CN119207023A - Coal and gas outburst hazard zone identification and early warning method based on multi-parameter fusion - Google Patents
Coal and gas outburst hazard zone identification and early warning method based on multi-parameter fusion Download PDFInfo
- Publication number
- CN119207023A CN119207023A CN202411324690.6A CN202411324690A CN119207023A CN 119207023 A CN119207023 A CN 119207023A CN 202411324690 A CN202411324690 A CN 202411324690A CN 119207023 A CN119207023 A CN 119207023A
- Authority
- CN
- China
- Prior art keywords
- signal
- early warning
- abnormal
- microseismic
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/12—Alarms for ensuring the safety of persons responsive to undesired emission of substances, e.g. pollution alarms
- G08B21/16—Combustible gas alarms
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Emergency Management (AREA)
- Computing Systems (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Health & Medical Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of coal mine safety and coal and gas prediction, and discloses a coal and gas outburst danger area identification early warning method based on multi-parameter fusion, wherein multi-parameter data are acquired through a sensor network and are connected with the sensor network through a monitoring transmission strategy, and the multi-parameter data are transmitted to a cloud platform; the method comprises the steps of extracting characteristics of multi-parameter data transmitted to a cloud platform through a characteristic fusion strategy, carrying out fusion processing, constructing an outburst early warning model and an outburst early warning strategy according to the multi-parameter characteristics, training the outburst early warning model through acquiring historical outburst events and normal events, improving prediction accuracy and reliability of coal and gas outburst risks, identifying abnormal states through the outburst early warning model and the outburst early warning strategy, visually displaying signals and signal areas in the cloud platform, simultaneously transmitting the signals and the signal areas to management staff and professional analysts, carrying out remote analysis and judging of prediction effects, and dynamically adjusting the outburst early warning model and the outburst early warning strategy according to the multi-parameter data and the prediction effects.
Description
Technical Field
The invention relates to the technical field of coal mine safety and coal and gas prediction, in particular to a coal and gas outburst danger area identification early warning method based on multi-parameter fusion.
Background
At present, researchers collect data through various sensors and comprehensively analyze the data collected by the sensors, so that prediction and warning are carried out on dangerous areas with prominent coal and gas, and the method has important practical significance in the aspects of reducing the risk of coal mine disasters, improving the safety of miners and the like. The research result shows that if the ground stress is in a static and constant state, the ground stress can not excite the protrusion, and the gas mainly exists in an adsorption state and does not drive the protrusion energy. Meanwhile, when the mining method and the mining intensity are greatly changed, the stress tension degree of the working face is greatly increased, the space and time for relieving the stress tension are not enough for the concentrated stress of the working face, the direct reason for the occurrence of the salience is not dependent on the gas in the coal seam, but is dependent on whether the concentrated stress degree of the ground stress can damage roof rocks which play a main bearing role to generate strong impact force, so that the remote early warning monitoring analysis, guidance and standard management of the working face are realized, and the method is a very effective way and method for solving and preventing the salience accident. However, how to integrate and extract features of the acquired multi-parameter data is not solved in most cases, so that an early warning model and an early warning strategy are constructed to identify mine anomalies, early warning signals and early warning dangerous areas are generated and visually displayed, and meanwhile, the early warning model and the early warning strategy are dynamically adjusted according to early warning effects.
The method carries out prominent risk evaluation on a coal seam working surface by using a conventional index capable of quantitatively representing, carries out weight coefficient distribution on the conventional index, then introduces basic information for qualitative representation as a comprehensive index coefficient, fuses the conventional index for quantitative representation and the multi-parameter basic information for qualitative representation with each other to realize comprehensive early warning, and can describe the consistency of real conditions of a monitored area so as to reflect the nature of things more truly and comprehensively, thereby making up the defect of conventional index early warning and providing more accurate early warning for coal and gas prominent risk area judgment on a coal mine site.
If the Chinese patent with the authorized bulletin number of CN110043317B discloses a method for judging and early warning a multi-parameter local dangerous area of a mine disaster, the position and the dangerous grade of the local dangerous area can be accurately judged and recognized, the mine can be guided to carry out disaster protection in a targeted manner, and the site requirements of each mine can be met. The early warning method comprises the steps of 1, spatially locating mine disaster monitoring points, 2, obtaining initial dangerous index I single point initial of each monitoring point, 3, searching the conditions of other monitoring points around each monitoring point, 4, correcting the initial dangerous index of the monitoring point, and 5, obtaining the position and the dangerous grade of a local dangerous area. The method solves the problems that the existing early warning method can not accurately judge the position and the danger level of the local dangerous area and can not guide the mine to carry out disaster protection in a targeted manner.
The coal and gas outburst dangerous area judgment and identification comprehensive early warning method comprises the steps of carrying out outburst dangerous assessment on a coal seam working face through conventional indexes capable of being quantitatively represented, carrying out weight coefficient distribution on the conventional indexes, introducing basic information for qualitative representation as a comprehensive index coefficient, mutually fusing the conventional indexes capable of being quantitatively represented and multi-parameter basic information capable of being qualitatively represented, and further realizing comprehensive early warning, obtaining initial dangerous index I single-point initial of each monitoring point through spatial positioning of mine disaster monitoring points, searching conditions of other monitoring points around each monitoring point, and correcting the initial dangerous indexes of the monitoring points to obtain local dangerous area positions and dangerous grades. The two patents do not solve the problem of how to combine and extract characteristics of acquired multi-parameter data to construct an early warning model and an early warning strategy to identify mine anomalies, generate early warning signals and early warning dangerous areas and visually display the early warning signals and the early warning dangerous areas, and dynamically adjust the early warning model and the early warning strategy according to early warning effects. In order to solve the problem, the invention provides a coal and gas outburst danger area identification early warning method based on multi-parameter fusion.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
The invention is provided in view of the problems of the existing coal and gas outburst dangerous area identification and early warning method based on multi-parameter fusion.
Therefore, the invention aims to provide a coal and gas outburst dangerous area identification early warning method based on multi-parameter fusion.
In order to solve the technical problems, the invention provides the following technical scheme:
Acquiring multi-parameter data through a sensor network, connecting the sensor network through a monitoring transmission strategy, and transmitting the multi-parameter data to a cloud platform;
extracting characteristics of multi-parameter data transmitted to the cloud platform through a characteristic fusion strategy, generating multi-parameter characteristics, and carrying out fusion processing;
According to the multi-parameter characteristics, an outstanding early warning model and an outstanding early warning strategy are established, and the outstanding early warning model is trained by acquiring historical outstanding events and normal events;
Identifying an abnormal state through the salient early warning model and the salient early warning strategy, generating a signal if the abnormality is identified, positioning the signal to a signal area, and simultaneously sending a control instruction;
Visually displaying the signals and the signal areas in the cloud platform, simultaneously transmitting the signals and the signal areas to management staff and professional analysts, and remotely analyzing and judging the prediction effect;
And dynamically adjusting the outstanding early warning model and the outstanding early warning strategy according to the multi-parameter data and the prediction effect.
