Mine disaster monitoring and early warning method and device, control system and related equipment

Abstract

The invention provides a mine disaster monitoring and early warning method. The method comprises the following steps: acquiring disaster monitoring data of a mine; preprocessing the collected disaster monitoring data, and matching a corresponding optimal relevance prediction analysis model according to a current task target; feature extraction is carried out on the preprocessed disaster monitoring data, and then the preprocessed disaster monitoring data are input into a corresponding optimal relevance prediction and analysis model to carry out disaster prediction and relevance analysis between disasters; acquiring a disaster prediction result, a disaster correlation analysis result and a disaster solution suggestion result output by the optimal correlation prediction analysis model, and performing visual output; according to the invention, various influence factors of mine disasters and relevance among the disasters are comprehensively considered, comprehensive monitoring, early warning and control of the mine disasters are realized, effective solution suggestions can be given for different disaster conditions, and the accuracy of disaster early warning, risk assessment and control management is improved; the method is suitable for the mine disaster monitoring and control field.

Description

Technical Field

[0001] The present application relates to the field of mine disaster monitoring and control, and specifically to a mine disaster monitoring and early warning method, device, control system and related equipment. Background Art

[0002] At present, mine safety is one of the major challenges facing the mining industry. With the deepening and complexity of mining activities, mine disasters occur frequently, posing a serious threat to the safety of life and property. In order to effectively prevent and respond to mine disasters, existing technical solutions mostly focus on the monitoring and early warning of a single type of disaster, lacking in-depth research and effective analysis of the correlation between mine disasters. This has led to obvious deficiencies in disaster early warning and emergency response, and it is impossible to comprehensively and accurately assess the overall risk of mine disasters.

[0003] Therefore, it is necessary to develop a mine disaster monitoring and early warning method that can fully consider the correlation of mine disasters, so as to achieve comprehensive monitoring, early warning and risk assessment of mine disasters and improve the level of mine safety production. Summary of the invention

[0004] In order to solve one of the above-mentioned technical defects, the present application provides a mine disaster monitoring and early warning method, device, control system and related equipment.

[0005] According to the first aspect of the present application, a mine disaster monitoring and early warning method is provided, comprising: collecting mine disaster monitoring data, the disaster monitoring data comprising: disaster type, real-time monitoring values ​​of various indicators of disaster occurrence, the various indicators being one or more of geological data, production data and environmental data; preprocessing the collected disaster monitoring data, and matching the corresponding optimal correlation prediction and analysis model according to the current task objectives; extracting features from the preprocessed disaster monitoring data and inputting the data into the corresponding optimal correlation prediction and analysis model to perform disaster prediction and correlation analysis between disasters; obtaining disaster prediction results, disaster correlation analysis results and disaster solution recommendation results output by the optimal correlation prediction and analysis model, and performing visual output.

[0006] Preferably, it also includes: constructing the optimal correlation prediction and analysis model corresponding to different task objectives; the construction of the optimal correlation prediction and analysis model specifically includes: collecting various disaster training data of the mine, the disaster training data includes: the types of disasters that have occurred, the corresponding indicator values ​​when such disasters occur, the changing trends of the indicator values ​​during the disaster, the indicator values ​​after the disaster and the related processing solutions; wherein the related processing solutions include: personnel operation records, system operation records and related data changes after the operation processing; pre-processing the collected various disaster training data, and dividing the pre-processed training data into training set, verification set and test set; through the pre-processed training data, the cause mechanism and influencing factors of various disasters are analyzed. Perform analysis to identify the commonalities and differences between different types of disasters and form a set of possible correlation factors; extract features from the training set and the set of possible correlation factors and input them into multiple backup correlation prediction analysis models to analyze and train the conditions for disaster occurrence, potential correlations and influencing factors between disasters, and solutions after disasters occur; during the training process, use the validation set to iteratively optimize and adjust each backup correlation prediction analysis model, and evaluate the impact of input features on model performance based on the validation results to obtain feature importance evaluation results; after the training is completed, use the test set to conduct a final evaluation of each optimized backup correlation prediction analysis model, and based on the validation results and feature importance evaluation results, obtain the optimal correlation prediction analysis model corresponding to different task objectives.

