coal blocks based on image analysis.

[0134] The coal block size distribution information is obtained by integrating the information on the range of coal block sizes with the information on the distribution of coal block quantities.

[0135] It should be noted that the process of identifying coal block contour features and analyzing relative sizes from enhanced image data specifically involves identifying coal block contour features in the image data and performing area ratio analysis between the contour range and the entire image to obtain coal block size range information. Furthermore, by comprehensively analyzing and statistically processing multiple original image datasets, coal block quantity distribution information can be obtained. This coal block quantity distribution information includes quantity information corresponding to different coal block size ranges.

[0136] It is worth mentioning that the size distribution of coal lumps in the same batch is relatively consistent. Through image recognition analysis, the size distribution of coal lumps in the current batch can be obtained, providing a precise data basis for adjusting the parameters of the coal mill. In the subsequent analysis process, targeted preset parameters for the equipment can be obtained for the current batch of coal lumps.

[0137] According to an embodiment of the present invention, the step of importing coal block size distribution information into a coal mill operation simulation model for analysis to obtain preset coal mill operation parameter information and preset coal mill monitoring data includes:

[0138] Construct a simulation model of coal mill operation;

[0139] Obtain historical operation monitoring data and corresponding historical operation parameter data of the coal mill;

[0140] Import historical operation monitoring data and historical operation parameter data into the coal mill operation simulation model for dataset training;

[0141] After appropriate training, historical operation monitoring data and corresponding historical operation parameter data are used as a two-way test set to obtain a pre-set standard coal mill operation simulation model.

[0142] It should be noted that the historical operation monitoring data and operation parameter data include monitoring the coal mill's inlet air temperature, outlet temperature, operating power, vibration frequency and amplitude range, etc., while the operation parameter data include inlet air volume, loading force, coal feed rate, coal feed rate, separator speed, etc.

[0143] Furthermore, the step of using historical operation monitoring data and corresponding historical operation parameter data as a bidirectional test set specifically involves importing the historical monitoring data and historical operation parameter data as test data into the coal mill operation simulation model for bidirectional testing, and obtaining corresponding test result data. The test result data includes both historical operation parameter data and historical operation monitoring data. The preset standard specifically requires that the coal mill operation simulation model can perform simulation analysis based on the historical monitoring data or historical operation parameter data to obtain correct historical operation parameter data or historical operation monitoring data.

[0144] According to an embodiment of the present invention, the step of importing coal block size distribution information into a coal mill operation simulation model for analysis to obtain preset coal mill operation parameter information and preset coal mill monitoring data specifically includes:

[0145] The coal block size distribution information is imported into the coal mill operation simulation model to predict simulation parameters and obtain test parameter information within the prediction range;

[0146] Based on the test parameter information, the parameter range is divided to obtain N test coal mill operating parameter information;

[0147] The test coal mill operating parameter information is imported into the coal mill operation simulation model for operation simulation analysis to obtain the corresponding N coal mill monitoring data;

[0148] The monitoring data of N coal mills are compared with historical stable detection data, and the optimal coal mill monitoring data is selected to obtain the preset coal mill monitoring data. The corresponding coal mill operating parameter information is then used as the preset coal mill operating parameter information.

[0149] It should be noted that, in the process of importing the coal block size distribution information into the coal mill operation simulation model for simulation parameter prediction, and obtaining test parameter information within the prediction range, the coal mill operation simulation model will estimate the reasonable parameter range of the coal mill based on the coal block size distribution information, thus obtaining test parameter information within the prediction range. Furthermore, the coal mill operation parameters corresponding to coal grinding operations for different coal block sizes will also be different. In the N test coal mill operation parameter information, the value of N is determined by the size of the prediction range, specifically the reasonable parameter prediction range; the larger the range, the larger N. The historical stable detection data specifically refers to the detection data during stable operation of the coal mill.

