CN117473274B - Mine fire multisource information fusion intelligent early warning system - Google Patents
Mine fire multisource information fusion intelligent early warning system Download PDFInfo
- Publication number
- CN117473274B CN117473274B CN202311812503.4A CN202311812503A CN117473274B CN 117473274 B CN117473274 B CN 117473274B CN 202311812503 A CN202311812503 A CN 202311812503A CN 117473274 B CN117473274 B CN 117473274B
- Authority
- CN
- China
- Prior art keywords
- fire
- risk
- influence
- index
- coefficient
- 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.)
- Active
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 11
- 238000012544 monitoring process Methods 0.000 claims abstract description 59
- 238000004458 analytical method Methods 0.000 claims abstract description 55
- 238000007781 pre-processing Methods 0.000 claims abstract description 24
- 238000011156 evaluation Methods 0.000 claims description 44
- 239000007789 gas Substances 0.000 claims description 25
- 238000000034 method Methods 0.000 claims description 24
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 19
- 239000001301 oxygen Substances 0.000 claims description 19
- 229910052760 oxygen Inorganic materials 0.000 claims description 19
- 239000000779 smoke Substances 0.000 claims description 19
- 239000012634 fragment Substances 0.000 claims description 12
- 230000010354 integration Effects 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 11
- 238000003892 spreading Methods 0.000 claims description 10
- 230000002265 prevention Effects 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 description 3
- 239000003245 coal Substances 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 230000002269 spontaneous effect Effects 0.000 description 2
- 238000009423 ventilation Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000004817 gas chromatography Methods 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
- E21F17/18—Special adaptations of signalling or alarm devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mining & Mineral Resources (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Human Resources & Organizations (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent early warning system for mine fire disaster multi-source information fusion, which comprises a multi-source information acquisition unit, an information preprocessing unit, a core analysis unit and a fire disaster early warning unit, wherein the multi-source information acquisition unit is used for monitoring fire disaster influence information of a mine tunnel, the information preprocessing unit is used for carrying out data conversion, the multi-source information is integrated into standard data which can be uniformly processed, the core analysis unit is used for carrying out deep analysis to obtain influence coefficients of multi-source parameter indexes, then the comprehensive fire disaster risk degree is fused and evaluated, the overall trend of the comprehensive fire disaster risk degree is monitored, the fire disaster prediction risk coefficient of a current fire disaster monitoring point in a certain future time period is obtained, the fire disaster risk early warning unit is used for carrying out refined analysis to judge the risk degree of the fire disaster monitoring point, a fire disaster prediction track is generated, and accordingly, the fire disaster is prevented in advance, and the accurate and reliable fire disaster monitoring early warning management is realized.
Description
Technical Field
The invention relates to the technical field of mine management, in particular to an intelligent early warning system for mine fire disaster multisource information fusion.
Background
Mine fires can be categorized into external and internal fires. External fires are caused by external sources of fire, such as electrical shorts, welding, mechanical friction, gas and dust explosions, and the like. The internal fire is spontaneous combustion fire, and is mainly caused by the oxidation and heat accumulation of coal or other inflammable substances. Spontaneous combustion fires take an important role in mine fires, have a high occurrence frequency, are difficult to extinguish in time, can cause long-time fires, endanger personnel safety and cause a great deal of coal resource loss.
The arrangement of the tunnel in the mine aims at realizing effective utilization of resources, including necessary preparation projects such as ore transportation, ventilation, drainage and the like. The roadway is also used for extracting concentrated gas and using the concentrated gas as gas fuel. However, gas is inflammable and explosive, so that factors such as gas emission amount, air quality, temperature and the like in roadway air need to be measured periodically, and measures such as effective ventilation and fire source inhibition are adopted to prevent fire.
However, the existing mine fire monitoring and early warning technology has some problems, including defects that multisource information is difficult to effectively fuse, data processing is unreliable, pertinence is lacked, fire risks cannot be comprehensively and accurately estimated, fire prediction and risk monitoring are difficult to perform, and the like. Therefore, in order to solve these technical defects and improve the efficiency of fire prevention and treatment, a novel comprehensive, reliable and targeted monitoring and early warning system is needed.
