Coal mine enterprise illegal production operation judgment method and system based on machine learning

Abstract

The invention discloses a coal mine enterprise illegal production operation judgment method and system based on machine learning, and relates to the technical field of power operation management, and the method comprises the following steps: building an enterprise power consumption abnormity recognition model based on enterprise historical power monitoring data and historical coal mine enterprise illegal production judgment results; inputting power consumption data of each coal mine area obtained from the result data of the enterprise power consumption classification estimation calculation into an enterprise power consumption abnormity identification model, and determining a power consumption abnormity area and abnormal power consumption; and carrying out association analysis on the abnormal power consumption and the personnel change characteristics of the suspected mining operation point, and determining whether the suspected mining operation point is a mining operation point or not. According to the method, clustering analysis is carried out on the power consumption abnormal area through the personnel characteristic data, association analysis is carried out on the abnormal power consumption of the suspected mining operation point and the personnel change characteristics, whether the suspected mining operation point is the mining operation point is determined, and illegal behaviors in coal mine production operation are automatically identified and judged.

Description

Technical Field

[0001] The present invention relates to the technical field of power operation management, and in particular to a method and system for judging illegal production operations of coal mining enterprises based on machine learning. Background Art

[0002] The hazards of illegal production by coal mining enterprises mainly include insufficient investment in safety facilities, electrical fires and electric shock hazards, and increased risk of major accidents in coal mines.

[0003] Insufficient investment in safety facilities: When coal mining enterprises face losses, they may reduce investment in safety facilities, resulting in the inability to keep up with the necessary safety facilities, thus affecting safe production.

[0004] Electrical fire and electric shock hazards: If the electrical equipment used in coal mine production systems and auxiliary systems is overloaded for a long time, it may generate a lot of heat, causing the internal insulators of the electrical equipment to be damaged and the protection and monitoring devices to fail, which may cause electrical hazards such as fire and explosion.

[0005] Increased risk of major accidents in coal mines: Overcapacity production is a major risk factor for major accidents in coal mines. Overload production may cause problems with the mine's safety monitoring system, such as failure to install a safety monitoring system, personnel location monitoring system or system failure to operate normally, as well as modification, deletion and shielding of system data, all of which may increase the risk of major accidents in coal mines.

[0006] To sum up, illegal production by coal mining enterprises may not only lead to insufficient investment in safety facilities, but may also cause electrical fires and electric shock hazards, as well as increase the risk of major accidents in coal mines, which is extremely detrimental to production safety. Therefore, it is particularly important to judge illegal production operations by coal mining enterprises. Summary of the invention

[0007] In view of the problems existing in the existing machine learning-based judgment and system for illegal production operations of coal mining enterprises, the present invention is proposed.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0009] In a first aspect, an embodiment of the present invention provides a method for judging illegal production operations of a coal mining enterprise based on machine learning, which comprises the following steps:

[0010] Based on the historical power monitoring data of enterprises and the historical judgment results of illegal production of coal mine enterprises, a model for identifying abnormal power consumption of enterprises is established by using machine learning;

[0011] The power consumption data of each coal mine area obtained from the result data of the enterprise power consumption classification estimation calculation is input into the enterprise power consumption abnormality identification model to determine the power consumption abnormal area and abnormal power consumption;

[0012] Obtaining personnel characteristic data of the abnormal power consumption area, performing cluster analysis on the abnormal power consumption area based on the personnel characteristic data, and obtaining suspected mining operation points;

[0013] Conduct correlation analysis on abnormal power consumption and personnel change characteristics at suspected mining operation points to determine whether the suspected mining operation points are mining operation points.

[0014] As a preferred solution of the method for judging illegal production operations of coal mining enterprises based on machine learning according to the present invention, after determining that the mining operation point is a mining operation point, it also includes:

[0015] When the abnormal power consumption at the mining operation point exceeds the first-level power consumption, an excessive intensity illegal production warning message is generated;

[0016] When the abnormal power consumption at the collection operation point is less than the first-level power consumption and greater than the second-level power consumption, and the number of workers at the mining operation point exceeds 20% of the preset number, an excessive-intensity illegal production warning information is generated.

