A comprehensive detection system for real-time early warning of coal and gas outbursts

Abstract

The present invention relates to the technical field of coal and gas outburst early warning, and discloses a comprehensive detection system for real-time early warning of coal and gas outburst, comprising a data acquisition module, a data processing module, a gas prediction module, an outburst early warning module, and a response module; wherein: the data acquisition module is used to collect gas emission volume and outburst characteristic indicators; the data processing module is used to process and encode the gas emission volume and outburst characteristic indicators; the gas prediction module predicts the gas emission volume based on the gas emission volume and the outburst characteristic indicators; the outburst early warning module issues an outburst event early warning based on the predicted result of the gas emission volume; the response module performs feedback adjustment on the collection of gas emission volume and outburst characteristic indicators based on the outburst early warning; the present invention can accurately analyze the changing trends of coal seam ground stress and gas emission volume, timely discover potential outburst events, and reduce the possibility of accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of coal and gas outburst early warning, and in particular to a comprehensive detection system for real-time early warning of coal and gas outburst. Background Art

[0002] Currently, a variety of technical approaches are used to monitor and provide early warning for coal and gas outbursts, primarily traditional monitoring methods and the recently emerging intelligent monitoring technologies. Traditional monitoring methods include, but are not limited to, geological exploration, borehole surveying, and acoustic emission monitoring. These methods can, to a certain extent, provide information on coal seam structure and indicate outburst precursors. Despite certain advances, existing monitoring and early warning technologies still have some shortcomings in practical application. Traditional monitoring methods often require manual, periodic data collection, preventing real-time monitoring and limiting the timeliness of early warnings. Outburst precursors vary across different mine environments, and existing early warning models often struggle to adapt to diverse mine conditions. To address these challenges, an innovative solution is needed that can address the early warning challenges in these changing environments. This solution should provide adaptable and flexible early warning strategies for different mines, different coal seams, and different areas within the same mine. Furthermore, it should provide multi-layered early warning strategies and contingency plans to address outbursts of varying urgency and mitigate the risk of accidents.

[0003] For example, Chinese patent application CN110778364B discloses a coal and gas outburst early warning method, which includes: case representation; retrieval and matching; determination of signal weights; case reuse; storage and maintenance; and the calculation of risk factors based on signal trends and case weights from real-time online monitoring data. This method is more adaptable to multiple factors and large amounts of data, providing rapid and accurate early warning results. The effectiveness of these warnings increases with the number of cases. Compared to conventional methods, this method significantly improves accuracy and reliability.

[0004] For example, the Chinese patent application with authorization announcement number CN116877203B discloses a coal and gas outburst monitoring and early warning device, which includes: gas concentration sensors, evenly distributed in the coal mine tunnel, for real-time monitoring of gas concentration in various areas; temperature and humidity sensors, distributed in the coal mine tunnel, wherein a wind direction sensor is also provided in the coal mine tunnel; plug-in anchoring components, vertically plugged and distributed on the side walls of the surrounding rock of the coal mine tunnel, the plug-in anchoring components can monitor the stress change data in the side walls of the surrounding rock in real time; an extraction and drainage monitoring mechanism, erected in the coal mine tunnel, the extraction and drainage monitoring mechanism can cooperate with the plug-in anchoring components to perform gas extraction and drainage monitoring on the side walls of the surrounding rock of the goaf; a voice alarm system and an indicator light alarm system, correspondingly distributed at the wellhead and the working face, for issuing strong early warning alarms; a central monitoring system, which is equipped with data storage, real-time display, alarm triggering and data analysis, and the central monitoring system is also externally connected to an expert system.

[0005] The above existing technologies all have the problem raised by this background technology: the early warning scheme for outburst events is difficult to adapt to diverse mine conditions.

[0006] The information disclosed in this background section is only intended to enhance understanding of the overall background of the invention and should not be considered as an admission or any form of suggestion that the information constitutes the prior art already known to a person of ordinary skill in the art. Summary of the Invention

[0007] The technical problem to be solved by the present invention is to overcome the defects of the existing technology and provide a comprehensive detection system for real-time early warning of coal and gas outbursts, accurately analyze the changing trends of coal seam ground stress and gas outburst volume, timely discover potential outburst events, and reduce the possibility of accidents.

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

[0009] The present invention provides a comprehensive detection system for real-time early warning of coal and gas outbursts, comprising a data acquisition module, a data processing module, a gas prediction module, an outburst early warning module, and a response module; wherein:

[0010] The data acquisition module is used to collect gas emission and prominent characteristic indicators;

[0011] The data processing module is used to process and encode the gas emission volume and prominent characteristic index;

[0012] The gas prediction module predicts the gas emission amount based on the gas emission amount and the prominent characteristic index;

[0013] The outburst warning module provides outburst warning based on the prediction results of gas outburst volume;

[0014] The response module performs feedback adjustment on the gas outburst volume and the collection of outburst characteristic indicators based on the outburst warning.