Disclosure of Invention
The invention aims at: the method solves the defects that the existing mine fire monitoring and early warning technology is difficult to effectively fuse multi-source information, unreliable in data processing, low in pertinence and incomplete in analysis and difficult to accurately evaluate fire risks, the multi-source information acquisition unit monitors fire influence information of mine tunnels, the information preprocessing unit performs data conversion, the multi-source information is integrated into standard data which can be uniformly processed, the core analysis unit performs deep analysis and fusion to evaluate comprehensive fire risk degree, further obtains a fire prediction risk coefficient of a current fire monitoring point in a certain future time period, and the fire risk early warning unit performs refined analysis to judge the risk degree of the fire monitoring point, generates a fire spreading prediction track, and accordingly performs advanced fire prevention to realize fine and reliable fire monitoring and early warning management.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the mine fire disaster multi-source information fusion intelligent early warning system comprises a multi-source information acquisition unit, an information preprocessing unit, a core analysis unit and a fire disaster early warning unit, wherein the multi-source information acquisition unit, the information preprocessing unit, the core analysis unit and the fire disaster early warning unit are connected through signals;
the multi-source information acquisition unit is used for acquiring fire information: firstly, a mine roadway distribution three-dimensional model is obtained through three-dimensional modeling, fire monitoring points are set and marked, fire influence information of the fire monitoring points is collected through mobile inspection equipment, and N0 fire monitoring points are preset;
the information preprocessing unit is used for preprocessing fire influence information: the fire condition influence information comprises a plurality of influence parameter indexes, and each parameter index is preprocessed to be converted into standard data;
the core analysis unit is used for carrying out depth analysis on the standard sample data: firstly, establishing a parameter analysis integration model, processing standard data of each parameter index, respectively obtaining influence coefficients of each parameter index, and further obtaining a comprehensive fire evaluation index by combining the influence coefficients of each parameter index; then establishing a fire trend prediction model, and carrying out overall trend analysis on the comprehensive fire evaluation index to obtain a risk prediction evaluation coefficient;
the fire risk early warning unit is used for carrying out refined analysis on risk prediction evaluation coefficients: the risk degree of fire monitoring points is divided and judged, and fire spreading prediction tracks are generated through descending order sequencing, so that fire is prevented in advance, and fine and reliable fire monitoring and early warning management is realized.
Further, the specific process of collecting and preprocessing the fire influence information is as follows:
the fire information comprises light intensity, temperature, gas concentration, smoke content, oxygen ratio, air pressure and air flow rate, and the light intensity, temperature, gas concentration, smoke content, oxygen ratio, air pressure and air flow rate are integrated into an influence parameter index set of the fire information;
establishing a data preprocessing model, and converting the influencing parameter indexes:
setting input data as an influence parameter index A, presetting a standard range of the influence parameter index A as [ Wa1, wa2], and when the data value of the influence parameter index A is in the standard range, indicating that the value of the influence parameter index A is normal, otherwise, indicating that the value of the influence parameter index A is abnormal;
a preset formula is adopted to obtain standard data Ba affecting a parameter index A:wherein, the standard data Ba is parabolic with upward opening, and the standard data Ba is more than or equal to 0; when the influence parameter index A is in the standard range, the standard data Ba of the influence parameter index A is less than or equal to +.>The method comprises the steps of carrying out a first treatment on the surface of the Otherwise, the standard data Ba affecting the parameter index A is greater than +.>；
And substituting the influence parameter indexes of the fire influence information into the data preprocessing model in sequence, so as to obtain corresponding standard data.
Further, the specific process of establishing the parameter analysis integration model is as follows:
inputting standard data Ba affecting a parameter index A into a parameter analysis integration model, setting an information acquisition period Tc, taking the information acquisition period Tc as an abscissa, and taking the standard data Ba as an ordinate to construct a dynamic curve Sa of the standard data Ba-information acquisition period Tc;
presetting a high-risk interval of standard data Ba, extracting a curve segment of a dynamic curve Sa in the high-risk interval, marking the curve segment as a high-risk segment, carrying out targeted analysis on the high-risk segment, and acquiring risk factor coefficients of n0 high-risk segments through the targeted analysis;
acquiring the high risk duration duty ratio ZBa of the dynamic curve Sa through the abscissa of the high risk segment si and the dynamic curve Sa;
the method comprises the steps of comprehensively obtaining an influence coefficient YXa of an influence parameter index A by combining risk factor coefficients of n0 high risk segments of a dynamic curve Sa with a high risk duration ratio ZBa;
and substituting the influence parameter indexes of the fire condition influence information into the parameter analysis integration model in sequence to obtain the influence coefficients of all the parameter indexes, and further obtaining the comprehensive fire condition evaluation index by combining the influence coefficients of all the influence parameter indexes.
Further, the specific process of carrying out targeted analysis on the high-risk fragments is as follows:
presetting n0 high-risk fragments, marking any one high-risk fragment as si, acquiring coordinates and slopes of all points of the high-risk fragment si, presetting n1 points of the high-risk fragment si, marking any one point as P (Xp, yp), and marking the slope of the point P as Kp;
the maximum amplitude Ai of the high-risk segment si is obtained by descending order of the ordinate of the n1 points; average value calculation is carried out on the slopes of n1 points to obtain the average slope of the high risk segment siFurther, obtaining the increase rate fluctuation coefficient sigma i of the high risk segment si through measuring and calculating the standard deviation;
maximum amplitude by high risk segment siAi. Average slopeAnd combining the increased rate fluctuation coefficient sigma i to obtain a risk factor coefficient Xi of the high risk segment si.