[0150] According to an embodiment of the present invention, the step of comparing and analyzing the coal mill operation monitoring data with preset coal mill monitoring data to obtain abnormal deviation data specifically involves:

[0151] Obtain the actual vibration frequency and actual amplitude range from the coal mill operation monitoring data;

[0152] Obtain the preset vibration frequency and preset amplitude range from the preset coal mill monitoring data;

[0153] The actual vibration frequency and amplitude range are compared and analyzed with the preset vibration frequency and amplitude range respectively;

[0154] If the actual vibration frequency is higher than the preset vibration frequency and the actual amplitude range is greater than the preset amplitude range, then the deviation between the vibration frequency and the amplitude range is calculated to obtain the vibration frequency deviation data and the amplitude range deviation data.

[0155] Abnormal deviation data are obtained by processing the vibration frequency deviation data and amplitude range deviation data.

[0156] It should be noted that the deviation calculation of vibration frequency and amplitude range specifically involves calculating the difference between the actual vibration frequency and the preset vibration frequency, and calculating the data range difference between the actual amplitude range and the preset amplitude range.

[0157] According to an embodiment of the present invention, the step of performing simulation analysis based on abnormal deviation data to obtain parameter correction information, and then correcting the operating parameters of the coal mill based on the parameter correction information, specifically includes:

[0158] The abnormal deviation data and preset parameter information are imported into the coal mill operation simulation model for deviation analysis to obtain parameter correction information and preset correction time.

[0159] The preset parameter information is corrected based on the parameter correction information, and the corrected preset parameter information is used as the operating parameters of the coal mill.

[0160] It should be noted that during the production operation of a coal mill, problems such as sluggish operation and large vibration amplitude often occur due to foreign objects or coal blockage. This invention monitors and analyzes the vibration frequency and amplitude range of the coal mill equipment to obtain corresponding parameter correction information, thereby solving the problems encountered by the coal mill in the production process more efficiently and accurately, reducing the consumption of human resources, and greatly improving production efficiency.

[0161] According to an embodiment of the present invention, the step of performing simulation analysis based on abnormal deviation data to obtain parameter correction information, and then correcting the operating parameters of the coal mill based on the parameter correction information, specifically includes:

[0162] Real-time acquisition of coal mill correction operation monitoring data;

[0163] Anomaly monitoring analysis was performed between the corrected operation monitoring data of the coal mill and the preset coal mill monitoring data to obtain the duration of the abnormal data deviation.

[0164] Compare the duration of abnormal data deviation with the preset correction time;

[0165] If the duration of abnormal data deviation exceeds the preset correction time, the corrected coal mill operation monitoring data and the preset coal mill monitoring data will be compared to perform a monitoring data deviation early warning analysis to obtain equipment operation early warning information.

[0166] It should be noted that the equipment operation early warning information includes early warning level and monitoring deviation information. The early warning level is specifically determined by the degree of deviation between the corrected operating monitoring data of the coal mill and the preset monitoring data; the greater the deviation, the higher the early warning level. Based on the equipment operation early warning information, the current abnormal operating status of the coal mill equipment can be grasped in real time and accurately, thereby enabling safer production.

[0167] According to an embodiment of the present invention, it further includes:

[0168] Acquire coal powder image data after coal mill production operation;

[0169] The coal powder image data is smoothed, denoised, and color-enhanced preprocessed to obtain color-enhanced image data.

[0170] Acquire comparative coal powder image data; perform colorimetric recognition and color distribution analysis on the color-enhanced image data and the comparative coal powder image data to obtain information on the uniformity of coal powder particles and the fineness of coal powder particles;

[0171] The information on the uniformity of coal powder particles and the fineness of coal powder particles are imported into the coal mill operation simulation model for reverse simulation analysis to obtain secondary correction parameter information.

