CN111709606A - Mining working face gas emission abnormity early warning method based on big data analysis - Google Patents
Mining working face gas emission abnormity early warning method based on big data analysis Download PDFInfo
- Publication number
- CN111709606A CN111709606A CN202010428668.1A CN202010428668A CN111709606A CN 111709606 A CN111709606 A CN 111709606A CN 202010428668 A CN202010428668 A CN 202010428668A CN 111709606 A CN111709606 A CN 111709606A
- Authority
- CN
- China
- Prior art keywords
- early warning
- abnormal
- gas emission
- data
- variation
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH 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
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
-
- 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
Abstract
The invention relates to a mining working face gas emission abnormity early warning method based on big data analysis, which comprises the following steps: determining monitoring points and monitoring point arrangement; establishing a judgment index of data fluctuation abnormity by using mathematical statistics knowledge; carrying out early warning of abnormal gas emission state and early warning of abnormal gas emission trend based on the index; and judging abnormal gas emission. The invention optimizes a cut-off type alarm mode of abnormal gas emission, fully excavates the data information of the monitoring point, and establishes the exclusive judgment standard and method of abnormal gas concentration emission of the monitoring point; the early warning of abnormal gas emission is divided into state early warning and trend early warning, so that the gas emission characteristics can be comprehensively mastered, and the early warning result is more convincing; the variation coefficient is introduced to judge the abnormal fluctuation of the data, so that the abnormal data can be accurately found, and an effective tool is provided for judging the abnormal gas emission.
Description
The technical field is as follows:
the invention belongs to the technical field of coal mine safety, and particularly relates to a mining working face gas emission abnormity early warning method based on big data analysis.
Background art:
the gas concentration of the mining working face is one of the most important parameters for monitoring and controlling the safety of a coal mine, the monitoring and controlling of the gas concentration of the mining working face is mainly based on the methane concentration overrun acousto-optic alarm or power failure control, and the method for early warning the abnormal gas emission is still rare. Under normal conditions, the concentration of methane in the excavation face and the return air flow thereof is lower than 1%, normal production can be realized, and acousto-optic alarm or power-off locking is carried out when the concentration of methane reaches or exceeds 1%. With the continuous and intensive research on gas accidents, researchers find that abnormal fluctuation of gas concentration is the most obvious expression of coal and gas outburst under the condition that the gas concentration of a mining face and return air flow of the mining face is lower than 1%, and many scholars also directly provide the characteristic of gas concentration change in air flow as an early warning index of coal and gas outburst, so that a plurality of beneficial exploration and attempts are made, and therefore, the problem that attention should be paid to the abnormal gas outburst is due to the safety monitoring of the mining face.
The coal mine safety monitoring system has the following technical requirements (AQ6201-2019) that the coal mine safety monitoring system has the functions of methane concentration overrun acousto-optic alarm and power failure/power restoration control, when the methane concentration of the methane sensors at the tunneling working face and the air return position reaches or exceeds 1.0%, the acousto-optic alarm is given, and when the methane concentration of the air inlet branch air inlet of the tunneling working face reaches or exceeds 0.5%, the acousto-optic alarm is given; when the methane concentration of the methane sensors on the coal face and the return air flow reaches or exceeds 1.0%, the sound and light alarm is carried out, and when the methane concentration of the methane sensors on the air inlet roadway of the coal face reaches or exceeds 0.5%, the sound and light alarm is carried out.
Although the gas concentration is monitored and monitored, the gas concentration monitoring device is in a 'one-time' type alarm mode.
For a mine, mine gas sources mainly comprise gas emission of a mining layer, gas emission of an adjacent layer, gas emission of a coal wall, coal falling gas emission and gas emission of a goaf, wherein the gas emission amount of each gas source is different along with different mining depths, mining methods and geological structures, namely the gas emission amount is different on a stoping surface and a tunneling surface and is influenced by coal falling behaviors and wind currents, the gas emission amount and emission characteristics of the stoping surface, an air inlet lane, a corner return corner and an air return lane are different, the gas emission amount and emission characteristics of a tunneling head and the air return flow are different, and if a cut-and-cut alarm concentration index is adopted, precursor information of coal and gas outburst is ignored, so that 'follow-point planning', namely the gas emission amount and emission characteristics of each monitoring point are followed, and a special gas emission abnormal early warning concentration index is established.