[0007] Preferably, after feature extraction of the training set and the possible correlation factor set and inputting them into multiple backup correlation prediction analysis models, the following steps are performed: basic analysis is performed on the feature data to identify the overall structure of each disaster data and the basic relationship between each variable; correlation analysis is performed on each disaster data that has undergone basic analysis to calculate the degree of correlation and direction of correlation between each type of disaster; on the basis of the correlation analysis, potential factors that may lead to the occurrence of disasters are identified, and the manner and degree of influence of potential factors on each type of disaster are analyzed; relevant treatment plans after the occurrence of the disaster and relevant data changes after the treatment are analyzed, and the control effect and elimination effect of each treatment method on each type of disaster are identified.

[0008] Preferably, the basic analysis of the characteristic data is performed to identify the overall structure of each disaster data and the basic relationship between each variable, specifically including: a preliminary description of the statistical summary and distribution pattern of the characteristic data to obtain the distribution, relationship and trend of each data, the statistical summary is one or more of the mean, median, mode, variance and standard deviation; exploratory analysis is performed on the data after the preliminary description, the exploratory analysis includes: cluster analysis to identify the natural grouping or pattern of the data; correlation analysis to identify the degree and direction of correlation between variables; regression analysis to obtain the dependency relationship between variables and predict the value of the dependent variable; mining analysis is performed on the data after exploratory analysis, the mining analysis includes: classification processing to divide the data into different categories or groups; association rule mining to find the association and relationship between data items; prediction processing to predict future trends or results based on historical data; and collating and analyzing the results of the exploratory analysis and the mining analysis to identify the overall structure of each disaster data and the basic relationship between each variable.

[0009] Preferably, the correlation analysis is performed on the disaster data that have undergone basic analysis to calculate the correlation degree and correlation direction between various disasters, specifically including: establishing a grey correlation analysis model based on the disaster data that have undergone basic analysis; taking the most representative disaster type or indicator as a reference sequence, and taking other disaster types or indicators as a comparison sequence, and using the grey correlation analysis model to calculate and output the correlation degree between the reference sequence and the comparison sequence; and analyzing and identifying the correlation degree and correlation direction between different disasters based on the calculated correlation degree.

[0010] Preferably, the method further comprises: identifying potential factors that may lead to disasters based on correlation analysis, and analyzing the manner and extent of the impact of potential factors on various disasters, specifically including: identifying potential factors that may lead to disasters based on correlation analysis; establishing a causal model using statistical methods to analyze the degree and direction of the impact of potential factors on various disasters and the interactions and relationships between different potential factors; obtaining the manner and extent of the impact of different potential factors on various disasters based on the analysis results of the causal model, and identifying the main disaster-causing factors and risk points by comparing the importance of different potential factors.

[0011] According to a second aspect of the present application, a mine disaster monitoring and early warning device is provided, comprising a module for implementing the mine disaster monitoring and early warning method as described above.

[0012] According to a third aspect of the present application, a mine disaster control system is provided, comprising: Monitoring and early warning device: It is the mine disaster monitoring and early warning device mentioned above, which is used to monitor the index data of various mine disasters, output disaster prediction results, correlation analysis results between disasters and disaster solution recommendation results; Alarm unit: used to issue an alarm based on the disaster prediction results output by the monitoring and early warning device; Control unit: used to control the corresponding equipment to act according to the correlation analysis results between disasters and the disaster solution suggestion results output by the monitoring and early warning device; Main control unit: used to receive the output results of the monitoring and early warning device, send corresponding alarm commands to the alarm unit according to the disaster prediction results, identify and analyze the correlation analysis results between disasters and the recommended results of disaster solutions, and send action control commands to the corresponding equipment according to the identification and analysis results.

[0013] According to a fourth aspect of the present application, a mine disaster monitoring and early warning device is provided, comprising: Memory; Processor; and Computer programs; Wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement the mine disaster monitoring and early warning method as described above.

[0014] According to a fifth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored; the computer program is executed by a processor to implement the mine disaster monitoring and early warning method as described above.

[0015] The mine disaster monitoring and early warning method provided in this application comprehensively considers the various influencing factors of mine disasters and the correlation between disasters, and adopts innovative algorithms and technologies to construct data models. It can not only deeply explore the correlation between mine disasters on the basis of a single disaster warning, but also provide effective solution suggestions for different disaster situations, thereby improving the accuracy of disaster warning, risk assessment and control management, overcoming the limitations of existing technical solutions for studying a single disaster type, and realizing comprehensive monitoring, early warning and control of mine disasters; this application will also output the predicted results, correlation analysis results and solution recommendation results of the mine disasters obtained by analysis in a visual form, so that mine managers can intuitively understand the probability of disaster occurrence and the distribution of disaster risks, thereby improving decision-making efficiency and accuracy.