[0015] As a preferred solution of the comprehensive detection system for real-time early warning of coal and gas outbursts described in the present invention, wherein: the outburst characteristic indicators include coal cannon sound frequency, coal cannon sound intensity, microseismic frequency, and microseismic energy;

[0016] The data acquisition module includes a sensor unit and a feature extraction unit; wherein the sensor unit includes a gas sensor for measuring gas concentration and a wind speed sensor for measuring wind speed; the feature extraction unit calculates the gas outflow rate based on the gas concentration and wind speed;

[0017] The sensor unit also includes an acoustic emission sensor for collecting acoustic signals of coal cannon sounds; the feature extraction unit counts the number of occurrences of coal cannon sounds within a monitoring period based on the acoustic signals as the frequency of the coal cannon sounds, and calculates the average amplitude of the acoustic signals within a monitoring period as the intensity of the coal cannon sounds;

[0018] The sensor unit also includes a microseismic signal sensor for collecting microseismic signals; the feature extraction unit processes the microseismic signals, counts the number of occurrences of microseismic signals in a monitoring cycle as the microseismic frequency, and calculates the average energy of the microseismic signals in a monitoring cycle as the microseismic energy.

[0019] As a preferred solution of the comprehensive detection system for real-time early warning of coal and gas outbursts described in the present invention, the outburst characteristic indicators further include support load, support displacement, coal seam thickness, and coal seam inclination; the sensor unit further includes a pressure sensor for measuring the support load; and further includes a displacement sensor for collecting the support displacement;

[0020] The sensor unit also includes an inclinometer for measuring the inclination of the coal seam; an electromagnetic sensor for generating an electromagnetic field and receiving electromagnetic signals reflected from underground; the feature extraction unit processes the electromagnetic signals and calculates the thickness of the coal seam based on transient electromagnetic method or ground electromagnetic method.

[0021] As a preferred solution of the comprehensive detection system for real-time early warning of coal and gas outbursts described in the present invention, the data processing module includes a data cleaning unit and a data sorting unit; the data cleaning unit is used to perform data cleaning on the gas outburst volume and outburst characteristic indicators; the data sorting unit is used to sort the gas outburst volume after data cleaning into a gas outburst sequence in chronological order, and to standardize each outburst characteristic indicator after data cleaning, and to encode each outburst characteristic indicator after standardization and the gas outburst sequence into feature vectors.

[0022] As a preferred solution of the comprehensive detection system for real-time early warning of coal and gas outbursts described in the present invention, the gas prediction module is configured with a gas prediction model; the input of the gas prediction model is the characteristic vector of the gas outburst sequence and the characteristic vector of each outburst characteristic indicator, and the output is the predicted value of the gas outburst volume at N consecutive time points in the future; the gas prediction model includes an input layer, a first LSTM layer, a second LSTM layer, a fully connected layer, and an output layer; wherein:

[0023] The input layer is used to receive the feature vectors of the gas emission sequence and the prominent feature index, and concatenate the feature vectors of the gas emission sequence and the prominent feature index to form a comprehensive feature vector;

[0024] The first LSTM layer is used to extract features from the comprehensive feature vector;

[0025] The second LSTM layer is used to further extract the features of the comprehensive feature vector;

[0026] The fully connected layer is used to map the features of the comprehensive feature vector to the output space;

[0027] The output layer is used to calculate and output the predicted value of gas emission.

[0028] As a preferred embodiment of the comprehensive detection system for real-time early warning of coal and gas outbursts described in the present invention, the outburst early warning module includes a first early warning unit, which is configured with a first early warning strategy for providing an outburst early warning based on a gas outburst sequence and a predicted value of a gas outburst volume; specifically, the strategy is as follows:

[0029] Extracting the most recent M gas emission amounts in the gas emission sequence and combining them with the predicted values ​​of the N gas emission amounts in chronological order to form a gas judgment sequence;

[0030] The change index of gas emission is calculated based on the gas judgment sequence, and the formula is as follows:

[0031] ;

[0032] Among them, V represents the change index of gas emission; Indicates the value of the i-th gas emission in the gas judgment sequence, where the value of i ranges from 1, 2, ..., M+N; Indicates the value of the i-1th gas emission in the gas judgment sequence;

[0033] The first warning unit is also configured with a change threshold of the change index of the gas outflow volume; if the change index of the gas outflow volume is higher than the change threshold, the first warning unit sends a first warning message to the response module.

