Monitoring and early warning system fused coal mine disaster evolution risk analysis method

Abstract

The invention relates to a monitoring and early warning system fused coal mine disaster evolution risk analysis method, and belongs to the technical field of coal mine safety production. The problems that in the prior art, data are not fused due to the information islanding effect, the abnormal severity and the development speed cannot be evaluated due to the single analysis dimension, and continuous tracking is not achieved after closed-loop management measures are lacked are solved. The method comprises the following steps: establishing a multi-system data collaboration mechanism to synchronously acquire structured and unstructured data of a mine disaster monitoring and early warning system; fusing the data to construct a multi-dimensional early warning index system and model containing an abnormal strength dimension, a space-time dimension and an evolution trend dimension; carrying out risk situation iterative calculation by adopting a sliding time window algorithm and outputting early warning information; and early warning information is displayed and adaptively pushed in multiple modes. Monitoring and early warning information is deeply fused for the first time, the disaster abnormal state and development trend are deeply analyzed, potential disaster evolution paths are found in advance, and disaster accidents are avoided.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of coal mine safety production, and particularly relates to a method for dynamically analyzing coal mine disaster evolution risk by fusing information of a monitoring system and an early warning system. BACKGROUND

[0002] In the process of coal mine production, gas, roof, water, fire, and rock burst are the main disasters that have existed for a long time and seriously threaten the safety of personnel life and property. With the increasingly strict requirements for safety production in the industry and the continuous advancement of coal mine intelligentization construction, most modernized mines have been equipped with monitoring systems and early warning systems for these main disasters.

[0003] These existing systems can guarantee the safety production of coal mines to a certain extent, and their main function is to monitor various parameters related to disasters (such as gas concentration, roof separation displacement, hydrological data, etc.) in real time, and trigger an alarm when the parameters exceed the preset threshold, or give a warning signal according to simple trend changes. However, the limitations of the existing technology are also very obvious:

[0004] Information island effect: the monitoring system and the early warning system often run independently, and the data cannot be effectively fused. The monitoring system provides raw data, and the early warning system makes judgments based on a simple model, and there is a lack of deep data interaction and correlation analysis between the two.

[0005] Single analysis dimension: the system is mostly "static" over-limit alarm, and cannot comprehensively evaluate the severity, development speed, spatio-temporal evolution law of the anomaly, and the coupling effect of multi-source anomaly information. For example, the system cannot distinguish the essential difference between a slow, continuous low-intensity anomaly and a sudden, rapidly intensifying high-intensity anomaly in risk evolution.

[0006] Lack of closed-loop management: after the alarm or warning occurs, the existing technology lacks a mechanism for continuously tracking and verifying whether the disposal measures are effective and the risk is truly eliminated. This leads to the risk continuing to evolve even after measures are taken, ultimately resulting in accidents.

[0007] Therefore, there is an urgent need in the industry for a method that can deeply fuse monitoring and early warning information, comprehensively analyze and warn the disaster evolution risk from a multi-dimensional and dynamic perspective, to make up for the shortcomings of the existing technology and truly support the realization of the coal mine "zero accident" safety goal. SUMMARY

[0008] In view of this, the purpose of the present application is to provide a coal mine disaster evolution risk analysis method of monitoring and early warning system fusion. The method mainly fuses the information of coal mine disaster monitoring system and early warning system, comprehensively considers the multi-dimensional factors of abnormal intensity dimension, space-time dimension and evolution trend dimension, and carries out comprehensive early warning of coal mine disaster evolution risk from the aspects of abnormal deviation intensity degree and change dynamic of disaster monitoring data and disaster early warning result, abnormal change gradient, abnormal spatial correlation degree, abnormal time intensity, abnormal situation processing result, etc. The method firstly establishes a multi-system data cooperation mechanism, synchronously collects the data of mine disaster monitoring and early warning system; secondly, fuses the information of disaster monitoring and early warning system, constructs a multi-dimensional early warning index system and model containing intensity dimension, space-time dimension and evolution trend dimension, and realizes the dynamic fusion of monitoring data and early warning signal; then, the sliding time window algorithm is used for risk situation iterative calculation, and early warning information is given; finally, the early warning information is intuitively displayed and adaptively pushed in multiple ways and multiple channels. Compared with the prior art, the method firstly fuses the disaster monitoring and early warning information, and embeds the time series prediction into the risk assessment framework, deeply analyzes the abnormal state and development trend of information, discovers the potential disaster evolution path in advance, avoids the further development of disaster anomaly and the occurrence of disaster accidents, and supports the realization of "zero accident" of safety production.