[0016] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the contents indicated in the written description and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A schematic diagram of the structure of the mine disaster control system provided for this application; In the figure, 10 is a monitoring and early warning device, 20 is an alarm unit, 30 is a control unit, and 40 is a main control unit. DETAILED DESCRIPTION

[0018] In order to make the technical solutions and advantages in the embodiments of the present application more clearly understood, the exemplary embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than an exhaustive list of all the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0019] In view of some problems existing in the prior art: In the first aspect, a method for monitoring and early warning of mine disasters is provided in the embodiments of the present application. The method can be performed by a mine disaster monitoring and early warning device, or by a component configured inside the mine disaster monitoring and early warning device, such as a chip, a chip system, etc., or by a logic module or software having some or all of the functions of a mine disaster monitoring and early warning device. The present application does not limit this.

[0020] Exemplarily, the mine disaster monitoring and early warning method includes: collecting mine disaster monitoring data, the disaster monitoring data includes: disaster type, real-time monitoring values ​​of various indicators of disaster occurrence, the various indicators are one or more of geological data, production data and environmental data; specifically, the geological data can be information such as surface coverage, vegetation changes, geological structure, strata, rock type, mineral distribution, etc. of the mining area. In actual implementation: remote sensing technology (such as satellite remote sensing, drone remote sensing, etc.) can be used to obtain information such as surface coverage and vegetation changes of the mining area, and measuring instruments (such as total stations, GPS, laser scanners, etc.) can be used to measure the topography and locate the ore body in the mining area, and geological samples can be collected and laboratory analysis can be used to obtain data such as the chemical composition and physical properties of the ore; production data can be set Equipment data, ore data, activity data, etc., among which equipment data can be information such as the operating status, production efficiency, and fault conditions of mining equipment; ore data can be information such as the mining volume, grade, transportation, and storage of ore; activity data can be information such as safety, environmental protection, and personnel operation during the mining process. In actual implementation: Internet of Things technology can be used to monitor the equipment operating status, production activities, and other information of the mine in real time; environmental data can be surrounding environment data, emission data, and assessment data, among which surrounding environment data can be information such as air quality, water quality, and soil pollution around the mine; emission data can be information such as the emission volume, waste composition, and waste treatment conditions of waste (such as wastewater, waste gas, and waste residue) of the mine during production activities; and assessment data can be the impact of mining activities on the ecological environment and residents' health; Preprocess the collected disaster monitoring data, and match the corresponding optimal correlation prediction and analysis model according to the current task goal; specifically, the current task goal can be directly obtained by receiving a specified command input from the outside, or can be inferred and obtained according to the characteristics of the collected disaster monitoring data; that is, the system can infer the most likely current task goal according to the characteristics of the collected disaster monitoring data; The pre-processed disaster monitoring data is extracted for features and then input into the corresponding optimal correlation prediction and analysis model to perform disaster prediction and correlation analysis between disasters; Obtain the disaster prediction results, disaster correlation analysis results and disaster solution recommendation results output by the optimal correlation prediction analysis model, and perform visual output.

[0021] Based on the above scheme, this application comprehensively considers the various influencing factors of mine disasters and the correlation between disasters, and can also give effective solution suggestions for different disaster situations, overcoming the limitations of existing technical solutions on the study of a single disaster type, and realizing comprehensive monitoring, early warning and control of mine disasters; and equipped with appropriate optimal data models for different task objectives, improving the accuracy of disaster early warning, risk assessment and control management; in addition, by visually outputting the predicted results, correlation analysis results and solution recommendations of mine disasters obtained by analysis, mine managers can intuitively understand the probability of disaster occurrence and the distribution of disaster risks, thereby improving decision-making efficiency and accuracy. This application has strong practicality and can be widely used in various mining production scenarios to provide strong support for mine safety production.