[0034] As a preferred solution of the comprehensive detection system for real-time early warning of coal and gas outbursts described in the present invention, the outburst early warning module further includes a second early warning unit, which is configured with a second early warning strategy for performing outburst early warning based on the gas judgment sequence, specifically as follows:

[0035] Reading the gas judgment sequence, dividing the gas judgment sequence into n subsequences of length m, where m and n are both positive integers;

[0036] Calculate the fluctuation index of gas emission of each subsequence using the following formula:

[0037] ;

[0038] in, It represents the fluctuation index of the gas emission of the jth subsequence, and the value range of j is 1, 2, ..., n; It represents the value of the kth gas emission in the jth subsequence, where the value of k ranges from 1, 2, ..., n;

[0039] The second warning unit is also configured with a threshold range of a fluctuation index; if the fluctuation index of the gas emission of more than s subsequences exceeds the threshold range of the fluctuation index, the second warning unit sends a second warning message to the response module.

[0040] As a preferred solution of the comprehensive detection system for real-time early warning of coal and gas outbursts described in the present invention, the response module includes an early warning response unit; if the early warning response unit receives the first early warning information and does not receive the second early warning information, it sends a second verification instruction to the data acquisition module; the data acquisition module responds to the second verification instruction, collects the microseismic frequency and microseismic energy in real time and transmits them to the second early warning unit; the second early warning unit is also configured with a second verification strategy, and the second early warning unit performs abnormal detection on the microseismic frequency and microseismic energy based on the second verification strategy. If the microseismic frequency and microseismic energy fail the abnormal detection, the second early warning unit sends a second early warning information to the response module.

[0041] As a preferred solution of the comprehensive detection system for real-time early warning of coal and gas outbursts described in the present invention, if the early warning response unit does not receive the first early warning information, but receives the second early warning information, it sends a first verification instruction to the data acquisition module; the data acquisition module responds to the first verification instruction, collects the coal cannon sound frequency and gas outburst volume in real time and transmits them to the first early warning unit; the first early warning unit is also configured with a first verification strategy, and the first early warning unit performs abnormal detection on the coal cannon sound frequency and gas outburst volume based on the first verification strategy. If the coal cannon sound frequency and gas outburst volume fail the abnormal detection, the first early warning unit sends the first early warning information to the response module.

[0042] As a preferred solution of the comprehensive detection system for real-time early warning of coal and gas outbursts of the present invention, if the early warning response unit receives the first early warning information and the second early warning information, it sends an emergency detection instruction to the data acquisition module;

[0043] The data acquisition module is provided with a monitoring cycle; at the beginning of each monitoring cycle, the data acquisition module collects the gas outflow volume and prominent characteristic indicators once; when the data acquisition module receives the emergency detection instruction, the monitoring cycle is set as the emergency collection cycle.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] Through continuous monitoring and deep learning models, it is possible to more accurately analyze the changing trends of coal seam ground stress and gas outburst volume at the same time and space, timely detect potential outburst events, and reduce the possibility of accidents.

[0046] This system not only focuses on gas emission but also incorporates multi-dimensional information such as microseismic signals, coal seam structure, and support status, improving the comprehensiveness and accuracy of the early warning system. Deep learning technology is used to process complex time series data, capturing the characteristics of nonlinear environmental factors and achieving accurate predictions.

[0047] Combining the dynamic characteristics of time series with statistical static thresholds, the system assesses the degree of gas emission anomalies from different perspectives, enhancing the robustness and reliability of the early warning system. Different emergency response plans are set based on outburst risk, enabling more scientific and efficient outburst response solutions that adapt to diverse mine conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0049] Figure 1 A schematic structural diagram of a comprehensive detection system for real-time early warning of coal and gas outbursts provided by the present invention;

[0050] Figure 2 A working principle diagram of a comprehensive detection system for real-time early warning of coal and gas outbursts provided by the present invention;

[0051] Figure 3 This is a structural diagram of the gas prediction model provided by the present invention. DETAILED DESCRIPTION

[0052] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0053] This embodiment introduces a comprehensive detection system for real-time early warning of coal and gas outbursts, referring to Figure 1 The system includes a data acquisition module, a data processing module, a gas prediction module, a gas outburst warning module, a response module, and a monitoring and display module; wherein: the data acquisition module is used to collect gas outburst volume and gas outburst characteristic indicators;

[0054] The prominent characteristic indicators include coal seam thickness, coal seam inclination, support load, support displacement, coal cannon sound frequency, coal cannon sound intensity, microseismic frequency, and microseismic energy;

[0055] The data acquisition module includes a sensor unit and a feature extraction unit. The sensor unit includes a gas sensor for measuring gas concentration and a wind speed sensor for measuring wind speed. The feature extraction unit calculates the gas outburst rate based on the gas concentration and wind speed. There is a direct correlation between gas outburst rate and coal and gas outburst events. Outburst events are typically caused by gas pressure accumulating in a coal seam to a certain level, exceeding the structural strength of the coal body, resulting in a sudden release of coal and gas. By monitoring gas outburst rate, precursors to outburst events can be detected promptly.