As a preferable scheme of the coal and gas outburst dangerous area judgment and early warning method based on multi-parameter fusion, the sensor network comprises a microseismic sensor, a gas sensor, a wind speed sensor, an equipment start-stop sensor, a power-off controller, a voice playing alarm and a visual camera;
the multi-parameter data comprise microseismic signals, gas concentration, gas emission quantity, wind speed and equipment operation conditions;
acquiring the multi-parameter data through the sensor network, connecting the sensor network through the monitoring transmission strategy, and transmitting the multi-parameter data to a cloud platform, wherein the monitoring transmission strategy comprises:
Integrating the multi-parameter data acquired by the sensor network, synchronizing the multi-parameter data according to a time sequence, compressing the multi-parameter data into data packets, dynamically selecting a transmission path of the data packets according to network conditions, setting a data buffer area at a receiving end of a cloud platform, placing the received data packets into the data buffer area, and dynamically adjusting the transmission bandwidth of the data packets according to data quantity.
As a preferable scheme of the coal and gas outburst dangerous area judgment and early warning method based on multi-parameter fusion, the invention dynamically selects a transmission path of a data packet according to network conditions, and a function expression of the transmission path selection is as follows:
Where t represents a transmission path selected according to a network condition, d represents a network delay, max (d) represents a maximum value of the network delay, min (d) represents a minimum value of the network delay, l represents a network packet loss rate, max (l) represents a maximum value of the network packet loss rate, and min (l) represents a minimum value of the network packet loss rate.
As a preferable scheme of the coal and gas outburst danger area identification early warning method based on multi-parameter fusion, the outburst early warning strategy comprises the following steps:
Acquiring the event number and the released energy of the microseismic signals, extracting the amplitude and the duration of the microseismic signals, configuring a threshold value, an amplitude threshold value and a duration threshold value, judging the state of the microseismic signals, and if the amplitude of the microseismic signals is greater than or equal to the amplitude threshold value and the duration of the microseismic signals is greater than or equal to the duration threshold value, indicating that a large event occurs and marking the event as abnormal ground stress activity;
if the amplitude of the microseismic signal is larger than a threshold value and the amplitude of the microseismic signal is smaller than the threshold value, indicating that a small event occurs, and marking the small event as abnormal ground stress activity;
And if the amplitude of the microseismic signal is smaller than or equal to a threshold value and the duration of the microseismic signal is smaller than or equal to a duration threshold value, the working face shows that the ground stress activity is normal.
As a preferable scheme of the coal and gas outburst danger area identification early warning method based on multi-parameter fusion, the outburst early warning strategy further comprises the following steps:
acquiring the extreme value of the gas concentration, configuring a concentration safety threshold, judging the state of the gas concentration, and if the extreme value of the gas concentration is greater than or equal to the concentration safety threshold, marking the extreme value as concentration abnormality;
if the extreme value of the gas concentration is smaller than the concentration safety threshold, the working surface displays normal concentration;
acquiring the extreme value of the gas emission quantity, configuring an emission safety threshold, judging the state of the gas emission quantity, and if the extreme value of the gas emission quantity is greater than or equal to the emission safety threshold, marking as abnormal emission;
If the extreme value of the gas emission quantity is smaller than the emission safety threshold value, the working surface shows that the emission is normal;
Acquiring abnormal fluctuation of wind speed, extracting wind speed variation, configuring a wind speed variation threshold value, judging the state of the wind speed, and if the wind speed variation is greater than or equal to the wind speed variation threshold value, marking the abnormal ventilation state;
If the wind speed variation is smaller than the wind speed variation threshold, the working face displays that the ventilation state is normal;
acquiring equipment abnormality, judging the state of equipment, and if the equipment is abnormal, marking the abnormal state as equipment abnormality;
If the equipment is not abnormal, the working face display equipment is normal.
As a preferable scheme of the coal and gas outburst danger area identification early warning method based on multi-parameter fusion, the method comprises the steps of identifying an abnormal state through the outburst early warning model and the outburst early warning strategy, wherein the strategy for identifying the abnormal state comprises the following steps:
Judging the output result of the salient early warning model, if no salient danger is displayed, indicating that the working surface is in a normal state, continuously monitoring the multi-parameter data, and generating a safety signal;
If the abnormal state is displayed, comprehensively identifying the abnormal state through the salient early warning strategy, and if the working surfaces are in the normal state, indicating that the abnormal state is not identified, continuously monitoring the multi-parameter data, and generating a safety signal;
if the working surface has an abnormal state, judging the state of equipment, and if the working surface display equipment is abnormal, identifying the abnormality and generating an early warning signal;
judging the state of the microseismic signal if the working surface display equipment is normal, judging the state of microseismic energy if the ground stress activity of the working surface display equipment is abnormal, and identifying the abnormality if the microseismic energy is abnormal to generate a critical signal;
if the microseismic energy is normal, comprehensively judging the state of the microseismic event and the abnormal situation of the ground stress activity;
Judging the states of the gas concentration, the gas emission quantity and the wind speed if the ground stress activity of the working surface is normal, and identifying the abnormality if the concentration, the emission abnormality and the ventilation state of the working surface are abnormal, so as to generate an early warning signal;
and if the working surface displays concentration abnormality or surging abnormality or ventilation state abnormality, continuously monitoring the multi-parameter data to generate a safety signal.
As a preferable scheme of the coal and gas outburst dangerous area identification early warning method based on multi-parameter fusion, the strategy for identifying abnormal states further comprises the following steps:
Judging the state of a microseismic event and the state of microseismic energy, extracting the microseismic event frequency and the microseismic energy of a microseismic signal, configuring an event frequency threshold and a microseismic energy threshold, and if the microseismic event frequency is smaller than or equal to the event frequency threshold, indicating that the microseismic event is normal;
if the frequency of the microseismic event is greater than the event frequency threshold, indicating that the microseismic event is abnormal;
if the microseismic energy is smaller than or equal to the microseismic energy threshold, the microseismic energy is normal;
if the microseismic energy is greater than the microseismic energy threshold, then the microseismic energy is abnormal.
As a preferable scheme of the coal and gas outburst dangerous area identification early warning method based on multi-parameter fusion, the strategy for identifying abnormal states further comprises the following steps:
comprehensively judging the state of the microseism event and the abnormal situation of the ground stress activity, and if a large event occurs and the microseism event is normal, identifying the abnormality and generating a dangerous signal;
If a large event and a microseism event are abnormal, identifying the abnormality and generating a critical signal;
if a small event occurs and the microseism event is normal, identifying abnormality and generating an early warning signal;
Judging the states of the gas concentration, the gas emission quantity and the wind speed if a small event and a microseismic event are abnormal, and identifying the abnormality if the working surface shows that the concentration is abnormal, the emission is abnormal and the ventilation state is normal, so as to generate a critical signal;
If the working surface shows that the concentration is abnormal, the emission is abnormal or the ventilation state is abnormal, the abnormality is identified, and a danger signal is generated.
As a preferable scheme of the coal and gas outburst dangerous area identification early warning method based on multi-parameter fusion, the strategy for identifying abnormal states further comprises the following steps:
if the safety signal is generated, the signal area is a safety area;
if the early warning signal is generated, the signal area is a threat area;
If the dangerous signal is generated, the signal area is a dangerous area;
And if the critical signal is generated, the signal area is a critical area.
As an optimal scheme of the coal and gas outburst dangerous area identification early warning method based on multi-parameter fusion, the method comprises the following steps of visually displaying the signals and the signal areas in a cloud platform:
constructing a three-dimensional map according to a working surface, marking the position of the sensor network on the three-dimensional map, superposing the multi-parameter data on the three-dimensional map, marking the multi-parameter data according to the state of the multi-parameter data, distinguishing the signal and the signal area, and normally displaying the three-dimensional map if the signal and the signal area are the safety signal and the safety area;
if the security signal and the security zone are not present, the three-dimensional map is highlighted.
The method has the beneficial effects that the multi-parameter data is acquired through the sensor network, and is connected with the sensor network through the monitoring transmission strategy, the multi-parameter data is transmitted to the cloud platform, so that real-time transmission of the multi-parameter data and remote monitoring of the cloud platform are realized, comprehensive monitoring of outstanding early warning in a mine is realized, the on-site data is transmitted to the cloud platform in real time through the effective monitoring transmission strategy, and timeliness of the data is ensured, which is very important for quick response to possible dangerous conditions; the method comprises the steps of extracting characteristics of multi-parameter data transmitted to a cloud platform through a characteristic fusion strategy to generate multi-parameter characteristics, carrying out fusion processing to more accurately represent the safety state of a mine, constructing an outburst early warning model and an outburst early warning strategy according to the multi-parameter characteristics, training the outburst early warning model through acquiring historical outburst events and normal events to improve the prediction accuracy and reliability of coal and gas outburst risks, identifying abnormal states through the outburst early warning model and the outburst early warning strategy, generating signals if the abnormal states are identified, positioning the signals to a signal area, simultaneously transmitting control instructions, automatically identifying the abnormal states and positioning the dangerous area, accelerating a decision process, reducing the dependence on manual intervention, effectively distributing escape and rescue resources, visually displaying the signals and the signal area in the cloud platform, simultaneously transmitting the signals to management personnel and professional analysts, remotely judging the prediction effect, helping to reduce casualty accidents, improving the overall safety of miners, and dynamically adjusting the outburst early warning model and the outburst early warning strategy according to the multi-parameter data and the prediction effect.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained from these drawings without inventive effort for a person skilled in the art. Wherein:
FIG. 1 is a flow chart of a method for identifying and pre-warning coal and gas outburst risk areas based on multi-parameter fusion;
FIG. 2 is a flow chart of a monitoring and transmitting strategy of the coal and gas outburst danger zone identification early warning method based on multi-parameter fusion;
FIG. 3 is a flow chart of ventilation state judgment based on the coal and gas outburst danger zone judgment and early warning method based on multi-parameter fusion;
FIG. 4 is a flow chart of an abnormal state identification strategy of the coal and gas outburst risk area identification early warning method based on multi-parameter fusion.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will be able to make a similar generalization without departing from the spirit of the invention, so that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Example 1
In this embodiment, a method flowchart of a coal and gas outburst risk area identification early warning method based on multi-parameter fusion is provided, as shown in fig. 1, the coal and gas outburst risk area identification early warning method based on multi-parameter fusion includes:
s1, acquiring multi-parameter data through a sensor network, connecting the sensor network through a monitoring transmission strategy, transmitting the multi-parameter data to a cloud platform, realizing real-time transmission and remote monitoring of the multi-parameter data, and providing comprehensive mine environment depiction, so that monitoring is more comprehensive and accurate, timeliness of the multi-parameter data is ensured, and possible dangerous situations can be responded in time.
The sensor network comprises a microseismic sensor, a gas sensor, a wind speed sensor, an equipment start-stop sensor, a power-off controller, a voice playing alarm and a visual camera.
The multi-parameter data comprise microseismic signals, gas concentration, gas emission quantity, wind speed and equipment operation conditions;
Acquiring multi-parameter data through a sensor network, and connecting the sensor network through a monitoring transmission strategy, wherein the monitoring transmission strategy is shown in fig. 2 and specifically comprises the following steps of:
Integrating multi-parameter data acquired by a sensor network, synchronizing the multi-parameter data according to a time sequence, compressing the multi-parameter data into data packets, dynamically selecting a transmission path of the data packets according to network conditions, setting a data buffer area at a receiving end of a cloud platform, placing the received data packets into the data buffer area, and dynamically adjusting the transmission bandwidth of the data packets according to data quantity.
The transmission path of the data packet is dynamically selected according to the network condition, and the function expression of the transmission path selection is as follows:
Where t represents a transmission path selected according to a network condition, d represents a network delay, max (d) represents a maximum value of the network delay, min (d) represents a minimum value of the network delay, l represents a network packet loss rate, max (l) represents a maximum value of the network packet loss rate, and min (l) represents a minimum value of the network packet loss rate.
The transmission bandwidth of the data packet is dynamically adjusted according to the data volume, and the function expression of the transmission bandwidth adjustment is as follows:
Where w represents a transmission bandwidth adjusted according to the data amount, p represents the data amount, max (p) represents the maximum value of the data amount, min (p) represents the minimum value of the data amount, n represents the available bandwidth, max (n) represents the maximum value of the available bandwidth, and min (n) represents the minimum value of the available bandwidth.
The method comprises the steps that a microseismic signal is obtained through a microseismic sensor, gas concentration and gas emission quantity are obtained through a gas sensor, the wind speed of the surrounding environment is obtained through a wind speed sensor, an equipment start-stop sensor is used for detecting the start-stop state of equipment, a power-off controller is used for detecting disconnection and reconnection of the equipment, a voice playing alarm is used for voice broadcasting, particularly workers under and on the mine can be timely notified when a threat zone, a dangerous zone and a critical zone are located, a visual camera is used for real-time picture transmission of the conditions under the mine, and in order to better visually display the signals and the signal zone in a cloud platform, and the equipment operation condition refers to the operation condition of large mining equipment on a working face.