[0022] In some possible implementations of the first aspect, the mine disaster monitoring and early warning method further includes: constructing an optimal correlation prediction and analysis model corresponding to different task objectives; The construction of the optimal correlation prediction analysis model specifically includes: Collect various types of disaster training data of the mine, the disaster training data includes: the types of disasters that have occurred, the corresponding index values ​​when the disaster occurred, the changing trends of the index values ​​during the disaster, the index values ​​after the disaster occurred and the related treatment plans; the related treatment plans include: personnel operation records, system operation records and related data changes after the operation processing; Preprocess the collected various disaster training data, and divide the preprocessed training data into training set, validation set and test set; Through the pre-processed training data, the causal mechanisms and influencing factors of various types of disasters are analyzed, the similarities and differences between different types of disasters are identified, and a set of possible related factors is formed; After feature extraction of the training set and the possible correlation factor set, the training set is input into multiple alternative correlation prediction analysis models to analyze and train the conditions for disaster occurrence, the potential correlation and influencing factors between disasters, and the solutions after the disaster occurs; During the training process, the validation set is used to iteratively optimize and adjust each backup correlation prediction analysis model, and the impact of the input features on the model performance is evaluated based on the validation results to obtain the feature importance evaluation results; After the training, the test set is used to conduct a final evaluation of the optimized alternative correlation prediction analysis models, and based on the verification results and feature importance evaluation results, the optimal correlation prediction analysis model corresponding to different task objectives is obtained.

[0023] In this embodiment, the training set is used to train the model, the validation set is used to adjust the model parameters, and the test set is used to evaluate the performance of the model. Before formal training, a preliminary analysis of the correlation between various types of disasters is performed through the training data to form a set of possible correlation factors. The possible correlation factor set and the training data are then input into the model together for formal training. In this way, the training efficiency of the model and the accuracy of the results can be improved to a certain extent.

[0024] Optionally, after extracting features from the training set and the possible correlation factor set and inputting them into a plurality of standby correlation prediction analysis models, the following steps are performed: Conduct basic analysis on characteristic data to identify the overall structure of each disaster data and the basic relationship between each variable; Conduct correlation analysis on the disaster data that have undergone basic analysis to calculate the correlation degree and correlation direction between various disasters; Based on the correlation analysis, identify the potential factors that may lead to disasters, and analyze the impact of potential factors on various disasters. Analyze the relevant treatment plans after the disaster occurs and the relevant data changes after the treatment, and identify the control and elimination effects of various treatment methods on various disasters.

[0025] Further optionally, the basic analysis of the characteristic data to identify the overall structure of each disaster data and the basic relationship between each variable specifically includes: A preliminary description of the statistical summary and distribution form of the characteristic data is made to obtain the distribution, relationship and trend of each data. The statistical summary is one or more of the mean, median, mode, variance and standard deviation. Specifically, the statistical summary can be calculated using descriptive statistics methods, and the distribution form can be displayed using visualization tools (such as histograms, box plots, scatter plots, etc.); An exploratory analysis was conducted on the data that had been preliminarily described, and the exploratory analysis included: Cluster analysis, identifying natural groupings or patterns in data; Correlation analysis, identifying the degree and direction of correlation between variables; Regression analysis, to obtain the dependency between variables and predict the value of the dependent variable; The exploratory analysis described above is mainly used to conduct in-depth exploration of patterns and trends in the data.

[0026] Performing mining analysis on the data after exploratory analysis, the mining analysis includes: Categorical processing, dividing data into different categories or groups for better understanding and processing; Association rule mining, finding the associations and relationships between data items; Predictive processing, predicting future trends or outcomes based on historical data; The results of exploratory analysis and mining analysis are collated and analyzed to identify the overall structure of each disaster data and the basic relationship between each variable.

[0027] Further optionally, the above-mentioned performing correlation analysis on the disaster data after the basic analysis to calculate the correlation degree and correlation direction between the various disasters specifically includes: Based on the disaster data that have undergone basic analysis, a grey correlation analysis model is established; the grey correlation analysis model is particularly suitable for situations where the amount of data is small or the data regularity is not strong, and it can reveal the strength of the relationship between factors; The most representative disaster type or index is used as the reference sequence, and other disaster types or indexes are used as the comparison sequence. The grey correlation analysis model is used to calculate and output the correlation between the reference sequence and the comparison sequence. Based on the calculated correlation, the degree and direction of correlation between different disasters are analyzed and identified; the higher the correlation, the stronger the potential correlation between the two disasters. By comparing the correlation between different disasters, the main correlation patterns and trends between different disasters can be identified.

[0028] Further optionally, based on the correlation analysis, potential factors that may lead to disasters are identified, and the impact of potential factors on various disasters is analyzed in terms of their impact and extent, specifically including: Based on the correlation analysis, potential factors that may lead to disasters are identified, which may be one or more of geological conditions, mining activities, environmental factors (such as rainfall, earthquakes, etc.) and human factors (such as poor management, operational errors, etc.); Use statistical methods (such as regression analysis, causal network analysis, etc.) to establish causal models to analyze the degree and direction of the impact of potential factors on various disasters, as well as the interactions and relationships between different potential factors; Based on the analysis results of the causal model, the way and degree of influence of different potential factors on various disasters are obtained, and by comparing the importance of different potential factors, the main disaster-causing factors and risk points are identified.