[0056] The sensor unit also includes an inclinometer for measuring the inclination of the coal seam; it also includes an electromagnetic sensor for generating an electromagnetic field and receiving electromagnetic signals reflected from the underground; the feature extraction unit processes the electromagnetic signals and calculates the thickness of the coal seam based on transient electromagnetic method or ground electromagnetic method; the thickness of the coal seam will affect the storage capacity of gas, and the inclination angle of the coal seam will affect the distribution of ground stress and the flow of gas, both of which have an important impact on the outburst event.

[0057] The sensor unit also includes a pressure sensor for measuring the support load and a displacement sensor for detecting support displacement. The pressure sensor can be mounted on a support column or beam. A sudden increase in support load may indicate increased coal seam pressure; abnormal support displacement may indicate coal seam movement. Abnormal support load and support displacement are both precursors to an outburst event.

[0058] The sensor unit also includes an acoustic emission sensor for collecting the acoustic wave signal of the coal blasting sound; the feature extraction unit counts the number of occurrences of the coal blasting sound within a monitoring period based on the acoustic wave signal as the coal blasting sound frequency, and calculates the average amplitude of the acoustic wave signal within a monitoring period as the coal blasting sound intensity. Coal blasting sound refers to the sound produced by the sudden fracture of the coal body and the release of energy due to stress concentration generated inside the coal seam due to ground pressure during the coal mining process. The amplitude of the coal blasting sound can be used to assess the stability of the coal seam. Excessively high frequency of coal blasting sound may indicate the accumulation of coal seam pressure and the risk of coal and gas outburst.

[0059] The sensor unit also includes a microseismic signal sensor for collecting microseismic signals. The feature extraction unit processes the microseismic signals, counting the number of occurrences of microseismic signals within a monitoring cycle as the microseismic frequency, and calculating the average energy of the microseismic signals within a monitoring cycle as the microseismic energy. Microseismic signals typically refer to seismic wave signals generated when underground rock fractures or stress releases. When microseismic signals increase and high-energy microseismic signals appear, it indicates a greater risk of coal and gas outbursts.

[0060] The data processing module is used to process and encode the gas emission volume and prominent characteristic indicators; it includes a data cleaning unit and a data sorting unit; wherein the data cleaning unit is used to perform data cleaning on the gas emission volume and prominent characteristic indicators; including outlier detection and replacement, missing value difference filling, and duplicate value deletion; the data sorting unit is used to sort the gas emission volume after data cleaning into a gas emission sequence in chronological order, and to standardize each prominent characteristic indicator after data cleaning, and to encode each prominent characteristic indicator after standardization and the gas emission sequence into a feature vector.

[0061] The gas prediction module predicts the gas emission amount based on the gas emission amount and the prominent characteristic index;

[0062] The gas prediction module is equipped with a gas prediction model; the input of the gas prediction model is the characteristic vector of the gas emission sequence and the characteristic vector of each prominent characteristic index, and the output is the predicted value of the gas emission at P consecutive time points in the future, where P is a positive integer; Figure 3 The gas prediction model includes an input layer, a hidden layer, and an output layer; among them, the hidden layer includes the first LSTM layer, the second LSTM layer, and the fully connected layer.

[0063] The input layer is used to receive the feature vectors of the gas emission sequence and the prominent feature index, and concatenate the feature vectors of the gas emission sequence and the prominent feature index to form a comprehensive feature vector;

[0064] The first LSTM layer is used to extract features from the comprehensive feature vector; the number of neurons is 128, and the return sequence is set to True to pass the comprehensive feature sequence to the second LSTM layer; dropout regularization is used, and the ratio of dropped neurons is 0.2 to prevent overfitting;

[0065] The second LSTM layer is used to further extract the features of the comprehensive feature vector; the number of neurons is 64, and the return sequence is set to False; dropout regularization is used, and the ratio of discarded neurons is 0.2;

[0066] The fully connected layer is used to map the features of the comprehensive feature vector to the output space; the ReLU function is used as the activation function, and the number of neurons is 32;

[0067] The output layer is used to calculate and output the predicted value of gas emission. It uses a linear activation function with N neurons, where N is the number of predicted values ​​of gas emission output; each neuron corresponds to the predicted value of gas emission at a given time point.

[0068] Different mines have different environmental characteristics and different risks of outbursts. Therefore, it is difficult to formulate a universal outburst risk criterion for different mine environments. The key to early warning of coal and gas outbursts is to capture precursor information, including changes in ground stress and changes in gas outburst volume. The present invention selects a number of outburst characteristic indicators that reflect changes in ground stress, combines the time series of gas outburst volume, and constructs a prediction model through a deep learning algorithm. On the one hand, it captures the time series characteristics of gas outburst volume, and on the other hand, it learns the characteristics of other related outburst characteristic indicators, thereby achieving accurate prediction of gas outburst volume in different mine environments and providing a data basis for subsequent coal and gas outburst early warning.

[0069] The outburst warning module provides outburst warning based on the prediction results of gas outburst volume;

[0070] The outburst warning module includes a first warning unit and a second warning unit. The first warning unit is configured with a first warning strategy for performing outburst warning based on the gas outburst sequence and the predicted value of the gas outburst amount. The details are as follows:

[0071] The most recent M gas emission values ​​in the gas emission sequence are extracted, where M is a positive integer, and the predicted values ​​of the N gas emission values ​​are combined in chronological order to form a gas judgment sequence, denoted as G, in the following format:

[0072] ;

[0073] in, Indicates the value of the i-th gas emission in the gas judgment sequence, where the value of i ranges from 1, 2, ..., M+N;

[0074] The change index of gas emission volume is calculated based on the gas warning sequence, and the formula is as follows:

[0075] ;

[0076] Among them, V represents the change index of gas emission; Indicates the value of the i-1th gas emission in the gas judgment sequence;

[0077] The first warning unit is further configured with a change threshold of the gas emission index; if the gas emission index exceeds the change threshold, the first warning unit sends a first warning message to the response module;

[0078] The second warning unit is configured with a second warning strategy, which performs a gas outburst warning based on the gas judgment sequence, specifically as follows:

[0079] Reading the gas judgment sequence, dividing the gas judgment sequence into n subsequences of length m, where m and n are both positive integers;

[0080] Calculate the fluctuation index of gas emission of each subsequence using the following formula:

[0081] ;

[0082] in, It represents the fluctuation index of the gas emission of the jth subsequence, and the value range of j is 1, 2, ..., n; It represents the value of the kth gas emission in the jth subsequence, where the value of k ranges from 1, 2, ..., n;

[0083] The second warning unit is also configured with a threshold range of a fluctuation index; if the fluctuation index of the gas emission of more than s subsequences exceeds the threshold range of the fluctuation index, the second warning unit sends a second warning message to the response module.

[0084] The first early warning strategy uses the dynamic characteristics of the gas judgment sequence to determine the risk of a sudden event. Specifically, it assesses the degree of abnormality in gas emission by using the cumulative rate of change. The second early warning strategy uses a statistical static threshold criterion, specifically analyzing the fluctuations in gas emission within each time period to detect anomalies. The issuance of the first warning indicates a significant fluctuation in gas emission, posing a certain risk of a sudden event. The issuance of the second warning indicates significant fluctuations in gas emission, posing a high risk of a sudden event. If both large fluctuations and significant fluctuations are present, the risk of a sudden event is extremely high. Combining the dynamic characteristics of the time series with the statistical static threshold provides a rational and comprehensive approach to determining gas emission anomalies. By incorporating multiple dimensions of analysis, potential anomalies can be more comprehensively captured. This dual judgment mechanism, combining dynamic and static analysis, not only improves the sensitivity and specificity of gas emission anomaly detection but also enhances the robustness and adaptability of the system.

[0085] The response module performs feedback adjustment on the gas outburst volume and the collection of outburst characteristic indicators based on the outburst warning.

[0086] The response module includes an early warning response unit; if the early warning response unit receives the first early warning information and does not receive the second early warning information, it sends a second verification instruction to the data acquisition module; the data acquisition module responds to the second verification instruction, collects the microseismic frequency and microseismic energy in real time and transmits them to the second early warning unit; the second early warning unit is also configured with a second verification strategy, and the second early warning unit performs anomaly detection on the microseismic frequency and microseismic energy based on the second verification strategy. If the microseismic frequency and microseismic energy fail to pass the anomaly detection, the second early warning unit sends a second early warning information to the response module.

[0087] The second verification strategy is specifically as follows: Calculate the second anomaly index using the following formula:

[0088] ;

[0089] in, represents the second anomaly index; f represents the microseismic frequency collected in real time; represents the mean value of the microseismic frequency in the latest R monitoring periods, represents the variance of the microseismic frequency in the latest R monitoring periods; E represents the microseismic energy collected in real time; represents the mean value of microseismic energy in the latest R monitoring periods, represents the variance of microseismic energy in the latest R monitoring periods; 、 These are weight coefficients and can be set according to actual needs. R is a positive integer.

[0090] If the second abnormality index is greater than the preset second abnormality threshold , the microseismic frequency and microseismic energy fail to pass the abnormality detection; otherwise, the microseismic frequency and microseismic energy pass the abnormality detection.

[0091] Microseismic signals are typically generated by underground rock fractures or stress release. Increased microseismic frequency and the presence of high-energy microseismic signals indicate a change in the stability of the rock surrounding the coal seam, reflecting an unstable coal seam. If the early warning response unit receives the first warning message but not the second, this indicates that the gas emission rate has fluctuated significantly, but the fluctuations are still within a relatively normal range. At this point, the coal seam structure may be in the early stages of instability. Executing the second verification strategy can improve the sensitivity of gas emission fluctuation detection, helping to promptly identify potential coal seam change trends and prevent coal outburst risks.

[0092] Preferably, the response module further comprises a plan unit; the plan unit is configured with an emergency plan, which includes a prominent threat plan, a prominent danger plan, and a prominent emergency plan;

[0093] When the early warning response unit receives the first early warning information and does not receive the second early warning information, and the microseismic frequency and microseismic energy pass the abnormal detection, the emergency plan unit sends a sudden threat emergency plan to relevant management personnel;

[0094] If the early warning response unit does not receive the first early warning information, but receives the second early warning information, it sends a first verification instruction to the data acquisition module; the data acquisition module responds to the first verification instruction, collects the coal cannon sound frequency and gas outflow volume in real time and transmits them to the first early warning unit; the first early warning unit is also configured with a first verification strategy, and the first early warning unit performs anomaly detection on the coal cannon sound frequency and gas outflow volume based on the first verification strategy. If the coal cannon sound frequency and gas outflow volume fail to pass the anomaly detection, the first early warning unit sends a first early warning information to the response module.

[0095] The first verification strategy is as follows:

[0096] If the frequency of the coal cannon sound collected in real time is greater than the preset frequency threshold or the difference between the real-time collected gas outflow volume and the average of the gas outflow volume in the last R monitoring cycles exceeds the preset threshold range, the frequency of the coal cannon sound and the gas outflow volume fail the abnormality detection; otherwise, the frequency of the coal cannon sound and the gas outflow volume pass the abnormality detection.

[0097] Excessively high frequency of coal cannon sounds may indicate the accumulation of coal seam pressure, and changes in coal seam pressure will affect gas pressure, which in turn reflects the risk of gas outburst. Gas outburst volume is directly related to coal and gas outburst events. Changes in gas outburst volume can reflect the dynamic changes in gas pressure. When gas pressure accumulates to a certain level, gas outburst volume will increase significantly. If the early warning response unit does not receive the first early warning information but receives the second early warning information, it means that the fluctuation of gas outburst volume is obvious, but the amplitude of the change has not yet reached the warning standard. This may indicate a change in gas pressure. By executing the first verification strategy, abnormal changes in gas pressure can be captured more promptly to avoid outburst accidents caused by sudden changes in gas pressure.

[0098] When the early warning response unit receives the second early warning information and does not receive the first early warning information, and the frequency of the coal cannon sound and the gas emission volume pass the abnormal detection, the emergency plan unit sends the emergency plan for the outburst danger to the relevant management personnel;

[0099] If the warning response unit receives the first warning information and the second warning information, it sends an emergency detection instruction to the data acquisition module;

[0100] The data acquisition module is configured with a monitoring cycle. At the beginning of each monitoring cycle, the module collects gas outflow volume and gas outburst characteristic indicators. When the module receives the emergency detection instruction, it sets the monitoring cycle to the emergency collection cycle. Simultaneously, the emergency plan unit sends the gas outburst emergency plan to relevant management personnel.

[0101] The emergency data collection cycle is shorter than the monitoring cycle during normal operation. For example, the monitoring cycle can be shortened by 50% to serve as the emergency data collection cycle. If the early warning response unit receives both the first and second early warning messages simultaneously, it indicates a high risk of a sudden outage. In this case, comprehensive, high-precision, and high-frequency monitoring of various indicators is necessary to obtain the most accurate information in a timely manner, providing reliable data support for subsequent decision-making and minimizing the likelihood of a sudden outage.

[0102] During mine operations, emergency plans are established based on the actual conditions of the mine, and sudden warnings are continuously carried out; based on the sudden warning results, corresponding emergency plans are extracted to deal with the threats of potential sudden incidents and minimize the hazards of sudden accidents.

[0103] An example of a prominent threat plan is as follows: strengthen emergency training for on-site workers to ensure that they are aware of the latest emergency measures; prepare necessary emergency supplies and equipment, such as rescue equipment, personal protective equipment, etc.; organize evacuation drills to ensure that all personnel are familiar with emergency evacuation routes.

[0104] An example of a prominent hazard plan is as follows: inviting experts in geology and safety to conduct on-site assessments and guidance; disseminating updates to all relevant personnel to ensure information transparency; and being prepared to initiate emergency evacuation procedures at any time to ensure that personnel can evacuate quickly.

[0105] An example of a prominent emergency plan is as follows: immediately stop all operations and ensure that all personnel are quickly evacuated; issue emergency notices through various channels, including informing local management and the media; isolate the mine and prohibit unauthorized personnel from entering; organize an expert team to conduct a post-event evaluation, analyze the cause of the incident, and formulate corrective measures.

[0106] The monitoring and display module includes a visualization unit and a human-computer interaction unit; the visualization unit is used to visualize the system parameters, including gas outflow volume and prominent characteristic indicators, gas outflow volume prediction value, warning information and corresponding triggered emergency plans; the human-computer interaction unit provides human-computer interaction functions, supporting managers to manually add or modify emergency plans. In this embodiment, the mechanism of the coordinated work of the various modules of the system is as follows: Figure 2 shown.

[0107] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the purpose and scope of protection of the present invention, which are all protected by the present invention.

Claims

1. A comprehensive detection system for real-time early warning of coal and gas outbursts, characterized by: It includes data acquisition module, data processing module, gas prediction module, outburst warning module and response module; among them: The data acquisition module is used to collect gas emission and prominent characteristic indicators; The data processing module is used to process and encode the gas emission volume and prominent characteristic index; The gas prediction module predicts the gas emission amount based on the gas emission amount and the prominent characteristic index; The outburst warning module provides outburst warning based on the prediction results of gas outburst volume; specifically, it includes: Calculating a change index of the gas emission volume, and sending a first warning message to a response module based on the change index; Calculating a fluctuation index of the gas emission amount, and sending a second warning message to a response module based on the fluctuation index; The response module performs feedback adjustment on the gas outburst volume and the collection of outburst characteristic indicators based on the outburst warning; specifically, if the first warning information is received but the second warning information is not received, the data collection module collects the microseismic frequency and microseismic energy in real time; the outburst warning module performs anomaly detection on the microseismic frequency and microseismic energy, and if the microseismic frequency and microseismic energy fail the anomaly detection, the second warning information is sent to the response module; If the first warning information is not received and the second warning information is received, the data acquisition module collects the coal cannon sound frequency and gas emission volume in real time; the prominent warning module performs an abnormality detection on the coal cannon sound frequency and gas emission volume, and if the coal cannon sound frequency and gas emission volume fail the abnormality detection, the first warning information is sent to the response module; If the first warning information is received and the second warning information is received, the monitoring period of the gas outburst volume and the prominent characteristic index is adjusted.

2. The comprehensive detection system for real-time early warning of coal and gas outbursts according to claim 1, characterized in that: The prominent characteristic indicators include coal blasting sound frequency, coal blasting sound intensity, microseismic frequency, and microseismic energy; The data acquisition module includes a sensor unit and a feature extraction unit; wherein the sensor unit includes a gas sensor for measuring gas concentration and a wind speed sensor for measuring wind speed; the feature extraction unit calculates the gas outflow rate based on the gas concentration and wind speed; The sensor unit also includes an acoustic emission sensor for collecting acoustic signals of coal cannon sounds; the feature extraction unit counts the number of occurrences of coal cannon sounds within a monitoring period based on the acoustic signals as the frequency of the coal cannon sounds, and calculates the average amplitude of the acoustic signals within a monitoring period as the intensity of the coal cannon sounds; The sensor unit also includes a microseismic signal sensor for collecting microseismic signals; the feature extraction unit processes the microseismic signals, counts the number of occurrences of microseismic signals in a monitoring cycle as the microseismic frequency, and calculates the average energy of the microseismic signals in a monitoring cycle as the microseismic energy.

3. A comprehensive detection system for real-time early warning of coal and gas outbursts according to claim 2, characterized in that: The prominent characteristic indicators also include support load, support displacement, coal seam thickness, and coal seam inclination; the sensor unit also includes a pressure sensor for measuring the support load; and a displacement sensor for collecting the support displacement; The sensor unit also includes an inclinometer for measuring the inclination of the coal seam; an electromagnetic sensor for generating an electromagnetic field and receiving electromagnetic signals reflected from underground; the feature extraction unit processes the electromagnetic signals and calculates the thickness of the coal seam based on transient electromagnetic method or ground electromagnetic method.

4. A comprehensive detection system for real-time early warning of coal and gas outbursts according to claim 3, characterized in that: The data processing module includes a data cleaning unit and a data sorting unit; wherein the data cleaning unit is used to perform data cleaning on the gas outflow volume and prominent characteristic indicators; the data sorting unit is used to sort the gas outflow volume after data cleaning into a gas outflow sequence in chronological order, and to perform standardization on each prominent characteristic indicator after data cleaning, and to encode each prominent characteristic indicator after standardization and the gas outflow sequence into a feature vector.

5. The comprehensive detection system for real-time early warning of coal and gas outburst according to claim 4, characterized in that: The gas prediction module is configured with a gas prediction model; the input of the gas prediction model is the feature vector of the gas emission sequence and the feature vector of each prominent feature indicator, and the output is the predicted value of the gas emission at N consecutive time points in the future; the gas prediction model includes an input layer, a first LSTM layer, a second LSTM layer, a fully connected layer, and an output layer; wherein: The input layer is used to receive the feature vectors of the gas emission sequence and the prominent feature index, and concatenate the feature vectors of the gas emission sequence and the prominent feature index to form a comprehensive feature vector; The first LSTM layer is used to extract features from the comprehensive feature vector; The second LSTM layer is used to extract the features of the comprehensive feature vector; The fully connected layer is used to map the features of the comprehensive feature vector to the output space; The output layer is used to calculate and output the predicted value of gas emission.

6. A comprehensive detection system for real-time early warning of coal and gas outbursts according to claim 5, characterized in that: The outburst warning module includes a first warning unit, which is configured with a first warning strategy for performing outburst warning based on a gas outburst sequence and a predicted value of a gas outburst amount; specifically, as follows: Extracting the most recent M gas emission amounts in the gas emission sequence and combining them with the predicted values ​​of the N gas emission amounts in chronological order to form a gas judgment sequence; Calculating a change index of gas emission based on the gas judgment sequence; The first warning unit is also configured with a change threshold of the change index of the gas outflow volume; if the change index of the gas outflow volume is higher than the change threshold, the first warning unit sends a first warning message to the response module.

7. A comprehensive detection system for real-time early warning of coal and gas outbursts according to claim 6, characterized in that: The gas outburst warning module further includes a second warning unit configured with a second warning strategy for performing a gas outburst warning based on the gas judgment sequence, specifically as follows: Reading the gas judgment sequence, dividing the gas judgment sequence into n subsequences of length m, where m and n are both positive integers; Calculate the fluctuation index of gas emission of each subsequence; The second early warning unit is also configured with a threshold range of the fluctuation index; If the fluctuation index of the gas emission amount of more than s subsequences exceeds the threshold range of the fluctuation index, the second early warning unit sends a second early warning message to the response module.

8. A comprehensive detection system for real-time early warning of coal and gas outbursts according to claim 7, characterized in that: The response module includes an early warning response unit; if the early warning response unit receives the first early warning information and does not receive the second early warning information, it sends a second verification instruction to the data acquisition module; The data acquisition module responds to the second verification instruction, collects the microseismic frequency and microseismic energy in real time and transmits them to the second early warning unit; the second early warning unit is also configured with a second verification strategy, and the second early warning unit performs anomaly detection on the microseismic frequency and microseismic energy based on the second verification strategy. If the microseismic frequency and microseismic energy fail to pass the abnormal detection, the second early warning unit sends a second early warning information to the response module.

9. A comprehensive detection system for real-time early warning of coal and gas outbursts according to claim 8, characterized in that: If the early warning response unit does not receive the first early warning information, but receives the second early warning information, it sends a first verification instruction to the data acquisition module; The data acquisition module responds to the first verification instruction, collects the coal cannon sound frequency and gas outflow volume in real time and transmits them to the first early warning unit; the first early warning unit is also configured with a first verification strategy, and the first early warning unit performs abnormal detection on the coal cannon sound frequency and gas outflow volume based on the first verification strategy. If the coal cannon sound frequency and gas outflow volume fail to pass the abnormal detection, the first early warning unit sends a first early warning information to the response module.

10. A comprehensive detection system for real-time early warning of coal and gas outbursts according to claim 9, characterized in that: If the warning response unit receives the first warning information and the second warning information, it sends an emergency detection instruction to the data acquisition module; The data acquisition module is set with a monitoring cycle; at the beginning of each monitoring cycle, the data acquisition module collects gas emission volume and prominent characteristic indicators once; When the data acquisition module receives the emergency detection instruction, it sets the monitoring period as the emergency acquisition period.

Images