The method comprises the steps of carrying out preliminary data fusion on a sensor network, integrating multi-parameter data from different sensor networks, adopting a high-efficiency data compression algorithm, compressing the multi-parameter data into data packets, dynamically selecting a transmission path of the data packets according to network conditions, considering network delay and network packet loss rate in the network conditions, selecting an optimal transmission path according to historical performance and current network conditions, setting a data buffer area at a receiving end of a cloud platform, firstly placing the received data packets into the data buffer area, dynamically adjusting the transmission bandwidth of the data packets according to the data volume, considering the data volume of the data packets and the residual available bandwidth of the transmission bandwidth, and judging the priority of data packet transmission according to the importance degree of data in the data packets.
S2, extracting characteristics of the multi-parameter data transmitted to the cloud platform through a characteristic fusion strategy, generating multi-parameter characteristics, and carrying out fusion processing, so that the safety state of the mine can be more accurately represented.
Extracting characteristics of multi-parameter data transmitted to the cloud platform through a characteristic fusion strategy and carrying out fusion processing on the characteristics, wherein the characteristic fusion strategy comprises the following steps:
And extracting the characteristics of the multi-parameter data transmitted to the cloud platform, generating multi-parameter characteristics, calculating the correlation of the multi-parameter characteristics, identifying and eliminating redundant characteristics, and carrying out fusion processing on the multi-parameter characteristics.
The functional expression of the correlation of the multi-parameter feature is as follows:
Where r XY denotes the correlation coefficient of feature X and feature Y, X i denotes the ith observation of feature X, Represents the average of the observations of feature X, Y i represents the ith observation of feature Y,Represents the average value of the observed values of the feature Y, and m represents the total number of observed values.
If r XY →1, it means that the feature Y increases when the feature X increases;
If r XY →0, it means that feature X is not related to feature Y;
If r XY → -1, it means that feature X increases, feature Y decreases.
The method comprises the steps of extracting characteristics of multi-parameter data transmitted to a cloud platform to generate multi-parameter characteristics, wherein the multi-parameter characteristics comprise the number of events of microseismic signals, the released energy, the extreme value of gas concentration, the extreme value of gas emission quantity, abnormal fluctuation of wind speed, abnormal equipment conditions and the like, and the number of events of the microseismic signals refers to the number of times of fracture and destruction of coal and rock.
When the correlation coefficient r XY of the feature X and the feature Y is closer to 1, the strong positive correlation is shown between the two features, when the correlation coefficient r XY of the feature X and the feature Y is closer to-1, the strong negative correlation is shown between the two features, when the correlation coefficient r XY of the feature X and the feature Y is closer to 0, the correlation between the two features is not shown, for the correlation calculation between each pair of features, a feature threshold r is set, the features of |r XY | < r are removed, for each pair of features of |r XY | is selected to remain the features more important to the salient early warning model, the other features are removed, and the multi-parameter features after redundant feature identification and removal are subjected to fusion treatment.
S3, constructing a protrusion early warning model and a protrusion early warning strategy according to the multi-parameter characteristics, and training the protrusion early warning model by acquiring historical protrusion events and normal events to ensure that the protrusion early warning model can accurately predict protrusion risks.
And constructing an outstanding early warning model and an outstanding early warning strategy according to the multi-parameter characteristics, wherein the function expression of the outstanding early warning model is as follows:
Where M final represents the final selected salient alert model, The method comprises the steps of representing a prominent early-warning model with the maximum value of P (M, T) found in an index set, wherein P (M, T) represents the index set for performing performance evaluation on the prominent early-warning model, M represents a constructed prominent early-warning model, and T represents a training data set comprising historical prominent events and normal events.
The training data set represents a set of all training samples, including feature vectors and corresponding labels, wherein the corresponding labels are obtained through a constructed salient early warning model according to the event number and the released energy of the microseismic signals, the extreme value of gas concentration, the extreme value of gas emission quantity, abnormal fluctuation of wind speed and the feature vectors of abnormal conditions of equipment, 1 represents that the salient risks exist, 0 represents that the salient risks exist, and the construction mode of the salient early warning model comprises but is not limited to a support vector machine, a convolution neural network and a circulation neural network.
The outstanding early warning strategy comprises the following steps:
Acquiring the event number and the released energy of the microseismic signals, extracting the amplitude and the duration time of the microseismic signals, configuring a threshold value, an amplitude threshold value and a duration time threshold value, judging the state of the microseismic signals, and if the amplitude of the microseismic signals is greater than or equal to the amplitude threshold value and the duration time of the microseismic signals is greater than or equal to the duration time threshold value, indicating that a large event occurs and recording the event as abnormal ground stress activity;
if the amplitude of the microseismic signal is larger than the threshold value and the amplitude of the microseismic signal is smaller than the amplitude threshold value, indicating that a small event occurs, and marking the small event as abnormal ground stress activity;
If the amplitude of the microseismic signal is smaller than or equal to the threshold value and the duration of the microseismic signal is smaller than or equal to the duration threshold value, the working face shows that the ground stress activity is normal;
acquiring an extreme value of the gas concentration, configuring a concentration safety threshold value, judging the state of the gas concentration, and if the extreme value of the gas concentration is greater than or equal to the concentration safety threshold value, marking the extreme value as concentration abnormality;
if the extreme value of the gas concentration is smaller than the concentration safety threshold value, the working surface displays that the concentration is normal;
Acquiring an extremum of the gas emission quantity, configuring an emission safety threshold, judging the state of the gas emission quantity, and if the extremum of the gas emission quantity is greater than or equal to the emission safety threshold, marking as abnormal emission;
If the extreme value of the gas emission quantity is smaller than the emission safety threshold value, the working surface shows that the emission is normal;
As shown in fig. 3, acquiring abnormal fluctuation of wind speed, extracting a wind speed variation, configuring a wind speed variation threshold, judging the state of wind speed, and if the wind speed variation is greater than or equal to the wind speed variation threshold, recording as abnormal ventilation state;
If the wind speed variation is smaller than the wind speed variation threshold, the working face displays that the ventilation state is normal;
acquiring equipment abnormality, judging the state of equipment, and if the equipment is abnormal, marking the abnormal state as equipment abnormality;
If the equipment is not abnormal, the working face display equipment is normal.
The abnormal judgment is respectively carried out on the event number of the microseismic signals, the released energy, the extreme value of the gas concentration, the extreme value of the gas emission quantity, the abnormal fluctuation of the wind speed and the abnormal condition of equipment so as to comprehensively identify the abnormal state by the subsequent combined salient early warning model, the threshold value can more accurately identify small events, the amplitude threshold value is the maximum amplitude released when the main bearing rock stratum is damaged, and can more accurately identify large events, wherein if the small events occur throughout the day, particularly when the working surface is unmanned, the working surface is in continuous transfer position and aggravation of concentrated stress, the working surface enters a threat zone from a safety zone at the moment, the stress intensity of the hard roof rock stratum reaches a critical state when the large events begin to occur, the monitoring personnel must pay close attention to the change condition of other multi-parameter data, reminding mine management personnel to take proper safety measures, wherein the working face enters an outstanding dangerous area, when a large event occurs intensively, the hard roof rock is broken in a large scale, the energy accumulated by the broken rock layer begins to impact the coal bed, the energy of the collected microseismic signals is suddenly changed, the energy value can reach more than tens of thousands of joules, the air permeability of the coal bed can be changed due to the impact force of the coal bed, the coal bed gas characteristics are changed, the working personnel are required to be informed to withdraw in time, when the gas concentration is changed, whether abnormal fluctuation of the wind speed leads to the change of the gas concentration is observed, when the ventilation state is stable, the gas concentration is changed, the gas characteristics of the coal bed are changed, and the gas emission quantity is changed under the condition that the wind speed is unchanged, and the gas characteristics of the coal bed are changed, meanwhile, whether the working conditions of the large working face mining equipment are abnormal or not can influence whether the working conditions of the working face mining equipment are concentrated due to the fact that ground stress is concentrated or not caused by working operation of the working face mining equipment, most of protruding accidents occurring on the working face mining equipment are related to the operation of mechanical equipment, the operation state of the underground mining equipment can influence the stress tension degree of the working face mining equipment, many protruding accidents are all induced by the construction of the mechanical equipment, the stress tension of the working face mining equipment is aggravated by continuous operation of the working face mining equipment, the protruding danger of the working face mining equipment is increased, the operation of the working face mining equipment is stopped, the stress tension of the working face is relieved, the largest concentrated stress is reduced, the working face mining equipment is transferred to the deep part of the working face mining equipment, a large safety distance is generated in front of the working face mining equipment, the protruding danger is reduced, the working state of the mining equipment can be detected through an equipment starting and stopping sensor, and the mining equipment is controlled to operate in a safe working range.
S4, identifying an abnormal state through the salient early warning model and the salient early warning strategy, generating a signal if the abnormal state is identified, positioning the signal to a signal area, and simultaneously sending a control instruction.
The abnormal state is identified by the salient early warning model and the salient early warning strategy, and the strategy for identifying the abnormal state is shown in fig. 4, and specifically comprises the following steps:
judging the output result of the salient early warning model, if no salient danger is displayed, indicating that the working face is in a normal state, continuously monitoring multi-parameter data, and generating a safety signal;
If the abnormal state is displayed, comprehensively identifying the abnormal state through an outstanding early warning strategy, and if the working surfaces are in a normal state, indicating that the abnormal state is not identified, continuously monitoring multi-parameter data, and generating a safety signal;
if the working surface has an abnormal state, judging the state of equipment, and if the working surface display equipment is abnormal, identifying the abnormality and generating an early warning signal;
If the working face display equipment is normal, judging the state of the microseismic signal, if the ground stress activity of the working face display equipment is abnormal, extracting the microseismic event frequency and microseismic energy of the microseismic signal, configuring an event frequency threshold and a microseismic energy threshold to obtain the state of the microseismic event and the state of the microseismic energy, and if the microseismic event frequency is smaller than or equal to the event frequency threshold, indicating that the microseismic event is normal;
if the frequency of the microseismic event is greater than the event frequency threshold, indicating that the microseismic event is abnormal;
if the microseismic energy is smaller than or equal to the microseismic energy threshold, the microseismic energy is normal;
If the microseismic energy is greater than the microseismic energy threshold, indicating that the microseismic energy is abnormal;
judging the state of the microseismic energy, if the microseismic energy is abnormal, identifying the abnormality, and generating a critical signal;
if the microseism energy is normal, comprehensively judging the state of the microseism event and the abnormal situation of the ground stress activity, and if the microseism event is normal and a large event occurs, identifying the abnormality and generating a dangerous signal;
If a large event and a microseism event are abnormal, identifying the abnormality and generating a critical signal;
if a small event occurs and the microseism event is normal, identifying abnormality and generating an early warning signal;
judging the states of gas concentration, gas emission and wind speed if a small event and a microseism event are abnormal, and identifying the abnormality if the working surface shows that the concentration is abnormal, the emission is abnormal and the ventilation state is normal, so as to generate a critical signal;
if the working surface shows that the concentration is abnormal or the emission is abnormal or the ventilation state is abnormal, identifying the abnormality and generating a dangerous signal;
judging the states of gas concentration, gas emission and wind speed if the ground stress activity displayed on the working surface is normal, and identifying the abnormality if the concentration displayed on the working surface is abnormal, the emission is abnormal and the ventilation state is abnormal, so as to generate an early warning signal;
if the working surface displays concentration abnormality or surging abnormality or ventilation state abnormality, continuously monitoring multi-parameter data to generate a safety signal.
When the microseismic event is abnormal, the small event is frequently happened, and when the working surface is abnormal in display concentration, abnormal in surging and normal in ventilation state, the coal seam characteristics are changed.
For the occurrence of a large event, the coal measure strata are identified to have hard rock fracture, and at the same time, the concentration is abnormal and the gushing is abnormal under the condition that the ventilation state of the working face is normal, so that the coal measure strata are marked with a dangerous precursor.
When the microseismic energy rises greatly and exceeds the microseismic energy threshold, and the gas concentration and the gas emission amount are increased sharply under the condition of normal ventilation, a prominent accident may occur.
If the safety signal is generated, the signal area is a safety area, and the sent control instruction is continuous monitoring multi-parameter data;
if the early warning signal is generated, the signal area is a threat area, the operation in the prominent threat area is described, the sent control instruction is to pay close attention to the change of the occurrence condition of the coal seam, the occurrence condition of the coal seam comprises the thickness, the dip angle and the like of the coal seam, and necessary prominent danger verification work is adopted;
if a dangerous signal is generated, the signal area is a dangerous area, the operation in the protruding dangerous area is described, and the sent control instruction is to stop or delay the operation of the mining equipment so as to slow down the protruding danger;
if the critical signal is generated, the signal area is the critical area, and the sent control instruction is to immediately cut off power and evacuate related personnel.
Meanwhile, when a dangerous signal or an early warning signal is sent out, whether the equipment is in a working state is judged, and when the equipment is in the working state and the degree of abnormality of the working surface is smaller, the working surface abnormality is judged to be caused by the mining equipment.
The functional expression of the localization signal region is as follows:
In the formula, q=0 represents a safety signal, q=1 represents an early warning signal, q=2 represents a danger signal, e (s, g) represents the position of an early warning area obtained through position information s of a sensor network and GIS integrated data g, and h (s, g) represents the position of the danger area obtained through position information s of the sensor network and GIS integrated data g.
It should be explained that the position information of the sensor network can be obtained through the positioning function of the sensor, the GIS integrated data is obtained by integrating the acquired multi-parameter data with the GIS system, and the accurate positioning of the abnormal data is obtained through the geographic and spatial analysis technology.
The method comprises the steps of generating a safety signal, continuously monitoring the change of multi-parameter data, periodically checking and maintaining all sensor networks and monitoring equipment to ensure the accuracy of the multi-parameter data, simultaneously enabling underground workers to continuously observe all standard safety operation programs, starting an early warning response flow, adjusting an operation plan, avoiding high risk areas, adding safety patrol, continuously paying close attention to the data change and field condition of the multi-parameter data, evaluating whether a predicted condition is worsened, stopping operation of all mining equipment after the dangerous signal is generated, closing unnecessary power supplies and equipment to reduce the risk of secondary disasters so as to relieve the outstanding danger, timely notifying underground workers of emergency evacuation after the dangerous signal is generated to ensure that all workers know the latest safety exit and evacuation route, immediately closing all power supplies and equipment, starting an emergency response center, integrating specialized rescue teams and implementing rescue operation.
And S5, visually displaying the signals and the signal areas in the cloud platform, transmitting the signals and the signal areas to management staff and professional analysts, remotely analyzing and judging the prediction effect, and helping the management staff to quickly understand the situation and make decisions.
Strategies for visually displaying signals and signal areas in a cloud platform include:
Constructing a three-dimensional map according to a working surface, marking the position of a sensor network on the three-dimensional map, superposing multi-parameter data on the three-dimensional map, marking the multi-parameter data according to the state of the multi-parameter data, distinguishing signals and signal areas, and if the signals and the signal areas are safety signals and safety areas, normally displaying the three-dimensional map;
if the signals are not secure and the regions are not secure, the three-dimensional map is highlighted.
The method comprises the steps of creating a three-dimensional map through a GIS technology, accurately displaying the layout and key places of a mine, marking the positions of all sensor networks on the three-dimensional map so as to intuitively observe data collection points, superposing multi-parameter data acquired in real time on the three-dimensional map, distinguishing states of the multi-parameter data by using different labels, including normal and abnormal states of the multi-parameter data, and ensuring that the multi-parameter data can be updated in real time so as to reflect the latest monitoring state, when an early warning or danger or emergency occurs in a certain area, highlighting the area on the three-dimensional map, and respectively corresponding to the early warning, danger and emergency situations of the area through yellow, orange and red colors, and clicking corresponding threat areas, danger areas and emergency areas on the three-dimensional map so as to view detailed threat information, danger information and emergency information, including time, possible influence range, corresponding safety measures and emergency degree and the like.
The method comprises the steps of recording the response time from early warning signals and dangerous signals to management staff and staff, judging the prediction effect, simultaneously analyzing the data change of multi-parameter data after the early warning signals, the dangerous signals and the dangerous signals are sent, including the change trend of gas concentration, the change trend of gas emission quantity, the event number of microseismic signals, the released energy and the like, so as to judge the necessity and timeliness of prediction, monitor the early warning signals, the dangerous signals and the process of being transmitted to the management staff and professional analyzers from a cloud platform, give security guidance through a voice playing alarm, obtain real-time picture transmission under mine through a visual camera, ensure the speed and accuracy of information transmission, optimize the transmission path and the transmission bandwidth according to the feedback of the information transmission, and reduce network delay and information loss.
And S6, dynamically adjusting the outstanding early warning model and the outstanding early warning strategy according to the multi-parameter data and the prediction effect, and adapting to the change of the mine environment and continuously optimizing the prediction accuracy.
The method comprises the steps of continuously monitoring the performance of an outstanding early warning model, including indexes such as accuracy, recall rate and F1 score, collecting feedback information of a prediction effect, including the accuracy and timeliness of prediction and response of miners and management staff, inputting new multi-parameter data and event results into a training set of the outstanding early warning model in real time so as to ensure that the outstanding early warning model can adapt to the latest data trend, dynamically adjusting the threshold value of each multi-parameter data according to the prediction effect, reducing false alarm and missing report, evaluating the effectiveness of emergency response in real time, ensuring that actions can be rapidly taken when early warning signals, dangerous signals and emergency signals occur, and improving efficiency and safety.
Example 2
In this embodiment, a computer device is provided, including a memory and a processor, where the memory is configured to store instructions, and the processor is configured to execute the instructions, so that the computer device executes the steps of implementing the above method for identifying and early warning of a coal and gas outburst risk area based on multi-parameter fusion.
Example 3
In this embodiment, a computer readable storage medium is provided, on which a computer program is stored, which when executed implements the steps of the above-mentioned coal and gas outburst risk area identification early warning method based on multi-parameter fusion.
The computer readable storage medium includes various media storing program codes such as a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (10)
1. The coal and gas outburst dangerous area identification and early warning method based on multi-parameter fusion is characterized by comprising the following steps of:
Acquiring multi-parameter data through a sensor network, connecting the sensor network through a monitoring transmission strategy, and transmitting the multi-parameter data to a cloud platform;
extracting characteristics of multi-parameter data transmitted to the cloud platform through a characteristic fusion strategy, generating multi-parameter characteristics, and carrying out fusion processing;
According to the multi-parameter characteristics, an outstanding early warning model and an outstanding early warning strategy are established, and the outstanding early warning model is trained by acquiring historical outstanding events and normal events;
Identifying an abnormal state through the salient early warning model and the salient early warning strategy, generating a signal if the abnormality is identified, positioning the signal to a signal area, and simultaneously sending a control instruction;
Visually displaying the signals and the signal areas in the cloud platform, simultaneously transmitting the signals and the signal areas to management staff and professional analysts, and remotely analyzing and judging the prediction effect;
And dynamically adjusting the outstanding early warning model and the outstanding early warning strategy according to the multi-parameter data and the prediction effect.
2. The coal and gas outburst danger area identification early warning method based on multi-parameter fusion according to claim 1, wherein the sensor network comprises a microseismic sensor, a gas sensor, a wind speed sensor, an equipment start-stop sensor, a power-off controller, a voice playing alarm and a visual camera;
the multi-parameter data comprise microseismic signals, gas concentration, gas emission quantity, wind speed and equipment operation conditions;
acquiring the multi-parameter data through the sensor network, connecting the sensor network through the monitoring transmission strategy, and transmitting the multi-parameter data to a cloud platform, wherein the monitoring transmission strategy comprises:
Integrating the multi-parameter data acquired by the sensor network, synchronizing the multi-parameter data according to a time sequence, compressing the multi-parameter data into data packets, dynamically selecting a transmission path of the data packets according to network conditions, setting a data buffer area at a receiving end of a cloud platform, placing the received data packets into the data buffer area, and dynamically adjusting the transmission bandwidth of the data packets according to data quantity.
3. The method for identifying and pre-warning coal and gas outburst risk areas based on multi-parameter fusion according to claim 2, wherein the transmission paths of the data packets are dynamically selected according to network conditions, and the function expression of the transmission path selection is as follows:
Where t represents a transmission path selected according to a network condition, d represents a network delay, max (d) represents a maximum value of the network delay, min (d) represents a minimum value of the network delay, l represents a network packet loss rate, max (l) represents a maximum value of the network packet loss rate, and min (l) represents a minimum value of the network packet loss rate.
4. The coal and gas outburst risk area identification early warning method based on multi-parameter fusion according to claim 3, wherein the outburst early warning strategy comprises:
Acquiring the event number and the released energy of the microseismic signals, extracting the amplitude and the duration of the microseismic signals, configuring a threshold value, an amplitude threshold value and a duration threshold value, judging the state of the microseismic signals, and if the amplitude of the microseismic signals is greater than or equal to the amplitude threshold value and the duration of the microseismic signals is greater than or equal to the duration threshold value, indicating that a large event occurs and marking the event as abnormal ground stress activity;
if the amplitude of the microseismic signal is larger than a threshold value and the amplitude of the microseismic signal is smaller than the threshold value, indicating that a small event occurs, and marking the small event as abnormal ground stress activity;
And if the amplitude of the microseismic signal is smaller than or equal to a threshold value and the duration of the microseismic signal is smaller than or equal to a duration threshold value, the working face shows that the ground stress activity is normal.
5. The method for identifying and pre-warning coal and gas outburst risk areas based on multi-parameter fusion according to claim 4, wherein the outburst pre-warning strategy further comprises:
acquiring the extreme value of the gas concentration, configuring a concentration safety threshold, judging the state of the gas concentration, and if the extreme value of the gas concentration is greater than or equal to the concentration safety threshold, marking the extreme value as concentration abnormality;
if the extreme value of the gas concentration is smaller than the concentration safety threshold, the working surface displays normal concentration;
acquiring the extreme value of the gas emission quantity, configuring an emission safety threshold, judging the state of the gas emission quantity, and if the extreme value of the gas emission quantity is greater than or equal to the emission safety threshold, marking as abnormal emission;
If the extreme value of the gas emission quantity is smaller than the emission safety threshold value, the working surface shows that the emission is normal;
Acquiring abnormal fluctuation of wind speed, extracting wind speed variation, configuring a wind speed variation threshold value, judging the state of the wind speed, and if the wind speed variation is greater than or equal to the wind speed variation threshold value, marking the abnormal ventilation state;
If the wind speed variation is smaller than the wind speed variation threshold, the working face displays that the ventilation state is normal;
acquiring equipment abnormality, judging the state of equipment, and if the equipment is abnormal, marking the abnormal state as equipment abnormality;
If the equipment is not abnormal, the working face display equipment is normal.
6. The method for identifying and pre-warning a coal and gas outburst risk area based on multi-parameter fusion according to claim 5, wherein the method for identifying the abnormal state by the outburst pre-warning model and the outburst pre-warning strategy comprises the following steps:
Judging the output result of the salient early warning model, if no salient danger is displayed, indicating that the working surface is in a normal state, continuously monitoring the multi-parameter data, and generating a safety signal;
If the abnormal state is displayed, comprehensively identifying the abnormal state through the salient early warning strategy, and if the working surfaces are in the normal state, indicating that the abnormal state is not identified, continuously monitoring the multi-parameter data, and generating a safety signal;
if the working surface has an abnormal state, judging the state of equipment, and if the working surface display equipment is abnormal, identifying the abnormality and generating an early warning signal;
judging the state of the microseismic signal if the working surface display equipment is normal, judging the state of microseismic energy if the ground stress activity of the working surface display equipment is abnormal, and identifying the abnormality if the microseismic energy is abnormal to generate a critical signal;
if the microseismic energy is normal, comprehensively judging the state of the microseismic event and the abnormal situation of the ground stress activity;
Judging the states of the gas concentration, the gas emission quantity and the wind speed if the ground stress activity of the working surface is normal, and identifying the abnormality if the concentration, the emission abnormality and the ventilation state of the working surface are abnormal, so as to generate an early warning signal;
and if the working surface displays concentration abnormality or surging abnormality or ventilation state abnormality, continuously monitoring the multi-parameter data to generate a safety signal.
7. The method for identifying and pre-warning the coal and gas outburst risk area based on multi-parameter fusion according to claim 6, wherein the strategy for identifying the abnormal state further comprises the following steps:
Judging the state of a microseismic event and the state of microseismic energy, extracting the microseismic event frequency and the microseismic energy of a microseismic signal, configuring an event frequency threshold and a microseismic energy threshold, and if the microseismic event frequency is smaller than or equal to the event frequency threshold, indicating that the microseismic event is normal;
if the frequency of the microseismic event is greater than the event frequency threshold, indicating that the microseismic event is abnormal;
if the microseismic energy is smaller than or equal to the microseismic energy threshold, the microseismic energy is normal;
if the microseismic energy is greater than the microseismic energy threshold, then the microseismic energy is abnormal.
8. The method for identifying and pre-warning the coal and gas outburst risk area based on multi-parameter fusion according to claim 7, wherein the strategy for identifying the abnormal state further comprises the following steps:
comprehensively judging the state of the microseism event and the abnormal situation of the ground stress activity, and if a large event occurs and the microseism event is normal, identifying the abnormality and generating a dangerous signal;
If a large event and a microseism event are abnormal, identifying the abnormality and generating a critical signal;
if a small event occurs and the microseism event is normal, identifying abnormality and generating an early warning signal;
Judging the states of the gas concentration, the gas emission quantity and the wind speed if a small event and a microseismic event are abnormal, and identifying the abnormality if the working surface shows that the concentration is abnormal, the emission is abnormal and the ventilation state is normal, so as to generate a critical signal;
If the working surface shows that the concentration is abnormal, the emission is abnormal or the ventilation state is abnormal, the abnormality is identified, and a danger signal is generated.
9. The method for identifying and pre-warning the coal and gas outburst risk area based on multi-parameter fusion according to claim 8, wherein the strategy for identifying the abnormal state further comprises the following steps:
if the safety signal is generated, the signal area is a safety area;
if the early warning signal is generated, the signal area is a threat area;
If the dangerous signal is generated, the signal area is a dangerous area;
And if the critical signal is generated, the signal area is a critical area.
10. The coal and gas outburst risk area identification and early warning method based on multi-parameter fusion according to claim 9, characterized in that the visually displaying the signals and the signal areas in a cloud platform comprises:
constructing a three-dimensional map according to a working surface, marking the position of the sensor network on the three-dimensional map, superposing the multi-parameter data on the three-dimensional map, marking the multi-parameter data according to the state of the multi-parameter data, distinguishing the signal and the signal area, and normally displaying the three-dimensional map if the signal and the signal area are the safety signal and the safety area;
if the security signal and the security zone are not present, the three-dimensional map is highlighted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411324690.6A CN119207023A (en) | 2024-09-23 | 2024-09-23 | Coal and gas outburst hazard zone identification and early warning method based on multi-parameter fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411324690.6A CN119207023A (en) | 2024-09-23 | 2024-09-23 | Coal and gas outburst hazard zone identification and early warning method based on multi-parameter fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119207023A true CN119207023A (en) | 2024-12-27 |
Family
ID=94049315
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411324690.6A Pending CN119207023A (en) | 2024-09-23 | 2024-09-23 | Coal and gas outburst hazard zone identification and early warning method based on multi-parameter fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119207023A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119417243A (en) * | 2025-01-09 | 2025-02-11 | 西安科技大学 | A coal mine fire and gas disaster risk prediction method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101787897A (en) * | 2009-12-30 | 2010-07-28 | 西安西科测控设备有限责任公司 | System and method for predicting coal and gas outburst risk of mine in real time |
| CN105673075A (en) * | 2016-01-13 | 2016-06-15 | 中国矿业大学(北京) | Coal and rock dynamic disaster multi-parameter wireless monitoring comprehensive early-warning technology and method |
| CN111396131A (en) * | 2020-03-30 | 2020-07-10 | 西安西科测控设备有限责任公司 | Device for tracking and early warning composite coal and rock dynamic disasters of mine in real time |
| CN113556384A (en) * | 2021-06-21 | 2021-10-26 | 西安西科测控设备有限责任公司 | Outburst prevention early warning analysis system suitable for mining heading machine |
| CN114810213A (en) * | 2022-05-27 | 2022-07-29 | 煤炭科学技术研究院有限公司 | Multi-source information fusion intelligent early warning method and device for coal and gas outburst |
| US11630227B1 (en) * | 2022-03-21 | 2023-04-18 | Liaoning University | Method and system for recognizing mine microseismic event |
| CN117156167A (en) * | 2023-09-13 | 2023-12-01 | 玉林师范学院 | An adaptive data transmission method and device for a converged transmission system |
-
2024
- 2024-09-23 CN CN202411324690.6A patent/CN119207023A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101787897A (en) * | 2009-12-30 | 2010-07-28 | 西安西科测控设备有限责任公司 | System and method for predicting coal and gas outburst risk of mine in real time |
| CN105673075A (en) * | 2016-01-13 | 2016-06-15 | 中国矿业大学(北京) | Coal and rock dynamic disaster multi-parameter wireless monitoring comprehensive early-warning technology and method |
| CN111396131A (en) * | 2020-03-30 | 2020-07-10 | 西安西科测控设备有限责任公司 | Device for tracking and early warning composite coal and rock dynamic disasters of mine in real time |
| CN113556384A (en) * | 2021-06-21 | 2021-10-26 | 西安西科测控设备有限责任公司 | Outburst prevention early warning analysis system suitable for mining heading machine |
| US11630227B1 (en) * | 2022-03-21 | 2023-04-18 | Liaoning University | Method and system for recognizing mine microseismic event |
| CN114810213A (en) * | 2022-05-27 | 2022-07-29 | 煤炭科学技术研究院有限公司 | Multi-source information fusion intelligent early warning method and device for coal and gas outburst |
| CN117156167A (en) * | 2023-09-13 | 2023-12-01 | 玉林师范学院 | An adaptive data transmission method and device for a converged transmission system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119417243A (en) * | 2025-01-09 | 2025-02-11 | 西安科技大学 | A coal mine fire and gas disaster risk prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190080565A1 (en) | Safety Management System for Worker at Tunnel Construction Site | |
| CN119207023A (en) | Coal and gas outburst hazard zone identification and early warning method based on multi-parameter fusion | |
| CN116480412A (en) | Mine disaster rescue method and device | |
| CN110121053A (en) | A kind of video monitoring method of situ of drilling well risk stratification early warning | |
| CN110685750A (en) | Mine disaster megaevent monitoring and early warning system and method | |
| CN120061926B (en) | Coal and gas outburst hazard early warning method and system in machine-dug working face | |
| CN116966468A (en) | Intelligent fire-fighting equipment supervision system | |
| CN110552740A (en) | local progressive focusing type detection early warning method for coal rock dynamic disaster dangerous area | |
| CN110631682A (en) | A kind of cable tunnel load-bearing body strain safety monitoring method | |
| CN118246632A (en) | Multi-disaster comprehensive prevention and control method based on intelligent mine comprehensive management and control platform | |
| CN119106925A (en) | A coal mine safety supervision method and system | |
| CN114091743A (en) | Mountain forest fire-fighting command decision method and system | |
| CN117423201A (en) | Intelligent fire-fighting state monitoring method and system for restaurant | |
| CN119761816A (en) | Coal mine disaster simulation prediction system based on multidimensional data collection | |
| CN119593806A (en) | Rock tunnel intelligent support system and method adaptive to geological conditions | |
| CN114741431A (en) | Data transmission management system for urban underground comprehensive pipe gallery | |
| CN206532124U (en) | A kind of oil field construction adventure management system | |
| CN118071532A (en) | Intelligent supervision system for mine safety production | |
| CN116739870B (en) | Emergency system management system and method | |
| CN118269068A (en) | Three-dimensional inspection system of inspection robot | |
| CN113565570B (en) | Index setting method for water damage early warning | |
| CN116961237A (en) | Intelligent monitoring system for power distribution safety operation | |
| CN114611944B (en) | Mine goaf risk prevention and control management method, controller and system | |
| CN114564859A (en) | Earthquake early warning system based on intelligent equipment control | |
| CN117198004B (en) | Ground disaster automatic monitoring equipment linkage early warning technology based on intelligent internet of things cradle head |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |