CN117314218A - Coal mine water damage real-time early warning method based on big data analysis - Google Patents
Coal mine water damage real-time early warning method based on big data analysis Download PDFInfo
- Publication number
- CN117314218A CN117314218A CN202311085343.8A CN202311085343A CN117314218A CN 117314218 A CN117314218 A CN 117314218A CN 202311085343 A CN202311085343 A CN 202311085343A CN 117314218 A CN117314218 A CN 117314218A
- Authority
- CN
- China
- Prior art keywords
- index
- early warning
- time period
- preset time
- monitoring
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 131
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000003245 coal Substances 0.000 title claims abstract description 34
- 238000007405 data analysis Methods 0.000 title claims abstract description 20
- 238000012544 monitoring process Methods 0.000 claims abstract description 141
- 239000013598 vector Substances 0.000 claims abstract description 75
- 230000002159 abnormal effect Effects 0.000 claims abstract description 12
- 239000011435 rock Substances 0.000 claims description 17
- 239000000126 substance Substances 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000011161 development Methods 0.000 claims description 7
- 238000006073 displacement reaction Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 abstract description 5
- 230000008859 change Effects 0.000 description 28
- 230000008569 process Effects 0.000 description 8
- 150000002500 ions Chemical class 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 239000002243 precursor Substances 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- BVKZGUZCCUSVTD-UHFFFAOYSA-M Bicarbonate Chemical compound OC([O-])=O BVKZGUZCCUSVTD-UHFFFAOYSA-M 0.000 description 1
- BHPQYMZQTOCNFJ-UHFFFAOYSA-N Calcium cation Chemical compound [Ca+2] BHPQYMZQTOCNFJ-UHFFFAOYSA-N 0.000 description 1
- VEXZGXHMUGYJMC-UHFFFAOYSA-M Chloride anion Chemical compound [Cl-] VEXZGXHMUGYJMC-UHFFFAOYSA-M 0.000 description 1
- JLVVSXFLKOJNIY-UHFFFAOYSA-N Magnesium ion Chemical compound [Mg+2] JLVVSXFLKOJNIY-UHFFFAOYSA-N 0.000 description 1
- NPYPAHLBTDXSSS-UHFFFAOYSA-N Potassium ion Chemical compound [K+] NPYPAHLBTDXSSS-UHFFFAOYSA-N 0.000 description 1
- FKNQFGJONOIPTF-UHFFFAOYSA-N Sodium cation Chemical compound [Na+] FKNQFGJONOIPTF-UHFFFAOYSA-N 0.000 description 1
- QAOWNCQODCNURD-UHFFFAOYSA-L Sulfate Chemical compound [O-]S([O-])(=O)=O QAOWNCQODCNURD-UHFFFAOYSA-L 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009172 bursting Effects 0.000 description 1
- 229910001424 calcium ion Inorganic materials 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 229910001425 magnesium ion Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910001414 potassium ion Inorganic materials 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 229910001415 sodium ion Inorganic materials 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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 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
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- 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
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Mining & Mineral Resources (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a coal mine water damage real-time early warning method based on big data analysis. The method comprises the following steps: acquiring an auxiliary monitoring area of an area around a mine, and analyzing the auxiliary monitoring area to acquire an auxiliary judgment index and a direction index; acquiring a predictive monitoring index in a next preset time period; in the next preset time period, all prediction monitoring indexes at the same moment are obtained to form a prediction index vector, and the number of abnormal monitoring indexes is obtained; calculating the similarity of each predictor vector and other predictor vectors to obtain a similarity sequence; acquiring a comprehensive judgment index according to the fluctuation degree and the mean value of the similarity sequence, the number of abnormal monitoring indexes corresponding to the prediction index vector of the similarity sequence, and the mean value and the direction index of the auxiliary judgment index; and carrying out water damage early warning according to the comprehensive judgment index. The invention can improve the accuracy of mine water damage early warning and advance the early warning time.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a coal mine water damage real-time early warning method based on big data analysis.
Background
Coal plays a role in the energy field, is a key ring in China, gradually exhausts along with the exploitation of shallow coal, gradually needs to go deep underground for the exploitation of coal, deepens along with the depth of exploitation, and coal mine water damage becomes a great difficulty in coal mine exploitation, so that the exploitation of coal mine resources is prevented, when serious, the safety of workers is threatened, various mechanical and electromechanical equipment in a mine can cause great loss along with the occurrence of water damage, and the recovery is very difficult, and therefore the coal mine water damage needs to be monitored and the water damage needs to be early warned in real time according to the acquired data.
The existing method for real-time early warning of the coal mine water damage is characterized in that early warning is carried out based on a plurality of independent monitoring indexes, each independent monitoring index is compared with a determined threshold value to judge whether the water damage is early-warned, the relation among different types of monitoring indexes is not considered, and the influence of the change condition of the monitoring indexes and historical data on the early warning of the coal mine water damage is not considered, so that the early warning is inaccurate.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a coal mine water damage real-time early warning method based on big data analysis, which adopts the following technical scheme:
the embodiment of the invention provides a coal mine water damage real-time early warning method based on big data analysis, which comprises the following steps:
acquiring at least two auxiliary monitoring areas of the mine outside the boundary of the mine; acquiring the number of microseismic events, the energy of the microseismic events and the positions of the microseismic events of each auxiliary monitoring area in a preset time period; obtaining auxiliary judgment indexes based on the number of the microseismic events and the microseismic event energy; obtaining a direction index according to the microseismic event position;
at least two monitoring indexes in the mine are collected at each collection time within a preset time period;
constructing a data prediction model corresponding to each monitoring index; inputting one monitoring index in a preset time period into a corresponding data prediction model to obtain a predicted monitoring index in a next preset time period;
in the next preset time period, all prediction monitoring indexes at the same moment are obtained to form prediction index vectors, and the number of abnormal monitoring indexes in each prediction index vector is obtained; calculating the similarity of each predictor vector and other predictor vectors to obtain a similarity sequence; acquiring a comprehensive judgment index according to the fluctuation degree and the mean value of the similarity sequence, the number of abnormal monitoring indexes corresponding to the prediction index vector of the similarity sequence, and the mean value and the direction index of the auxiliary judgment index; and carrying out water damage early warning according to the comprehensive judgment index.
Preferably, at least two auxiliary monitoring areas of the mine are acquired outside the boundary of the mine, comprising:
acquiring a boundary of a mine, and then acquiring a minimum circumcircle of the whole mine area; dividing the minimum circumscribed circle equally through the circle center to obtain a preset number of sectors; and acquiring an auxiliary monitoring area in each sector area, wherein the auxiliary monitoring area is round and tangent to the side of the minimum circumscribing circle and the side of the sector.
Preferably, obtaining the auxiliary judgment index based on the number of microseismic events and the microseismic event energy includes:
the ratio of the number of microseismic events in an auxiliary monitoring area in a preset time period to the time length of the preset time period is a time density index;
the calculation formula of the auxiliary judgment index is:
wherein YP represents an auxiliary judgment index of an auxiliary monitoring area;representing the average value of the number of microseismic events in an auxiliary monitoring area in a preset time period; />Representing an average value of the microseismic event energy of an auxiliary monitoring area; ρ t And (5) representing the time density index of the microseismic event of the auxiliary monitoring area within a preset time period.
Preferably, the obtaining the direction index according to the microseismic event position includes:
acquiring the position of a microseismic event in each auxiliary monitoring area in a preset time period, if the position of the microseismic event of one auxiliary monitoring area appears in the preset time period, continuously changing towards the mine direction, wherein the time of the continuously changing is not less than the preset time length, coding the time as 1, otherwise, coding as 0; wherein the number of codes is equal to the number of auxiliary monitoring areas; all codes are summed to obtain the direction indicator.
Preferably, at least two monitoring indexes in the mine are acquired at each acquisition time within a preset time period, including: the monitoring indexes are water level, water inflow, first chemical index, second chemical index, water hardness, pH value, stress, displacement of rock stratum, microseismic event number, microseismic energy and air humidity in a mine tunnel respectively.
Preferably, constructing a data prediction model corresponding to each monitoring index includes:
constructing a data prediction model and a corresponding loss function, wherein the loss function consists of a first loss function and a second loss function; and taking the historical data of each monitoring index as a training sample, and training the data prediction model based on the loss function by using the training sample.
Preferably, the loss function is:
L＝αL 1 +βL 2 ，
wherein α and β represent a first weight coefficient and a second weight coefficient, respectively; l (L) 1 And L 2 A first loss function and a second loss function, respectively;
the first loss function is a mean square error loss function, and the second loss function is specifically:
wherein L is 2 Representing a second loss function; n represents the number of groups of all samples involved in training; p is p a A pearson correlation coefficient representing the a-th set of real samples and the a-th set of predicted data; e represents a natural constant.
Preferably, calculating the similarity of each predictor vector to other predictor vectors to obtain a similarity sequence includes: the calculation formula of the similarity is specifically as follows
Wherein xs is ij Representing the similarity between the ith predictor vector and the jth predictor vector, wherein the values of i and j are in the range of [0, 24 ]]Is a positive integer and is unequal; YX ij The cosine similarity between the ith predictor vector and the jth predictor vector is represented; d (D) ij Representing the Euclidean distance between the ith predictor vector and the jth predictor vector; gamma denotes the first parameter and has a positive value infinitely close to zero.
Preferably, the calculation formula of the comprehensive judgment index is:
wherein ZP c Representing the comprehensive judgment index corresponding to the c-th prediction index vector; n (N) c A number of monitor indicators representing anomalies in one predictor vector; YP (YP) PJ Representing predicted preset timesAn average value of all auxiliary judgment indexes in a preset time period before the interval; FX represents the direction index corresponding to all auxiliary monitoring areas in the previous preset time period of the predicted preset time period; var c Representing the fluctuation degree, namely the variance, of the similarity sequence corresponding to the c-th predictor vector; g c Representing the average value of the similarity sequence corresponding to the c-th predictor vector; b 1 And b 2 Is a weight coefficient.
Preferably, the water damage early warning is performed according to the comprehensive judgment index, including:
acquiring an early warning threshold, comparing comprehensive judgment indexes corresponding to all prediction index vectors in the next preset time period with the early warning indexes to acquire all moments of the comprehensive judgment indexes which are more than or equal to the early warning threshold, wherein the moment arranged at the forefront in time sequence is the water damage development starting moment; and sending out early warning in the current preset time period to remind workers to take corresponding measures according to the beginning moment of water damage development.
The embodiment of the invention has at least the following beneficial effects: according to the method, a plurality of auxiliary monitoring areas of the mine are obtained outside the boundary of the mine, microseismic data of the auxiliary monitoring areas are further analyzed, auxiliary judging indexes and direction indexes are obtained, the possibility of water damage of the mine is judged in an auxiliary mode according to geological change conditions around the mine, and therefore accuracy of early warning of the water damage of the mine is further enhanced; further, in a preset time period, various monitoring indexes are collected, the indexes are used for predicting the prediction monitoring indexes in the next preset time period, the prediction monitoring indexes at the same moment are used for forming a prediction index vector, the prediction index vectors at other moments are combined for analysis, a similarity sequence is obtained, the relation between various monitoring indexes at one moment and the indexes at other moments is considered, and the early warning accuracy can be improved; then, combining analysis results of the auxiliary judgment index, the direction index and the prediction index vector to obtain a comprehensive judgment index for early warning, and further carrying out early warning, and combining the condition in the mine and the condition in the surrounding area of the mine to enable the early warning to be more accurate; meanwhile, the predicted monitoring data is longer in advance, so that early warning time can be more advanced, and staff can have enough time to deal with the early warning.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for real-time early warning of coal mine water damage based on big data analysis according to an embodiment of the invention.
Detailed Description
In order to further explain the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects thereof of the coal mine water damage real-time early warning method based on big data analysis according to the invention by combining the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a concrete scheme of a coal mine water damage real-time early warning method based on big data analysis, which is specifically described below with reference to the accompanying drawings.
Examples:
the main application scene of the invention is as follows: once water damage occurs in a mine, the mining of the mine can be greatly influenced, and the mine is not easy to recover, so that the working environment is deteriorated, the physical health of workers is influenced, excessive accumulated water can damage various production equipment and facilities, corrosion and rust of the equipment and facilities can be caused, and when the water inflow is large, the life safety problem of mining personnel can be influenced even. Therefore, the data in each mine in the coal mining area needs to be collected in real time so as to achieve the purpose of monitoring the water damage, and the water damage of the mine can be timely pre-warned.
The coal mine water damage is a multi-factor and nonlinear space problem, and the prediction of the coal mine water damage relates to various factors such as hydrogeology, rock mechanics, exploitation conditions and the like, and the factors have complex nonlinear relations, so that accurate analysis is needed to determine the position where the suspected water damage occurs; meanwhile, the existing monitoring of the mine water damage is basically carried out based on various hydrological data of the mine, rock stratum data, data obtained through an electric method and the like, the influence of the change condition of other areas on the mine water damage is not considered, for example, the geological condition of a certain area close to the mine is changed, the mine close to the mine is influenced, but the monitoring index of the mine is not abnormal in a short time, so that the area around the mine is also required to be monitored, and the water damage of each mine is further monitored more finely.
Referring to fig. 1, a flow chart of a coal mine water damage real-time early warning method based on big data analysis provided by the embodiment of the invention is shown, and the method comprises the following steps:
step S1, at least two auxiliary monitoring areas of a mine are obtained outside the boundary of the mine; acquiring the number of microseismic events, the energy of the microseismic events and the positions of the microseismic events of each auxiliary monitoring area in a preset time period; obtaining auxiliary judgment indexes based on the number of microseismic events and the energy of the microseismic events; and obtaining a direction index according to the position of the microseismic event.
In the actual production process, the mine water damage is a process quantity, although the water damage is sudden, a certain evolution process exists before the water damage occurs, in the evolution process, the current hydrological data or other monitoring indexes of the mine may not change obviously, but water burst precursors may exist in surrounding areas of the mine, so that besides the real-time monitoring of the mine, synchronous monitoring is also needed in the surrounding areas of the mine.
Specifically, the boundary of the mine is obtained, the minimum circumscribing circle of the whole mine area is obtained immediately, then the minimum circumscribing circle is equally divided by the circle center to obtain a preset number of sectors, preferably, in the embodiment of the invention, the minimum circumscribing circle is equally divided into 36 sectors, namely 36 sectors taking the circle center of the minimum circumscribing circle as the vertex are obtained, the preset number value is 36, the auxiliary monitoring area is obtained in the sector area, the auxiliary monitoring area is round and tangent to the edge of the minimum circumscribing circle and the edge of the sector, and 36 auxiliary monitoring areas are obtained in total. The minimum circumcircle of the mine area is obtained, then 36 auxiliary monitoring areas are divided, and the mine water damage condition can be monitored in a certain way from multiple directions in an omnibearing manner, so that the mine water damage early warning is more accurate.
Furthermore, since the auxiliary monitoring area data cannot directly reflect the water damage condition of the mine, dynamic data in the mine is also needed to assist for pre-judging.
For an auxiliary monitoring area, pre-judging is needed according to the condition of acquiring data in the area, monitoring through microseismic data is a common means for monitoring mine water damage, and microseismic data monitoring is to monitor water damage by monitoring and collecting microseismic wave information sent out along with rock fracture and dislocation, analyzing and processing and determining information such as the occurrence position, quantity and energy release of microseismic events.
Acquiring the number and the microseismic energy of microseismic events in an auxiliary monitoring area in a space taking the auxiliary monitoring area as the top surface by utilizing a microseismic detector, and further, establishing a three-dimensional coordinate system in the space taking the auxiliary monitoring area as the top surface to acquire the position of the microseismic events so as to acquire the time density index of the microseismic events; it should be noted that, the specific model of the microseism detector can be selected by an implementer according to specific situations, and meanwhile, when the microseism data is acquired, some data are possibly noise data, so that the microseism data need to be noise-reduced to acquire effective microseism data, and then, data such as microseism events are extracted from the microseism data.
The time density index refers to the number of microseismic events occurring in unit time in a preset time period, the calculation method of the time density index in the invention is to use the ratio of the number of all microseismic events in an auxiliary monitoring area in the preset time period to 24 hours in the preset time period, wherein the duration of the preset time period is one day in the embodiment of the invention, the time of collecting data is once per hour, the time of collecting data is the collecting time, the interval between the two collecting time is one hour, the time scale can be adjusted by an implementer according to the actual situation, the water disaster is pre-judged only from the number of the microseismic events, the accuracy is insufficient, the larger the number of the microseismic events is, the higher the density is, the possibility of occurrence of the water disaster is higher, the microseismic events are monitored only from the number of the microseismic events and the microseismic energy, and the accuracy is lower, so that the time density index of the microseismic events is required to be added for characterization.
Acquiring auxiliary judgment indexes according to the number of microseismic events, microseismic energy and time density indexes:
wherein YP represents an auxiliary judgment index of an auxiliary monitoring area;representing the average value of the number of microseismic events in an auxiliary monitoring area in a preset time period; />Representing an average value of the microseismic event energy of an auxiliary monitoring area; ρ t The time density index in the preset time period of the microseismic event of the auxiliary monitoring area is represented, wherein the larger the YP value is, the larger the influence of the area around the mine on the mine water damage is, the larger the probability of the mine water damage is, and the more careful monitoring is needed for the mine. It should be noted that the parameters involved in calculation all need to be first dimensionalized and standardizedEnsuring the consistent dimension.
Within a preset time period, 36 auxiliary judgment indexes can be obtained, and the average value YP of all the auxiliary judgment indexes is obtained PJ Meanwhile, the position of the microseismic event in each auxiliary monitoring area in a preset time period is obtained, if the position of the microseismic event in one auxiliary monitoring area continuously changes towards the mine direction in the preset time period, wherein the continuous change time is not less than the preset time length, preferably, the preset time length is 6 hours, the position of the microseismic event in the auxiliary monitoring area is coded into 1, for example, the integral trend of the position change direction of the microseismic event in the first hour and the second hour in the preset time period is continuously towards the mine, the position change of the microseismic event in the same auxiliary monitoring area continuously trends towards the mine only once, namely, the number of codes is 36, if the position change does not continuously trend towards the mine, the position change is coded into 0, the sum of the codes is obtained, and the direction index is normalized, and the average value and the direction index of the auxiliary judgment index have important effects on the early warning of mine water damage.
And S2, collecting at least two monitoring indexes in the mine at each collection time in a preset time period.
In step S1, the influence of the area around the mine on the water damage early warning of the mine is analyzed, two influence indexes are obtained, further, various monitoring indexes in the mine need to be obtained to monitor the water damage of the mine, and main data comprise water level, water inflow, water temperature, water quality parameter data and data generated by the change of underground rock.
In the research process of the water damage of the coal mine, the water level SW of the water-bearing layer of the mine is found to be quite obvious in the water damage of the mine, so that when the water level of the water-bearing layer is an index abnormal condition, the probability of the water damage of the mine is quite high, and the water level change is quite sensitive to the water damage. Meanwhile, the water inflow of the water holes can be obviously changed in the earlier stage of water damage and when water damage occurs, so that the water inflow SL of the mine has great importance and high sensitivity to the water damage of the mine. The two indexes have a direct relation with the coal mine water damage, so that the effectiveness is high, and when the water damage occurs, the water temperature changes to a certain extent, but the change is not obvious compared with other indexes, so that the water temperature index is abandoned in the embodiment of the invention.
When the indexes are collected, the key positions of the mine tunnel are required to be monitored by using corresponding devices, the key positions are selected and determined by staff according to the actual conditions of the mine, the water level is required to be monitored by drilling, and the water inflow is the total water inflow of the whole mine.
The water quality index refers to the content of chemical components in underground water of a mine, and mainly comprises the content of ions, wherein the main ion components are as follows: sulfate ion, potassium ion, calcium ion, magnesium ion, sodium ion chloride ion and bicarbonate ion; however, in different mines, the variation of various ions in groundwater may be different, so that the ions with more remarkable variation need to be screened for different mines for monitoring. In the embodiment of the invention, two chemical indexes with the largest average concentration change difference of various chemical ions of a water sample sampled by a mine in history data are needed to be used as monitoring indexes and respectively recorded as first chemical indexes HX 1 And a second chemical index HX 2 The method comprises the steps of carrying out a first treatment on the surface of the It is to be noted that, when selecting different ions, the determination needs to be performed according to the actual situation of the mine; furthermore, in the process of sampling and analyzing underground water of a mine, the hardness YD of the underground water is found to be obviously and gradually increased in the water bursting process, and meanwhile, the variation difference of the pH value of the water is also larger, so that the pH value needs to be listed as a monitoring index; regarding to the water quality index to be detected by utilizing a water quality sensor, preferably, the embodiment of the invention adopts a WMP6 multi-parameter water quality sensor to monitor, and the water sample is collected and detected at a key position of a mine tunnel.
Further, in addition to monitoring the water quality change, the rock stratum change needs to be monitored, wherein the rock stratum stress has a great influence on the stability of the water-resisting layer, the rock stratum stress change can reflect the change trend of the rock mass, and the stress has a great influence on the formation of cracks in the rock stratum, so that the stress change needs to be further monitored, the formation of cracks is accompanied with the displacement of the rock stratum, the displacement of the rock stratum needs to be monitored, and the stress F and the displacement S of the rock stratum are collected and detected particularly at a key position by using a stress sensor and a displacement sensor. If the number of microseismic events at the same position is more, the situation that a series of microseismic events occur at the position is indicated, and before water damage occurs, the rock stratum can generate microseismic events, so that the number WS of microseismic events and the microseismic energy E need to be acquired.
Before water damage occurs, the air humidity in the mine tunnel changes, so the air humidity SD in the mine tunnel needs to be collected.
It should be noted that all the obtained data indexes are collectively referred to as monitoring indexes; after the water level SW, the water inflow SL and the first chemical index HX are obtained 1 Second chemical index HX 2 The method comprises the steps of collecting 11 monitoring indexes in total, namely, collecting one monitoring index at one collecting time every hour, collecting 11 monitoring indexes at one collecting time, taking one day as a preset time period, so that the monitoring indexes collected in one preset time period are 24, 11 indexes in total, and taking the time at which one hour ends as a node at the early warning time.
Step S3, constructing a data prediction model corresponding to each monitoring index; inputting one monitoring index in a preset time period into a corresponding data prediction model to obtain a predicted monitoring index in a next preset time period.
Because the water damage needs to be pre-warned in advance, the pre-warning time needs to be advanced, in the existing pre-warning method related to the water damage, most of the pre-warning methods related to the water damage are based on continuous data to predict data at the next moment, and whether pre-warning is performed is judged according to comparison of the data at the next moment and a corresponding threshold value, and the situation of adjacent data before and after the data is not considered, so that the accuracy of pre-warning is not high enough.
In the embodiment of the invention, the predicted data is data in a preset time period, and the water damage is monitored according to the data in the time period.
Specifically, a data prediction model is constructed, wherein the data prediction model refers to a TCN neural network, the TCN neural network is a time domain convolutional neural network model, time sequence data can be predicted in a time domain well, the historical data of various monitoring indexes are used as training samples, the training samples are divided into a training set and a verification set according to the ratio of 7:3, it is required to be explained that each monitoring index needs to correspond to one data prediction model, all data of each monitoring index in each preset time period are used as input data, and output is data in one preset time period.
Specifically, the loss function of the data prediction model is composed of two parts, wherein the first part is a mean square error loss function, and the expression is:
wherein L is 1 Representing a mean square error loss function, denoted as a first loss function; m represents the number of samples; y is i Representing the i-th real sample,representing a predicted value corresponding to the ith real sample;
meanwhile, as the change trend of one group of monitoring indexes is the water damage monitoring indexes of the mine, the similarity degree between the change trend of the monitoring indexes input into the preset time period and the predicted change trend of the monitoring indexes of the next preset time period is also required to be considered; the specific loss function of the second part is specifically:
wherein L is 2 Representing a loss function for monitoring the change trend, and recording the loss function as a second loss function; n represents the number of groups of all the samples involved in training, the data input each time is one group of data, and n represents how many groups of such data are; p is p a Pirson correlation coefficient representing a group a of real samples and output predicted data for constraining variation trend of a group of real samples and output predicted data, L 2 The smaller the converged value, the closer the trend change of the predicted data is to the change of each monitoring index of the mine under real conditions; e represents a natural constant.
The calculation formula of the pearson correlation coefficient is:
wherein ρ is X,Y Pearson correlation coefficients representing two sets of data; sigma (sigma) X Sum sigma Y Respectively representing the standard deviation of each of the two groups of data; cov (X, Y) represents the covariance of the two sets of data.
The loss function of the data training model is: l=αl 1 +βL 2 ；
Wherein α and β represent a first weight coefficient and a second weight coefficient, respectively, and preferably, α and β take a value of 0.5 in the embodiment of the present invention; the actual situation of the data to be predicted may be adjusted by the practitioner.
It should be noted that the mean square error loss function, that is, the first loss function, is trained by constraining the model in terms of values, and the second loss function is trained by constraining the model in terms of the relationship of the trend of the data, so that the model can learn the potential trend change relationship in the data sample.
Inputting the monitoring index of the current preset time period into the data prediction model which is trained correspondingly, and outputting the corresponding predicted monitoring index of the next preset time period, wherein each type of monitoring index corresponds to one data prediction model; the predictive monitoring index of the next preset time period of each monitoring index can be obtained.
Step S4, in the next preset time period, acquiring all prediction monitoring indexes at the same moment to form prediction index vectors, and acquiring the number of abnormal monitoring indexes in each prediction index vector; calculating the similarity of each predictor vector and other predictor vectors to obtain a similarity sequence; acquiring a comprehensive judgment index according to the fluctuation degree and the mean value of the similarity sequence, the number of abnormal monitoring indexes corresponding to the prediction index vector of the similarity sequence, and the mean value and the direction index of the auxiliary judgment index; and carrying out water damage early warning according to the comprehensive judgment index.
In step S3, a predicted monitoring index of a next preset time period corresponding to each monitoring index is obtained, so that water burst can be predicted in advance, and the early warning advance is larger due to shorter dividing time; further, each kind of predicted monitoring index corresponding to the same time within the preset time period is formed into a predicted index vector, and the elements in one predicted index vector are respectively a water level SW, a water inflow SL and a first chemical index HX corresponding to the same time 1 Second chemical index HX 2 Hardness YD, pH, stress F, displacement S of the rock formation, number of microseismic events WS, microseismic energy E, and air humidity SD in the mine tunnel; 24 predictor vectors can be obtained within a preset time period; calculating the similarity of each predictor vector and other predictor vectors respectively, wherein one predictor vector can obtain 23 similarities to form a similarity sequence XS; the similarity is calculated specifically as follows:
wherein xs is ij Representing the similarity between the ith predictor vector and the jth predictor vector, wherein the values of i and j are in the range of [0, 24 ]]Is a positive integer and is unequal; YX ij The cosine similarity between the ith predictor vector and the jth predictor vector is represented; d (D) ij Represent the firstThe Euclidean distance between the i predictor vector and the j-th predictor vector; gamma denotes the first parameter and has a positive value infinitely close to zero. In the process of calculating the similarity, the similarity is calculated not only from the trend, but also from the numerical difference.
Carrying out mathematical statistics on historical data of a mine in a normal state, acquiring an upper limit value and a lower limit value of the numerical value of each monitoring index to acquire a normal fluctuation range of each monitoring index, acquiring the number of elements which are not in the normal fluctuation range in one prediction index vector, namely acquiring the number of abnormal monitoring indexes in one prediction index vector, and marking the number as N c ；
Further, the fluctuation degree and the average value of the similarity sequence corresponding to each predictor vector are obtained, for the fluctuation degree and the average value of the similarity sequence, if the predictor vector corresponding to one moment is basically the same as other predictor vectors, the similarity is higher, and the similarities do not have too large fluctuation, the mine at the moment corresponding to the predictor vector is in a normal state, if the predictor vector corresponding to one moment is quite different from the other predictor vectors, the similarity is lower, and the fluctuation degree between the similarities is quite large, the moment corresponding to the predictor is likely to be the precursor moment of the mine water damage, and then the mine water damage needs to be warned. The degree of fluctuation of the similarity sequence is expressed by the variance of the sequence.
And finally, fusing the acquired various indexes to obtain a comprehensive judgment index, wherein the calculation formula of the comprehensive judgment index is as follows:
wherein ZP c Representing the comprehensive judgment index corresponding to the c-th prediction index vector; n (N) c A number of monitor indicators representing anomalies in one predictor vector; YP (YP) PJ Representing the average value of all auxiliary judgment indexes in the previous preset time period of the predicted preset time period; FX represents a predictive presetsThe direction indexes corresponding to all auxiliary monitoring areas in the previous preset time period of the time period; var c Representing the fluctuation degree, namely the variance, of the similarity sequence corresponding to the c-th predictor vector; g c Representing the average value of the similarity sequence corresponding to the c-th predictor vector; b 1 And b 2 The values of the weight coefficients are respectively 0.75 and 0.35.
Note that N c The number of abnormal elements in the predictor vector corresponding to one time of the prediction, that is, the number of types of monitoring indexes which do not change in the normal range, is larger, the probability of occurrence of water damage in the mine is larger, and the YP is larger PJ And FX represents the surrounding area of the well, the change of the rock stratum, YP PJ The larger the value of the micro-earthquake event is, the more frequent the micro-earthquake occurs in the surrounding area is, the change condition of the micro-earthquake position can be monitored by combining the direction index FX, and if the whole trend is to move towards the mine, the probability of water damage of the mine can be increased to a certain extent; var c And G c The variance and the average value of the similarity sequence are respectively expressed, the larger the variance is, the larger the fluctuation degree of the similarity sequence is, the smaller the average value is, the smaller the similarity between the predictive index vector and other indexes is, and the moment corresponding to the predictive index sequence is likely to be the precursor starting moment before the occurrence of water damage.
When the comprehensive judgment index is calculated, all data needs to be subjected to dimensionality removal, and the total obtained comprehensive judgment index is a normalized result.
Finally, calculating comprehensive judgment indexes corresponding to each acquisition time based on historical data, judging whether early warning is needed or not by combining various monitoring indexes of the mine at the time, and carrying out mathematical statistics to obtain an early warning threshold T; and comparing the comprehensive judgment index corresponding to each prediction index vector in the preset time period with an early warning threshold T, acquiring all moments corresponding to the comprehensive judgment index which is larger than or equal to the early warning threshold T, wherein the forefront moment is the water damage development starting moment, and if the water damage development moment is monitored, early warning is carried out on the working personnel of the mine and the personnel of the master control desk in the current preset time period so as to facilitate the working personnel to carry out further processing according to the water damage development moment.
In addition, it should be noted that, when predicting various monitoring indexes, it is not necessary to start prediction by using a complete one-day monitoring index, in the embodiment of the present invention, "one-day" refers to 24 hours, and not a generalized one-day time, for example, the "one-day" in the embodiment of the present invention may be 13 on the first day to 13 on the second day, and at this time, the early warning time is 13 on the second day, where monitoring is continuous.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (10)
1. The coal mine water damage real-time early warning method based on big data analysis is characterized by comprising the following steps of:
acquiring at least two auxiliary monitoring areas of the mine outside the boundary of the mine; acquiring the number of microseismic events, the energy of the microseismic events and the positions of the microseismic events of each auxiliary monitoring area in a preset time period; obtaining auxiliary judgment indexes based on the number of the microseismic events and the microseismic event energy; obtaining a direction index according to the microseismic event position;
at least two monitoring indexes in the mine are collected at each collection time within a preset time period;
constructing a data prediction model corresponding to each monitoring index; inputting one monitoring index in a preset time period into a corresponding data prediction model to obtain a predicted monitoring index in a next preset time period;
in the next preset time period, all prediction monitoring indexes at the same moment are obtained to form prediction index vectors, and the number of abnormal monitoring indexes in each prediction index vector is obtained; calculating the similarity of each predictor vector and other predictor vectors to obtain a similarity sequence; acquiring a comprehensive judgment index according to the fluctuation degree and the mean value of the similarity sequence, the number of abnormal monitoring indexes corresponding to the prediction index vector of the similarity sequence, and the mean value and the direction index of the auxiliary judgment index; and carrying out water damage early warning according to the comprehensive judgment index.
2. The method for real-time early warning of coal mine water damage based on big data analysis according to claim 1, wherein the step of acquiring at least two auxiliary monitoring areas of the mine outside the boundary of the mine comprises the following steps:
acquiring a boundary of a mine, and then acquiring a minimum circumcircle of the whole mine area; dividing the minimum circumscribed circle equally through the circle center to obtain a preset number of sectors; and acquiring an auxiliary monitoring area in each sector area, wherein the auxiliary monitoring area is round and tangent to the side of the minimum circumscribing circle and the side of the sector.
3. The method for real-time early warning of coal mine water damage based on big data analysis according to claim 1, wherein the obtaining the auxiliary judgment index based on the number of microseismic events and the energy of the microseismic events comprises the following steps:
the ratio of the number of microseismic events in an auxiliary monitoring area in a preset time period to the time length of the preset time period is a time density index;
the calculation formula of the auxiliary judgment index is:
wherein YP represents an auxiliary judgment index of an auxiliary monitoring area;representing the average value of the number of microseismic events in an auxiliary monitoring area in a preset time period; />Representing an average value of the microseismic event energy of an auxiliary monitoring area; ρ t And (5) representing the time density index of the microseismic event of the auxiliary monitoring area within a preset time period.
4. The method for real-time early warning of coal mine water damage based on big data analysis according to claim 1, wherein the obtaining the direction index according to the microseismic event position comprises the following steps:
acquiring the position of a microseismic event in each auxiliary monitoring area in a preset time period, if the position of the microseismic event of one auxiliary monitoring area appears in the preset time period, continuously changing towards the mine direction, wherein the time of the continuously changing is not less than the preset time length, coding the time as 1, otherwise, coding as 0; wherein the number of codes is equal to the number of auxiliary monitoring areas; all codes are summed to obtain the direction indicator.
5. The real-time early warning method for coal mine water damage based on big data analysis according to claim 1, wherein the collecting at least two monitoring indexes in the mine at each collecting time in a preset time period comprises the following steps: the monitoring indexes are water level, water inflow, first chemical index, second chemical index, water hardness, pH value, stress, displacement of rock stratum, microseismic event number, microseismic energy and air humidity in a mine tunnel respectively.
6. The method for real-time early warning of coal mine water damage based on big data analysis according to claim 1, wherein the constructing a data prediction model corresponding to each monitoring index comprises the following steps:
constructing a data prediction model and a corresponding loss function, wherein the loss function consists of a first loss function and a second loss function; and taking the historical data of each monitoring index as a training sample, and training the data prediction model based on the loss function by using the training sample.
7. The real-time early warning method for coal mine water damage based on big data analysis of claim 6, wherein the loss function is:
L＝αL 1 +βL 2 ，
wherein α and β represent a first weight coefficient and a second weight coefficient, respectively; l (L) 1 And L 2 A first loss function and a second loss function, respectively;
the first loss function is a mean square error loss function, and the second loss function is specifically:
wherein L is 2 Representing a second loss function; n represents the number of groups of all samples involved in training; p is p a A pearson correlation coefficient representing the a-th set of real samples and the a-th set of predicted data; e represents a natural constant.
8. The method for real-time early warning of coal mine water damage based on big data analysis according to claim 1, wherein the calculating the similarity between each predictor vector and other predictor vectors to obtain a similarity sequence comprises: the calculation formula of the similarity is specifically as follows
Wherein xs is ij Representing the ith predictionSimilarity of index vector and jth predictor vector, wherein the values of i and j range 0, 24]Is a positive integer and is unequal; YX ij The cosine similarity between the ith predictor vector and the jth predictor vector is represented; d (D) ij Representing the Euclidean distance between the ith predictor vector and the jth predictor vector; gamma denotes the first parameter and has a positive value infinitely close to zero.
9. The real-time early warning method for coal mine water damage based on big data analysis according to claim 1, wherein the calculation formula of the comprehensive judgment index is as follows:
wherein ZP c Representing the comprehensive judgment index corresponding to the c-th prediction index vector; n (N) c A number of monitor indicators representing anomalies in one predictor vector; YP (YP) PJ Representing the average value of all auxiliary judgment indexes in the previous preset time period of the predicted preset time period; FX represents the direction index corresponding to all auxiliary monitoring areas in the previous preset time period of the predicted preset time period; var c Representing the fluctuation degree, namely the variance, of the similarity sequence corresponding to the c-th predictor vector; g c Representing the average value of the similarity sequence corresponding to the c-th predictor vector; b 1 And b 2 Is a weight coefficient.
10. The real-time early warning method for coal mine water damage based on big data analysis according to claim 1, wherein the early warning for water damage according to the comprehensive judgment index comprises the following steps:
acquiring an early warning threshold, comparing comprehensive judgment indexes corresponding to all prediction index vectors in the next preset time period with the early warning indexes to acquire all moments of the comprehensive judgment indexes which are more than or equal to the early warning threshold, wherein the moment arranged at the forefront in time sequence is the water damage development starting moment; and sending out early warning in the current preset time period to remind workers to take corresponding measures according to the beginning moment of water damage development.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311085343.8A CN117314218B (en) | 2023-08-28 | 2023-08-28 | Coal mine water damage real-time early warning method based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311085343.8A CN117314218B (en) | 2023-08-28 | 2023-08-28 | Coal mine water damage real-time early warning method based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117314218A true CN117314218A (en) | 2023-12-29 |
| CN117314218B CN117314218B (en) | 2024-03-22 |
Family
ID=89272742
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311085343.8A Active CN117314218B (en) | 2023-08-28 | 2023-08-28 | Coal mine water damage real-time early warning method based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117314218B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118067200A (en) * | 2024-04-17 | 2024-05-24 | 河北省沧州生态环境监测中心 | River water quality real-time monitoring and early warning system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110580655A (en) * | 2019-09-17 | 2019-12-17 | 山东浪潮通软信息科技有限公司 | Method and system for predicting coal mine water inflow based on LSTM algorithm |
| CN113605984A (en) * | 2021-08-31 | 2021-11-05 | 中煤科工集团重庆研究院有限公司 | Method for judging alarm threshold value for water damage microseismic |
| CN113723595A (en) * | 2021-09-02 | 2021-11-30 | 重庆大学 | Coal mine rock burst intelligent early warning method based on microseismic event quantitative prediction |
| CN114251125A (en) * | 2021-11-23 | 2022-03-29 | 煤炭科学技术研究院有限公司 | Intelligent early warning system for water damage of coal mine |
| US11630227B1 (en) * | 2022-03-21 | 2023-04-18 | Liaoning University | Method and system for recognizing mine microseismic event |
-
2023
- 2023-08-28 CN CN202311085343.8A patent/CN117314218B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110580655A (en) * | 2019-09-17 | 2019-12-17 | 山东浪潮通软信息科技有限公司 | Method and system for predicting coal mine water inflow based on LSTM algorithm |
| CN113605984A (en) * | 2021-08-31 | 2021-11-05 | 中煤科工集团重庆研究院有限公司 | Method for judging alarm threshold value for water damage microseismic |
| CN113723595A (en) * | 2021-09-02 | 2021-11-30 | 重庆大学 | Coal mine rock burst intelligent early warning method based on microseismic event quantitative prediction |
| CN114251125A (en) * | 2021-11-23 | 2022-03-29 | 煤炭科学技术研究院有限公司 | Intelligent early warning system for water damage of coal mine |
| US11630227B1 (en) * | 2022-03-21 | 2023-04-18 | Liaoning University | Method and system for recognizing mine microseismic event |
Non-Patent Citations (2)
| Title |
|---|
| 朱宗奎;徐智敏;孙亚军;: "矿井水害的临突监测指标及预警模型", 煤矿安全, no. 01, 20 January 2014 (2014-01-20) * |
| 靳德武;赵春虎;段建华;乔伟;鲁晶津;李鹏;周振方;李德山;: "煤层底板水害三维监测与智能预警系统研究", 煤炭学报, no. 06, 15 June 2020 (2020-06-15) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118067200A (en) * | 2024-04-17 | 2024-05-24 | 河北省沧州生态环境监测中心 | River water quality real-time monitoring and early warning system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117314218B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117314218B (en) | Coal mine water damage real-time early warning method based on big data analysis | |
| CN110580655A (en) | Method and system for predicting coal mine water inflow based on LSTM algorithm | |
| CN105550943A (en) | Method for identifying abnormity of state parameters of wind turbine generator based on fuzzy comprehensive evaluation | |
| CN115638833B (en) | Monitoring data processing method and system | |
| CN108561119A (en) | A kind of drilling well overflow safety closed-in time prediction technique and system | |
| CN116227365B (en) | Landslide displacement prediction method based on improved VMD-TCN | |
| CN103088803A (en) | Method of distinguishing collapse causing factors of karst collapse | |
| CN115083123B (en) | Mine coal spontaneous combustion intelligent grading early warning method driven by measured data | |
| CN109902265B (en) | Underground early warning method based on hidden Markov model | |
| CN115017206A (en) | Mine CO abnormal disturbance intelligent identification and coal spontaneous combustion early warning value determination method | |
| CN112800688B (en) | Rainfall type landslide displacement trend prediction method based on monitoring data timing diagram self-learning | |
| CN110956155B (en) | Fuzzy clustering identification method for fully mechanized mining face operation procedure based on CO data | |
| CN117312919A (en) | Rock burst early warning method based on BO-CNN-LSTM model | |
| CN107256333A (en) | A kind of Argo profile anomaly detection methods based on prediction and dynamic threshold | |
| CN108154263B (en) | Monitoring and predicting method for natural water resource | |
| CN115019476B (en) | Landslide space-time information monitoring and early warning method based on multi-source information fusion | |
| CN116593051A (en) | Coal wall caving grading early warning method based on coal wall energy index | |
| CN113139681B (en) | Neural network rock burst prediction method based on time sequence data | |
| CN113685166B (en) | Drilling accident early warning method and system | |
| Xue et al. | A method to predict rockburst using temporal trend test and its application | |
| Tan et al. | Development of an optimization model for a monitoring point in tunnel stress deduction using a machine learning algorithm | |
| CN115238365B (en) | Tunnel post-disaster damage early warning method and system based on dynamic deep learning | |
| CN116204760B (en) | Drilling strain data anomaly extraction method based on GRU network | |
| CN118013842A (en) | Early warning method, device, terminal and storage medium for rock burst in well and mine | |
| Wang et al. | Characteristic space-based algorithm for detecting abnormal monitoring data in underground engineering |
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 |