[0009] In order to achieve the above purpose, the present application provides the following technical scheme:

[0010] A coal mine disaster evolution risk analysis method of monitoring and early warning system fusion, comprising the following steps:

[0011] S1: a multi-system data cooperation mechanism is established, and the structured data and unstructured data of the disaster monitoring system and the disaster early warning system of the mine are synchronously collected.

[0012] S2: the data of the disaster monitoring system and the disaster early warning system are fused, and a disaster evolution risk multi-dimensional early warning index system and model containing abnormal intensity dimension, space-time dimension and evolution trend dimension are constructed.

[0013] S3: a sliding time window algorithm is used, the disaster evolution risk multi-dimensional early warning index system and model are used for risk situation iterative calculation, and early warning information is output.

[0014] S4: the early warning information is displayed and adaptively pushed in multiple ways and multiple channels through at least one of the underground perception terminal, the broadcast system, the personnel positioning system and the visual board.

[0015] Further, in the S1, the synchronously collected data further includes mine personnel positioning system information, broadcast system information and transparent geological system information; the data of the disaster monitoring system and the disaster early warning system includes monitoring sensor data of the disaster, abnormal threshold data, early warning result information and reasons, early warning processing measures and energy efficiency information.

[0016] Further, in the S2, the constructed disaster evolution risk multi-dimensional early warning index system covers abnormal intensity dimension, time and space dimension and evolution trend dimension of disaster monitoring and early warning, and includes the following five types of indexes:

[0017] Basic abnormal deviation intensity index;

[0018] Dynamic change characteristic index;

[0019] Time and space correlation index;

[0020] Coupling analysis index of monitoring and early warning information interaction coupling;

[0021] Disposal efficiency index.

[0022] Further, the basic abnormal deviation intensity index includes disaster monitoring abnormal deviation intensity and disaster early warning abnormal deviation intensity;

[0023] The dynamic change characteristic index includes disaster monitoring deviation change trend, disaster monitoring deviation change gradient, disaster early warning deviation change trend and disaster early warning deviation change gradient;

[0024] The time and space correlation index includes disaster abnormal spatial correlation degree and disaster abnormal time intensity;

[0025] The coupling analysis index includes comprehensive abnormal deviation intensity and comprehensive abnormal change trend;

[0026] The disposal efficiency index includes abnormal measure processing situation and deviation intensity improvement effect after processing.

[0027] Further, in the S2, the constructed model is an analysis model based on index quantification and dynamic change characteristics, and the construction process includes:

[0028] The abnormal deviation intensity of the monitoring data and the early warning result is quantified by using the benchmark comparison method and the rate calculation;

[0029] The change trajectory of the abnormal deviation intensity is tracked, and the characteristic analysis of the deviation intensity change trend, change gradient, time and space correlation degree and abnormal time intensity is performed in combination with the space and time relationship;

[0030] The "index-risk" mapping mechanism is established, the single-index threshold judgment and multi-index weighted fusion form an expert knowledge base, and the general, heavier and serious three-level risk early warning is output.

[0031] Further, the comprehensive abnormal deviation intensity and the comprehensive abnormal change trend in the coupling analysis index are obtained by the Bayesian network method, real-time integration of the correlation of monitoring and early warning data, and generation of a comprehensive abnormal evaluation model through adaptive weight learning.

[0032] Further, the expert knowledge base is determined according to the preset disaster monitoring abnormal deviation intensity value, disaster early warning abnormal deviation intensity value, abnormal time intensity, comprehensive abnormal deviation intensity, disaster monitoring deviation change trend, disaster early warning deviation change trend, disaster monitoring deviation change gradient or disaster early warning deviation change gradient. Single or combined threshold to determine the disaster evolution risk as general, heavier or serious grade.

[0033] Further, the display and adaptive push of the early warning information in S4 includes the following three levels:

[0034] Display layer: interactive and intuitive display of early warning information through mobile and web situational awareness terminals, or panel positioning display on the mine map;

[0035] Release layer: connecting individual equipment, personnel positioning system and emergency broadcast system, according to the disaster evolution risk warning level, intelligently adjusting the information radiation range and response priority;

[0036] Control layer: interface with integrated control platform or comprehensive management and control platform, automatically send corresponding level of danger resolution measures, and synchronously generate emergency response digital archives.