[0029] Based on the above scheme, this application adopts innovative algorithms and technologies, and constructs the optimal correlation prediction and analysis model corresponding to different task objectives according to data characteristics and different task objectives. It can deeply explore the correlation between mining disasters on the basis of a single disaster warning, and further improve the accuracy of disaster warning, risk assessment and control management.

[0030] In some possible implementations of the first aspect, preprocessing the collected data (including disaster monitoring data and various disaster training data) specifically includes: Perform format conversion and standardization on the collected data; format conversion mainly converts data into a unified format and type preset by the system to suit system analysis, such as converting text data into numerical data; standardization is mainly to eliminate format and unit differences between data from different sources, as well as the impact of different dimensions and units on data analysis; Identify and process missing values, duplicate values, and outliers in the data; missing values ​​can be processed by deletion, replacement (such as using mean, median, mode, etc.) or interpolation (such as regression interpolation, multiple interpolation, etc.); duplicate values ​​can be directly deleted to remove data fields or records that are not related to the analysis target to reduce data redundancy; Integrate data from different sources into a unified data set.

[0031] In the practical application of this application, the identification and processing of outliers are particularly important for the quality and reliability of data. Therefore: Optionally, one or more of the following methods are used to identify outliers in the data: Calculate the mean of the data set, and then calculate the number of standard deviations between each data point and the mean; Determine whether the standard deviation of each data point exceeds the threshold. If so, identify the data point as an outlier. Usually, data points with a standard deviation exceeding 3 are considered outliers. Or calculate the statistical value based on the premise that the data set conforms to the normal distribution; When the statistical value of a data point is greater than the statistical value of other data points, it is determined whether the difference exceeds the threshold. If so, the data point is identified as an outlier. If the statistical value of a data point is significantly greater than that of other data points, the data point is considered an outlier. Or draw a box plot based on the data set, which shows the minimum, maximum, median, first quartile and third quartile of the data set; Determine whether the position of each data point in the box plot exceeds 1.5 times the interquartile range (IQR). If so, identify the data point as an outlier; Or draw a scatter plot based on the data set; Find the data point that is significantly different from other data points and identify it as an outlier; Or use the Isolation Forest algorithm or the One-Class SVM algorithm to detect outliers; the Isolation Forest algorithm determines whether a data point is an outlier based on the density of the data, and the One-Class SVM algorithm determines whether a data point is an outlier based on the distance of the data.

[0032] Optionally, after an outlier is identified, in order to determine whether it is a true outlier or an erroneous value caused by some reason (such as data entry error, equipment failure, etc.), the identified outlier needs to be verified. The verification method may adopt one or more of the following methods: Access the original data source and read the original data corresponding to the outliers; Compare outliers with the original data to confirm whether the outliers are caused by data entry errors or equipment failures; Or start the abnormal value judgment logic to judge whether the abnormal value is reasonable. If so, it is determined to be a pseudo abnormal value, and the pseudo abnormal value is marked as a normal value, and the subsequent processing continues. Otherwise, it is determined to be a real abnormal value; Or receive feedback information from external input to determine whether the outlier is reasonable. If so, it is determined to be a true outlier. Otherwise, it is determined to be a false outlier, a warning message is output, and the outlier is stored in the database to be revised for subsequent processing; external input feedback information is generally the judgment feedback made by relevant personnel based on experience or common sense. For example, in sales data, an abnormally high sales volume may be a true outlier or it may be caused by a large order.

[0033] Optionally, after checking the outliers, one or more of the following methods are used to process the real outliers: Count the number of outliers and analyze their importance. If the number of outliers is within the threshold and the outliers have little impact on the overall data analysis, delete the outliers directly. Or directly replace outliers with appropriate values ​​(such as median, mean, etc.); Or treat outliers as missing values ​​and use missing value processing methods (such as interpolation, deletion, etc.) to handle them; The information contained in the outliers is analyzed. If the outliers contain important information, the outliers are retained and marked so that they can be considered in subsequent analysis.

[0034] In a second aspect, an embodiment of the present application provides a mine disaster monitoring and early warning device, including a module for implementing the mine disaster monitoring and early warning method as described above.