The invention content is as follows:
in view of the shortcomings of the prior art, the present invention contemplates: firstly, determining the positions and the number of gas monitoring points on a mining face according to the requirements of coal mine safety regulations; secondly, dividing the early warning of gas emission abnormity into early warning of gas emission state and early warning of gas emission trend; thirdly, early warning of the gas emission state is to perform real-time early warning on the gas emission, the early warning comprises judgment of gas emission abnormal data and judgment of gas emission abnormal state threat, and a variation coefficient is introduced by utilizing mathematical statistics knowledge to serve as a judgment index of the gas emission abnormal judgment and the gas emission abnormal state threat; the early warning of the gas emission trend takes a production class or a maintenance class as a target point, judges whether the production class or the maintenance class is abnormal by using the coefficient of variation, and sends out a threat early warning of the gas emission abnormal trend; and finally, judging whether the gas emission is abnormal or not by combining the early warning result of the abnormal gas emission state and the early warning result of the trend.
The invention aims to accurately early warn gas emission abnormity of a mining working face, comprehensively master the gas emission characteristic of the mining working face, know the abnormal fluctuation behavior of the gas emission of the mining working face in advance, adopt necessary prevention and treatment measures to eliminate the occurrence of gas accidents in the bud by taking problems as guidance, and aims to provide a fine early warning method for the gas emission abnormity of the mining working face based on big data analysis.
In order to overcome the problem of inaccurate early warning of gas emission, a cut-off type warning mode is optimized, regional early warning of gas early warning is carried out, information of monitoring data of each monitoring point is fully mined, variation coefficients are introduced to judge the gas emission state and trend, early warning information is sent out by combining two early warning results, and the purposes of point-by-point implementation and accurate early warning are achieved.
The invention provides a mining working face gas emission abnormity early warning method based on big data analysis, which comprises the following steps:
(1) determining monitoring points and monitoring point arrangement;
(2) establishing a judgment index of data fluctuation abnormity by using mathematical statistics knowledge;
(3) carrying out early warning of abnormal gas emission state and early warning of abnormal gas emission trend based on the index; the gas emission abnormal state early warning takes the gas emission concentration at intervals as a target point, firstly, whether the current gas concentration is abnormal is judged by using the variation index, and whether the gas emission abnormal state threat early warning is sent out is determined according to the number of abnormal data; the gas emission abnormal trend early warning takes the gas concentration mean value of each production class or maintenance class as a target point, judges whether the gas emission of each class is abnormal or not by using the variation index, sends out gas emission abnormal trend threat early warning, synthesizes the state early warning and trend early warning results, and sends out gas emission abnormal threat early warning or danger early warning signals;
(4) and judging the gas emission abnormity, and synthesizing the state early warning and trend early warning results to send out a gas emission abnormity threat early warning or danger early warning signal.
According to the regulation, in the step (1), methane sensors are arranged on a tunneling head, a tunneling surface return air flow, a stope face stope, a stope face air inlet lane, a return air corner and a stope face return air lane.
In a preferred embodiment of the present invention, in the step (2), the variation coefficient r is introduced as an index for determining whether the data is abnormal:
the judgment indexes are as follows:
when the maximum value of the two numbers belongs to (0, 0.1), no early warning is carried out;
when two number maximum ∈ (0.1, 0.2)]When r is greater than raThen is abnormal, ra＝0.6；
When two number maximum ∈ (0.2, 0.3)]When r is greater than rbThen is abnormal, rb＝0.5；
When two number maximum ∈ (0.3, 0.4)]When r is greater than rcThen is abnormal, rc＝0.33；
When two number maximum ∈ (0.4, 0.5)]When r is greater than rdThen is abnormal, rd＝0.25；
When two number maximum ∈ (0.5, 0.6)]When r is greater than reThen is abnormal, re＝0.2；
When two number maximum ∈ (0.6, 0.7)]When r is greater than rfThen is abnormal, rf＝0.16；
When two number maximum ∈ (0.7, 0.8)]When r is greater than rgThen is abnormal, rg＝0.14；
When two number maximum ∈ (0.8, 0.9)]When r is greater than rhThen is abnormal, rh＝0.12；
When two number maximums ∈ (0.9, 1.0], it is directly flagged as anomalous data.
In a preferred embodiment of the present invention, in the step (3), the determination method of the gas emission abnormal state early warning is to read a data from the database every 30s with a production shift or a maintenance shift as a period, and the first data is recorded as a1The ith is denoted as ai960 data are analyzed in one period, and judgment of abnormal data and early warning of gas emission abnormal states are carried out.
The judgment of the abnormal data specifically comprises the following steps: data aiWhether the abnormality is detected: obtaining (a)i-1，ai) Coefficient of variation r ofiAnd max (a)i-1，ai) Judging max (a)i-1，ai) Belong to (0.1, 0.2)]、(0.2，0.3]、(0.3，0.4]、(0.4，0.5]、(0.5，0.6]、(0.6，0.7]、(0.7，0.8]、(0.8，0.9]、(0.9，1.0]In which interval r is comparediAnd the size of the variation index, if riIf the data is smaller than the variation index, the data is normal, and the calculation is carried out until one production class or one maintenance class is finished; if r isiOnce greater than the variation index or ai∈(0.9,1]Judging the abnormal gas emission;
the judgment of the early warning of the abnormal gas emission state specifically comprises the following steps: when a isiAfter being recognized as anomalous data, the data is expressed as ai-1As a reference point, it is determined whether the data is abnormal within the next 5 minutes, that is, (a) is obtainedi-1，ai+1)，(ai-1，ai+2)，(ai-1，ai+3)，(ai-1，ai+4)，(ai-1，ai+5)，(ai-1，ai+5)，(ai-1，ai+6)，(ai-1，ai+7)，(ai-1，ai+8)，(ai-1，ai+9)，(ai-1，ai+10) And comparing the variation coefficient with the corresponding judgment index, and if the number of the abnormal data is more than 5 within five minutes, sending out a signal for early warning of the inrush abnormal threat.
In a preferred embodiment of the present invention, in the step (3), the method for determining the gas emission abnormal trend early warning is the gas monitoring data mean value X of the ith production shift or overhaul shifti(i > 1) is used as a reference value to obtain (X)i-1，Xi) Coefficient of variation RiDetermining max (X)i-1，Xi) To which interval R belongs, compare RiAnd the size of the variation index, if greater than the variation index or Xi∈(0.9,1]And then sending out a gas emission abnormal trend threat early warning signal.
In a preferred embodiment of the present invention, in the step (4), when the gas emission abnormality is determined, if only the gas emission state threat early warning or the trend threat early warning appears, a gas emission abnormality threat early warning signal is sent out; and on the premise of threat early warning of the gas emission state, when the trend early warning of the shift is the threat state, a gas emission abnormal danger early warning signal is sent out.
The invention has the following positive effects:
(1) optimizing a cut-off alarm mode of abnormal gas emission, fully mining data information of a monitoring point, and establishing a judgment standard and a method for abnormal gas emission of the monitoring point;
(2) the early warning of abnormal gas emission is divided into state early warning and trend early warning, so that the gas emission characteristics can be comprehensively mastered, and the early warning result is more convincing;
(3) the variation coefficient is introduced to judge the abnormal fluctuation of the data, so that the abnormal data can be accurately found, and an effective tool is provided for judging the abnormal gas emission.
Description of the drawings:
FIG. 1 is a schematic view of the structure of monitoring points and the arrangement of the monitoring points of the present invention;
FIG. 2 is a flow chart of the early warning of abnormal gas emission state according to the present invention;
fig. 3 is a flow chart of the gas emission abnormal trend early warning of the present invention.
The specific implementation mode is as follows:
the following detailed description of the preferred embodiments of the present invention, taken in conjunction with the accompanying drawings, will make the advantages and features of the invention more readily understood by those skilled in the art, and thus will more clearly and distinctly define the scope of the invention.
The invention is realized by the following technical scheme.
The invention relates to a mining working face gas emission abnormity early warning method based on big data analysis, which comprises the following steps:
firstly, monitoring points and monitoring point arrangement are determined.
According to the coal mine safety regulation, methane high-low concentration sensors T are arranged on the air return flow of the tunneling head and the tunneling surface1And T2The methane sensors T are arranged on the air inlet lane, the recovery face, the return corner and the recovery face return lane of the recovery face0、T1、T2、T3、T4As shown in fig. 1.
And secondly, establishing an abnormal data judgment standard.
The threshold value of the gas acousto-optic alarm concentration is 1%, the aim is to search an abnormal value in the range of 0-1% relative to the normal fluctuation range of the gas emission, and in order to correctly discriminate the abnormal value, a coefficient of variation r is introduced
When the mean value is unchanged, the larger the data discreteness is, the larger the variation coefficient is;
the coefficient of variation of two adjacent data in 0-1 is calculated by using the formula, and the result is as follows:
as shown in the above table, when the standard deviation is constant, the larger the mean value is, the smaller the coefficient of variation is, which means that the coefficient of variation between large values is small, and the coefficient of variation between small values is large, i.e. the number aiThe coefficient of variation is 0.25 from 0.3 → 0.5, and the number aiThe coefficient of variation is 0.16 from 0.5 → 0.7, and the data is increased by 0.2, but the coefficient of variation is different, so different criteria need to be established for different data.
| (0.05,0.2) | (0.1,0.2) | |
| r | 0.6 | 0.33 |
When the maximum value of two numbers is 0.2 and the other is less than 0.05, the coefficient of variation of two numbers is more than 0.6, therefore, the maximum value ∈ (0.1, 0.2) of two adjacent numbers]When r is greater than raThen is abnormal, ra＝0.6；
| (0.1,0.3) | (0.2,0.3) | |
| r | 0.5 | 0.20 |
When the maximum value of two numbers is 0.3 and the other is less than 0.1, the coefficient of variation of two numbers is greater than 0.5, therefore, the maximum values ∈ (0.2, 0.3) of two adjacent numbers]When r is greater than rbThen is abnormal, rb＝0.5；
| (0.1,0.4) | (0.2,0.4) | (0.3,0.4) | |
| r | 0.6 | 0.33 | 0.14 |
When the maximum value of two numbers is 0.4 and the other is less than 0.2, the coefficient of variation of two numbers is greater than 0.33, therefore, the maximum values ∈ (0.3, 0.4) of two adjacent numbers]When r is greater than rcThen is abnormal, rc＝0.33；
| (0.1,0.5) | (0.2,0.5) | (0.3,0.5) | (0.4,0.5) | |
| r | 0.67 | 0.43 | 0.25 | 0.11 |
When the maximum value of two numbers is 0.5 and the other is less than 0.3, the coefficient of variation of two numbers is greater than 0.25, therefore, the maximum values ∈ (0.4, 0.5) of two adjacent numbers]When r is greater than rdThen is abnormal, rd＝0.25；
| (0.1,0.6) | (0.2,0.6) | (0.3,0.6) | (0.4,0.6) | (0.5,0.6) | |
| r | 0.71 | 0.5 | 0.33 | 0.2 | 0.09 |
When the maximum value of two numbers is 0.6 and the other is less than 0.4, the coefficient of variation of two numbers is greater than 0.2, therefore, the maximum values ∈ (0.5, 0.6) of two adjacent numbers]When r is greater than reThen is abnormal, re＝0.2；
When the maximum value of two numbers is 0.7 and the other is less than 0.5, the coefficient of variation of two numbers is greater than 0.16, therefore, the maximum values ∈ (0.6, 0.7) of two adjacent numbers]When r is greater than rfThen is abnormal, rf＝0.16；
| (0.1,0.8) | (0.2,0.8) | (0.3,0.8) | (0.4,0.8) | (0.5,0.8) | (0.6,0.8) | (0.7,0.8) | |
| r | 0.14 | 0.14 | 0.14 | 0.14 | 0.14 | 0.14 | 0.14 |
When the maximum value of two numbers is 0.8 and the other is less than 0.6, the coefficient of variation of two numbers is greater than 0.14, therefore, the maximum values ∈ (0.7, 0.8) of two adjacent numbers]When r is greater than rgThen is abnormal, rg＝0.14；
| (0.1,0.9) | (0.2,0.9) | (0.3,0.9) | (0.4,0.9) | (0.5,0.9) | (0.6,0.9) | (0.7,0.9) | (0.8,0.9) | |
| r | 0.8 | 0.64 | 0.5 | 0.38 | 0.29 | 0.2 | 0.12 | 0.06 |
When the maximum value of two numbers is 0.9 and the other is less than 0.7, the coefficient of variation of two numbers is greater than 0.12, therefore, the maximum values ∈ (0.8, 0.9) of two adjacent numbers]When r is greater than rhThen is abnormal, rh＝0.12；
When the maximum value of the two numbers belongs to (0, 0.1), no early warning is given, and when the maximum value of the two numbers belongs to (0.9, 1.0), abnormal data are directly marked.
Thirdly, early warning of abnormal gas emission state.
The method for early warning of the gas emission state is described by taking a production shift as an example, the state early warning comprises two parts of abnormal data judgment and gas emission abnormity judgment, and the specific flow is shown in fig. 2.
1) Judging abnormal data:
reading data from the database every 30s, the first data being denoted as a1The ith is denoted as aiThere are 960 data in total for one cycle, and the 960 data are analyzed as follows:
(1) when reading the first data a1When it is, note r1＝0；
(2) When reading the second data a2First, the method determines (a)1，a2) Coefficient of variation r of2And max (a)1，a2) (ii) a Next, max (a) is determined1，a2) Belong to (0.1, 0.2)]、(0.2，0.3]、(0.3，0.4]、(0.4，0.5]、(0.5，0.6]、(0.6，0.7]、(0.7，0.8]、(0.8，0.9]Which interval of time; thirdly, determining a variation index (r) according to the section attributiona、rb、rc、rd、re、rf、rg、rh) (ii) a Finally, the coefficient of variation r is determined2If not, judging a3；
(3) When reading the third data a3First, the method determines (a)2，a3) Coefficient of variation r of3And max (a)2，a3) (ii) a Next, max (a) is determined2，a3) Belong to (0.1, 0.2)]、(0.2，0.3]、(0.3，0.4]、(0.4，0.5]、(0.5，0.6]、(0.6，0.7]、(0.7，0.8]、(0.8，0.9]Which interval of time; thirdly, determining a coefficient of variation index (r) according to the section attributiona、rb、rc、rd、re、rf、rg、rh) (ii) a Finally, the coefficient of variation r is determined3If the coefficient of variation is larger than the coefficient of variation index, if not, judging a4；……；
(4) When reading the ith data aiFirst, the method determines (a)i-1，ai) Coefficient of variation r ofiAnd max (a)i-1，ai) (ii) a Next, max (a) is determinedi-1，ai) Belong to (0.1, 0.2)]、(0.2，0.3]、(0.3，0.4]、(0.4，0.5]、(0.5，0.6]、(0.6，0.7]、(0.7，0.8]、(0.8，0.9]Which interval of time; thirdly, determining a coefficient of variation index (r) according to the section attributiona、rb、rc、rd、re、rf、rg、rh) (ii) a Finally, the coefficient of variation r is determinediIf the coefficient of variation is larger than the coefficient of variation index, if not, judging ai+1(ii) a And when i is larger than 960, judging the whole shift monitoring data to be finished, indicating that the gas concentration in the shift is normal, preparing to enter the next period, and calculating the average value of the shift monitoring data for judging the trend early warning.
2) And (3) judging abnormal gas emission:
when reading aiFound out riGreater than the variation index or ai∈(0.9,1]Then record aiIs 0# abnormal data;
then with ai-1Judging whether the data in the next five minutes is abnormal data or not by taking the data as a reference;
judgment of ai+1Whether it is abnormal data: comparison (a)i-1，ai+1) Whether the coefficient of variation of (a) is greater than the index of variation or ai+1Whether ∈ (0.9, 1)]If yes, record ai+11# abnormal data;
judgment of ai+2Whether it is abnormal data: comparison (a)i-1，ai+2) Whether the coefficient of variation of (a) is greater than the index of variation or ai+2Whether ∈ (0.9, 1)]If yes, record ai+1Bit 2# exception data;
judgment of ai+3Whether it is abnormal data: comparison (a)i-1，ai+3) Whether the coefficient of variation of (a) is greater than the index of variation or ai+3Whether ∈ (0.9, 1)]If yes, record ai+1Is 3# abnormal data;
……
and when 5 abnormal data appear in the following 5min, judging that the gas emission abnormality is a threat level, if the number of the abnormal data in the following 5min is less than 5, not triggering an abnormality early warning signal, and still using the variation coefficients of two adjacent numbers as the primary screening indexes for judging the abnormal data.
Fourthly, early warning of abnormal gas emission trend, and the specific flow is shown in figure 3.
1) Calculating a monitoring data reference value:
the data is processed by a monitoring data object of one production class as follows:
calculating the mean of the data
Obtaining the production class average value of the monitoring point
Will be provided with
Respectively as representative values of production shifts, taking the shift as an observation point, and calculating the variation coefficient R of two adjacent production shiftsi。
2) And (3) judging the flow:
firstly, the mean value of the monitoring data of the ith production shift is recorded as Xi(i > 1) to obtain (X)i-1，Xi) Coefficient of variation RiNext, max (X) is determinedi-1，Xi) Belong to (0.1, 0.2)]、(0.2，0.3]、(0.3，0.4]、(0.4，0.5]、(0.5，0.6]、(0.6，0.7]、(0.7，0.8]、(0.8，0.9]Which interval of time;
thirdly, determining a variation index (r) according to the section attributiona、rb、rc、rd、re、rf、rg、rh)；
Finally, the coefficient of variation R is determinediWhether or not it is greater than the variation index or Xi∈(0.9,1]Is there a If not, continuing to judge downwards, and if so, sending out an early warning signal of abnormal threat of gas emission.
And fifthly, judging the abnormal gas emission.
1) If only gas emission state threat early warning or trend threat early warning occurs, a gas emission abnormal threat early warning signal is sent out, the possibility that the working face has a prominent danger is high, important attention is needed, and management is strengthened;
2) on the premise of threat early warning of a gas emission state, when the trend early warning of the shift is in the threat state, a gas emission abnormal danger early warning signal is sent out, the working face is indicated to have a outburst danger, and operation needs to be stopped and outburst prevention measures need to be taken.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention.
Claims (7)
1. A mining working face gas emission abnormity early warning method based on big data analysis is characterized by comprising the following steps:
(1) determining monitoring points and monitoring point arrangement;
(2) establishing a judgment index of data fluctuation abnormity by using mathematical statistics knowledge;
(3) carrying out early warning of abnormal gas emission state and early warning of abnormal gas emission trend based on the index; the gas emission abnormal state early warning takes the gas emission concentration of every 30s as a target point, firstly, whether the current gas concentration is abnormal is judged by using a variation index, and whether the gas emission abnormal state threat early warning is sent out is determined according to the number of abnormal data; the gas emission abnormal trend early warning takes the gas concentration mean value of each production class or maintenance class as a target point, judges whether the gas emission of each class is abnormal or not by using the variation index, and sends out gas emission abnormal trend threat early warning;
(4) and judging the gas emission abnormity, and synthesizing the state early warning and trend early warning results to send out a gas emission abnormity threat early warning or danger early warning signal.
2. The mining face gas emission abnormity early warning method based on big data analysis as claimed in claim 1, wherein: in the step (1), methane sensors are arranged on a tunneling head, a tunneling surface return air flow, a stope stop.
3. The mining face gas emission abnormity early warning method based on big data analysis as claimed in claim 1, wherein in step (2), a coefficient of variation r is introduced as an index for judging whether the data is abnormal:
the judgment indexes are as follows:
when the maximum value of the two numbers belongs to (0, 0.1), no early warning is carried out;
when two number maximum ∈ (0.1, 0.2)]When r is greater than raThen is abnormal, ra＝0.6；
When two number maximum ∈ (0.2, 0.3)]When r is greater than rbThen is abnormal, rb＝0.5；
When two number maximum ∈ (0.3, 0.4)]When r is greater than rcThen is abnormal, rc＝0.33；
When two number maximum ∈ (0.4, 0.5)]When r is greater than rdThen is abnormal, rd＝0.25；
When two number maximum ∈ (0.5, 0.6)]When r is greater than reThen is abnormal, re＝0.2；
When two number maximum ∈ (0.6, 0.7)]When r is greater than rfThen is abnormal, rf＝0.16；
When two number maximum ∈ (0.7, 0.8)]When r is greater than rgThen is abnormal, rg＝0.14；
When two number maximum ∈ (0.8, 0.9)]When r is greater than rhThen is abnormal, rh＝0.12；
When two number maximums ∈ (0.9, 1.0], the flag is abnormal data.
4. The big data analysis-based gas emission abnormity early warning method for the mining working face according to claim 1, wherein in the step (3),the judgment method for early warning of the abnormal gas emission state takes a production shift or a maintenance shift as a period, reads data from the database every 30s, and records the first data as a1The ith is denoted as ai960 data are analyzed in one period, and judgment of abnormal data and early warning of gas emission abnormal states are carried out.
5. The big data analysis-based gas emission abnormity early warning method for the mining working face according to claim 4,
the judgment of the abnormal data specifically comprises the following steps: data aiWhether the abnormality is detected: obtaining (a)i-1，ai) Coefficient of variation r ofiAnd max (a)i-1，ai) Judging max (a)i-1，ai) Belong to (0.1, 0.2)]、(0.2，0.3]、(0.3，0.4]、(0.4，0.5]、(0.5，0.6]、(0.6，0.7]、(0.7，0.8]、(0.8，0.9]In which interval r is comparediAnd the size of the variation index, if riIf the data is smaller than the variation index, the data is normal, and the calculation is carried out until one production class or one maintenance class is finished; if r isiOnce greater than the variation index or ai∈(0.9,1]Judging the abnormal gas emission;
the judgment of the early warning of the abnormal gas emission state specifically comprises the following steps: when a isiAfter being recognized as anomalous data, the data is expressed as ai-1As a criterion, judging whether the data is abnormal within the next 5 minutes, namely obtaining (a)i-1，ai+1)，(ai-1，ai+2)，(ai-1，ai+3)，(ai-1，ai+4)，(ai-1，ai+5)，(ai-1，ai+5)，(ai-1，ai+6)，(ai-1，ai+7)，(ai-1，ai+8)，(ai-1，ai+9)，(ai-1，ai+10) And comparing the variation coefficient with the corresponding judgment index, and if the number of the abnormal data is more than 5 within five minutes, giving out early warning of the inrush abnormal threat.
6. The big data analysis-based gas emission abnormity early warning method for the mining working face according to claim 1, wherein in the step (3), the judgment method for gas emission abnormity trend early warning is the gas monitoring data mean value X of the ith production class or overhaul classi(i > 1) is used as a reference value to obtain (X)i-1，Xi) Coefficient of variation RiDetermining max (X)i-1，Xi) To which interval R belongs, compare RiAnd if the variation index is larger than the variation index, sending out a gas emission abnormal trend threat early warning signal.
7. The mining face gas emission abnormity early warning method based on big data analysis according to claim 1, wherein in the step (4), if only gas emission state threat early warning or trend threat early warning appears, a gas emission abnormity threat early warning signal is sent out; and on the premise of threat early warning of the gas emission state, when the trend early warning of the shift is the threat state, a gas emission abnormal danger early warning signal is sent out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010428668.1A CN111709606B (en) | 2020-05-20 | 2020-05-20 | Mining working face gas emission abnormal early warning method based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010428668.1A CN111709606B (en) | 2020-05-20 | 2020-05-20 | Mining working face gas emission abnormal early warning method based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111709606A true CN111709606A (en) | 2020-09-25 |
| CN111709606B CN111709606B (en) | 2023-07-18 |
Family
ID=72537544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010428668.1A Active CN111709606B (en) | 2020-05-20 | 2020-05-20 | Mining working face gas emission abnormal early warning method based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111709606B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112282733A (en) * | 2020-10-29 | 2021-01-29 | 中煤科工集团重庆研究院有限公司 | Method for determining coal bed gas abnormity by gas emission quantity characteristic while drilling |
| CN114087023A (en) * | 2021-11-29 | 2022-02-25 | 贵州博益科技发展有限公司 | Method for detecting abnormal gas emission |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101858228A (en) * | 2010-04-27 | 2010-10-13 | 煤炭科学研究总院重庆研究院 | Continuous prediction method of gas emission dynamic characteristic outburst of tunneling surface |
| CN108661715A (en) * | 2018-04-17 | 2018-10-16 | 天地（常州）自动化股份有限公司 | The evaluation method of mine supervision system Gas early warning result |
| CN109711632A (en) * | 2018-12-29 | 2019-05-03 | 辽宁工程技术大学 | A kind of Coal and Gas Outbursts Prediction method based on gas effusion intensity sensitive indicator |
-
2020
- 2020-05-20 CN CN202010428668.1A patent/CN111709606B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101858228A (en) * | 2010-04-27 | 2010-10-13 | 煤炭科学研究总院重庆研究院 | Continuous prediction method of gas emission dynamic characteristic outburst of tunneling surface |
| CN108661715A (en) * | 2018-04-17 | 2018-10-16 | 天地（常州）自动化股份有限公司 | The evaluation method of mine supervision system Gas early warning result |
| CN109711632A (en) * | 2018-12-29 | 2019-05-03 | 辽宁工程技术大学 | A kind of Coal and Gas Outbursts Prediction method based on gas effusion intensity sensitive indicator |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112282733A (en) * | 2020-10-29 | 2021-01-29 | 中煤科工集团重庆研究院有限公司 | Method for determining coal bed gas abnormity by gas emission quantity characteristic while drilling |
| CN114087023A (en) * | 2021-11-29 | 2022-02-25 | 贵州博益科技发展有限公司 | Method for detecting abnormal gas emission |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111709606B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111709606A (en) | Mining working face gas emission abnormity early warning method based on big data analysis | |
| CN102926810B (en) | Forecasting method of coal and gas outburst | |
| CN108984817B (en) | Real-time TBM cutter abrasion loss evaluation method | |
| CN102608286A (en) | Method for monitoring abnormality of gas monitored value of coal mine in real time | |
| CN111721209A (en) | Road tunnel engineering safety real-time monitoring management system based on big data | |
| CN110593954B (en) | Method and device for identifying position abnormality of gas sensor on coal mine coal face | |
| CN112348237A (en) | Dynamic drilling data abnormal trend detection method | |
| CN110348603B (en) | Coal spontaneous combustion danger degree multi-source information fusion early warning method | |
| CN112541480A (en) | Online identification method and system for tunnel foreign matter invasion event | |
| CN115017206A (en) | Mine CO abnormal disturbance intelligent identification and coal spontaneous combustion early warning value determination method | |
| CN111476420A (en) | Method for optimizing early warning index of microseism monitoring rock burst | |
| CN106246226A (en) | The recognition methods that a kind of Mine Gas Gushing is abnormal | |
| CN117495157A (en) | Coal mine goaf karst tunnel full-period construction characteristic information fusion and quality tracing system | |
| CN114582083B (en) | Tunnel monitoring multi-sensor data fusion fire disaster early warning method | |
| CN113685166B (en) | Drilling accident early warning method and system | |
| CN115796573A (en) | Multi-factor safety grade evaluation method for underground excavation section of mine | |
| CN116108339A (en) | Actual measurement data outlier detection and correction method for tunnel boring machine | |
| CN115653691A (en) | Safety early warning method and system based on mine mining data analysis | |
| CN115163195A (en) | Coal mine coal face gas sensor numerical value distortion identification method and system | |
| CN115372932A (en) | System and method for evaluating driveability of monorail crane and predicting roadway risk | |
| CN110991363B (en) | Method for extracting CO emission characteristics of coal mine safety monitoring system in different coal mining processes | |
| CN113586150A (en) | Coal and gas outburst early warning method | |
| CN113159586A (en) | Regional gas extraction standard-reaching evaluation visualization system and method | |
| CN114970921A (en) | Early warning method and system for severity of drilling blockage | |
| CN108319915B (en) | Multi-time-window simplified form identification method for dynamically adjusting rock burst signal threshold |
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 |