[0037] Further, the release layer also includes real-time tracking information touch rate, touch time and confirmation delay.

[0038] Further, the control layer also includes recording the complete decision and execution process from early warning to measure implementation.

[0039] The beneficial effects of the present application are that the information of the disaster monitoring system and the early warning system of the coal mine is deeply fused for the first time, and a multi-dimensional risk analysis framework containing abnormal intensity, space-time dimension and evolution trend is innovatively constructed. By establishing an expert knowledge base of 'index-risk' mapping, the method can dynamically track the deviation intensity, change gradient, space-time correlation and disposal effect of disaster anomalies, deeply analyze the disaster anomaly state and development trend, so as to discover the potential disaster evolution path in advance. This not only makes up for the short board of the insufficient analysis ability of the traditional early warning system, but also verifies the effectiveness of the disposal measures, forms a closed loop of risk management, thereby effectively avoiding the final evolution of disaster anomalies to accidents, and providing strong technical support for realizing the goal of 'zero accident' of coal mine safety production.

[0040] Other advantages, objects, and features of the present application will be apparent to those skilled in the art from the following specification, and it is intended to be covered by the following claims. The objects and other advantages of the present application can be realized and obtained by means of the following specification. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to make the objects, technical solutions and advantages of the present application clearer, the preferred detailed description of the present application will be combined with the drawings to describe the present application, in which:

[0042] Figure 1 A flow chart of a coal mine disaster evolution risk early warning method of a monitoring and early warning system fusion provided by the present application is shown in the figure.

[0043] Figure 2 A multi-dimensional early warning index system structure diagram of a coal mine disaster evolution risk early warning method of a monitoring and early warning system fusion provided by the present application is shown in the figure.

[0044] Figure 3 An expert knowledge base model structure diagram of a coal mine disaster evolution risk early warning method of a monitoring and early warning system fusion provided by the present application is shown in the figure. DETAILED DESCRIPTION

[0045] The embodiments of the present application are described below through specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the disclosure of the present specification. The present application can also be implemented or applied by different specific embodiments, and the details in the specification can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be noted that the diagrams provided in the following examples only illustrate the basic concept of the present application in a schematic manner, and the following examples and features in the examples can be combined with each other without conflict.

[0046] Among them, the drawings are only used for illustrative description, and the representation is only a schematic diagram, not a physical diagram, and cannot be understood as a limitation on the present application; in order to better illustrate the embodiments of the present application, some components of the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product; for those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings can be omitted.

[0047] The same or similar reference numerals in the drawings of the embodiments of the present application correspond to the same or similar components; in the description of the present application, it should be understood that if the orientation or position relationship indicated by the terms "upper", "lower", "left", "right", "front", "back" and the like is based on the orientation or position relationship shown in the drawings, it is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, therefore the terms describing the position relationship in the drawings are only used for illustrative description, and cannot be understood as a limitation on the present application, for those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0048] This embodiment takes the gas disaster prevention of a certain intelligent mine as an example, and details the complete process of a coal mine disaster evolution risk analysis method combining monitoring and early warning systems.

[0049] S1: Establish a multi-system data collaboration mechanism

[0050] Firstly, the present method connects and integrates multiple heterogeneous information systems in the mine by developing a unified data interface and data collection service. This step establishes a multi-system data collaboration mechanism, which can continuously collect data from each system for 24 hours and store them in a unified time series database or relational database, providing a data basis for subsequent analysis.

[0051] In this embodiment, the data sources and specific data contents collected include:

[0052] Disaster monitoring system: mainly refers to the gas monitoring system. The structured data collected includes monitoring sensor data such as gas concentration, wind speed, carbon monoxide concentration of each measuring point, and abnormal threshold data such as alarm threshold, power-off threshold of these parameters.

[0053] Disaster early warning system: mainly refers to gas overrun early warning, outburst danger early warning and other systems. The data collected includes early warning result information output by the early warning system (such as "gas concentration rising trend early warning"), early warning reason (such as "abnormal increase of gas emission at the tunneling working face"), and early warning processing measures taken for the early warning (such as "adjusting ventilation volume", "stopping work and evacuating personnel", etc.) and energy efficiency information after processing (such as whether the gas concentration has fallen).

[0054] Other related systems: In order to conduct more accurate risk assessment and information push, this method also synchronously collects mine personnel positioning system information (acquire personnel position and quantity in dangerous area), emergency broadcasting system information (acquire available broadcasting terminal), and transparent geological system information (acquire working face space position, working face geological structure, and coal seam occurrence background information).

[0055] S2: Construction of multi-dimensional early warning index system and model

[0056] On the basis of obtaining comprehensive data, the core of this method is to construct a scientific and comprehensive disaster evolution risk multi-dimensional early warning index system and analysis model.

[0057] 1. Construction of multi-dimensional early warning index system

[0058] As shown in Figure 2 , the index system starts from multiple dimensions such as abnormal intensity, space-time, and evolution trend, and contains five categories of indexes:

[0059] 1.1 Basic abnormal deviation intensity index: quantifying the static severity of abnormality.

[0060] Disaster monitoring abnormal deviation intensity (CS): for example, the gas concentration of a sensor is 1.2%, and the alarm threshold is 1.0%, then the deviation intensity can be quantified as (1.2-1.0) / 1.0=20%, or divided into different levels according to the multiple.

[0061] Disaster warning abnormal deviation intensity (YS): mapping the qualitative warning levels such as "blue", "yellow", "orange", and "red" output by the warning system into danger indexes (such as 2, 4, 8, 16), to realize quantification.

[0062] 1.2 Dynamic change characteristic index: capturing the development trend and speed of abnormality.

[0063] Disaster monitoring deviation change trend (CQ) and change gradient (CG): through derivation or slope calculation on time series data, it is obtained whether the concentration change is "rising", "falling", or "stable", and the rising or falling rate, and whether the data is "abrupt", "rapid", or "slow".

[0064] Disaster warning deviation change trend (YT) and change gradient (YG): analyzing the change of warning level in a short time, such as from "blue" to "yellow", indicating that the risk is increasing.

[0065] 1.3 Space-time correlation index: analyzing the correlation of abnormality in time and space.

[0066] Disaster anomaly spatial correlation (K): analyze whether multiple monitoring points in adjacent areas or upstream and downstream of the same ventilation system appear abnormal at the same time. High correlation means systematic risk.

[0067] Disaster anomaly time intensity (T): record the duration of abnormal state (such as over-limit). The longer the duration, the higher the risk.

[0068] 1.4 Coupling analysis index: deep integration of monitoring and early warning information.

[0069] Synthetic anomaly deviation intensity (ZS) and synthetic anomaly change trend (ZQ): this is a key innovation of the present application. This step uses the Bayesian Network method, taking the above monitoring data (CS, CQ, CG) and early warning data (YS, YT, YG) as network nodes, training the network structure and conditional probability table through expert experience and historical data, and realizing adaptive weight learning. Finally, the network can output a comprehensive anomaly evaluation value (ZS) and trend (ZQ). This evaluation model integrates the correlation of multi-source data in real time, and is more reliable than a single information source.

[0070] 1.5 Disposal efficiency index: form a closed loop of risk management.

[0071] Abnormal measure processing: record whether measures have been taken for the anomaly.

[0072] Improved effect of deviation intensity after processing: compare the monitoring data before and after the implementation of measures to evaluate whether the measures are effective.

[0073] 2. Establishment of analysis model and expert knowledge base

[0074] As shown in Figure 3 , the core architecture of the analysis model includes three levels:

[0075] Anomaly quantification: adopt benchmark comparison method, convert all indexes into comparable numerical values or grades through multiplication rate calculation.

[0076] Feature analysis: track the time series change trajectory of each index, and perform trend, gradient and spatio-temporal correlation analysis.

[0077] “Index-risk” mapping: establish an expert knowledge base to output general, relatively heavy and severe three-level risk early warning. The judgment rules of the knowledge base are based on single-index threshold and multi-index weighted fusion.

[0078] The following are some rule examples of the expert knowledge base:

[0079] Rule 1 (General Danger): When the "Disaster Monitoring Abnormal Deviation Intensity (CS)" exceeds the first-level threshold C1, or the "Disaster Warning Abnormal Deviation Intensity (YS)" reaches the first-level threshold Y1, it is determined as "General Danger".

[0080] Rule 2 (More Serious Danger): When the "Comprehensive Abnormal Deviation Intensity (ZS)" reaches the first-level threshold Z1; or when "CS" reaches the second-level threshold C2 and "Abnormal Time Intensity (T)" reaches the second-level threshold T2, it is determined as "More Serious Danger".

[0081] Rule 3 (Serious Danger): When "CS" reaches the third-level threshold C3 or "YS" reaches the third-level threshold Y3; or when the "Disaster Monitoring Deviation Change Gradient (CG)" or the "Disaster Warning Deviation Change Gradient (YG)" exceeds the threshold G1 (indicating sharp deterioration); or when the "Comprehensive Abnormal Deviation Intensity (ZS)" reaches the second-level threshold Z2, it is determined as "Serious Danger".

[0082] Rule 4 (Post-Treatment Assessment): After determining "Serious Danger" and taking treatment measures, if the data deviation intensity is still large (such as not reduced to below C1), the risk level is adjusted to "More Serious Danger", indicating that the risk is controlled but not completely eliminated, and needs to be continuously monitored.

[0083] S3: Iterative Calculation of Risk Situation

[0084] This method uses a sliding time window algorithm for iterative calculation of the risk situation. For example, set the time window to 10 minutes and the calculation frequency to 1 minute. The system will obtain all data within the last 10 minutes every minute and recalculate all index values and the final risk level according to the index system and model constructed in S2. This iterative calculation ensures the real-time and dynamic nature of risk analysis.

[0085] S4: Multi-level Display and Push of Warning Information

[0086] When the risk level calculated by S3 is not "normal", the system will trigger multi-mode and multi-channel display and adaptive push of warning information. This process is divided into three levels:

[0087] (1) Display layer:

[0088] On the large screen in the dispatch center and the Web-based situational awareness terminal of the mine leader, display the risk area, level and key indicators in a prominent color (such as yellow, orange and red corresponding to general, more serious and serious).

[0089] On the mobile APP of the underground team leader, synchronously push the warning information and perform panelized positioning display on the mine map to intuitively display the risk point position.

[0090] (2) Release layer:

[0091] The system directly connects the emergency broadcasting system, and automatically broadcasts voice in the dangerous area and the affected range according to the risk level (such as the “serious” level): “Warning! The gas in the excavation face is seriously over-limit, the risk level is serious, all personnel immediately evacuate!”.

[0092] The system connects the personnel positioning system, obtains the personnel list in the dangerous area, and carries out point-to-point vibration and text warning through individual equipment (such as intelligent mine lamp or bracelet).

[0093] This level can intelligently adjust the information radiation range, for example, “heavy” risk only informs the shift captain and the dispatch room, and “serious” risk informs all related personnel and broadcasts throughout the mine.

[0094] At the same time, the system background will track the information reach rate (how many people received the warning), reach time and confirmation delay (the time when the personnel received the information and how long after clicking “received” on the device), to ensure that the early warning is quickly and effectively conveyed.

[0095] (3) Control layer:

[0096] The system interfaces with the mine comprehensive management and control platform, and when it is determined to be “serious danger”, it can automatically send corresponding level of danger resolution measure instructions, such as automatically executing “wind and gas locking” to cut off the power supply of the working face.

[0097] At the same time of the early warning, the system automatically generates an emergency response digital archive, records the complete decision and execution process from the time when the early warning is issued, the push object, the personnel confirmation, to the danger resolution measures executed by the management and control platform, the measure implementation time, and the subsequent risk level changes, to provide a basis for post-analysis and traceability, and form a complete management closed loop.

[0098] In summary, through the complete process of data collection, index modeling, iterative calculation and hierarchical response, the embodiment realizes the deep analysis and accurate early warning of the evolution risk of coal mine disasters, and fully embodies the core idea and all technical solutions of the present application.

[0099] Finally, it should be explained that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit, although the present application 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 application can be modified or replaced by equivalents without departing from the purpose and scope of the technical solutions, which should be covered in the scope of the claims of the present application.

Claims

1. A method for analyzing the evolution risk of coal mine disasters by integrating monitoring and early warning systems, characterized in that: Includes the following steps: S1: Establish a multi-system data collaboration mechanism to simultaneously collect structured and unstructured data from the mine's disaster monitoring and early warning systems; S2: Integrate the data from the disaster monitoring system and the disaster early warning system to construct a multi-dimensional early warning indicator system and model for disaster evolution risk, which includes the dimensions of abnormal intensity, spatiotemporal dimension and evolution trend. S3: Using a sliding time window algorithm, risk situation iterative calculation is performed based on the multi-dimensional early warning indicator system and model of disaster evolution risk, and early warning information is output; S4: The early warning information is displayed and pushed adaptively in multiple ways and through multiple channels using at least one of the following: downhole sensing terminal, broadcasting system, personnel positioning system and visual dashboard.

2. The coal mine disaster evolution risk analysis method integrating monitoring and early warning systems according to claim 1, characterized in that: In S1, the synchronously collected data also includes information from the mine personnel positioning system, broadcasting system, and transparent geological system; the data from the disaster monitoring system and disaster early warning system include disaster monitoring sensor data, abnormal threshold data, early warning result information and causes, early warning handling measures, and energy efficiency information.

3. The coal mine disaster evolution risk analysis method integrating monitoring and early warning systems according to claim 1, characterized in that: In S2, the constructed multi-dimensional early warning indicator system for disaster evolution risk covers the dimensions of abnormal intensity, spatiotemporal dimension, and evolution trend dimension of disaster monitoring and early warning, and includes the following five categories of indicators: Basic abnormal deviation intensity index; Dynamic change characteristic indicators; Spatiotemporal correlation indicators; Coupling analysis indicators of the interaction and coupling effect between monitoring and early warning information; Effectiveness indicators for handling cases.

4. The coal mine disaster evolution risk analysis method integrating monitoring and early warning systems according to claim 3, characterized in that: The basic abnormal deviation intensity index includes the abnormal deviation intensity of disaster monitoring and the abnormal deviation intensity of disaster early warning; The dynamic change characteristic indicators include the trend of disaster monitoring deviation, the gradient of disaster monitoring deviation, the trend of disaster early warning deviation, and the gradient of disaster early warning deviation; The spatiotemporal correlation indicators include the spatial correlation degree of disaster anomalies and the temporal intensity of disaster anomalies; The coupling analysis indicators include the comprehensive anomaly deviation intensity and the comprehensive anomaly change trend; The effectiveness indicators include the handling of abnormal measures and the improvement effect of the deviation intensity after handling.

5. The coal mine disaster evolution risk analysis method integrating monitoring and early warning systems according to claim 1, characterized in that: In step S2, the constructed model is an analytical model based on index quantification and dynamic change characteristics, and its construction process includes: The benchmark comparison method is adopted to quantify the intensity of abnormal deviation and the intensity of abnormal time between the monitoring data and the early warning results through multiplier calculation; Track the trajectory of changes in abnormal deviation intensity, and combine spatial and temporal relationships to conduct characteristic analysis of the trend, gradient, spatiotemporal correlation, and abnormal temporal intensity of deviation intensity; Establish an "indicator-risk" mapping mechanism, and form an expert knowledge base by combining single indicator threshold judgment with multi-indicator weighted fusion to output three levels of risk warning: general, relatively severe, and serious.

6. The coal mine disaster evolution risk analysis method integrating monitoring and early warning systems according to claim 4, characterized in that: The comprehensive anomaly deviation intensity and comprehensive anomaly change trend in the coupling analysis indicators are obtained by integrating the correlation between monitoring and early warning data in real time through the Bass network method, and generating a comprehensive anomaly evaluation model through adaptive weight learning.

7. The coal mine disaster evolution risk analysis method integrating monitoring and early warning systems according to claim 5, characterized in that: The expert knowledge base determines the risk of disaster evolution as general, relatively severe, or serious based on preset thresholds for disaster monitoring abnormal deviation intensity value, disaster early warning abnormal deviation intensity value, abnormal time intensity, comprehensive abnormal deviation intensity, disaster monitoring deviation change trend, disaster early warning deviation change trend, disaster monitoring deviation change gradient, or disaster early warning deviation change gradient.

8. The coal mine disaster evolution risk analysis method integrating monitoring and early warning systems according to claim 1, characterized in that: The display and adaptive push of early warning information in S4 includes the following three levels: Presentation layer: Interactive and intuitive display of early warning information through situational awareness terminals on mobile and web terminals, or panel-based positioning display on the mine map; The dissemination layer connects individual soldier equipment, personnel positioning systems, and emergency broadcasting systems, and intelligently adjusts the information dissemination range and response priority according to the risk warning level of disaster evolution; Control layer: Connects to the integrated control platform or comprehensive management and control platform, automatically sends the corresponding level of emergency response measures, and simultaneously generates emergency response digital files.

9. The coal mine disaster evolution risk analysis method integrating monitoring and early warning systems according to claim 8, characterized in that: The publishing layer also includes real-time tracking of information reach rate, reach time, and confirmation delay.

10. The coal mine disaster evolution risk analysis method integrating monitoring and early warning systems according to claim 8, characterized in that: The control layer also includes recording the complete decision-making and execution process from the issuance of an early warning to the implementation of measures.

Images