[0035] Exemplarily, the mine disaster monitoring and early warning device includes: The first acquisition module is used to collect disaster monitoring data of the mine, wherein the disaster monitoring data includes: the type of disaster, the real-time monitoring values ​​of various indicators of the disaster, and the various indicators are one or more of geological data, production data and environmental data; The first preprocessing module is used to preprocess the collected disaster monitoring data and match the corresponding optimal correlation prediction and analysis model according to the current task objectives; Correlation analysis module: used to extract features from the pre-processed disaster monitoring data and input them into the corresponding optimal correlation prediction analysis model to predict disasters and analyze the correlation between disasters; Result acquisition module: used to obtain the disaster prediction results, disaster correlation analysis results and disaster solution recommendation results output by the optimal correlation prediction analysis model, and perform visual output.

[0036] In some possible implementations of the second aspect, the mine disaster monitoring and early warning device further includes: a model building module; The model building module includes: The second acquisition module is used to collect various disaster training data of the mine, and the disaster training data includes: the types of disasters that have occurred, the corresponding index values ​​when the disaster occurs, the change trend of the index values ​​during the disaster, the index values ​​after the disaster occurs and the relevant processing schemes; wherein the relevant processing schemes include: personnel operation records, system operation records and the relevant data changes after the operation processing; The second preprocessing module is used to preprocess the collected various disaster training data; Dataset partitioning module: used to divide the preprocessed training data into training set, validation set and test set; Preliminary analysis module of related factors: used to analyze the causes and influencing factors of various disasters through pre-processed training data, identify the similarities and differences between different types of disasters, and form a set of possible related factors; Correlation analysis training module: used to extract features from the training set and possible correlation factor set and then input them into multiple backup correlation prediction analysis models to analyze and train the conditions for disaster occurrence, potential correlations and influencing factors between disasters, and solutions after disasters occur; Model optimization module: used to iteratively optimize and adjust each backup correlation prediction analysis model using the validation set during the training process, and evaluate the impact of input features on model performance based on the validation results to obtain feature importance evaluation results; Optimal model establishment module: After the training is completed, the test set is used to conduct a final evaluation of the optimized alternative correlation prediction analysis models, and based on the verification results and feature importance evaluation results, the optimal correlation prediction analysis model corresponding to different task objectives is obtained.

[0037] Optionally, the relevance analysis training module includes: Data exploration module: used to conduct basic analysis of characteristic data and identify the overall structure of each disaster data and the basic relationship between each variable; Correlation analysis module: used to conduct correlation analysis on various disaster data that have undergone basic analysis, and calculate the correlation degree and correlation direction between various disasters; Potential Factor Analysis Module: It is used to identify potential factors that may lead to disasters based on correlation analysis, and analyze the impact of potential factors on various disasters. Solution analysis module: used to analyze the relevant treatment plans after the disaster occurs and the relevant data changes after the treatment, and identify the control and elimination effects of various treatment methods on various disasters.

[0038] Further optionally, the data exploration module includes: Preliminary description module: used to make a preliminary description of the statistical summary and distribution form of the feature data to obtain the distribution, relationship and trend of each data. The statistical summary is one or more of the mean, median, mode, variance and standard deviation; Exploratory analysis module: used to conduct exploratory analysis on data that has been preliminarily described; Mining analysis module: used to perform mining analysis on data that has undergone exploratory analysis; Result analysis module: used to organize and analyze the results of exploratory analysis and mining analysis, and identify the overall structure of each disaster data and the basic relationship between each variable; Specifically: The exploratory analysis module includes: Cluster analysis module: used to perform cluster analysis on the data that has been initially described and identify natural groups or patterns of the data; Correlation analysis module: used to perform correlation analysis on the data that have been preliminarily described, and identify the degree and direction of correlation between variables; Regression analysis module: used to perform regression analysis on the data that has been preliminarily described, obtain the dependency relationship between variables, and predict the value of the dependent variable; The excavation analysis module includes: Classification module: used to classify the data after exploratory analysis and divide the data into different categories or groups; Association rule mining module: used to perform association rule mining on data that has undergone exploratory analysis, and find out the associations and relationships between data items; Prediction module: used to perform predictive processing on data that has undergone exploratory analysis and predict future trends or results based on historical data.

[0039] Further optionally, the association analysis module includes: Grey correlation analysis model building module: used to build a grey correlation analysis model based on various disaster data that have undergone basic analysis; Correlation calculation module: used to take the most representative disaster type or indicator as the reference sequence, take other disaster types or indicators as the comparison sequence, and use the grey correlation analysis model to calculate and output the correlation between the reference sequence and the comparison sequence; Correlation degree establishment module: used to analyze and identify the correlation degree and correlation direction between different disasters based on the calculated correlation degree.

[0040] Further optionally, the potential factor analysis module includes: Potential Factor Identification Module: used to identify potential factors that may lead to disasters based on correlation analysis; Causal model building module: used to build causal models using statistical methods to analyze the degree and direction of the impact of potential factors on various disasters, as well as the interactions and relationships between different potential factors; Disaster-causing factors determination module: used to obtain the impact mode and degree of different potential factors on various disasters based on the analysis results of the causal model, and identify the main disaster-causing factors and risk points by comparing the importance of different potential factors.

[0041] In a third aspect, the present application provides a mine disaster control system, such as Figure 1 As shown, the mine disaster control system includes: Monitoring and early warning device 10: is the aforementioned mine disaster monitoring and early warning device, used to monitor the index data of various mine disasters, and output disaster prediction results, correlation analysis results between disasters, and disaster solution recommendation results; Alarm unit 20: used to issue an alarm according to the disaster prediction result output by the monitoring and early warning device 10; Control unit 30: used to control corresponding devices to perform actions according to the disaster correlation analysis results and disaster solution suggestion results output by the monitoring and early warning device 10; Main control unit 40: used to receive the output results of the monitoring and early warning device 10, send corresponding alarm commands to the alarm unit 20 according to the disaster prediction results, identify and analyze the correlation analysis results between disasters and the disaster solution recommendation results, and send action control commands to corresponding devices according to the identification and analysis results.

[0042] Fourthly, a mine disaster monitoring and early warning device is provided in an embodiment of the present application. The mine disaster monitoring and early warning device can be any device that can realize the mine disaster monitoring and early warning function. The device can be various terminal devices, such as: desktop computers, laptops, tablet computers, handheld devices, etc., which can be implemented through software and / or hardware.

[0043] Exemplarily, the device comprises: Memory; Processor; and Computer programs; Wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement the mine disaster monitoring and early warning method as described above.

[0044] In a fifth aspect, a computer-readable storage medium is provided in an embodiment of the present application. The computer-readable storage medium may be: ROM, RAM, a disk or an optical disk, etc.

[0045] Exemplarily, a computer program is stored on the computer-readable storage medium; the computer program is executed by a processor to implement the mine disaster monitoring and early warning method as described above.

[0046] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program codes. The scheme in the embodiments of the present application may be implemented in various computer languages, for example, C language, VHDL language, Verilog language, object-oriented programming language Java, and literal scripting language JavaScript, etc.

[0047] The present application is described with reference to the operation flow of the method, device, system and computer program product according to the embodiment of the present application. It should be understood that each flow can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in the flow description.

[0048] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in the process description.

[0049] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the process description.

[0050] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0051] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0052] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A mine disaster monitoring and early warning method, characterized in that: include: Collecting mine disaster monitoring data, the disaster monitoring data includes: disaster type, real-time monitoring values ​​of various indicators of disaster occurrence, the various indicators are one or more of geological data, production data and environmental data; Pre-process the collected disaster monitoring data and match the corresponding optimal correlation prediction and analysis model according to the current mission objectives; The pre-processed disaster monitoring data is extracted for features and then input into the corresponding optimal correlation prediction and analysis model to perform disaster prediction and correlation analysis between disasters; Obtain the disaster prediction results, disaster correlation analysis results and disaster solution recommendation results output by the optimal correlation prediction analysis model, and perform visual output.

2. The mine disaster monitoring and early warning method according to claim 1 is characterized in that: Also includes: Construct the optimal correlation prediction and analysis model corresponding to different task objectives; The construction of the optimal correlation prediction analysis model specifically includes: Collect various types of disaster training data of the mine, the disaster training data includes: the types of disasters that have occurred, the corresponding index values ​​when the disaster occurred, the changing trends of the index values ​​during the disaster, the index values ​​after the disaster occurred and the related treatment plans; the related treatment plans include: personnel operation records, system operation records and related data changes after the operation processing; Preprocess the collected various disaster training data, and divide the preprocessed training data into training set, validation set and test set; Through the pre-processed training data, the causal mechanisms and influencing factors of various types of disasters are analyzed, the similarities and differences between different types of disasters are identified, and a set of possible related factors is formed; After feature extraction of the training set and the possible correlation factor set, the training set is input into multiple alternative correlation prediction analysis models to analyze and train the conditions for disaster occurrence, the potential correlation and influencing factors between disasters, and the solutions after the disaster occurs; During the training process, the validation set is used to iteratively optimize and adjust each backup correlation prediction analysis model, and the impact of the input features on the model performance is evaluated based on the validation results to obtain the feature importance evaluation results; After the training, the test set is used to conduct a final evaluation of the optimized alternative correlation prediction analysis models, and based on the verification results and feature importance evaluation results, the optimal correlation prediction analysis model corresponding to different task objectives is obtained.

3. The mine disaster monitoring and early warning method according to claim 2 is characterized in that: After extracting features from the training set and the possible correlation factor set and inputting them into multiple alternative correlation prediction analysis models, perform the following steps: Conduct basic analysis on characteristic data to identify the overall structure of each disaster data and the basic relationship between each variable; Conduct correlation analysis on the disaster data that have undergone basic analysis to calculate the correlation degree and correlation direction between various disasters; Based on the correlation analysis, identify the potential factors that may lead to disasters, and analyze the impact of potential factors on various disasters. Analyze the relevant treatment plans after the disaster occurs and the relevant data changes after the treatment, and identify the control and elimination effects of various treatment methods on various disasters.

4. The mine disaster monitoring and early warning method according to claim 3 is characterized in that: The basic analysis of the characteristic data is to identify the overall structure of each disaster data and the basic relationship between each variable, including: A preliminary description of the statistical summary and distribution form of the characteristic data is made to obtain the distribution, relationship and trend of each data, wherein the statistical summary is one or more of the mean, median, mode, variance and standard deviation; An exploratory analysis was conducted on the data that had been preliminarily described, and the exploratory analysis included: Cluster analysis, identifying natural groupings or patterns in data; Correlation analysis, identifying the degree and direction of correlation between variables; Regression analysis, to obtain the dependency between variables and predict the value of the dependent variable; Performing mining analysis on the data after exploratory analysis, the mining analysis includes: Categorical processing, dividing data into different categories or groups; Association rule mining, finding the associations and relationships between data items; Predictive processing, predicting future trends or outcomes based on historical data; The results of exploratory analysis and mining analysis are collated and analyzed to identify the overall structure of each disaster data and the basic relationship between each variable.

5. The mine disaster monitoring and early warning method according to claim 3 is characterized in that: The above-mentioned correlation analysis is performed on the disaster data after basic analysis to calculate the correlation degree and correlation direction between various disasters, specifically including: Based on the disaster data that have undergone basic analysis, a grey correlation analysis model is established; The most representative disaster type or index is used as the reference sequence, and other disaster types or indexes are used as the comparison sequence. The grey correlation analysis model is used to calculate and output the correlation between the reference sequence and the comparison sequence. Based on the calculated correlation, the correlation degree and direction between different disasters are analyzed and identified.

6. The mine disaster monitoring and early warning method according to claim 3 is characterized in that: Based on the correlation analysis, the potential factors that may lead to disasters are identified, and the impact of potential factors on various disasters is analyzed, including: Based on correlation analysis, identify potential factors that may lead to disasters; Use statistical methods to establish causal models to analyze the degree and direction of the impact of potential factors on various disasters, as well as the interactions and relationships between different potential factors; Based on the analysis results of the causal model, the way and degree of influence of different potential factors on various disasters are obtained, and by comparing the importance of different potential factors, the main disaster-causing factors and risk points are identified.

7. A mine disaster monitoring and early warning device, characterized in that: It comprises a module for implementing the mine disaster monitoring and early warning method according to any one of claims 1 to 6.

8. A mine disaster control system, characterized in that: include: Monitoring and early warning device (10): the mine disaster monitoring and early warning device according to claim 7, used to monitor the index data of various mine disasters, and output disaster prediction results, correlation analysis results between disasters, and disaster solution recommendation results; Alarm unit (20): used to generate an alarm according to the disaster prediction result output by the monitoring and early warning device (10); A control unit (30): used to control corresponding equipment to perform actions according to the disaster correlation analysis results and disaster solution suggestion results output by the monitoring and early warning device (10); A main control unit (40) is used to receive the output results of the monitoring and early warning device (10), send a corresponding alarm command to the alarm unit (20) according to the disaster prediction results, identify and analyze the correlation analysis results between disasters and the disaster solution suggestion results, and send an action control command to the corresponding device according to the identification and analysis results.

9. A mine disaster monitoring and early warning device, characterized in that: include: Memory; processor; as well as Computer programs; Wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement the mine disaster monitoring and early warning method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon; the computer program is executed by a processor to implement the mine disaster monitoring and early warning method as described in any one of claims 1 to 6.

Images