[0172] It should be noted that the comparative coal powder image data specifically refers to historically existing images of qualified coal powder products, which have good comparative reference value. The information on the uniformity and fineness of the coal powder particles can accurately reflect the production and operation effect of the coal mill. Combined with the coal mill operation simulation model, secondary correction parameter information can be obtained, thereby performing secondary parameter correction on the coal mill, achieving precise control of the coal mill equipment, and further improving the production efficiency of the coal mill.

[0173] According to an embodiment of the present invention, it further includes:

[0174] Obtain vibration frequency deviation data and amplitude range deviation data;

[0175] Intelligent analysis of the degree of deviation is performed based on the vibration frequency deviation data and amplitude range deviation data to obtain the degree of damage to the coal mill fault.

[0176] Obtain coal mill structural data;

[0177] The structural data, vibration frequency deviation data, and amplitude range deviation data of the coal mill are imported into a CNN-based fault prediction model, and the fault points of the coal mill are predicted and analyzed to obtain information on the fault damage location.

[0178] Based on the information on the location of the fault damage, the structural range of the coal mill is analyzed to obtain the information on the scope of the fault's impact.

[0179] Fault warning information is generated based on the degree of damage to the coal mill, the location of the damage, and the scope of the impact of the fault.

[0180] It should be noted that in the CNN-based fault prediction model, the CNN specifically refers to a convolutional neural network. Through the prediction algorithm of the convolutional neural network, the fault location of the coal mill can be accurately predicted, thereby generating targeted fault warning information and further improving the efficiency of resolving coal mill faults. The coal mill structural data specifically refers to the three-dimensional structural data of the coal mill.

[0181] This invention discloses a data analysis-based method and system for monitoring coal mill equipment. The invention acquires raw image data of coal blocks, performs image recognition and analysis based on this data to obtain coal block size distribution information, and further analyzes the data through a model to obtain targeted preset operating parameters for the coal mill, thereby improving the mill's production efficiency. Furthermore, by comparing actual monitoring data with preset monitoring data, the invention obtains parameter correction information, further enhancing the mill's ability to respond to abnormal situations, thus reducing manpower consumption and ultimately improving economic efficiency.

[0182] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0183] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0184] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0185] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0186] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0187] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A data analysis based coal mill plant monitoring method, characterized by, The method comprises the following steps: acquiring raw image data of coal blocks, performing image recognition and analysis on the raw image data of the coal blocks to obtain coal block size distribution information based on image analysis; introducing the coal block size distribution information into a coal mill operation simulation model for analysis to obtain preset coal mill operation parameter information and preset coal mill monitoring data; performing coal mill operation according to the preset coal mill operation parameter information and acquiring real-time coal mill operation monitoring data; comparing and analyzing the coal mill operation monitoring data and the preset coal mill monitoring data to obtain abnormal deviation data; performing simulation analysis according to the abnormal deviation data to obtain parameter correction information, and correcting the operation parameters of the coal mill according to the parameter correction information; wherein the step of introducing the coal block size distribution information into the coal mill operation simulation model for analysis to obtain the preset coal mill operation parameter information and the preset coal mill monitoring data comprises the following steps: constructing a coal mill operation simulation model; acquiring historical coal mill operation monitoring data and corresponding historical operation parameter data; introducing the historical coal mill operation monitoring data and the corresponding historical operation parameter data into the coal mill operation simulation model for data set training; after corresponding training, testing the historical coal mill operation monitoring data and the corresponding historical operation parameter data as a bidirectional test set to obtain a preset standard coal mill operation simulation model; wherein the step of introducing the coal block size distribution information into the coal mill operation simulation model for analysis to obtain the preset coal mill operation parameter information and the preset coal mill monitoring data specifically comprises the following steps: introducing the coal block size distribution information into the coal mill operation simulation model for simulation parameter prediction to obtain test parameter information within a prediction range; dividing the parameter range according to the test parameter information to obtain N test coal mill operation parameter information; introducing the test coal mill operation parameter information into the coal mill operation simulation model for operation simulation analysis to obtain corresponding N coal mill monitoring data; comparing the N coal mill monitoring data with historical stable detection data and screening out optimal coal mill monitoring data to obtain preset coal mill monitoring data, and taking the corresponding coal mill operation parameter information as preset coal mill operation parameter information.

2. A data analysis based coal mill plant monitoring method as claimed in claim 1 wherein, The step of acquiring raw image data of coal blocks, performing image recognition and analysis on the raw image data of the coal blocks to obtain coal block size distribution information based on image analysis specifically comprises the following steps: acquiring raw image data of coal blocks; performing smoothing, noise reduction and grayscale processing on the raw image data to obtain enhanced image data; performing coal block contour feature recognition and relative size analysis on the enhanced image data to obtain coal block size range information and coal block quantity distribution information based on image analysis; integrating the coal block size range information and the coal block quantity distribution information to obtain coal block size distribution information.

3. A data analytics based coal mill plant monitoring method as claimed in claim 1 wherein, The step of comparing and analyzing the coal mill operation monitoring data and the preset coal mill monitoring data to obtain abnormal deviation data specifically comprises the following steps: acquiring actual vibration frequency and actual amplitude range in the coal mill operation monitoring data; acquiring preset vibration frequency and preset amplitude range in the preset coal mill monitoring data; comparing and analyzing the actual vibration frequency and the actual amplitude range with the preset vibration frequency and the preset amplitude range, respectively; If the actual vibration frequency is higher than the preset vibration frequency and the actual amplitude range is greater than the preset amplitude range, the vibration frequency and the amplitude range are subjected to deviation calculation to obtain vibration frequency deviation data and amplitude range deviation data; The vibration frequency deviation data and the amplitude range deviation data are subjected to data arrangement to obtain abnormal deviation data.

4. A data analytics based coal mill plant monitoring method as claimed in claim 1 wherein, The abnormal deviation data is subjected to simulation analysis to obtain parameter correction information, and the operation parameters of the coal mill are corrected according to the parameter correction information, specifically: The abnormal deviation data and the preset parameter information are imported into the coal mill operation simulation model for deviation analysis to obtain parameter correction information and a preset correction time; The preset parameter information is corrected according to the parameter correction information, and the corrected preset parameter information is used as the operation parameters of the coal mill.

5. A data analytics based coal mill plant monitoring method as claimed in claim 4 wherein, The abnormal deviation data is subjected to simulation analysis to obtain parameter correction information, and the operation parameters of the coal mill are corrected according to the parameter correction information, specifically: Real-time acquisition of coal mill correction operation monitoring data; Abnormal monitoring analysis of the coal mill correction operation monitoring data and the preset coal mill monitoring data is performed to obtain abnormal data deviation duration; The abnormal data deviation duration is compared with the preset correction time; If the abnormal data deviation duration is greater than the preset correction time, the coal mill correction operation monitoring data and the preset coal mill monitoring data are subjected to monitoring data deviation early warning analysis to obtain equipment operation early warning information.

6. A data analytics based coal mill plant monitoring system characterized in that, The system comprises a memory and a processor, the memory comprises a coal mill equipment monitoring method based on data analysis program, and the coal mill equipment monitoring method based on data analysis program is executed by the processor to realize the steps of the coal mill equipment monitoring method based on data analysis according to claim 1.

7. A data analysis based coal mill plant monitoring system as claimed in claim 6 wherein, The coal block original image data is acquired, and image recognition and analysis are performed on the coal block original image data to obtain coal block size distribution information based on image analysis, specifically: Acquisition of coal block original image data; The original image data is subjected to smoothing, noise reduction, and gray scale processing to obtain enhanced image data; The enhanced image data is subjected to coal block contour feature recognition and relative size analysis to obtain coal block size range information and coal block quantity distribution information based on image analysis; The coal block size range information and the coal block quantity distribution information are integrated to obtain the coal block size distribution information.

Images