[0017] As a preferred solution of the method for judging illegal production operations of coal mining enterprises based on machine learning described in the present invention, the step of establishing the abnormal power consumption recognition model of the enterprise includes:

[0018] Establish the corresponding relationship between the historical power monitoring data of enterprises and the historical judgment results of illegal production of coal mine enterprises;

[0019] Based on the corresponding relationship, the historical power monitoring data of the enterprise and the historical illegal production judgment results of the coal mine enterprise are used as training data to train the initial recognition model determined by machine learning to obtain the training results;

[0020] Based on the judgment criteria for illegal production operations of coal mining enterprises, the model attribute evaluation index is determined, and when the training results meet the model attribute evaluation index, the enterprise power consumption anomaly recognition model is obtained.

[0021] As a preferred solution of the method for judging illegal production operations of coal mining enterprises based on machine learning according to the present invention, the step of determining the abnormal power consumption area and abnormal power consumption includes:

[0022] Determine the power consumption data of each coal mine area through the result data, and process the power consumption data based on the time dimension to obtain multiple sets of input data;

[0023] Inputting the input data into the enterprise power consumption anomaly identification model in sequence to obtain the power consumption identification result of the coal mine area;

[0024] Based on the power consumption identification result, the abnormal power consumption area and the abnormal power consumption are obtained.

[0025] As a preferred solution of the method for judging illegal production operations of coal mining enterprises based on machine learning described in the present invention, the method for obtaining the suspected mining operation point includes:

[0026] Determine personnel location data, personnel quantity data and personnel race data according to the personnel characteristic data;

[0027] Determine the personnel area density through personnel location data and personnel quantity data, divide the abnormal power consumption area through the personnel area density to obtain multiple density areas, and obtain the target density area whose density meets the preset density from the multiple density areas;

[0028] Obtaining a density distribution sequence of the density size of the target density area, and determining the number of clusters and cluster centers based on the density distribution sequence;

[0029] Classify the regional name information of each target density area to obtain multiple name types, classify the personnel type data to obtain multiple job types, and establish an evaluation index system based on the name type and job type in combination with historical coal mine enterprise operation data;

[0030] By using a preset clustering algorithm and combining an evaluation index system, cluster analysis is performed on the target density area according to the number of clusters and cluster centers to obtain a regional clustering result;

[0031] The average feature of each group of target density areas is obtained from the regional clustering results, and the target density areas in the target density area group whose average features meet the preset operation features are taken as suspected mining operation points;

[0032] The method for determining the number of clusters and the cluster centers includes:

[0033] Obtaining the center point, mean point and median point of the density distribution sequence;

[0034] Determining the number of clusters by the center point and density distribution sequence length;

[0035] Then, the average value of the mean point and the median point is used as a cluster center, and based on the number of clusters and the length of the density distribution sequence, the density distribution sequence is divided, and other cluster centers are obtained based on the division points.

[0036] As a preferred solution of the method for judging illegal production operations of coal mining enterprises based on machine learning described in the present invention, the method for judging whether the suspected mining operation point is a mining operation point includes:

[0037] The abnormal power consumption of the mining operation point is analyzed according to the time dimension to obtain the abnormal power consumption curve, and the fluctuation point and fluctuation amplitude are obtained from the abnormal power consumption curve;

[0038] Obtain multiple groups of change features according to the change attributes of the personnel change features, and analyze each group of change features according to the time dimension to obtain an attribute change curve corresponding to the change attribute, and obtain the attribute fluctuation amplitude at the same time point as the fluctuation point from the attribute change curve;

[0039] Based on the influence of the changed attribute on the mining operation, a curve weight for the attribute change curve is determined, and based on the curve weight, a weighted analysis is performed on the attribute fluctuation range to obtain a target attribute fluctuation range;

[0040] Obtain the correlation between the fluctuation ranges of target attributes and the fluctuation ranges, and determine the comprehensive correlation between abnormal power consumption and personnel change characteristics of suspected mining operation points based on the correlation of all target attribute fluctuation ranges;

[0041] Determine a first score based on the magnitude of abnormal power consumption at the suspected mining operation point, obtain an average feature of the personnel change feature at the suspected mining operation point, determine a second score based on feature information of the average feature, and determine a third score based on the comprehensive correlation between the abnormal power consumption at the suspected mining operation point and the personnel change feature;

[0042] Based on the first score, the second score and the third score, a comprehensive score of the suspected mining operation point is obtained, and the suspected mining operation point with a comprehensive score greater than a preset score is selected as the mining operation point;

[0043] The method for determining the comprehensive correlation between abnormal power consumption and personnel change characteristics at a suspected mining operation point includes:

[0044] The correlations of the fluctuation amplitudes of the target attributes are accumulated to obtain the comprehensive correlations of the abnormal power consumption and personnel change characteristics of the suspected mining operation points.

[0045] As a preferred solution of the method for judging illegal production operations of coal mining enterprises based on machine learning described in the present invention, it also includes real-time adjustment of the abnormal power consumption recognition model of the enterprise, and the specific steps include:

[0046] Acquire real-time change data of coal mining enterprise operations, and input the real-time change data into the enterprise power consumption anomaly recognition model to obtain a first result;

[0047] Input the first result as a parameter in the next real-time change data into the enterprise power consumption anomaly recognition model to obtain a second result;

[0048] Based on the difference between the change trend of the first result and the second result and the actual change trend, the model parameters are adjusted in real time;

[0049] The steps of adjusting the model parameters in real time include:

[0050] Determine an adjustment range for the model parameters based on a difference between the change trends of the first result and the second result and the actual change trend, and determine a revised change trend of the change trends of the first result and the second result under the adjustment range;

[0051] Based on the difference between the revised change trend and the actual change trend, the model parameters are adjusted cyclically until the difference between the latest revised change trend and the actual change trend meets the difference requirement.

[0052] In a second aspect, an embodiment of the present invention provides a system for judging illegal production operations of coal mining enterprises based on machine learning, which includes a data collection and preprocessing module, a feature engineering module, an anomaly detection module, and a correlation analysis module;

[0053] The data collection and preprocessing module is used to collect the historical power monitoring data of the enterprise and the historical judgment results of illegal production of coal mine enterprises, and clean the data and process missing values ​​and abnormal values;

[0054] The feature engineering module is used to extract features from the power consumption data that are helpful for identifying illegal production;

[0055] The anomaly detection module is used to analyze power consumption data in real time or batch to identify abnormal patterns;

[0056] The correlation analysis module is used to correlate and analyze the abnormal power consumption of suspected mining operation points with the characteristics of personnel changes to determine whether mining operations are actually being carried out at these points.

[0057] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, any step of the above-mentioned method for judging illegal production operations of coal mining enterprises based on machine learning is implemented.

[0058] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned method for determining illegal production operations of coal mining enterprises based on machine learning is implemented.

[0059] The beneficial effects of the present invention are as follows: by using machine learning based on the enterprise's historical power monitoring data and historical coal mine enterprise illegal production judgment results, an enterprise power consumption abnormality recognition model is established, and the power consumption data of each coal mine area obtained from the result data of the enterprise's power consumption classification estimation calculation is input into the enterprise power consumption abnormality recognition model to determine the abnormal power consumption area and abnormal power consumption, thereby providing a basis for further determining the illegal production operation points, by obtaining the personnel characteristic data of the abnormal power consumption area, clustering analysis is performed on the abnormal power consumption area based on the personnel characteristic data to obtain suspected mining operation points, and correlation analysis is performed on the abnormal power consumption of the suspected mining operation points and the personnel change characteristics to determine whether the suspected mining operation points are mining operation points, thereby realizing automatic recognition and judgment of illegal behaviors in coal mine production operations, and realizing accurate judgment of the illegal production operations of coal mine enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0061] Figure 1 This is a flow chart of a method for determining illegal production operations in coal mining enterprises based on machine learning. DETAILED DESCRIPTION

[0062] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0063] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0064] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0065] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0066] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0067] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0068] Example 1

[0069] Reference Figure 1 , which is the first embodiment of the present invention, and provides a method for judging illegal production operations of coal mining enterprises based on machine learning, comprising the following steps:

[0070] S1. Based on the company's historical power monitoring data and historical coal mine production violation judgment results, use machine learning to establish an abnormal power consumption identification model for the company.

[0071] The steps of establishing the enterprise power consumption anomaly identification model include:

[0072] Establish the corresponding relationship between the historical power monitoring data of enterprises and the historical judgment results of illegal production of coal mine enterprises;

[0073] Based on the corresponding relationship, the historical power monitoring data of the enterprise and the historical illegal production judgment results of the coal mine enterprise are used as training data to train the initial recognition model determined by machine learning to obtain the training results;

[0074] Based on the judgment criteria for illegal production operations of coal mining enterprises, the model attribute evaluation index is determined, and when the training results meet the model attribute evaluation index, the enterprise power consumption anomaly recognition model is obtained;

[0075] Among them, the model attribute evaluation indicators include accuracy, robustness and overfitting;

[0076] By establishing a correspondence between the enterprise's historical power monitoring data and the historical coal mine enterprise's illegal production judgment results, taking the corresponding relationship as the standard, and using the enterprise's historical power monitoring data and the historical coal mine enterprise's illegal production judgment results as training data, the initial recognition model determined based on machine learning is trained to obtain training results, and based on the coal mine enterprise's illegal production operation judgment standard, the model attribute evaluation index is determined, and when the training results meet the model attribute evaluation index, the enterprise power consumption anomaly recognition model is obtained, which provides a basis for further determining illegal production operation points.

[0077] S2. The power consumption data of each coal mine area obtained from the result data of the enterprise power consumption classification estimation calculation is input into the enterprise power consumption abnormality identification model to determine the power consumption abnormal area and abnormal power consumption.

[0078] The step of determining the abnormal power consumption area and the abnormal power consumption includes:

[0079] Determine the power consumption data of each coal mine area through the result data, and process the power consumption data based on the time dimension to obtain multiple sets of input data;

[0080] Inputting the input data into the enterprise power consumption anomaly identification model in sequence to obtain the power consumption identification result of the coal mine area;

[0081] Based on the power consumption identification result, obtaining the abnormal power consumption area and the abnormal power consumption;

[0082] The power consumption data is processed based on the time dimension to obtain a plurality of groups of input data by dividing the data into a period according to the time dimension;

[0083] The power consumption identification results of the coal mine area include two types: one is the abnormal power consumption area and abnormal power consumption, and the other is the normal power consumption area and normal power consumption;

[0084] By determining the power consumption data of each coal mine area based on the result data and processing the power consumption data based on the time dimension, multiple groups of input data are obtained, and the input data are input into the enterprise power consumption abnormality identification model in sequence to obtain the power consumption identification results of the coal mine area. Based on the power consumption identification results, the abnormal power consumption area and abnormal power consumption are obtained, providing a basis for further determining the illegal production operation points.

[0085] S3. Obtaining personnel characteristic data of the abnormal power consumption area, performing cluster analysis on the abnormal power consumption area based on the personnel characteristic data, and obtaining suspected mining operation points.

[0086] The method for obtaining the suspected mining operation point includes:

[0087] Determine personnel location data, personnel quantity data and personnel race data according to the personnel characteristic data;

[0088] Determine the personnel area density through personnel location data and personnel quantity data, divide the abnormal power consumption area through the personnel area density to obtain multiple density areas, and obtain the target density area whose density meets the preset density from the multiple density areas;

[0089] Obtaining a density distribution sequence of the density size of the target density area, and determining the number of clusters and cluster centers based on the density distribution sequence;

[0090] Classify the regional name information of each target density area to obtain multiple name types, classify the personnel type data to obtain multiple job types, and establish an evaluation index system based on the name type and job type in combination with historical coal mine enterprise operation data;

[0091] By using a preset clustering algorithm and combining an evaluation index system, cluster analysis is performed on the target density area according to the number of clusters and cluster centers to obtain a regional clustering result;

[0092] The average feature of each group of target density areas is obtained from the regional clustering results, and the target density areas in the target density area group whose average features meet the preset operation features are taken as suspected mining operation points;

[0093] Among them, the name type is, for example, up and down well type, transportation type, etc.;

[0094] The evaluation index system is to evaluate the characteristics of the area based on the name type and the type of work, specifically the probability of whether it is a mining operation site;

[0095] By determining personnel location data, personnel quantity data and personnel type data from the personnel feature data, determining personnel area density based on the personnel location data and personnel quantity data, dividing the power consumption abnormal area based on the personnel area density to obtain multiple density areas, obtaining a target density area whose density meets the preset density from the multiple density areas, obtaining a density distribution sequence of the density of the target density area, and determining the number of clusters and the cluster center based on the density distribution sequence, classifying the area name information of each target density area to obtain multiple name types, classifying the personnel type data to obtain multiple job types, establishing an evaluation index system based on the name type and job type in combination with historical coal mine enterprise operation data, clustering analysis of the target density area according to the number of clusters and the cluster center based on a preset clustering algorithm and in combination with the evaluation index system to obtain regional clustering results, obtaining the average characteristics of each group of target density areas from the regional clustering results, and taking the target density areas in the target density area group whose average characteristics meet the preset operation characteristics as suspected mining operation points, identifying and judging illegal behaviors in coal mine production operations, and realizing accurate judgment of illegal production operations of coal mine enterprises.

[0096] The method for determining the number of clusters and the cluster centers includes:

[0097] Obtaining the center point, mean point and median point of the density distribution sequence;

[0098] Determining the number of clusters by the center point and density distribution sequence length;

[0099] Then, the average value of the mean point and the median point is used as a cluster center, and the density distribution sequence is divided based on the number of clusters and the length of the density distribution sequence, and other cluster centers are obtained based on the division points;

[0100] By obtaining the center point, mean point and median point of the density distribution sequence, the number of clusters is determined based on the center point and the length of the density distribution sequence, the average value of the mean point and the median point is used as a cluster center, and the density distribution sequence is divided based on the number of clusters and the length of the density distribution sequence, and other cluster centers are obtained based on the division points, thereby ensuring the accuracy of the cluster centers and providing a basis for cluster analysis.

[0101] S4, performing correlation analysis on abnormal power consumption and personnel change characteristics of the suspected mining operation point to determine whether the suspected mining operation point is a mining operation point;

[0102] 6. The method for determining whether the suspected mining operation point is a mining operation point includes:

[0103] The abnormal power consumption of the mining operation point is analyzed according to the time dimension to obtain the abnormal power consumption curve, and the fluctuation point and fluctuation amplitude are obtained from the abnormal power consumption curve;

[0104] Obtain multiple groups of change features according to the change attributes of the personnel change features, and analyze each group of change features according to the time dimension to obtain an attribute change curve corresponding to the change attribute, and obtain the attribute fluctuation amplitude at the same time point as the fluctuation point from the attribute change curve;

[0105] Based on the influence of the changed attribute on the mining operation, a curve weight for the attribute change curve is determined, and based on the curve weight, a weighted analysis is performed on the attribute fluctuation range to obtain a target attribute fluctuation range;

[0106] Obtain the correlation between the fluctuation ranges of target attributes and the fluctuation ranges, and determine the comprehensive correlation between abnormal power consumption and personnel change characteristics of suspected mining operation points based on the correlation of all target attribute fluctuation ranges;

[0107] Determine a first score based on the magnitude of abnormal power consumption at the suspected mining operation point, obtain an average feature of the personnel change feature at the suspected mining operation point, determine a second score based on feature information of the average feature, and determine a third score based on the comprehensive correlation between the abnormal power consumption at the suspected mining operation point and the personnel change feature;

[0108] Based on the first score, the second score and the third score, a comprehensive score of the suspected mining operation point is obtained, and the suspected mining operation point with a comprehensive score greater than a preset score is selected as the mining operation point;

[0109] Among them, the changing attributes include quantity, location, and type of work;

[0110] Based on the magnitude of abnormal power consumption at the suspected mining operation point, a first score is determined, the average characteristics of the personnel change characteristics at the suspected mining operation point are obtained, and based on the characteristic information of the average characteristics, a second score is determined, and based on the comprehensive correlation between the abnormal power consumption and the personnel change characteristics at the suspected mining operation point, a third score is determined, and a comprehensive score for the suspected mining operation point is obtained based on the first score, the second score and the third score. The suspected mining operation point with a comprehensive score greater than a preset score is selected as the mining operation point, and the mining operation point is determined from three aspects: power consumption, personnel change characteristics and the correlation between the two, to ensure the accuracy of the obtained mining operation point and achieve accurate judgment on illegal production operations of coal mining enterprises.

[0111] The method for determining the comprehensive correlation between abnormal power consumption and personnel change characteristics at a suspected mining operation point includes:

[0112] The correlations of the fluctuation ranges of the target attributes are accumulated to obtain the comprehensive correlations of the abnormal power consumption and personnel change characteristics of the suspected mining operation points;

[0113] By accumulating the correlations of the fluctuation ranges of all target attributes, the comprehensive correlation of abnormal power consumption and personnel change characteristics of suspected mining operations is obtained, ensuring that the obtained comprehensive correlation takes into account the fluctuation ranges of all target attributes to ensure accuracy.

[0114] After the mining operation point is determined as the mining operation point, the method further includes:

[0115] When the abnormal power consumption at the mining operation point exceeds the first-level power consumption, an excessive intensity illegal production warning message is generated;

[0116] When the abnormal power consumption of the collection operation point is less than the first-level power consumption and greater than the second-level power consumption, and the number of workers at the mining operation point exceeds 20% of the preset number, an excessive intensity illegal production warning information is generated;

[0117] Among them, the power consumption of the first level is greater than that of the second level;

[0118] When the abnormal power consumption at the mining operation point is greater than the first-level power consumption, an early warning information on excessively illegal production is generated; when the abnormal power consumption at the collection operation point is less than the first-level power consumption and greater than the second-level power consumption, and the number of workers at the mining operation point exceeds 20% of the preset number, an early warning information on excessively illegal production is generated, which makes it easier for staff to promptly discover excessively illegal production and make timely interventions.

[0119] In this embodiment, the enterprise power consumption anomaly identification model is used to obtain abnormal power monitoring data from the power monitoring data.

[0120] It also includes real-time adjustment of the enterprise power consumption anomaly recognition model. The specific steps include:

[0121] Acquire real-time change data of coal mining enterprise operations, and input the real-time change data into the enterprise power consumption anomaly recognition model to obtain a first result;

[0122] Input the first result as a parameter in the next real-time change data into the enterprise power consumption anomaly recognition model to obtain a second result;

[0123] Based on the difference between the change trend of the first result and the second result and the actual change trend, the model parameters are adjusted in real time;

[0124] Model parameters include, for example, parameters of the convolutional layer, parameters of the fully connected layer, and parameters of the data normalization layer;

[0125] By acquiring real-time change data of coal mining enterprise operations, the real-time change data is input into the enterprise's power consumption anomaly identification model to obtain a first result, and the first result is used as a parameter in the next real-time change data to input into the enterprise's power consumption anomaly identification model to obtain a second result. Based on the difference between the change trend of the first result and the second result and the actual change trend, the model parameters are adjusted in real time, and the adaptability of the model is improved through batch replacement and tuning of parameters.

[0126] The steps of adjusting the model parameters in real time include:

[0127] Determine an adjustment range for the model parameters based on a difference between the change trends of the first result and the second result and the actual change trend, and determine a revised change trend of the change trends of the first result and the second result under the adjustment range;

[0128] Based on the difference between the revised change trend and the actual change trend, the model parameters are adjusted cyclically until the difference between the latest revised change trend and the actual change trend meets the difference requirement;

[0129] By determining the adjustment range of the model parameters based on the difference between the change trend of the first result and the second result and the actual change trend, and determining the revised change trend of the change trend of the first result and the second result under the adjustment range, and based on the difference between the revised change trend and the actual change trend, cyclically adjusting the model parameters until the difference between the latest revised change trend and the actual change trend meets the difference requirements, the pillow and the model are corrected.

[0130] In summary, based on the company's historical power monitoring data and historical coal mine enterprise illegal production judgment results, machine learning is used to establish an enterprise power consumption anomaly recognition model, and the power consumption data of each coal mine area obtained from the result data of the enterprise's power consumption classification and estimation calculation is input into the enterprise power consumption anomaly recognition model to determine the abnormal power consumption area and abnormal power consumption, so as to provide a basis for further determining the illegal production operation points, and by obtaining the personnel characteristic data of the abnormal power consumption area, a cluster analysis is performed on the abnormal power consumption area based on the personnel characteristic data to obtain suspected mining operation points, and the abnormal power consumption of the suspected mining operation points and the personnel change characteristics are correlated and analyzed to determine whether the suspected mining operation points are mining operation points, so as to realize automatic identification and judgment of illegal behaviors in coal mine production operations, and realize accurate judgment of illegal production operations of coal mine enterprises.

[0131] Example 2

[0132] On the basis of the first embodiment, this embodiment further provides a coal mining enterprise illegal production operation judgment system based on machine learning, including 8. a data collection and preprocessing module, a feature engineering module, an anomaly detection module, and a correlation analysis module;

[0133] The data collection and preprocessing module is used to collect the historical power monitoring data of the enterprise and the historical judgment results of illegal production of coal mine enterprises, and clean the data and process missing values ​​and abnormal values;

[0134] The feature engineering module is used to extract features from the power consumption data that are helpful for identifying illegal production;

[0135] The anomaly detection module is used to analyze power consumption data in real time or batch to identify abnormal patterns;

[0136] The correlation analysis module is used to correlate and analyze the abnormal power consumption of suspected mining operation points with the characteristics of personnel changes to determine whether mining operations are actually being carried out at these points.

[0137] This embodiment also provides a computer device, which is suitable for the method of judging illegal production operations of coal mining enterprises based on machine learning, and includes a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method of judging illegal production operations of coal mining enterprises based on machine learning as proposed in the above embodiment.

[0138] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0139] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, a method for determining illegal production operations of coal mining enterprises based on machine learning is implemented as proposed in the above embodiment.

[0140] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0141] Example 3

[0142] On the basis of the previous two embodiments, this embodiment provides a method for judging illegal production operations of coal mining enterprises based on machine learning. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0143] Table 1: Comparison of simulation experiments of different methods

[0144]

[0145] It can be seen from the experimental data that the method of the present invention is superior to the existing technical methods in key indicators such as accuracy, recall rate and F1 score. By combining the power consumption anomaly recognition model and correlation analysis, the present invention can more accurately identify and judge the illegal production behavior of coal mining enterprises, effectively improving the efficiency and accuracy of supervision.

[0146] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for judging illegal production operations of coal mining enterprises based on machine learning, characterized by: The following steps are included: Based on the historical power monitoring data of enterprises and the historical judgment results of illegal production of coal mine enterprises, a model for identifying abnormal power consumption of enterprises is established by using machine learning; The power consumption data of each coal mine area obtained from the result data of the enterprise power consumption classification estimation calculation is input into the enterprise power consumption abnormality identification model to determine the power consumption abnormal area and abnormal power consumption; Obtaining personnel characteristic data of the abnormal power consumption area, performing cluster analysis on the abnormal power consumption area based on the personnel characteristic data, and obtaining suspected mining operation points; Conduct correlation analysis on abnormal power consumption and personnel change characteristics at suspected mining operation points to determine whether the suspected mining operation points are mining operation points.

2. The method for determining illegal production operations of coal mining enterprises based on machine learning according to claim 1, characterized in that: After the mining operation point is determined as the mining operation point, the method further includes: When the abnormal power consumption at the mining operation point exceeds the first-level power consumption, an excessive intensity illegal production warning message is generated; When the abnormal power consumption at the collection operation point is less than the first-level power consumption and greater than the second-level power consumption, and the number of workers at the mining operation point exceeds 20% of the preset number, an excessive-intensity illegal production warning information is generated.

3. The method for determining illegal production operations of coal mining enterprises based on machine learning according to claim 2, characterized in that: The steps of establishing the enterprise power consumption anomaly identification model include: Establish the corresponding relationship between the historical power monitoring data of enterprises and the historical judgment results of illegal production of coal mine enterprises; Taking the corresponding relationship as a standard, the historical power monitoring data of the enterprise and the historical illegal production judgment results of the coal mine enterprise are used as training data to train the initial recognition model determined by machine learning to obtain the training results; Based on the judgment criteria for illegal production operations of coal mining enterprises, the model attribute evaluation index is determined, and when the training results meet the model attribute evaluation index, the enterprise power consumption anomaly recognition model is obtained.

4. The method for determining illegal production operations of coal mining enterprises based on machine learning as claimed in claim 3, characterized in that: The step of determining the abnormal power consumption area and the abnormal power consumption includes: Determine the power consumption data of each coal mine area through the result data, and process the power consumption data based on the time dimension to obtain multiple sets of input data; Inputting the input data into the enterprise power consumption anomaly identification model in sequence to obtain the power consumption identification result of the coal mine area; Based on the power consumption identification result, the abnormal power consumption area and the abnormal power consumption are obtained.

5. The method for determining illegal production operations of coal mining enterprises based on machine learning according to claim 4, characterized in that: The method for obtaining the suspected mining operation point includes: Determine personnel location data, personnel quantity data and personnel race data according to the personnel characteristic data; Determine the personnel area density through personnel location data and personnel quantity data, divide the abnormal power consumption area through the personnel area density to obtain multiple density areas, and obtain the target density area whose density meets the preset density from the multiple density areas; Obtaining a density distribution sequence of the density size of the target density area, and determining the number of clusters and cluster centers based on the density distribution sequence; Classify the regional name information of each target density area to obtain multiple name types, classify the personnel type data to obtain multiple job types, and establish an evaluation index system based on the name type and job type in combination with historical coal mine enterprise operation data; By using a preset clustering algorithm and combining an evaluation index system, cluster analysis is performed on the target density area according to the number of clusters and cluster centers to obtain a regional clustering result; The average feature of each group of target density areas is obtained from the regional clustering results, and the target density areas in the target density area group whose average features meet the preset operation features are taken as suspected mining operation points; The method for determining the number of clusters and the cluster centers includes: Obtaining the center point, mean point and median point of the density distribution sequence; Determining the number of clusters by the center point and density distribution sequence length; Then, the average value of the mean point and the median point is used as a cluster center, and based on the number of clusters and the length of the density distribution sequence, the density distribution sequence is divided, and other cluster centers are obtained based on the division points.

6. The method for determining illegal production operations of coal mining enterprises based on machine learning according to claim 5, characterized in that: The method for determining whether the suspected mining operation point is a mining operation point includes: The abnormal power consumption of the mining operation point is analyzed according to the time dimension to obtain the abnormal power consumption curve, and the fluctuation point and fluctuation amplitude are obtained from the abnormal power consumption curve; Obtain multiple groups of change characteristics according to the change attributes of the personnel change characteristics, and analyze each group of change characteristics according to the time dimension to obtain an attribute change curve corresponding to the change attribute, and obtain the attribute fluctuation amplitude at the same time point as the fluctuation point from the attribute change curve; Based on the influence of the changed attribute on the mining operation, a curve weight for the attribute change curve is determined, and based on the curve weight, a weighted analysis is performed on the attribute fluctuation range to obtain a target attribute fluctuation range; Obtain the correlation between the fluctuation ranges of target attributes and the fluctuation ranges, and determine the comprehensive correlation between abnormal power consumption and personnel change characteristics of suspected mining operation points based on the correlation of all target attribute fluctuation ranges; Determine a first score based on the magnitude of abnormal power consumption at the suspected mining operation point, obtain an average feature of the personnel change feature at the suspected mining operation point, determine a second score based on feature information of the average feature, and determine a third score based on the comprehensive correlation between the abnormal power consumption at the suspected mining operation point and the personnel change feature; Based on the first score, the second score and the third score, a comprehensive score of the suspected mining operation point is obtained, and the suspected mining operation point with a comprehensive score greater than a preset score is selected as the mining operation point; The method for determining the comprehensive correlation between abnormal power consumption and personnel change characteristics at a suspected mining operation point includes: The correlations of the fluctuation amplitudes of the target attributes are accumulated to obtain the comprehensive correlations of the abnormal power consumption and personnel change characteristics of the suspected mining operation points.

7. The method for determining illegal production operations of coal mining enterprises based on machine learning according to claim 6, characterized in that: It also includes real-time adjustment of the enterprise power consumption anomaly recognition model. The specific steps include: Acquire real-time change data of coal mining enterprise operations, and input the real-time change data into the enterprise power consumption anomaly recognition model to obtain a first result; Input the first result as a parameter in the next real-time change data into the enterprise power consumption anomaly recognition model to obtain a second result; Based on the difference between the change trend of the first result and the second result and the actual change trend, the model parameters are adjusted in real time; The steps of adjusting the model parameters in real time include: Determine an adjustment range for the model parameters based on a difference between the change trends of the first result and the second result and the actual change trend, and determine a revised change trend of the change trends of the first result and the second result under the adjustment range; Based on the difference between the revised change trend and the actual change trend, the model parameters are adjusted cyclically until the difference between the latest revised change trend and the actual change trend meets the difference requirement.

8. A system for judging illegal production operations of coal mining enterprises based on machine learning, based on the method for judging illegal production operations of coal mining enterprises based on machine learning according to any one of claims 1 to 7, characterized in that: It includes data collection and preprocessing module, feature engineering module, anomaly detection module, and association analysis module; The data collection and preprocessing module is used to collect the historical power monitoring data of the enterprise and the historical judgment results of illegal production of coal mine enterprises, and clean the data and process missing values ​​and abnormal values; The feature engineering module is used to extract features from the power consumption data that are helpful for identifying illegal production; The anomaly detection module is used to analyze power consumption data in real time or batch to identify abnormal patterns; The correlation analysis module is used to correlate and analyze the abnormal power consumption of suspected mining operation points with the characteristics of personnel changes to determine whether mining operations are actually being carried out at these points.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for judging illegal production operations of coal mining enterprises based on machine learning are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for judging illegal production operations of coal mining enterprises based on machine learning according to any one of claims 1 to 7 are implemented.

Images