CN114170780B - Visual dynamic monitoring and early warning system for spontaneous combustion of coal in mine goaf - Google Patents
Visual dynamic monitoring and early warning system for spontaneous combustion of coal in mine goaf Download PDFInfo
- Publication number
- CN114170780B CN114170780B CN202111504763.6A CN202111504763A CN114170780B CN 114170780 B CN114170780 B CN 114170780B CN 202111504763 A CN202111504763 A CN 202111504763A CN 114170780 B CN114170780 B CN 114170780B
- Authority
- CN
- China
- Prior art keywords
- coal
- spontaneous combustion
- goaf
- early warning
- dynamic
- 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
- 239000003245 coal Substances 0.000 title claims abstract description 174
- 238000002485 combustion reaction Methods 0.000 title claims abstract description 152
- 230000002269 spontaneous effect Effects 0.000 title claims abstract description 152
- 238000012544 monitoring process Methods 0.000 title claims abstract description 56
- 230000000007 visual effect Effects 0.000 title claims abstract description 50
- 239000007789 gas Substances 0.000 claims abstract description 116
- 238000012545 processing Methods 0.000 claims abstract description 44
- 238000000034 method Methods 0.000 claims abstract description 31
- 230000007246 mechanism Effects 0.000 claims abstract description 30
- 230000005540 biological transmission Effects 0.000 claims abstract description 18
- 230000008878 coupling Effects 0.000 claims abstract description 15
- 238000010168 coupling process Methods 0.000 claims abstract description 15
- 238000005859 coupling reaction Methods 0.000 claims abstract description 15
- 230000008859 change Effects 0.000 claims description 33
- 238000005516 engineering process Methods 0.000 claims description 30
- 238000013135 deep learning Methods 0.000 claims description 17
- 230000004927 fusion Effects 0.000 claims description 17
- 238000013210 evaluation model Methods 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 4
- 238000012800 visualization Methods 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 230000002035 prolonged effect Effects 0.000 claims description 2
- 230000002618 waking effect Effects 0.000 claims 1
- 238000009826 distribution Methods 0.000 description 7
- 238000006243 chemical reaction Methods 0.000 description 5
- 230000006698 induction Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000009529 body temperature measurement Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 239000013307 optical fiber Substances 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 230000008439 repair process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000007958 sleep Effects 0.000 description 2
- 230000007480 spreading Effects 0.000 description 2
- 238000003892 spreading Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 239000000853 adhesive Substances 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000005059 dormancy Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000011010 flushing procedure Methods 0.000 description 1
- 238000004868 gas analysis Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000010008 shearing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/06—Electric actuation of the alarm, e.g. using a thermally-operated switch
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Alarm Systems (AREA)
- Fire Alarms (AREA)
Abstract
The invention relates to a mine goaf coal spontaneous combustion visualized dynamic monitoring and early warning system and method, comprising a data acquisition unit, a data transmission unit, a data processing unit, an image forming unit and an intelligent early warning unit of goaf coal spontaneous combustion characteristic information; the wireless sensor builds a lattice wireless sensor network in the goaf, collects the dynamic information of the internal environment temperature of the goaf and the spontaneous combustion characteristic gas of the coal, and builds a real-time visual dynamic temperature field and a gas seepage field; according to the scheme, the coal spontaneous combustion danger level is judged by utilizing a coupling mechanism between various coal spontaneous combustion characteristic gases and temperatures, the false alarm rate of the coal spontaneous combustion characteristic variable early warning method by means of single coal spontaneous combustion is reduced, real-time visual dynamic monitoring and intelligent early warning of the spontaneous combustion of the goaf coal are realized, and the timeliness, reliability and early warning accuracy of the spontaneous combustion monitoring of the goaf coal are improved.
Description
Technical Field
The invention relates to the technical field of coal spontaneous combustion safety monitoring and prevention and control, in particular to a visual dynamic monitoring and early warning system and method for spontaneous combustion of coal in a mine goaf.
Background
Coal resources are important energy sources in China, are important supports for guaranteeing continuous and rapid development of national economy, and have important significance for sustainable development of national economy in safe exploitation. Coal is associated with a variety of primary and secondary hazards during the mining process, with mine fires, gas burning and explosion hazards caused by spontaneous combustion of the coal being the leading causes of casualties and significant economic losses in coal mines. The coal spontaneous combustion fire disaster has the characteristics of difficult discovery, rapid development, difficult extinguishment and rescue, and the like. Once the fire disaster happens, the fire disaster has the advantages of high spreading speed, wide spreading range, multiple secondary disasters and huge personal and property losses. Therefore, the method has important significance for effectively preventing and controlling spontaneous combustion disasters of coal and ensuring safe production of the coal mine.
Currently, the method for monitoring and forecasting the spontaneous combustion of the coal mainly comprises a gas analysis method and a temperature measurement method, wherein the coal spontaneous combustion monitoring system based on optical fiber temperature measurement and beam tube monitoring is most widely applied, and is an effective means for early prediction and forecasting of the spontaneous combustion of the coal. However, the beam tube monitoring technology and the optical fiber temperature measuring technology have the defects of large interference, high cost, difficult installation, single index parameter, easy occurrence of misjudgment and the like, so that the requirements of modern intensive and conventional mine production are difficult to meet. In addition, the comprehensive analysis capability of the goaf coal spontaneous combustion monitoring system of most coal enterprises on the ground monitoring terminal is not perfect, the fire hazard situation is judged by a critical value method in most fire hazard judgment and early warning methods, the influence of an intrinsic coupling mechanism between the coal spontaneous combustion characteristic gas concentration and the environment temperature is not fully considered, and the purposes of dynamic monitoring and intelligent early warning are difficult to achieve.
Disclosure of Invention
Aiming at the problems, the technical scheme of the coal spontaneous combustion visualized dynamic monitoring and early warning system and method for the goaf in the mine is provided, the coal spontaneous combustion dangerous level is judged by utilizing a coupling mechanism between various coal spontaneous combustion characteristic gases and temperatures, the false alarm rate of the coal spontaneous combustion characteristic variable early warning method is reduced, real-time visualized dynamic monitoring and intelligent early warning of the spontaneous combustion of the coal in the goaf are realized, and the timeliness, reliability and early warning accuracy of the coal spontaneous combustion monitoring in the goaf are improved.
The invention provides the following technical scheme: a visual dynamic monitoring and early warning system for spontaneous combustion of coal in a mine goaf comprises a data acquisition unit, a data transmission unit, a data processing unit, an image forming unit and an intelligent early warning unit for spontaneous combustion characteristic information of the coal in the goaf; the wireless sensor builds a dot matrix wireless sensor network in the goaf, and acquires the dynamic information of the internal environment temperature of the goaf and the spontaneous combustion characteristic gas of the coal.
The method comprises the steps of constructing a goaf real-time visual dynamic temperature field and a gas seepage field based on deep learning and image processing technology, constructing a coal spontaneous combustion fire hazard evaluation model based on multi-source data fusion, and determining an early warning grade according to the goaf visual dynamic temperature field and the gas seepage field dynamic change combined with the coal spontaneous combustion fire hazard evaluation model.
The data acquisition unit acquires ambient temperature and coal spontaneous combustion characteristic gas by a dot matrix wireless sensor network arranged in the goaf; the data transmission unit comprises a wireless ad hoc network, a monitoring substation, an exchanger and a ground terminal, and the data transmission unit wirelessly transmits the goaf ambient temperature and the coal spontaneous combustion characteristic gas information acquired by the data acquisition unit to the monitoring substation, and then transmits data to the ground monitoring terminal through the exchanger; the data processing unit is used for comprehensively processing the goaf environment temperature and the coal spontaneous combustion characteristic gas information at a ground monitoring terminal based on the deep learning and multisource data fusion theory; the image forming unit establishes a real-time visualized dynamic temperature field and a gas seepage field according to an image processing technology; the intelligent early warning unit is used for accurately positioning and intelligently inspecting abnormal points in the visual dynamic image, and determining early warning grades by combining with a coal spontaneous combustion fire hazard evaluation model.
The wireless sensor network of the goaf under the coal mine adopts a dot matrix wireless sensor network, and the dot matrix wireless sensor network can construct a wireless network topological structure with fault tolerance capacity by adopting a distributed algorithm according to the actual condition of the spontaneous combustion area of the coal, so that the effective coverage of goaf area monitoring is realized.
The sensor adopts a wireless sensor, gel is wrapped outside the sensor, the sensor is adhered and fixed on the coal wall through the gel, and the sensor monitors the ambient temperature inside a goaf in the coal mine and the characteristic gas of spontaneous combustion of the coal. The wireless sensor adopts a wireless gel sensor, the gel sensor uses high-strength self-adhesive organic gel as a base material, a wireless transmission device is arranged in the gel sensor, the gel sensor is connected with a gas induction layer coated on the outer surface through an electric signal conversion chip, when the gas induction layer senses the change of external gas, signals can be given to the electric signal conversion chip, the electric signal conversion chip transmits the signals through the wireless transmission device, and the gas induction layer, the electric signal conversion chip and the wireless transmission device can all adopt materials and chips in the prior art.
Based on the arrangement azimuth of the lattice type sensor network nodes in the goaf, the wireless sensor accurately collects the ambient temperature of the goaf, a mine goaf temperature field cloud image is built, the collected data is converted into a visual dynamic temperature field cloud image by utilizing an image processing technology, and the visual dynamic temperature field is built based on the distributed type sensor network and the image processing technology.
And processing the coal spontaneous combustion characteristic gas data acquired by the wireless sensor based on deep learning, predicting the change trend of the gas concentration, and converting the coal spontaneous combustion characteristic gas data and the trend into a visual coal spontaneous combustion characteristic gas dynamic seepage field by using an image processing technology.
The wireless sensor network is added with an event triggering mechanism, the information transmission times of sensor nodes are dynamically adjusted, the service time of the wireless sensor is prolonged, the abnormal change points in the visual dynamic temperature field cloud image and the coal spontaneous combustion characteristic gas dynamic seepage field are accurately positioned and inspected, when the images at any node are abnormally changed, the system wakes up neighbor sensors around the node to comprehensively collect characteristic information, and the characteristic information is transmitted back to the data terminal to carry out intelligent analysis.
Based on a coupling mechanism between the coal spontaneous combustion characteristic gas and the temperature disclosed by multi-source data fusion, a coal spontaneous combustion fire hazard evaluation model is constructed, the false alarm rate of a single coal spontaneous combustion characteristic variable early warning method is reduced, and the timeliness, reliability and early warning accuracy of goaf coal spontaneous combustion monitoring are improved; the coal spontaneous combustion monitoring in the goaf adopts a grading early warning mechanism, the main judgment basis of each grade of early warning level is the image color change degree, the image color change is divided into 4 types of red, orange, yellow and green, the darker the color is the higher the coal spontaneous combustion dangerous degree, and the colors of a dynamic temperature field and a gas seepage field under the safety condition are determined to be green; when a yellow area appears in the dynamic image, a primary early warning mechanism is started; when an orange area appears, a secondary early warning mechanism is started; when red appears, a three-level early warning mechanism is started.
S1, arranging a lattice type wireless sensor network in a goaf under a coal mine, wherein the lattice type wireless sensor network adopts a distributed algorithm to construct a network topology structure with fault tolerance capability, and realizes effective coverage of goaf area monitoring; s3, establishing a visual dynamic temperature field by using a distributed sensor network and an image processing technology, accurately acquiring the ambient temperature of the goaf based on the arrangement azimuth of nodes of the lattice type sensor network, establishing a mine goaf temperature field cloud image, converting acquired data into a visual dynamic temperature field cloud image by using the image processing technology, establishing a visual coal spontaneous combustion characteristic gas dynamic seepage field based on the deep learning and the image processing technology, processing the coal spontaneous combustion characteristic gas data acquired by the wireless gel sensor based on the deep learning, predicting the change trend of the gas concentration, and converting the data and the trend into the visual coal spontaneous combustion characteristic gas dynamic seepage field by using the image processing technology; s5, positioning and intelligent inspection are carried out on abnormal points in the visual dynamic image, when the image at any node is abnormally changed, surrounding neighbor sensors at the node are awakened, comprehensive collection of characteristic information is carried out, and the characteristic information is transmitted back to a data terminal for analysis; s6, constructing a coal spontaneous combustion fire hazard evaluation model based on multi-source data fusion, and constructing the coal spontaneous combustion fire hazard evaluation model according to a coupling mechanism between coal spontaneous combustion characteristic gas and temperature revealed by the multi-source data fusion; s7, comprehensively analyzing a dynamic temperature field and a gas seepage field constructed according to an internal coupling mechanism between the spontaneous combustion characteristic gas concentration of the coal and the ambient temperature to determine the position of the fire and judge the spontaneous combustion danger level of the coal.
In the step S4, the concentrations of the characteristic gases of spontaneous combustion of coal in the underground goaf are all changed in real time, and the wind direction and the wind force under the mine are unstable, so that the data collected by the wireless sensor are changed in real time, therefore, based on deep learning, the collected information is comprehensively processed within a certain interval time range, the change trend of the concentrations of the gases is estimated, various characteristic gas concentrations of the spontaneous combustion goaf of the coal are more intuitively checked and estimated, and then the image processing technology is combined to establish a dynamic seepage field cloud image of the characteristic gases of spontaneous combustion of the coal, so that the change condition of the characteristic gases of spontaneous combustion of the coal is displayed in real time.
In step S5, the wireless sensor network node adopts an event triggering mechanism, dynamically adjusts the information transmission times of the sensor node, and prolongs the service time of the wireless sensor, but when the dynamic temperature field and the gas seepage field seepage cloud chart change, the system immediately performs area positioning, and immediately wakes up neighbor sensors around the node to perform comprehensive information acquisition, comprehensive analysis and processing, and makes necessary response.
From the above description, it can be seen that the advantages of the present invention are: 1. according to the invention, a dot matrix wireless sensor network is constructed in a coal mine goaf by utilizing a wireless sensor, a real-time visual dynamic change cloud picture of a temperature field and a gas seepage field in the goaf is realized by combining a deep learning theory and an image processing technology according to the accurate positioning function of the sensor, and an early warning grade is determined according to the color change of the cloud picture, so that the spontaneous combustion monitoring of coal is more timely and effective, and the requirements of safe production and intensive production construction of modern coal mines are met. 2. According to the invention, a dynamic temperature field and a gas seepage field are constructed based on the intrinsic coupling mechanism between the multi-source data fusion and the coal spontaneous combustion characteristic gas concentration and the ambient temperature, the correlation characteristics between various coal spontaneous combustion characteristic gases and temperatures are deeply analyzed, the false alarm rate of the coal spontaneous combustion characteristic variable early warning method is reduced, and the timeliness, reliability and early warning accuracy of goaf coal spontaneous combustion monitoring are improved. 3. The invention establishes a three-level early warning mechanism for the color change degree of the temperature field and the gas seepage field real-time visualization dynamic cloud picture, can monitor and intelligently early warn the coal spontaneous combustion condition development condition in real time, and forecast the coal fire evolution trend, thereby improving early warning accuracy and timeliness of prevention and control.
In the scheme, the dynamic temperature field and the gas seepage field constructed according to the intrinsic coupling mechanism between the spontaneous combustion characteristic gas concentration of the coal and the ambient temperature are comprehensively analyzed, the spontaneous combustion danger level of the coal is judged, the false alarm rate of the single spontaneous combustion characteristic variable early warning method is reduced, and the timeliness, the reliability and the early warning accuracy of spontaneous combustion of the coal are improved.
Drawings
Fig. 1 is a system block diagram of the present invention.
Fig. 2 is a cloud of real-time visual dynamic temperature field distribution in the system of the present invention.
Fig. 3 is a cloud of temperature field distribution around two wireless sensor nodes in the system of the present invention.
Fig. 4 is a cloud image of a real-time visual dynamic gas permeation field distribution in the system of the present invention.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is apparent that the described embodiment is only one embodiment of the present invention, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof;
as can be seen from the attached figure 1, the mine goaf coal spontaneous combustion visualization dynamic monitoring and early warning system comprises a data acquisition unit, a data transmission unit, a data processing unit, an image forming unit and an intelligent early warning unit, wherein the data acquisition unit is used for acquiring the spontaneous combustion characteristic information of the goaf coal; the wireless sensor builds a lattice wireless sensor network in the goaf, and acquires the dynamic information of the internal environment temperature of the goaf and the spontaneous combustion characteristic gas of the coal; a goaf visual dynamic temperature field and a gas seepage field are constructed based on deep learning and image processing technology, a coal spontaneous combustion fire hazard evaluation model is constructed based on multi-source data fusion, and an early warning grade is determined according to the dynamic change of two fields and the coal spontaneous combustion fire hazard evaluation model.
The data acquisition unit acquires ambient temperature and coal spontaneous combustion characteristic gas by a dot matrix wireless sensor network arranged in the goaf; the data transmission unit consists of a wireless ad hoc network, a monitoring substation, an exchanger, a ground terminal and the like, the goaf ambient temperature and coal spontaneous combustion characteristic gas information acquired by the data acquisition unit are transmitted to the monitoring substation in a wireless mode, then transmitted to the exchanger, and then transmitted to the ground monitoring terminal through the exchanger; the data processing unit is used for comprehensively processing the goaf environment temperature and the coal spontaneous combustion characteristic gas information at a ground monitoring terminal based on the deep learning and multisource data fusion theory; the image forming unit establishes a visualized dynamic temperature field and a gas seepage field according to an image processing technology; the intelligent early warning unit is used for accurately positioning and intelligently inspecting abnormal points in the visual dynamic image, and determining early warning grades by combining with a coal spontaneous combustion fire hazard evaluation model.
According to the system architecture block diagram as shown in fig. 1, the system embodiment may be performed as follows:
s1, arranging a dot matrix wireless sensor network in a goaf under a coal mine, constructing a network topology structure with fault tolerance capacity by adopting a distributed algorithm, and realizing effective coverage of goaf area monitoring.
Setting sensor node deployment areas according to the aggregation areas of the sensors, and distributing corresponding dominance to each sensor node deployment area, so that a network topology structure with fault tolerance is constructed, and effective coverage of goaf monitoring areas is realized. When the wireless sensor network operates, some sensor nodes fail due to special reasons, and some sensor nodes are added into the network due to the network, so that the number of the nodes in the network is dynamically changed, and the topology structure of the network is correspondingly dynamically changed. Therefore, methods such as a standby node repair algorithm, a network partition detection and repair algorithm and the like are required to be combined for active prevention and passive repair, so that the normal operation of the wireless sensor network is ensured.
S2, data acquisition is carried out on the environmental temperature of the underground goaf of the coal mine and the spontaneous combustion characteristic gas of the coal, and the wireless sensor is adopted as a sensor used in the lattice type wireless sensor network, so that the environmental temperature and the spontaneous combustion characteristic gas of the coal in the underground goaf of the coal mine can be monitored simultaneously.
The gel sensor has the special functions of tensile, pressure, shearing and flushing, has excellent characteristics of self-healing, self-adhesion, conductivity, induction sensitivity and the like due to the fact that the gel has fine molecular design and chemical synthesis, is made of high-strength self-adhesion organogel serving as a base material, is internally provided with a wireless transmission device, is connected with a gas induction layer coated on the outer surface through an electric signal conversion chip and is fixed on a coal wall through long-term self-adhesion of the gel, and can monitor the environmental temperature and coal spontaneous combustion characteristic gas in a coal mine goaf in a coal mine at the same time, so that the monitoring, transmission and early warning functions are realized for a long time, stably, efficiently and conveniently.
S3, a visual dynamic temperature field is established by using a distributed sensor network and an image processing technology, the wireless sensor is used for collecting the ambient temperature of the goaf based on the arrangement azimuth of the lattice sensor network nodes in the goaf, a mine goaf temperature field cloud picture is established, and the collected data is converted into the visual dynamic temperature field cloud picture by using the image processing technology.
The wireless sensor builds a dot matrix wireless sensor network in the goaf, can realize accurate collection of goaf environment information, collects dynamic information of goaf internal environment temperature and coal spontaneous combustion characteristic gas, combines with a deep learning theory, and applies a mathematical model and an image processing technology to comprehensively analyze and process collected data so as to convert the collected data into a visual dynamic temperature field cloud picture.
S4, establishing a visual coal spontaneous combustion characteristic gas dynamic seepage field based on a deep learning and image processing technology, processing coal spontaneous combustion characteristic gas data acquired by a wireless sensor based on the deep learning, predicting the change trend of gas concentration, and converting the data and the trend into the visual coal spontaneous combustion characteristic gas dynamic seepage field by utilizing the image processing technology.
The concentration of the spontaneous combustion characteristic gas of the coal in the goaf under the mine is changed in real time, and the wind direction and the wind force under the mine are unstable, so that the data collected by the wireless sensor are changed in real time. Therefore, based on deep learning, the acquired information is comprehensively processed within a certain interval time range, the change trend of the gas concentration is estimated, various characteristic gas concentrations in the coal spontaneous combustion goaf are more intuitively checked and estimated, and then a visual coal spontaneous combustion characteristic gas dynamic seepage field cloud chart is established by combining an image processing technology, so that the change condition of the coal spontaneous combustion characteristic gas is displayed in real time.
S5, positioning and intelligent inspection are carried out on abnormal points in the visual dynamic image, when the image at any node is abnormally changed, the system automatically wakes up wireless sensors around the node, comprehensively collects characteristic information, and transmits the characteristic information back to the data terminal for intelligent analysis.
In the using process of the wireless sensor, in order to prolong the lifetime of the wireless sensor network, the most common and direct solution at present is to adopt a node dormancy scheduling algorithm, automatically enter a sleep state when no work is needed, periodically wake up according to service needs, and enable the node energy to be maximally reasonably utilized by adjusting the duty cycle of node wake-up/sleep. Therefore, based on the consideration, the invention adopts an event triggering mechanism for the wireless sensor network node, dynamically adjusts the information transmission times of the sensor node, prolongs the service time of the wireless sensor, but when the dynamic temperature field and the gas seepage field cloud image change, the system immediately performs area positioning, and immediately wakes up neighbor sensors around the node to comprehensively acquire information, comprehensively analyze and process, and make necessary response.
S6, constructing a coal spontaneous combustion fire hazard evaluation model based on multi-source data fusion, and constructing the coal spontaneous combustion fire hazard evaluation model according to a coupling mechanism between the coal spontaneous combustion characteristic gas and the temperature revealed by the multi-source data fusion.
During actual production, the concentrations of the spontaneous combustion characteristic gases of the coal in the goaf under the mine are all changed in real time, dynamic monitoring and intelligent early warning cannot be simply carried out by adopting a critical value method, the correlation characteristics among various spontaneous combustion characteristic gases and temperatures of the coal are deeply analyzed based on a gray correlation analysis method and a multi-source data fusion theory, the false alarm rate of the single spontaneous combustion characteristic variable early warning method is reduced, and therefore real-time visual dynamic monitoring and intelligent early warning of spontaneous combustion of the coal in the goaf are realized, and the timeliness, reliability and early warning accuracy of spontaneous combustion monitoring of the coal in the goaf are improved.
S7, comprehensively analyzing a dynamic temperature field and a gas seepage field constructed according to an internal coupling mechanism between the spontaneous combustion characteristic gas concentration of the coal and the ambient temperature to determine the position of a fire condition and judge the spontaneous combustion danger level of the coal.
Based on gray correlation analysis method and multi-source data fusion theory, the correlation characteristics between various coal spontaneous combustion characteristic gases and temperatures are deeply analyzed, the color degree of dynamic temperature field and gas seepage field images is determined according to the intrinsic coupling mechanism between the coal spontaneous combustion characteristic gases and temperatures and the coal spontaneous combustion characteristic gases, and the danger degree of coal spontaneous combustion is determined by a method of directly using a single coal spontaneous combustion characteristic variable threshold value. The main judgment basis of each early warning level is the color change degree of the image, and the color change of the image is divided into 4 colors: the darker the color of red, orange, yellow and green is the higher the spontaneous combustion risk degree of the coal, and the color of the dynamic temperature field and the gas seepage field is determined to be green under the relative safety condition; when a yellow area appears in the dynamic image, a primary early warning mechanism is started; when an orange area appears, a secondary early warning mechanism is started; when red appears, a three-level early warning mechanism is started; the information of the wireless sensor node corresponding to the position can be retrieved and checked in real time at the image color change position of the visual dynamic temperature field and the gas seepage field, and can be manually verified in an auxiliary manner, so that the secondary monitoring can be further carried out through the optical fiber temperature measurement and beam tube monitoring system, the spontaneous combustion risk level of the coal is determined, and the problem of false alarm caused by the fault of the system is avoided.
Fig. 2 is a cloud of real-time visual dynamic temperature field distribution in the system of the present invention. As shown in the figure, according to the arrangement azimuth of the nodes of the matrix sensor network in the goaf, the wireless gel sensor accurately collects the ambient temperature of the goaf, a mine goaf temperature field cloud chart is established, the collected data is converted into a visual dynamic temperature field cloud chart by utilizing an image processing technology, the temperature change condition of the mine goaf can be monitored and observed more easily, the goaf temperature change trend is estimated, the early warning sensitivity is improved, the color degree change is shown through a temperature place, the temperature abnormality position is found more easily, and the coal fire early warning positioning accuracy is improved.
Fig. 3 is a cloud of temperature field distribution around two wireless sensor nodes in the system of the present invention. As shown in the figure, temperature fields are established around two wireless sensor nodes according to the fusion relation between the temperatures, so that the principle that the whole goaf shown in figure 2 is used for constructing a mine goaf temperature field cloud picture according to the relation is revealed.
Fig. 4 is a cloud image of a real-time visual dynamic gas permeation field distribution in the system of the present invention. As shown in the figure, according to the arrangement direction of the lattice type sensor network nodes constructed by the wireless gel sensor and the acquisition information acquisition of the coal spontaneous combustion characteristic gas, a real-time visual dynamic gas seepage field distribution cloud chart is established, the seepage flow of the coal spontaneous combustion characteristic gas is reflected by the color degree, the change degree of the concentration of the coal spontaneous combustion characteristic gas can be monitored more intuitively, and the seepage flow direction of the coal spontaneous combustion characteristic gas can be also observed more intuitively, so that the real-time visual dynamic monitoring of the coal spontaneous combustion characteristic gas in the goaf is realized.
According to the method, the visual dynamic temperature field and the gas seepage field of the mine goaf are constructed for comprehensive analysis, the image color degree of the dynamic temperature field and the gas seepage field is determined by utilizing the coupling mechanism between various coal spontaneous combustion characteristic gases and temperatures, so that the coal spontaneous combustion danger level is judged, the false alarm rate of a single coal spontaneous combustion characteristic variable early warning method is reduced, the timeliness, the reliability and the early warning accuracy of the goaf coal spontaneous combustion monitoring are improved, and the goaf coal spontaneous combustion real-time visual dynamic monitoring and intelligent early warning are realized.
Although particular embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations may be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. The coal spontaneous combustion visualized dynamic monitoring and early warning system for the goaf of the mine is characterized by comprising a data acquisition unit, a data transmission unit, a data processing unit, an image forming unit and an intelligent early warning unit of spontaneous combustion characteristic information of the coal in the goaf; the wireless sensor builds a lattice wireless sensor network in the goaf, and acquires the dynamic information of the internal environment temperature of the goaf and the spontaneous combustion characteristic gas of the coal;
the data acquisition unit acquires ambient temperature and coal spontaneous combustion characteristic gas by a dot matrix wireless sensor network arranged in the goaf; the data transmission unit comprises a wireless ad hoc network, a monitoring substation, an exchanger and a ground terminal, and the data transmission unit wirelessly transmits the goaf ambient temperature and the coal spontaneous combustion characteristic gas information acquired by the data acquisition unit to the monitoring substation, and then transmits data to the ground monitoring terminal through the exchanger; the data processing unit is used for comprehensively processing the goaf environment temperature and the coal spontaneous combustion characteristic gas information at a ground monitoring terminal based on the deep learning and multisource data fusion theory; the image forming unit establishes a real-time visualized dynamic temperature field and a gas seepage field according to an image processing technology; the intelligent early warning unit performs accurate positioning and intelligent inspection according to abnormal points in the visual dynamic image, and determines early warning level by combining with a coal spontaneous combustion fire hazard evaluation model;
the sensor adopts a wireless sensor, gel is wrapped outside the sensor, the sensor is adhered and fixed on the coal wall through the gel, and the sensor monitors the ambient temperature inside a goaf under the coal mine and the characteristic gas of spontaneous combustion of the coal;
based on the arrangement azimuth of the lattice type sensor network nodes in the goaf, the wireless sensor collects the ambient temperature of the goaf, a mine goaf temperature field cloud picture is established, and the collected data is converted into a visual dynamic temperature field cloud picture by utilizing an image processing technology;
processing the coal spontaneous combustion characteristic gas data acquired by the wireless sensor based on deep learning, predicting the change trend of gas concentration, and converting the coal spontaneous combustion characteristic gas data and trend into a visual coal spontaneous combustion characteristic gas dynamic seepage field by using an image processing technology;
and accurately positioning and inspecting abnormal change points in the visual dynamic temperature field cloud chart and the coal spontaneous combustion characteristic gas dynamic seepage field, and when the images at any node are abnormally changed, waking up neighbor sensors around the node by the system to comprehensively acquire characteristic information and transmitting the characteristic information back to a data terminal for intelligent analysis.
2. The mine goaf coal spontaneous combustion visualization dynamic monitoring and early warning system according to claim 1 is characterized in that a wireless network topology structure with fault tolerance is built by a dot matrix wireless sensor network through a distributed algorithm, and effective coverage of goaf area monitoring is achieved.
3. The visual dynamic monitoring and early warning system for spontaneous combustion of coal in a mine goaf according to claim 1 is characterized in that a coal spontaneous combustion fire hazard evaluation model is built based on a coupling mechanism between spontaneous combustion characteristic gas and temperature of coal revealed by multi-source data fusion, the false alarm rate of a single coal spontaneous combustion characteristic variable early warning method is reduced, and the timeliness, reliability and early warning accuracy of spontaneous combustion monitoring of coal in the goaf are improved; the main judgment basis for determining each level of early warning level is the color change degree of an image, wherein the color change of the image is divided into 4 types of red, orange, yellow and green, the darker the color is, the higher the spontaneous combustion danger degree of coal is, and the colors of a dynamic temperature field and a gas seepage field are determined to be green under the safety condition; when a yellow area appears in the dynamic image, a primary early warning mechanism is started; when an orange area appears, a secondary early warning mechanism is started; when red appears, a three-level early warning mechanism is started.
4. The visual dynamic monitoring and early warning method for spontaneous combustion of coal in a mine goaf is characterized by comprising the following steps of,
s1, arranging a dot matrix wireless sensor network in a goaf under a coal mine, constructing a network topology structure with fault tolerance capacity by the dot matrix wireless sensor network through a distributed algorithm, and realizing effective coverage of goaf area monitoring;
s2, acquiring data of the environmental temperature of the underground goaf of the coal mine and the spontaneous combustion characteristic gas of the coal, wherein a wireless sensor is adopted as a sensor used in the lattice type wireless sensor network, and the environmental temperature and the spontaneous combustion characteristic gas of the coal in the underground goaf of the coal mine are monitored at the same time;
s3, establishing a visual dynamic temperature field by using a distributed sensor network and an image processing technology, accurately acquiring the ambient temperature of the goaf by using a wireless sensor based on the arrangement direction of the lattice sensor network nodes in the goaf, establishing a mine goaf temperature field cloud picture, and converting acquired data into the visual dynamic temperature field cloud picture by using the image processing technology;
s4, establishing a visual coal spontaneous combustion characteristic gas dynamic seepage field based on deep learning and image processing technology, processing coal spontaneous combustion characteristic gas data acquired by a wireless gel sensor based on deep learning, predicting the change trend of gas concentration, and converting the data and the trend into the visual coal spontaneous combustion characteristic gas dynamic seepage field by utilizing the image processing technology;
s5, positioning and intelligent inspection are carried out on abnormal points in the visual dynamic image, when the image at any node is abnormally changed, surrounding neighbor sensors at the node are awakened, comprehensive collection of characteristic information is carried out, and the characteristic information is transmitted back to a data terminal for analysis;
s6, constructing a coal spontaneous combustion fire hazard evaluation model based on multi-source data fusion, and constructing the coal spontaneous combustion fire hazard evaluation model according to a coupling mechanism between coal spontaneous combustion characteristic gas and temperature revealed by the multi-source data fusion;
s7, comprehensively analyzing a dynamic temperature field and a gas seepage field constructed according to an internal coupling mechanism between the gas concentration of the spontaneous combustion characteristic of the coal and the ambient temperature to determine the position of a fire condition, and judging the spontaneous combustion risk level of the coal;
in the step S4, the concentrations of the spontaneous combustion characteristic gases of the coal in the underground goaf are all changed in real time, and the wind direction and the wind force under the mine are unstable, so that the data collected by the wireless sensor are changed in real time, the collected information needs to be comprehensively processed within a certain interval time range, the change trend of the gas concentrations is estimated, various characteristic gas concentrations of the spontaneous combustion goaf of the coal are more intuitively checked and estimated, and then the image processing technology is combined to establish a dynamic seepage field cloud picture of the spontaneous combustion characteristic gases of the coal, so that the change condition of the spontaneous combustion characteristic gases of the coal is displayed in real time.
5. The method for dynamically monitoring and early warning spontaneous combustion visualization of coal in a mine goaf according to claim 4, wherein in the step S5, the wireless sensor network node adopts an event triggering mechanism, the information transmission times of the sensor node are dynamically adjusted, the service time of the wireless sensor is prolonged, but when the dynamic temperature field and the gas seepage field cloud picture change, the system immediately performs area positioning, and immediately wakes up neighbor sensors around the node to comprehensively acquire information, comprehensively analyze and process, and make necessary response.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111504763.6A CN114170780B (en) | 2021-12-09 | 2021-12-09 | Visual dynamic monitoring and early warning system for spontaneous combustion of coal in mine goaf |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111504763.6A CN114170780B (en) | 2021-12-09 | 2021-12-09 | Visual dynamic monitoring and early warning system for spontaneous combustion of coal in mine goaf |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114170780A CN114170780A (en) | 2022-03-11 |
| CN114170780B true CN114170780B (en) | 2024-01-12 |
Family
ID=80485480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111504763.6A Active CN114170780B (en) | 2021-12-09 | 2021-12-09 | Visual dynamic monitoring and early warning system for spontaneous combustion of coal in mine goaf |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114170780B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118067785B (en) * | 2024-04-18 | 2024-06-14 | 中煤科工集团沈阳研究院有限公司 | Visual test system and method for spontaneous combustion behavior of coal |
| CN118247915A (en) * | 2024-05-29 | 2024-06-25 | 西南石油大学 | Monitoring image processing method and system based on computer vision |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108301872A (en) * | 2018-02-28 | 2018-07-20 | 山东科技大学 | A kind of visual mine warning system for real time monitoring and method based on data filtering |
| CN108915776A (en) * | 2018-08-07 | 2018-11-30 | 天地（常州）自动化股份有限公司 | Goaf coal spontaneous combustion temperature field real-time visual monitoring device, system and method |
| RU2723106C1 (en) * | 2019-12-02 | 2020-06-08 | Дмитрий Борисович Никишичев | Method for monitoring of mined-out space |
| CN112150746A (en) * | 2020-09-29 | 2020-12-29 | 福州大学 | Self-explosion monitoring and early warning device and method for vulcanized mine explosive |
| CN113107597A (en) * | 2021-03-08 | 2021-07-13 | 山东科技大学 | Mine fire transparency monitoring system and method |
| CN113605983A (en) * | 2021-08-20 | 2021-11-05 | 中国矿业大学(北京) | Coal mine goaf high-temperature detection early warning and fire prevention and extinguishing intelligent cooperative management and control system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6856272B2 (en) * | 2002-08-28 | 2005-02-15 | Personnel Protection Technoloties Llc | Methods and apparatus for detecting threats in different areas |
-
2021
- 2021-12-09 CN CN202111504763.6A patent/CN114170780B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108301872A (en) * | 2018-02-28 | 2018-07-20 | 山东科技大学 | A kind of visual mine warning system for real time monitoring and method based on data filtering |
| CN108915776A (en) * | 2018-08-07 | 2018-11-30 | 天地（常州）自动化股份有限公司 | Goaf coal spontaneous combustion temperature field real-time visual monitoring device, system and method |
| RU2723106C1 (en) * | 2019-12-02 | 2020-06-08 | Дмитрий Борисович Никишичев | Method for monitoring of mined-out space |
| CN112150746A (en) * | 2020-09-29 | 2020-12-29 | 福州大学 | Self-explosion monitoring and early warning device and method for vulcanized mine explosive |
| CN113107597A (en) * | 2021-03-08 | 2021-07-13 | 山东科技大学 | Mine fire transparency monitoring system and method |
| CN113605983A (en) * | 2021-08-20 | 2021-11-05 | 中国矿业大学(北京) | Coal mine goaf high-temperature detection early warning and fire prevention and extinguishing intelligent cooperative management and control system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114170780A (en) | 2022-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114170780B (en) | Visual dynamic monitoring and early warning system for spontaneous combustion of coal in mine goaf | |
| CN106017560A (en) | Cable well state comprehensive monitoring and early warning system | |
| CN103955174A (en) | Building health monitoring system based on building information model technology | |
| CN112464813B (en) | Mountain fire monitoring method and device | |
| CN213236990U (en) | Pipeline monitoring platform based on NB IOT | |
| CN102915619A (en) | Intelligent landslide monitoring and pre-warning system for multielement detection | |
| CN106949930A (en) | Contact net and power supply unit monitoring system and method based on automatic power supply and network | |
| CN111273130A (en) | Multi-parameter acquisition and abnormity prevention early warning method for cable channel of transformer substation and application | |
| CN203055099U (en) | Multivariate detection intelligent landslide monitoring and early warning system | |
| CN107277847B (en) | Antenna attitude measurement system and method based on NB-IoT transmission mode | |
| CN104635639A (en) | Intelligent building monitoring system based on optical fiber sensing | |
| CN208399019U (en) | A kind of Wireless Networking type Electric Wires & Cables temperature hidden danger early warning system | |
| CN115903973A (en) | Fire detection and emergency linkage control system based on Internet of things | |
| CN112684744A (en) | Wisdom city application underground pipe gallery model monitoring and early warning system | |
| CN104794860A (en) | Mountain landslide monitoring and warning device based on technology of Internet of things and control method thereof | |
| CN108271136A (en) | Geotechnical engineering safety intelligent monitor system | |
| LU500830B1 (en) | Coal Mine Safety Monitoring and Early Warning System | |
| CN113570829B (en) | Wireless gas detection alarm system | |
| CN211656391U (en) | Cable trench monitoring system | |
| CN113107597A (en) | Mine fire transparency monitoring system and method | |
| CN102606889A (en) | Gas valve pit leakage monitoring terminal | |
| CN116546043A (en) | Cable tunnel inspection personnel environment safety monitoring device and method | |
| CN115761650A (en) | Construction safety detection method and system based on BIM and Internet of things sensing technology | |
| CN115657523A (en) | Intelligent monitoring device integrating monitoring of cable running state and partial discharge testing | |
| CN114623390A (en) | System and method for online monitoring of gas leakage of petroleum and petrochemical pipelines |
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 |