Further, the specific process of obtaining the comprehensive fire evaluation index is as follows:
the influence coefficients of light intensity, temperature, gas concentration, smoke content, oxygen ratio, air pressure and air flow rate are respectively marked as a light intensity influence coefficient GQ, a temperature influence coefficient WD, a gas influence coefficient WS, a smoke influence coefficient YW, an oxygen influence coefficient YQ, an air pressure influence coefficient QY and an air flow influence coefficient QL;
firstly, generating a normal state detection index Zct by combining a light intensity influence coefficient GQ, a temperature influence coefficient WD and a gas influence coefficient WS;
then, the smoke influence coefficient YW, the oxygen influence coefficient YQ, the air pressure influence coefficient QY and the air flow influence coefficient QL are combined to generate a fire floating index Zhq;
setting a fire threshold Z0 of the fire floating index Zhq, and judging that the fire occurs in the current area when the fire floating index Zhq reaches the fire threshold Z0; when the fire floating index Zhq is lower than the fire threshold Z0, the combined fire evaluation index HQz is obtained by combining the normal state detection index Zct and the fire floating index Zhq.
Further, the specific process for establishing the fire trend prediction model is as follows:
the information acquisition period Tc is taken as an abscissa, the comprehensive fire evaluation index HQz is taken as an ordinate, and a dynamic curve Sz of the comprehensive fire evaluation index HQz-information acquisition period Tc is constructed;
acquiring all point coordinates and slopes of a dynamic curve Sz, presetting that the dynamic curve Sz has N1 points, marking any point as D (Xd, yd), and marking the slope of the point D as Kd;
obtaining the average increment rate of the dynamic curve Sz by measuring and calculating the average value of the slopes of N1 points；
Obtaining the average fire index of the dynamic curve Sz by averaging the ordinate of N1 pointsFurther solving a standard deviation, and obtaining the integral floating coefficient sigma z of the dynamic curve Sz;
then the average rate of increase through the dynamic curve SzMean fire index->And combining the integral floating coefficient sigma z to obtain a risk prediction assessment coefficient FX.
Further, the specific process of carrying out the refined analysis on the risk prediction evaluation coefficient is as follows:
sequentially acquiring risk prediction evaluation coefficients of N0 fire monitoring points, setting a fire risk interval of the risk prediction evaluation coefficient FX, judging the fire prediction risk degree of the current fire monitoring point, and respectively performing corresponding management operation on the fire monitoring points with different fire prediction risk degrees;
and (3) sequencing the risk prediction evaluation coefficients of the N0 fire monitoring points in descending order from high to low, and sequentially connecting fire monitoring points with the highest risk prediction evaluation coefficients as initial points according to the sequence to generate fire spreading prediction tracks so as to perform fire prevention management measures with different degrees.
In summary, due to the adoption of the technical scheme, the beneficial effects of the invention are as follows:
according to the invention, the fire condition influence information of a mine roadway is monitored through the multi-source information acquisition unit, the data conversion is carried out through the information preprocessing unit, the multi-source information is integrated into standard data which can be processed uniformly, the deep analysis is carried out through the core analysis unit, the fine analysis is carried out on the high-risk interval data of the multi-source parameter indexes, the influence coefficients of the multi-source parameter indexes are obtained, the comprehensive fire condition risk degree is obtained and evaluated through fusion of normal state detection and fire condition floating, the overall trend of the comprehensive fire condition risk degree is monitored, the fire condition prediction risk coefficient of the current fire monitoring point in a future time period is obtained, the risk degree of the fire condition monitoring point is judged through the fine analysis of the fire condition risk early warning unit, the fire condition spreading prediction track is generated, the fire condition is prevented in advance accordingly, and the fine and reliable fire condition monitoring early warning management is realized.
Drawings
FIG. 1 shows a schematic block diagram of the present invention;
fig. 2 shows a schematic flow chart of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
1-2, the mine fire disaster multi-source information fusion intelligent early warning system comprises a multi-source information acquisition unit, an information preprocessing unit, a core analysis unit and a fire disaster early warning unit, wherein the multi-source information acquisition unit, the information preprocessing unit, the core analysis unit and the fire disaster early warning unit are in signal connection;
the working steps are as follows:
s1: the multi-source information acquisition unit acquires fire information: firstly, a mine roadway distribution three-dimensional model is obtained through three-dimensional modeling, fire monitoring points are set and marked, fire influence information of the fire monitoring points is collected through mobile inspection equipment, N0 fire monitoring points are preset, and the specific process is as follows:
the fire information comprises light intensity, temperature, gas concentration, smoke content, oxygen ratio, air pressure and air flow rate, and the light intensity, temperature, gas concentration, smoke content, oxygen ratio, air pressure and air flow rate are integrated into an influence parameter index set of the fire information;
the fire information is measured and collected through the prior art, for example, the light intensity, the temperature, the gas concentration, the smoke content, the oxygen ratio, the air pressure and the air flow rate of the current fire monitoring point are respectively measured and collected through a light intensity sensor, a temperature sensor, an air detector, an optical sensor, a gas chromatography, a barometer and an air flow meter, and real-time data are stored in a multi-source information collecting unit;
s2: the information preprocessing unit preprocesses the fire influence information: the fire condition influence information comprises a plurality of influence parameter indexes, and each parameter index is preprocessed to be converted into standard data;
