CN109268072B - Big data cloud platform for intelligent and real-time prediction and early warning of water inrush disaster of coal mine floor - Google Patents
Big data cloud platform for intelligent and real-time prediction and early warning of water inrush disaster of coal mine floor Download PDFInfo
- Publication number
- CN109268072B CN109268072B CN201811365704.3A CN201811365704A CN109268072B CN 109268072 B CN109268072 B CN 109268072B CN 201811365704 A CN201811365704 A CN 201811365704A CN 109268072 B CN109268072 B CN 109268072B
- Authority
- CN
- China
- Prior art keywords
- coal mine
- water
- bottom plate
- floor
- 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.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 191
- 239000003245 coal Substances 0.000 title claims abstract description 162
- 238000012544 monitoring process Methods 0.000 claims abstract description 77
- 238000004458 analytical method Methods 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims description 15
- 239000011083 cement mortar Substances 0.000 claims description 8
- 238000012806 monitoring device Methods 0.000 claims description 8
- 238000009434 installation Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 6
- 238000005553 drilling Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 6
- 239000011148 porous material Substances 0.000 claims description 6
- 239000011435 rock Substances 0.000 claims description 6
- 239000003818 cinder Substances 0.000 claims description 5
- 238000011002 quantification Methods 0.000 claims description 5
- 230000004888 barrier function Effects 0.000 claims description 4
- 239000004743 Polypropylene Substances 0.000 claims description 3
- 229910000278 bentonite Inorganic materials 0.000 claims description 3
- 239000000440 bentonite Substances 0.000 claims description 3
- SVPXDRXYRYOSEX-UHFFFAOYSA-N bentoquatam Chemical compound O.O=[Si]=O.O=[Al]O[Al]=O SVPXDRXYRYOSEX-UHFFFAOYSA-N 0.000 claims description 3
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- -1 polypropylene Polymers 0.000 claims description 3
- 229920001155 polypropylene Polymers 0.000 claims description 3
- 238000005056 compaction Methods 0.000 claims description 2
- 230000002787 reinforcement Effects 0.000 claims description 2
- 238000007789 sealing Methods 0.000 claims description 2
- 239000003795 chemical substances by application Substances 0.000 claims 1
- 238000003825 pressing Methods 0.000 claims 1
- 239000002893 slag Substances 0.000 claims 1
- 238000012549 training Methods 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 11
- 238000003860 storage Methods 0.000 abstract description 6
- 238000005065 mining Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 239000003673 groundwater Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000035699 permeability Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000002002 slurry Substances 0.000 description 1
Images
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Excavating Of Shafts Or Tunnels (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
The invention belongs to the field of intelligent prediction, and relates to a big data cloud platform for intelligent and real-time prediction and early warning of water inrush disasters of a coal mine floor. And (4) adopting Hadoop programming model package design distributed storage. The distributed storage of data adopts a high-reliability, high-performance, column-oriented and scalable distributed database HBase. And a computing engine Spark is adopted to realize clustering analysis and prediction early warning algorithm. The real-time display and sending of the prediction result are realized by adopting a high-throughput distributed publish-subscribe message system. The method stores the data monitored by the coal mine floor monitoring Internet of things system of the working face floor to be predicted and early-warned and the water inrush situation of the working face floor into a historical coal mine floor monitoring Internet of things monitoring database. On the basis, the intelligent and real-time prediction model and the early warning threshold value of the coal mine floor water inrush disaster are corrected.
Description
Technical Field
The invention belongs to the field of intelligent prediction, and relates to a big data cloud platform for intelligent and real-time prediction and early warning of water inrush disasters of a coal mine floor.
Background
Shallow coal resources in China are gradually exhausted, deep water inrush disasters frequently occur, and safe production urgently needs a coal mine water inrush disaster related risk identification, prediction and early warning method and a big data application system. According to the invention, by researching the coal mine water inrush disaster big data intelligent prediction and early warning key technology, a cloud platform-based coal mine water inrush disaster prevention and control related prediction and early warning method and a big data application system are provided, coal mine water inrush risk judgment and early warning precision are improved, and safe production is guaranteed. By depending on the service market foundation of the prior art, the method can be popularized and applied in mines threatened by coal mine water inrush in China, value-added services such as coal mine water inrush disaster prevention and control big data mining analysis are provided for service mines, and water inrush prevention decision support is provided for government governing departments such as coal prisoner.
Disclosure of Invention
The invention provides a big data cloud platform for prediction and early warning of water inrush disasters of a coal mine floor, which is characterized in that a big data computing method is adopted, the type of the coal mine floor is determined according to the floor engineering geological conditions of a coal mine working face to be predicted, and then the intelligent and real-time prediction and early warning of the water inrush disasters of the coal mine floor are realized according to the working face monitoring data so as to prevent the water inrush disasters of the coal mine floor.
The technical scheme of the invention is as follows:
a big data cloud platform for intelligent and real-time prediction and early warning of water inrush disasters of a coal mine floor is realized by means of Ariiyun, self-built cloud platforms and the like. And designing and realizing distributed storage of data by adopting a Hadoop programming model packet. The distributed storage of data adopts a high-reliability, high-performance, column-oriented and scalable distributed database HBase. And a computing engine Spark is adopted to realize clustering analysis and prediction early warning algorithm. Real-time display and transmission of predictive results is achieved using a high throughput distributed publish-subscribe messaging system (Kafka).
A big data cloud platform for intelligent and real-time prediction and early warning of water inrush disasters of coal mine floors comprises a coal mine floor geological classification system, a coal mine floor monitoring Internet of things system and a real-time display and prediction early warning system.
The coal mine floor monitoring internet of things system transmits the acquired information to the coal mine floor geological classification system, and after data processing, the coal mine floor geological classification system transmits the data to the real-time display, prediction and early warning system.
The coal mine bottom plate geological classification system comprises a coal mine bottom plate geological information acquisition module, a coal mine bottom plate geological information quantification processing module, a coal mine bottom plate geological information database and a coal mine bottom plate geological clustering analysis module.
The acquisition module of coal mine bottom plate geological information realizes collecting engineering geological and hydrogeological information of the bottom plate of the coal mine, and the information comprises spatial distribution of the bottom plate of the coal mine, water-rich property of a water-containing layer, water head pressure of the water-containing layer, thickness of a water-resisting layer and the like.
The coal mine bottom plate geological information quantification processing module realizes the following processing on the information acquired by the coal mine bottom plate geological information acquisition module:
(1) for water-rich X in aquifer1Judging and grading: the water-rich property of the coal seam floor water-bearing layer is a material basis for water inrush, and the water-rich degree and the supply conditions of the coal seam floor water-bearing layer determine the water inrush quantity of the floor water inrush and whether the water inrush point can burst water for a long time. The factors influencing the water-rich property mainly comprise unit water inflow and permeability coefficient, and the water-rich property in the aquifer is divided into five grades, namely
(2) To aquifer head pressure X2And (4) judging: the water head pressure of the floor aquifer is a precondition for water inrush of the floor, and the higher the pressure of the confined water is, the easier the water inrush is under the same geological conditions of the floor of the coal bed.
(3) Thickness X to water barrier layer3And (4) judging: and when other geological conditions are the same, the larger the thickness of the water-resisting layer is, the stronger the water resistance is.
(4) Water conductivity to fracture X4And (3) grading: the fracture is divided into 5 types of water-rich fracture, water guide fracture, water storage fracture, water-free fracture and water blocking fracture according to the hydrogeological characteristics of the fracture, the water conductivity of the fracture is reduced in sequence, and the contribution to water inrush of the bottom plate is reduced in sequence.
(5) According to the lithologic combination X of the coal seam floor5And (3) grading: different lithologies have different mechanical strength, and impedance ability also is different, divides coal mine bottom plate rock mass lithology combination as follows:
the coal mine bottom plate geological information database is a distributed database which is designed based on a Hadoop programming model packet and has high reliability, high performance, orientation and scalability, and data processed quantitatively by the coal mine bottom plate geological information quantitative processing module is stored in the distributed database.
The coal mine bottom plate geological clustering analysis module adopts a clustering analysis algorithm realized based on a computing engine Spark to analyze data of a coal mine bottom plate geological information database, and the coal mine bottom plate is divided into four bottom plate types: the bottom plate is easy to cause water inrush disasters, difficult to cause water inrush disasters, and extremely difficult to cause water inrush disasters.
The coal mine bottom plate monitoring Internet of things system comprises an Internet of things monitoring device, a data transmission module and a coal mine bottom plate monitoring Internet of things monitoring database.
The monitoring device of the Internet of things comprises a micro-seismic sensor, a water pressure sensor, a drilling stress meter, a water flow sensor, a water quality analysis sensor and the like, and is further supplemented or screened according to field requirements and engineering construction conditions.
The sensing settings are as follows:
① microseismic sensor, which comprises removing residual water and coal cinder from the borehole by air gun, feeding the sensor to the bottom of the borehole by mounting tool to make the bottom of the sensor fully coupled with the rock wall and firmly attached, pouring cement mortar into the borehole, covering the sensor with mud, and withdrawing the mounting tool when the cement mortar begins to solidify and filling the borehole with cement mortar.
② Water pressure sensor, the invention adopts a pore water pressure gauge, drills a downward hole with a depth of 1.5m, sends the pore water pressure gauge to the designed depth by adopting a pressing-in method, backfills a bentonite mud ball with a depth of more than 1 m, finally seals the hole, and the specific installation requirement is properly adjusted according to the requirement of the sensor product.
③ borehole stress meter, which is to drill a round hole with a depth of 8m in the direction vertical to the coal wall by a drill bit with a diameter of 55mm and place the borehole stress meter in the hole.
④ Water flow sensor is arranged in the drain ditch of the working surface, and its coordinate is measured independently after the installation.
⑤ Water quality analysis sensor installed in the drainage ditch of working surface, and its coordinate is measured after the installation.
The data transmission module adopts a cable to connect the Internet of things monitoring device with the coal mine bottom plate monitoring Internet of things monitoring database, and the specific mode is as follows:
a, protecting a sleeve for a laid cable, wherein the sleeve is made of a PPR (polypropylene random) pipe material with the thickness of 3.5mm and is made of 2.0MPa, and a bidirectional joint is adopted between a line pipe and a line pipe for reinforcement;
and b, performing landfill protection on the laid cable, putting the sheathed cable into a 30cm wire groove, and performing landfill compaction to protect the cable by using coal cinder.
The coal mine bottom plate monitoring Internet of things monitoring database is a distributed database which is designed based on a Hadoop programming model packet and has high reliability, high performance, array orientation and flexibility. Real-time monitoring data such as microseismic event coordinates and related seismic source parameters, water pressure data, water flow data, stress data and water quality analysis data monitored by the coal mine baseboard monitoring Internet of things system, and information data such as spatial distribution of a working face, spatial coordinates of a microseismic sensor, a borehole stress meter, a water pressure sensor, a water flow sensor and a water quality analysis sensor are stored in the distributed database.
The real-time display, prediction and early warning system comprises a historical coal mine bottom plate monitoring Internet of things monitoring database, a prediction and early warning algorithm module and a real-time display module.
The prediction and early warning algorithm module analyzes data in the historical coal mine bottom plate monitoring Internet of things monitoring database and displays the data through the real-time display module.
The historical coal mine bottom plate monitoring Internet of things monitoring database is a distributed database which is designed based on a Hadoop programming model packet and has high reliability, high performance, array orientation and scalability.
The data stored in the historical coal mine baseboard monitoring Internet of things monitoring database has two types: the first is collected coal mine floor monitoring data in a coal mine floor geological classification system, and the part of data comprises microseismic event coordinates and relevant seismic source parameters, water pressure data, water flow data, stress data, real-time monitoring data of water quality analysis data, and information of space coordinates of a microseismic sensor, a water pressure sensor, a water flow sensor, a stress sensor and a water quality analysis sensor, water inrush condition of a working face floor and the like. And secondly, the mined coal mine bottom plate monitoring data provided with the coal mine bottom plate monitoring Internet of things system and the water inrush situation of the bottom plate of the working face are acquired.
The prediction early warning algorithm module is a deep neural network algorithm realized based on a calculation engine Spark. Data in an internet of things monitoring database are monitored through historical coal mine floors of four floor types of the coal mine floors, and intelligent and real-time prediction models and early warning threshold values of water inrush disasters of the coal mine floors corresponding to the four floor types are trained through a deep neural network algorithm realized based on a computing engine Spark. Therefore, the intelligent and real-time prediction early warning model of the coal mine floor water inrush disaster corresponding to different floor geological types is obtained.
The invention has the beneficial effects that:
(1) the method comprises the steps of collecting a large amount of real-time monitoring data such as domestic engineering geology and hydrogeology information of coal mine bottom plate spatial distribution, aquifer water-rich property, aquifer water head pressure, thickness of a water-resisting layer, thickness of the water-resisting layer and the like, microseismic event coordinates and related seismic source parameters, water pressure data, water flow data, stress data, water quality analysis data and the like, and information such as spatial coordinates of a microseismic sensor, a water pressure sensor, a water flow sensor, a stress sensor, a water quality analysis sensor and the like, water inrush situation of a working face bottom plate and the like, and establishing a coal mine bottom plate geological information database and a historical coal mine bottom.
(2) The coal mine bottom plate is divided into a bottom plate which is easy to cause water inrush disaster, a bottom plate which is difficult to cause water inrush disaster and a bottom plate which is extremely difficult to cause water inrush disaster through information such as water-rich water content of the aquifer of the coal mine bottom plate, water head pressure of the aquifer, thickness of the water-resisting layer and thickness of the water-resisting layer in a geological information database of the coal mine bottom plate, and a corresponding classification method is established.
(3) Data in the Internet of things monitoring database are monitored through historical coal mine floors of four floor types, and intelligent coal mine floor water inrush disaster, real-time prediction models and early warning threshold values corresponding to the four floor types are trained through a deep neural network algorithm realized based on a computing engine Spark. Therefore, the intelligent and real-time prediction early warning model of the coal mine floor water inrush disaster corresponding to different floor geological types is obtained.
(4) Analyzing the floor geological conditions of the early warning working face to be predicted, acquiring the coal mine floor geological information, carrying out quantitative processing on the coal mine floor geological information, and determining the geological type of the floor of the early warning working face to be predicted according to a cluster analysis algorithm realized by a computing engine Spark.
(5) A coal mine bottom plate monitoring Internet of things system is established on a bottom plate of a to-be-predicted early warning working face, real-time monitoring is carried out on the coal mine bottom plate monitoring Internet of things system, and the coal mine bottom plate monitoring Internet of things system is stored in a coal mine bottom plate monitoring Internet of things monitoring database.
(6) The method comprises the steps of selecting a proper model, monitoring data in an internet of things monitoring database based on a coal mine floor, adopting a proper coal mine floor water inrush disaster intelligence and real-time prediction model and an early warning threshold value, conducting real-time prediction and early warning on a working face disaster, and displaying and releasing a monitoring result and a prediction and early warning result in real time.
(7) And after the mining of the pre-prediction early-warning working face is finished, carrying out quantitative processing on the pre-prediction early-warning working face and storing the pre-prediction early-warning working face into a coal mine bottom plate geological information database. And storing the data monitored by the coal mine floor monitoring Internet of things system of the working face floor to be predicted and early-warned and the water inrush situation of the working face floor to a historical coal mine floor monitoring Internet of things monitoring database. On the basis, the intelligent and real-time prediction model and the early warning threshold value of the coal mine floor water inrush disaster are corrected.
Drawings
Fig. 1 is a schematic content diagram included in geological information of a coal mine floor.
FIG. 2 is a schematic diagram of a data warehouse architecture of a water inrush big data platform.
FIG. 3 is a schematic diagram of an online analysis and processing framework for water inrush big data.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
The first step is as follows: and arranging a coal mine bottom plate monitoring internet of things system on a bottom plate of a coal mining working face to be predicted.
The coal mine bottom plate monitoring Internet of things system comprises a micro-seismic sensor, a water pressure sensor, a water flow sensor, a stress sensor, a signal cable and a mine data acquisition center.
The micro-seismic sensor, the water pressure sensor, the water flow sensor and the stress sensor are respectively connected with a mine data acquisition center through signal cables, and the mine data acquisition center is used for monitoring micro-seismic signals, water pressure changes, flow changes, water quality changes and stress changes in the mining process of a coal mining working face to be predicted.
The method for establishing the monitoring Internet of things system comprises the following steps:
1.1 sensor arrangement
The distribution of the micro-shock, water pressure, water flow, water quality and stress sensors has different requirements on the drilling position, depth and inclination angle, and a mine ground measuring department measures the coordinates of the orifices and the bottoms of the drilling holes and calculates the coordinates of the sensors to form a report.
1.1.1 installing the microseismic sensor: firstly, residual water and coal cinder in the drill hole are removed by using an air gun. And then, the microseismic sensor is sent to the bottom of the drill hole, so that the bottom of the microseismic sensor is fully coupled and firmly attached to the rock wall. Then, a proper amount of cement mortar is slowly poured into the drill hole, the micro-vibration sensor is covered by the slurry, and the drill hole is filled with the cement mortar.
1.1.2 installation of water pressure sensor: the water pressure sensor adopts a pore water pressure gauge, a downward hole with the depth of 1.5m is drilled, the pore water pressure gauge is conveyed into the downward hole by adopting a pressing-in method, a bentonite mud ball with the depth of more than 1 m is backfilled, and finally hole sealing is carried out.
1.1.3 stress sensor installation: the stress sensor is arranged in a hole with the depth of 8m in the direction vertical to the coal wall by adopting a borehole stressometer.
1.1.4 installation of water flow sensor: the water flow sensor is fixed in the drainage ditch of the working surface and measures the coordinates of the water flow sensor independently.
1.2 Signal Cable laying
In order to ensure smooth signals between the mine data acquisition center and the sensor, the following measures are adopted to protect the cable:
1.2.1, sleeve protection is carried out on the signal cable, the sleeve is made of a PPR (polypropylene random) pipe material with the thickness of 3.5mm and the pipe is reinforced by a bidirectional knot;
1.2.2, burying and protecting the laid signal cables, putting the sheathed cables into a 30-32 cm wire groove, and burying and compacting by using coal cinder to protect the cables.
The second step is that: data analysis
And carrying out quantitative processing on the collected coal mine bottom plate geological information to form a coal mine bottom plate geological information data warehouse. And analyzing the coal mine floor geological information data warehouse by adopting a big data calculation method to determine the classification of coal mine floor geology.
The big data is calculated by a clustering analysis method;
the coal mine floor geological information quantification processing method comprises the following steps:
(1) water-rich property of the water-containing layer: the water-rich property of the coal seam floor water-bearing layer is a material basis for water inrush, and the water-rich degree and the supply conditions of the coal seam floor water-bearing layer determine the water inrush quantity of the floor water inrush and whether the water inrush point can burst water for a long time. The factors influencing the water-rich property mainly comprise unit water inflow and permeability coefficient, and the water-rich property in the aquifer is divided into five grades, namely
(2) Aquifer head pressure: the water head pressure of the floor aquifer is a precondition for water inrush of the floor, and under the condition that geological conditions of the coal seam floor are similar, the higher the pressure of the confined water is, the easier the water inrush is.
(3) Thickness of the water barrier layer: and when other geological conditions are similar, the larger the thickness of the water-resisting layer is, the stronger the water resistance is.
(4) Fracture water conductivity: the fracture can be divided into 5 types such as water-rich fracture, water guide fracture, water storage fracture, water-free fracture, water blocking fracture and the like according to the hydrogeological characteristics of the fracture, the water conductivity of the fracture is reduced in sequence, and the contribution to water inrush of the bottom plate is reduced in sequence.
(5) Combining the lithology of the coal seam floor: different lithologies have different mechanical strength, and impedance ability also is different, divides the combination of the lithologies of the common bottom plate rock mass of the coal mine as follows:
the third step: and determining the geological type of the bottom plate of the working face of the coal mine to be predicted by adopting a big data calculation method, namely pattern recognition, according to the geological condition of the bottom plate of the working face of the coal mine to be predicted according to the collected data information. And forming a coal mine bottom plate monitoring information data warehouse by using the monitoring data of the same coal mine working face bottom plate geological type.
The construction method of the coal mine baseboard monitoring information data warehouse comprises the following steps: monitoring data such as stress, water pressure, water quantity, water quality, micro-seismic and the like are sorted into different data marts according to different analysis themes, a groundwater gushing data warehouse is constructed on a Hadoop big data platform, and the online analysis and processing of groundwater gushing data of different data marts and different themes are realized, as shown in figure 3.
The fourth step: a big data calculation method, namely a deep neural network is adopted to learn the coal mine floor monitoring information data warehouse, and a coal mine floor water inrush disaster intelligent and real-time prediction early warning model corresponding to the floor geological type is trained. Therefore, the intelligent and real-time prediction early warning model of the coal mine floor water inrush disaster corresponding to different floor geological types is obtained.
Claims (3)
1. The intelligent real-time prediction early warning big data cloud platform for the water inrush disaster of the coal mine floor is characterized by comprising a coal mine floor geological classification system, a coal mine floor monitoring Internet of things system and a real-time display and prediction early warning system;
the coal mine floor monitoring Internet of things system transmits the acquired information to a coal mine floor geological classification system, and after data processing, the coal mine floor geological classification system transmits the data to a real-time display, prediction and early warning system;
the coal mine bottom plate geological classification system comprises a coal mine bottom plate geological information acquisition module, a coal mine bottom plate geological information quantification processing module, a coal mine bottom plate geological information database and a coal mine bottom plate geological clustering analysis module;
the acquisition module of the geological information of the coal mine bottom plate realizes the collection of the engineering geological and hydrogeological information of the bottom plate of the coal mine, and the information comprises the spatial distribution of the coal mine bottom plate, the water-rich property of an aquifer, the water head pressure of the aquifer and the thickness of a water barrier;
the coal mine bottom plate geological information quantification processing module realizes the following processing on the information acquired by the coal mine bottom plate geological information acquisition module:
a water-rich property X of aquifer1Judging and grading: the water-rich property of the coal seam floor aquifer is the material basis of water inrush, and the water-rich property in the aquifer is divided into five grades, namely
b to aquifer head pressure X2And (4) judging: the water head pressure of the bottom plate aquifer is a precondition for water inrush of the bottom plate, and under the condition that the geological conditions of the coal bed bottom plate are the same, the higher the pressure of the confined water is, the easier the water inrush is;
c thickness X of water barrier layer3And (4) judging: when other geological conditions are the same, the larger the thickness of the water-resisting layer is, the stronger the water resistance is;
d pair fracture conductivity X4And (3) grading: according to the characteristics of hydrogeology, the water-retaining agent is divided into five types, namely water-rich fracture, water-guiding fracture, water-storing fracture, water-free fracture and water-retaining fracture, wherein the water-guiding performance of;
e according to the lithologic combination X of the coal seam floor5And (3) grading: the lithology combination of the coal mine floor rock mass is divided as follows:
the coal mine bottom plate geological information database is a distributed database designed based on a Hadoop programming model packet, and data processed quantitatively by the coal mine bottom plate geological information quantitative processing module is stored in the distributed database;
the coal mine bottom plate geological clustering analysis module adopts a clustering analysis algorithm realized based on a computing engine Spark to analyze data of a coal mine bottom plate geological information database, and the coal mine bottom plate is divided into four bottom plate types: the bottom plate is easy to cause water inrush disasters, difficult to cause water inrush disasters and extremely difficult to cause water inrush disasters;
the coal mine bottom plate monitoring Internet of things system comprises an Internet of things monitoring device, a data transmission module and a coal mine bottom plate monitoring Internet of things monitoring database;
the monitoring device of the Internet of things comprises a micro-seismic sensor, a water pressure sensor, a drilling stress meter, a water flow sensor and a water quality analysis sensor; the data transmission module is used for connecting the Internet of things monitoring device with a coal mine bottom plate monitoring Internet of things monitoring database by adopting a cable;
the coal mine baseboard monitoring Internet of things monitoring database is a distributed database designed based on a Hadoop programming model packet; storing real-time monitoring data monitored by a coal mine bottom plate monitoring Internet of things system and spatial coordinate information data of a working face space distribution, a micro-seismic sensor, a borehole stressometer, a water pressure sensor, a water flow sensor and a water quality analysis sensor in a distributed database;
the real-time display, prediction and early warning system comprises a historical coal mine bottom plate monitoring Internet of things monitoring database, a prediction and early warning algorithm module and a real-time display module;
the prediction early warning algorithm module analyzes data in the historical coal mine floor monitoring Internet of things monitoring database and displays the data through the real-time display module;
the historical coal mine bottom plate monitoring Internet of things monitoring database is a distributed database designed based on a Hadoop programming model packet;
the data stored in the historical coal mine baseboard monitoring Internet of things monitoring database has two types: firstly, collected coal mine floor monitoring data in a coal mine floor geological classification system comprise microseismic event coordinates and relevant seismic source parameters, water pressure data, water flow data, stress data, real-time monitoring data of water quality analysis data, space coordinates of a microseismic sensor, a water pressure sensor, a water flow sensor, a stress sensor and a water quality analysis sensor, and water inrush condition information of a working face floor; secondly, coal mine bottom plate monitoring data of a mined coal mine bottom plate monitoring Internet of things system and a working face bottom plate water inrush situation are installed;
the prediction early warning algorithm module is a deep neural network algorithm realized based on a calculation engine Spark; monitoring data in an Internet of things monitoring database through historical coal mine floors of four floor types of the coal mine floors, and training coal mine floor water inrush disaster intelligence, a real-time prediction model and an early warning threshold value corresponding to the four floor types by adopting a deep neural network algorithm realized based on a computing engine Spark; therefore, the intelligent and real-time prediction early warning model of the coal mine floor water inrush disaster corresponding to different floor geological types is obtained.
2. The intelligent and real-time prediction and early warning big data cloud platform for water inrush disasters on coal mine floors according to claim 1, wherein the internet of things monitoring device is arranged as follows:
① micro-vibration sensor, using air gun to remove residual water and coal slag in the drill hole, using mounting tool to send the sensor to the bottom of the drill hole to couple the bottom of the sensor with the rock wall, then pouring cement mortar into the drill hole and making the mud cover the sensor, when the cement mortar is solidified, drawing out the mounting tool of the sensor and filling the drill hole with cement mortar;
② Water pressure sensor, drilling downward hole with depth of 1.5m by pore pressure gauge, feeding the pore pressure gauge to designed depth by pressing method, backfilling with bentonite mud ball of more than 1 m, and sealing hole;
③ borehole stress meter, adopting a drill bit with diameter of 55mm, drilling a round hole with depth of 8m in the direction vertical to the coal wall, and placing the borehole stress meter into the hole;
④ water flow sensor, wherein the water flow sensor is arranged in the drain ditch of the working surface, and the coordinates of the water flow sensor need to be measured independently after the water flow sensor is installed;
⑤ Water quality analysis sensor installed in the drainage ditch of working surface, and its coordinate is measured after the installation.
3. The intelligent real-time prediction and early warning big data cloud platform for the water inrush disaster on the coal mine floor according to claim 1 or 2, wherein the data transmission module is used for connecting the internet of things monitoring device with the monitoring database of the internet of things on the coal mine floor by cables, and the specific mode is as follows:
a, protecting a sleeve for a laid cable, wherein the sleeve is made of a PPR (polypropylene random) pipe material with the thickness of 3.5mm and is made of 2.0MPa, and a bidirectional joint is adopted between a line pipe and a line pipe for reinforcement;
and b, performing landfill protection on the laid cable, putting the sheathed cable into a 30cm wire groove, and performing landfill compaction to protect the cable by using coal cinder.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811365704.3A CN109268072B (en) | 2018-11-16 | 2018-11-16 | Big data cloud platform for intelligent and real-time prediction and early warning of water inrush disaster of coal mine floor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811365704.3A CN109268072B (en) | 2018-11-16 | 2018-11-16 | Big data cloud platform for intelligent and real-time prediction and early warning of water inrush disaster of coal mine floor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109268072A CN109268072A (en) | 2019-01-25 |
| CN109268072B true CN109268072B (en) | 2020-04-07 |
Family
ID=65189078
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811365704.3A Active CN109268072B (en) | 2018-11-16 | 2018-11-16 | Big data cloud platform for intelligent and real-time prediction and early warning of water inrush disaster of coal mine floor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109268072B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110552741B (en) * | 2019-09-09 | 2021-01-19 | 中煤科工集团西安研究院有限公司 | Coal face bottom plate water inrush comprehensive monitoring and early warning system and method |
| CN110847974A (en) * | 2019-12-06 | 2020-02-28 | 西安科技大学 | Auxiliary method for coal mine water inrush disaster early warning based on neural network |
| CN111287747B (en) * | 2020-02-05 | 2022-03-22 | 天地科技股份有限公司 | Water-controlled coal mining method on pressure-bearing water body |
| CN114087022B (en) * | 2021-10-28 | 2023-11-28 | 山东科技大学 | Coal seam floor variable parameter water inrush channel early warning system and water inrush risk judging method |
| CN114251124B (en) * | 2021-11-18 | 2023-09-29 | 煤炭科学技术研究院有限公司 | Intelligent early warning method and device for mine water damage |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101298840A (en) * | 2008-06-25 | 2008-11-05 | 中铁西南科学研究院有限公司 | Method for forecasting tunnel construction tunnel face front water burst position |
| CN201233230Y (en) * | 2008-06-20 | 2009-05-06 | 中国矿业大学 | Displacement measurement machine for working face baseboard |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6028848A (en) * | 1983-07-26 | 1985-02-14 | Soichi Yamaguchi | Sprayer for preventing dust in natom method |
| JPS6260821A (en) * | 1985-09-11 | 1987-03-17 | Parker Netsushiyori Kogyo Kk | Method for preventing gas exhaustion at rapid cooling of salt bath heated parts |
-
2018
- 2018-11-16 CN CN201811365704.3A patent/CN109268072B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201233230Y (en) * | 2008-06-20 | 2009-05-06 | 中国矿业大学 | Displacement measurement machine for working face baseboard |
| CN101298840A (en) * | 2008-06-25 | 2008-11-05 | 中铁西南科学研究院有限公司 | Method for forecasting tunnel construction tunnel face front water burst position |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109268072A (en) | 2019-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109268072B (en) | Big data cloud platform for intelligent and real-time prediction and early warning of water inrush disaster of coal mine floor | |
| CN110552741B (en) | Coal face bottom plate water inrush comprehensive monitoring and early warning system and method | |
| CN104747184B (en) | Measurement-while-drilling method and device for three-dimensional wave velocity imaging of rock mass in front of tunnel face | |
| Hencher | Preferential flow paths through soil and rock and their association with landslides | |
| CN106703888B (en) | Coal mining rock movement large space in-situ monitoring method | |
| CN110905403B (en) | Construction method of large-diameter groundwater environment monitoring well | |
| CN108468528A (en) | Fourth-series deep well layered water pumping and stopping device and water pumping and stopping method thereof | |
| CN107861157B (en) | A kind of underground water seal cave depot operation phase micro seismic monitoring method | |
| WO2013159749A1 (en) | Method for distributed storage and use of underground water in mine | |
| CN105158428A (en) | Multi-layer underground water monitoring pipe | |
| CN106372297B (en) | Method for determining safe vertical distance between shield and karst cave in sandy soil karst stratum | |
| CN106194262B (en) | Mine floor Austria limestone gushing water on-line monitoring intelligent early-warning system | |
| CN111577280A (en) | Mining area multi-layer water resource collaborative protective mining method | |
| KR101269517B1 (en) | Real-time resistivity measurement system | |
| CN105652311A (en) | Micro-seismic monitoring method for monitoring water inrush of base plate | |
| CN105182412A (en) | Detection method of coal mine underground reservoir coal pillar dam body earthquake safety | |
| CN104159087A (en) | Field monitoring platform for drilling machine | |
| CN107764323B (en) | A kind of multi-parameter enclosed area risk Monitoring and forecasting system in real-time method | |
| CN116006264A (en) | Mine rock burst and water damage cooperative early warning method based on acoustic wave detection | |
| CN1472422A (en) | Method for monitoring and predictnig mine water | |
| CN204903520U (en) | Groundwater multilayer position monitoring pipe | |
| CN213812473U (en) | Device suitable for karst wetland earth's surface and ground water level monitoring | |
| CN204013912U (en) | Rig on-site supervision platform | |
| CN112309088A (en) | Device for monitoring and early warning karst collapse by utilizing soil cave gas and working method | |
| CN109059833B (en) | Artesian water leads a liter band method for determining height under temperature-action of seepage-stress coupling |
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 |