s2-1: establishing a data preprocessing model, and converting data indexes:
setting input data as an influence parameter index A, presetting a standard range of the influence parameter index A as [ Wa1, wa2], and when the data value of the influence parameter index A is in the standard range, indicating that the value of the influence parameter index A is normal, otherwise, indicating that the value of the influence parameter index A is abnormal;
a preset formula is adopted to obtain standard data Ba affecting a parameter index A:wherein, the standard data Ba is parabolic with upward opening, and the standard data Ba is more than or equal to 0; when the influence parameter index A is in the standard range, the standard data Ba of the influence parameter index A is less than or equal to +.>Indicating that the influence parameter index A is normal; otherwise, the standard data Ba affecting the parameter index A is larger thanThe abnormal condition of the influence parameter index A is indicated, and when the standard data Ba is higher, the abnormal condition degree of the influence parameter index A is higher;
s2-2: substituting the influence parameter indexes of the fire influence information into the data preprocessing model in sequence to obtain corresponding standard data;
the method comprises the steps of respectively presetting standard ranges of light intensity, temperature, gas concentration, smoke content, oxygen ratio, air pressure and air flow rate in a mine tunnel, wherein for example, an influence parameter index A is light intensity, when a light intensity data value in the mine tunnel is collected and is within the standard range of the light intensity, the light intensity is normal, and when the light intensity data value in the mine tunnel is collected and exceeds the standard range of the light intensity, the light intensity is abnormal, fire risks are possible, and the light intensity data is higher when the fire is more serious;
s3: the core analysis unit performs depth analysis on the standard sample data: firstly, establishing a parameter analysis integration model, processing standard data of each parameter index, respectively obtaining influence coefficients of each parameter index, and further obtaining a comprehensive fire evaluation index by combining the influence coefficients of each parameter index; then establishing a fire trend prediction model, and carrying out overall trend analysis on the comprehensive fire evaluation index to obtain a risk prediction evaluation coefficient;
s3-1: the specific process for establishing the parameter analysis integration model is as follows:
s3-101: inputting standard data Ba affecting a parameter index A into a parameter analysis integration model, setting an information acquisition period Tc, taking the information acquisition period Tc as an abscissa, and taking the standard data Ba as an ordinate to construct a dynamic curve Sa of the standard data Ba-information acquisition period Tc;
when the standard data Ba is greater thanThe risk of influencing the parameter index A is indicated, and when the standard data Ba is higher, the risk of influencing the parameter index A is indicated to be higher;
s3-102: presetting a high-risk interval of standard data Ba, extracting a curve segment of a dynamic curve Sa in the high-risk interval, marking the curve segment as a high-risk segment, and carrying out targeted analysis on the high-risk segment:
s3-102-1: n0 high risk segments are preset, any one high risk segment is marked as si,
s3-102-2: acquiring all point coordinates and slopes of the high-risk segment si, presetting that the high-risk segment si has n1 points, marking any point as P (Xp, yp), and marking the slope of the point P as Kp;
wherein, the nearest point of the point P is marked as Q (Xq, yq), the calculation formula of the slope Kp is thatS3-102-3: the maximum amplitude Ai of the high-risk segment si is obtained by descending order of the ordinate of the n1 points;
s3-102-4: average value calculation is carried out on the slopes of n1 points to obtain the average slope of the high risk segment si：/>；
S3-102-5: and further obtaining the increase rate fluctuation coefficient sigma i of the high risk segment si through measuring and calculating the standard deviation:；
s3-102-6: maximum amplitude Ai, average slope through high risk segment siCombining the increased rate fluctuation coefficient sigma i to obtain a risk factor coefficient Xi of the high risk segment si: />Wherein α1, α2 and α3 are the maximum amplitude Ai, the average slope +.>And the weighting factor coefficient of the gain fluctuation coefficient sigma i, wherein alpha 1, alpha 2 and alpha 3 are all larger than 0; when maximum amplitude Ai, average slope +.>And the higher the increase rate fluctuation coefficient sigma i is, the higher the risk factor coefficient Xi is, representing the risk image of the high risk segment siThe higher the degree of ringing;
s3-103: further, through targeted analysis, risk factor coefficients of n0 high-risk fragments are obtained;
s3-104: marking the initial point of the high risk segment si as i0 (Xi 0, yi 0), marking the end point of the high risk segment si as i1 (Xi 1, yi 1), and obtaining the duration of the high risk segment si by the difference of the horizontal coordinates of the initial point i0 and the end point i1：/>Further acquiring the duration of n0 high-risk fragments;
s3-105: the high risk duration duty ratio ZBa of the dynamic curve Sa is obtained by combining the durations of the n0 high risk segments:wherein Xa1 is the abscissa of the end point of the dynamic curve Sa, and Xa0 is the abscissa of the initial point of the dynamic curve Sa;
s3-106: the influence coefficient YXa of the influence parameter index A is comprehensively obtained by combining the risk factor coefficients of n0 high risk segments of the dynamic curve Sa with the high risk duration ratio ZBa:wherein Ya1 is the ordinate of the end point of the dynamic curve Sa, and when the risk factor coefficient is higher, the high risk duration is higher than ZBa, and the ordinate of the end point of the dynamic curve Sa is higher, the influence coefficient YXa of the influence parameter index a is higher, which indicates that the risk influence degree of the influence parameter index a is higher;
s3-2: substituting the influence parameter indexes of the fire condition influence information into the parameter analysis integration model in sequence to obtain the influence coefficients of all the parameter indexes:
the influence coefficients of light intensity, temperature, gas concentration, smoke content, oxygen ratio, air pressure and air flow rate are respectively marked as a light intensity influence coefficient GQ, a temperature influence coefficient WD, a gas influence coefficient WS, a smoke influence coefficient YW, an oxygen influence coefficient YQ, an air pressure influence coefficient QY and an air flow influence coefficient QL;
s3-3: and then, the comprehensive fire evaluation index is obtained by combining the influence coefficients of various influence parameter indexes, and the specific process is as follows:
firstly, a light intensity influence coefficient GQ, a temperature influence coefficient WD and a gas influence coefficient WS are combined to generate a normal state detection index Zct:wherein, v 1, v 2 and v 3 are respectively weight factor coefficients of a light intensity influence coefficient GQ, a temperature influence coefficient WD and a gas influence coefficient WS, and v 1, v 2 and v 3 are all larger than 0; when the light intensity influence coefficient GQ, the temperature influence coefficient WD and the gas influence coefficient WS are higher, the normal state detection index Zct is higher, which indicates that the degree of risk of the fire sign is higher when the mine fire is detected normally;
s3-4: and then the smoke influence coefficient YW, the oxygen influence coefficient YQ, the air pressure influence coefficient QY and the air flow influence coefficient QL are combined to generate the fire floating index Zhq:wherein ω1, ω2, ω3 and ω4 are respectively the weight factor coefficients of the smoke influence coefficient YW, the oxygen influence coefficient YQ, the air pressure influence coefficient QY and the air flow influence coefficient QL, and ω1, ω2, ω3 and ω4 are all larger than 0; the higher the smoke influence coefficient YW, the oxygen influence coefficient YQ, the air pressure influence coefficient QY, and the air flow influence coefficient QL, the higher the fire floating index Zhq;
setting a fire threshold Z0 of a fire floating index Zhq, when the fire floating index Zhq reaches the fire threshold Z0, judging that a fire occurs in a current area, immediately starting a fire extinguishing operation of a mine fire, and when the fire floating index Zhq is higher, indicating that the situation of the fire is judged to be stronger in the process of monitoring the fire;
s3-5: when the fire floating index Zhq is lower than the fire threshold Z0, the integrated fire evaluation index HQz is obtained by combining the normal state detection index Zct and the fire floating index Zhq:wherein, beta 1 and beta 2 are weight factor coefficients of a normal state detection index Zct and a fire floating index Zhq respectively, and beta 1 and beta 2 are both larger than 0; when the normal state detection index Zct and the fire floating index Zhq are higher, the comprehensive fire evaluation index HQz is higher, which indicates that the comprehensive fire evaluation risk degree of the current fire monitoring point is higher;
s3-6: the specific process for establishing the fire trend prediction model is as follows:
s3-601: the information acquisition period Tc is taken as an abscissa, the comprehensive fire evaluation index HQz is taken as an ordinate, and a dynamic curve Sz of the comprehensive fire evaluation index HQz-information acquisition period Tc is constructed;
s3-602: acquiring all point coordinates and slopes of a dynamic curve Sz, presetting that the dynamic curve Sz has N1 points, marking any point as D (Xd, yd), and marking the slope of the point D as Kd;
s3-603: obtaining the average increment rate of the dynamic curve Sz by measuring and calculating the average value of the slopes of N1 points；
S3-604: obtaining the average fire index of the dynamic curve Sz by averaging the ordinate of N1 pointsFurther solving a standard deviation, and obtaining the integral floating coefficient sigma z of the dynamic curve Sz;
s3-605: then the average rate of increase through the dynamic curve SzMean fire index->In combination with the overall floating coefficient σz, a risk prediction assessment coefficient FX is obtained: />Wherein Yz is the ordinate of the end point of the dynamic curve Sz, +>For the predicted time period, the predicted time period is the time difference from the predicted time to the current time; when the average rate of increase of the dynamic curve Sz +.>Mean fire index->And the higher the overall floating coefficient sigma z, the higher the risk prediction evaluation coefficient FX, the higher the predicted risk degree of fire representing the current fire monitoring point, and when the predicted period +.>The longer the time, the more the fire prediction risk of the current fire monitoring point increases;
s4: the fire risk early warning unit performs refined analysis on the risk prediction evaluation coefficient: the risk degree of fire monitoring points is divided and judged, and a fire spreading prediction track is generated through descending order, so that fire is prevented in advance, fine and reliable fire monitoring and early warning management is realized, and the specific process is as follows:
sequentially acquiring risk prediction evaluation coefficients of N0 fire monitoring points, and setting a fire risk interval of the risk prediction evaluation coefficient FX:
the fire disaster prediction risk degree of the current fire disaster monitoring point is judged to be level I when a risk prediction evaluation coefficient FX is positioned in the primary fire disaster risk interval R1; when the risk prediction assessment coefficient FX is positioned in the secondary fire risk interval R2, judging that the fire prediction risk degree of the current fire monitoring point is II; when the risk prediction assessment coefficient FX is positioned in the three-level fire risk interval R3, judging that the fire prediction risk degree of the current fire monitoring point is III level;
corresponding management operations are respectively carried out on fire monitoring points with different fire prediction risk degrees, for example, normalized monitoring is carried out on fire monitoring points with I-level fire prediction risk degrees, fire key prevention monitoring measures are started on fire monitoring points with II-level fire prediction risk degrees, and preparation measures of a fire extinguishing emergency management scheme are started immediately on fire monitoring points with III-level fire prediction risk degrees;
and (3) sequencing the risk prediction evaluation coefficients of the N0 fire monitoring points in descending order, taking the fire monitoring point with the highest risk prediction evaluation coefficient as an initial point, and sequentially connecting the fire monitoring points in order to generate a fire spreading prediction track, so that fire prevention management measures with different degrees are carried out, and fire spreading is effectively restrained by carrying out early prevention management in the area where the fire does not spread.
In summary, the invention monitors the fire condition influence information of the mine tunnel through the multi-source information acquisition unit, performs data conversion through the information preprocessing unit, integrates the multi-source information into standard data which can be processed uniformly, performs deep analysis through the core analysis unit, acquires the influence coefficient of the multi-source parameter index, acquires and combines the normal state detection and the fire floating to integrate and evaluate the comprehensive fire condition risk degree, monitors the overall trend of the comprehensive fire condition risk degree, acquires the fire condition prediction risk coefficient of the current fire monitoring point in a certain future time period, performs refined analysis through the fire condition risk early warning unit, judges the risk degree of the fire monitoring point, generates a fire condition spreading prediction track, prevents the fire condition in advance accordingly, and realizes fine and reliable fire monitoring early warning management.
The interval and the threshold are set for the convenience of comparison, and the size of the threshold depends on the number of sample data and the number of cardinalities set for each group of sample data by a person skilled in the art; as long as the proportional relation between the parameter and the quantized value is not affected. The formula is a formula for acquiring a large amount of data and performing software simulation to obtain the latest real situation, and preset parameters in the formula are set by a person skilled in the art according to the real situation;
the foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (3)
1. A mine fire disaster multisource information fusion intelligent early warning system is characterized in that: the system comprises a multi-source information acquisition unit, an information preprocessing unit, a core analysis unit and a fire risk early warning unit, wherein the multi-source information acquisition unit, the information preprocessing unit, the core analysis unit and the fire risk early warning unit are connected through signals;
the multi-source information acquisition unit is used for acquiring fire information: firstly, a mine roadway distribution three-dimensional model is obtained through three-dimensional modeling, fire monitoring points are set and marked, fire influence information of the fire monitoring points is collected through mobile inspection equipment, and N0 fire monitoring points are preset;
the information preprocessing unit is used for preprocessing fire influence information: the fire condition influence information comprises a plurality of influence parameter indexes, and each parameter index is preprocessed to be converted into standard data;
the core analysis unit is used for carrying out depth analysis on the standard sample data: firstly, establishing a parameter analysis integration model, processing standard data of each parameter index, respectively obtaining influence coefficients of each parameter index, and further obtaining a comprehensive fire evaluation index by combining the influence coefficients of each parameter index; then establishing a fire trend prediction model, and carrying out overall trend analysis on the comprehensive fire evaluation index to obtain a risk prediction evaluation coefficient;
the fire risk early warning unit is used for carrying out refined analysis on risk prediction evaluation coefficients: dividing and judging the risk degree of fire monitoring points, and generating a fire spreading prediction track through descending order sequencing;
the specific process for collecting and preprocessing the fire influence information comprises the following steps:
the fire information comprises light intensity, temperature, gas concentration, smoke content, oxygen ratio, air pressure and air flow rate, and the light intensity, temperature, gas concentration, smoke content, oxygen ratio, air pressure and air flow rate are integrated into an influence parameter index set of the fire information;
establishing a data preprocessing model, and converting the influencing parameter indexes:
setting input data as an influence parameter index A, presetting a standard range of the influence parameter index A as [ Wa1, wa2], and when the data value of the influence parameter index A is in the standard range, indicating that the value of the influence parameter index A is normal, otherwise, indicating that the value of the influence parameter index A is abnormal;
a preset formula is adopted to obtain standard data Ba affecting a parameter index A:
wherein, the standard data Ba is parabolic with upward opening, and the standard data Ba is more than or equal to 0; when the influence parameter index A is in the standard range, the standard data Ba of the influence parameter index A is less than or equal to +.>The method comprises the steps of carrying out a first treatment on the surface of the Otherwise, the standard data Ba affecting the parameter index A is greater than +.>；
Substituting the influence parameter indexes of the fire influence information into the data preprocessing model in sequence to obtain corresponding standard data;
the specific process for establishing the parameter analysis integration model is as follows:
inputting standard data Ba affecting a parameter index A into a parameter analysis integration model, setting an information acquisition period Tc, taking the information acquisition period Tc as an abscissa, and taking the standard data Ba as an ordinate to construct a dynamic curve Sa of the standard data Ba-information acquisition period Tc;
presetting a high-risk interval of standard data Ba, extracting a curve segment of a dynamic curve Sa in the high-risk interval, marking the curve segment as a high-risk segment, carrying out targeted analysis on the high-risk segment, and acquiring risk factor coefficients of n0 high-risk segments through the targeted analysis;
acquiring the high risk duration duty ratio ZBa of the dynamic curve Sa through the abscissa of the high risk segment si and the dynamic curve Sa;
the method comprises the steps of comprehensively obtaining an influence coefficient YXa of an influence parameter index A by combining risk factor coefficients of n0 high risk segments of a dynamic curve Sa with a high risk duration ratio ZBa;
substituting the influence parameter indexes of the fire condition influence information into a parameter analysis integration model in sequence to obtain influence coefficients of all parameter indexes, and further obtaining a comprehensive fire condition evaluation index by combining the influence coefficients of all influence parameter indexes;
the specific process of carrying out targeted analysis on the high-risk fragments comprises the following steps:
presetting n0 high-risk fragments, marking any one high-risk fragment as si, acquiring coordinates and slopes of all points of the high-risk fragment si, presetting n1 points of the high-risk fragment si, marking any one point as P (Xp, yp), and marking the slope of the point P as Kp;
the maximum amplitude Ai of the high-risk segment si is obtained by descending order of the ordinate of the n1 points; average value calculation is carried out on the slopes of n1 points to obtain the average slope of the high risk segment siFurther, obtaining the increase rate fluctuation coefficient sigma i of the high risk segment si through measuring and calculating the standard deviation;
maximum amplitude Ai, average slope through high risk segment siCombining the increased rate fluctuation coefficient sigma i to obtain a risk factor coefficient Xi of the high risk segment si;
the specific process for establishing the fire trend prediction model is as follows:
the information acquisition period Tc is taken as an abscissa, the comprehensive fire evaluation index HQz is taken as an ordinate, and a dynamic curve Sz of the comprehensive fire evaluation index HQz-information acquisition period Tc is constructed;
acquiring all point coordinates and slopes of a dynamic curve Sz, presetting that the dynamic curve Sz has N1 points, marking any point as D (Xd, yd), and marking the slope of the point D as Kd;
obtaining the average increment rate of the dynamic curve Sz by measuring and calculating the average value of the slopes of N1 points；
Obtaining the average fire index of the dynamic curve Sz by averaging the ordinate of N1 pointsFurther solving a standard deviation, and obtaining the integral floating coefficient sigma z of the dynamic curve Sz;
then the average rate of increase through the dynamic curve SzMean fire index->And combining the integral floating coefficient sigma z to obtain a risk prediction assessment coefficient FX.
2. The mine fire disaster multisource information fusion intelligent early warning system according to claim 1, wherein the intelligent early warning system is characterized in that: the specific process for obtaining the comprehensive fire evaluation index is as follows:
the influence coefficients of light intensity, temperature, gas concentration, smoke content, oxygen ratio, air pressure and air flow rate are respectively marked as a light intensity influence coefficient GQ, a temperature influence coefficient WD, a gas influence coefficient WS, a smoke influence coefficient YW, an oxygen influence coefficient YQ, an air pressure influence coefficient QY and an air flow influence coefficient QL;
firstly, generating a normal state detection index Zct by combining a light intensity influence coefficient GQ, a temperature influence coefficient WD and a gas influence coefficient WS;
then, the smoke influence coefficient YW, the oxygen influence coefficient YQ, the air pressure influence coefficient QY and the air flow influence coefficient QL are combined to generate a fire floating index Zhq;
setting a fire threshold Z0 of the fire floating index Zhq, and judging that the fire occurs in the current area when the fire floating index Zhq reaches the fire threshold Z0; when the fire floating index Zhq is lower than the fire threshold Z0, the combined fire evaluation index HQz is obtained by combining the normal state detection index Zct and the fire floating index Zhq.
3. The mine fire disaster multisource information fusion intelligent early warning system according to claim 2, wherein the intelligent early warning system is characterized in that: the specific process for carrying out the refined analysis on the risk prediction evaluation coefficient is as follows:
sequentially acquiring risk prediction evaluation coefficients of N0 fire monitoring points, setting a fire risk interval of the risk prediction evaluation coefficient FX, judging the fire prediction risk degree of the current fire monitoring point, and respectively performing corresponding management operation on the fire monitoring points with different fire prediction risk degrees;
and (3) sequencing the risk prediction evaluation coefficients of the N0 fire monitoring points in descending order from high to low, and sequentially connecting fire monitoring points with the highest risk prediction evaluation coefficients as initial points according to the sequence to generate fire spreading prediction tracks so as to perform fire prevention management measures with different degrees.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311812503.4A CN117473274B (en) | 2023-12-27 | 2023-12-27 | Mine fire multisource information fusion intelligent early warning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311812503.4A CN117473274B (en) | 2023-12-27 | 2023-12-27 | Mine fire multisource information fusion intelligent early warning system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117473274A CN117473274A (en) | 2024-01-30 |
| CN117473274B true CN117473274B (en) | 2024-03-12 |
Family
ID=89629710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311812503.4A Active CN117473274B (en) | 2023-12-27 | 2023-12-27 | Mine fire multisource information fusion intelligent early warning system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117473274B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115392708A (en) * | 2022-08-25 | 2022-11-25 | 爱瑞克(大连)安全技术集团有限公司 | Fire risk assessment and early warning method and system for building fire protection |
| CN115408862A (en) * | 2022-08-31 | 2022-11-29 | 重庆科华安全设备有限责任公司 | Mine fire dynamic disaster scene construction and evolution system and method for VR |
| CN116446953A (en) * | 2023-03-28 | 2023-07-18 | 中煤能源研究院有限责任公司 | Polymorphic display coal spontaneous combustion early warning method based on coal mine underground regional characteristics |
| CN116480412A (en) * | 2023-04-11 | 2023-07-25 | 国能神东煤炭集团有限责任公司 | Mine disaster rescue method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11511143B2 (en) * | 2017-08-30 | 2022-11-29 | Donaphase (Pty) Limited | Mobile fire protection system and method |
-
2023
- 2023-12-27 CN CN202311812503.4A patent/CN117473274B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115392708A (en) * | 2022-08-25 | 2022-11-25 | 爱瑞克(大连)安全技术集团有限公司 | Fire risk assessment and early warning method and system for building fire protection |
| CN115408862A (en) * | 2022-08-31 | 2022-11-29 | 重庆科华安全设备有限责任公司 | Mine fire dynamic disaster scene construction and evolution system and method for VR |
| CN116446953A (en) * | 2023-03-28 | 2023-07-18 | 中煤能源研究院有限责任公司 | Polymorphic display coal spontaneous combustion early warning method based on coal mine underground regional characteristics |
| CN116480412A (en) * | 2023-04-11 | 2023-07-25 | 国能神东煤炭集团有限责任公司 | Mine disaster rescue method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117473274A (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109441547B (en) | Real-time monitoring and early warning system and method for coal and gas outburst of mining working face | |
| CN102117528B (en) | Dynamic feedback type tunnel fire intelligent evacuating and rescuing system based on digitizing technique | |
| CN114485570B (en) | Intelligent monitoring, measuring and early warning system and method for tunnel construction safety | |
| CN112065505B (en) | Goaf coal spontaneous combustion wireless ad hoc network monitoring system and danger dynamic identification early warning method | |
| CN101750152A (en) | Method for representing and diagnosing combustion instability | |
| CN116843174A (en) | Building engineering construction safety supervision system based on data analysis | |
| CN115240357A (en) | Public building fire scene temperature real-time monitoring and predicting system based on distributed optical fiber | |
| CN110552740A (en) | local progressive focusing type detection early warning method for coal rock dynamic disaster dangerous area | |
| CN107676133A (en) | A kind of coal mine down-hole fire monitoring based on Internet of Things | |
| CN106370306A (en) | Rock burst calamity infrared thermal image early warning identification method | |
| CN117473274B (en) | Mine fire multisource information fusion intelligent early warning system | |
| CN108661717B (en) | Spontaneous combustion early warning system for open-air coal | |
| CN113899930A (en) | Monitoring system for mountain fire disasters | |
| CN112924061A (en) | Wireless real-time monitoring system and method for non-uniform settlement stress of natural gas pipeline | |
| CN102354381A (en) | Dynamic prediction analysis technology of gas emission quantity in coal mine | |
| Zhang et al. | Research of synergy warning system for gas outburst based on Entropy-Weight Bayesian | |
| CN116182090A (en) | Gas pipeline accident disaster monitoring and managing method and system based on knowledge graph | |
| CN107860691B (en) | Laser mine coal dust telemetry method based on machine vision technology | |
| CN113107597A (en) | Mine fire transparency monitoring system and method | |
| CN113759219A (en) | Active environmental safety monitoring and early warning device, method and installation scheme | |
| LU500830B1 (en) | Coal Mine Safety Monitoring and Early Warning System | |
| CN111243213B (en) | Electromagnetic signal detection and positioning method for spontaneous combustion high-temperature abnormal area of coal pile or gangue dump | |
| CN117253335A (en) | Intelligent monitoring and early warning system for fuel system | |
| CN116537881A (en) | Fire monitoring and early warning method and system for mine goaf | |
| CN115083123B (en) | Mine coal spontaneous combustion intelligent grading early warning method driven by measured data |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |