CN113408322A - Method and device for identifying water inrush situation in mine - Google Patents
Method and device for identifying water inrush situation in mine Download PDFInfo
- Publication number
- CN113408322A CN113408322A CN202010183067.9A CN202010183067A CN113408322A CN 113408322 A CN113408322 A CN 113408322A CN 202010183067 A CN202010183067 A CN 202010183067A CN 113408322 A CN113408322 A CN 113408322A
- Authority
- CN
- China
- Prior art keywords
- scene
- water
- current
- data
- data vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 220
- 238000000034 method Methods 0.000 title claims abstract description 62
- 239000013598 vector Substances 0.000 claims abstract description 130
- 238000012544 monitoring process Methods 0.000 claims abstract description 47
- 238000012806 monitoring device Methods 0.000 claims abstract description 30
- 230000035515 penetration Effects 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000004088 simulation Methods 0.000 claims description 12
- 238000007637 random forest analysis Methods 0.000 claims description 7
- 230000035699 permeability Effects 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 238000003064 k means clustering Methods 0.000 claims description 2
- 239000011248 coating agent Substances 0.000 claims 2
- 238000000576 coating method Methods 0.000 claims 2
- 238000004891 communication Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 8
- 230000006378 damage Effects 0.000 description 7
- 238000011160 research Methods 0.000 description 6
- 230000007480 spreading Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 230000009172 bursting Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 239000003245 coal Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000000149 penetrating effect Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 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
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
- E21F17/18—Special adaptations of signalling or alarm devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Mining & Mineral Resources (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for judging and identifying a water inrush situation in a mine, wherein the method comprises the following steps: acquiring current monitoring water flow data of each monitoring device deployed in each roadway of a mine to form a current monitoring data vector h1(ii) a H is to be1Inputting the obtained data into a classifier, and obtaining h output by the classifier1A corresponding scene class; according to h1Judging the current water inrush or water permeation scene related to the scene data vector in the corresponding scene class; the classifier is obtained by training scene data sample sets classified into different scene classes in advance. The invention can be used for monitoring the current water flow data of each monitoring device in the roadway based on the mineAnd the water penetration situation in the mine is rapidly judged and identified so as to carry out corresponding emergency rescue and disposal in time.
Description
Technical Field
The invention relates to the technical field of mine water damage prevention and control, in particular to a method and a device for judging and identifying a water inrush situation in a mine.
Background
Coal resources are basic energy in China, and account for more than 60% of energy consumption in one time. The mine water disaster accident is one of the most main mine disasters in China, and is easy to cause a cluster death and group injury event. According to statistics, only in 2015, 15 mine water disaster accidents happen together, and 64 people die. Due to uncertainty of a mine water inrush mechanism, uncertainty of geological structures and hydrogeological conditions, uncertainty of a mine goaf and the like, mine water damage accidents, size of mine water inrush and time change rules of the mine water inrush are extremely difficult to predict.
A new version of coal mine water control rules officially implemented in 9/1/2018 is based on a principle of human-oriented, highlights the importance of education and training on water control knowledge of underground personnel, requires to strengthen and continuously revise and perfect emergency plan drilling, and emphasizes the pertinence, the scientificity and the operability of the emergency plan. Therefore, higher requirements are provided for analysis and research works such as monitoring, early warning, forecasting and the like of mine water damage.
Due to the complexity, uncertainty and easy mining influence of geological and hydrogeological conditions in China, water inrush accidents in the process of mine construction of coal mines become one of the main threats of mine exploitation. The water burst (permeation) condition refers to the water burst (permeation) position and water burst (permeation) flow time curve. Due to the characteristics of anisotropy and heterogeneity of the geologic body, the water bursting (penetrating) conditions cannot be accurately predicted at present, meanwhile, with the increase of mining depth, deep rock bodies show obvious nonlinear mechanical properties, the engineering geological conditions become more complex, and the forms of the mine water bursting (penetrating) conditions are increasingly diversified. The water burst accident can not be completely avoided, and once the accident occurs, the serious well flooding accident is easy to form. For sudden water disaster accidents of mines, the flow process of the sudden (permeable) water in the mine cannot be known and predicted in time due to the limitation of detection and observation equipment, and great troubles are caused for underground rescue and post-disaster treatment.
Aiming at the current situation that the water damage of the mine can cause group death and serious property loss and has larger prediction and early warning difficulty, a method for quickly judging and recognizing the water inrush scene in the mine is needed to be provided so as to carry out corresponding emergency rescue and treatment in time and effectively carry out analysis and research work before the water damage accident.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for identifying a water inrush situation in a mine, which can quickly identify the water inrush situation in the mine based on water flow data currently monitored by each monitoring device in a roadway of the mine, so as to perform corresponding emergency rescue and disposal in time.
Based on the above purpose, the invention provides an identification method for a water inrush situation in a mine, which comprises the following steps:
acquiring current monitoring water flow data of each monitoring device deployed in each roadway of a mine to form a current monitoring data vector h1；
H is to be1Inputting the obtained data into a classifier, and obtaining h output by the classifier1A corresponding scene class;
according to h1Judging the current water inrush or water permeation scene related to the scene data vector in the corresponding scene class;
the classifier is obtained by training scene data sample sets classified into different scene classes in advance; the scene data sample set comprises a plurality of scene data vectors
Wherein the content of the first and second substances,
the scene data vector is composed of water flow data collected at scene time t and monitored by each monitoring device under the scene c of water inrush or water permeation; c ∈ Ρ, t ∈ Τ Ρ, Ρ represents a set comprising various water-break, water-permeable scenes, Τ represents a scene simulation period under water-break or water-permeable scenes.
Wherein, the said is according to h1Judging the current water inrush or water permeation situation according to the water inrush or water permeation situation related to the situation data vector in the corresponding situation class, specifically comprising:
if the current judgment is the first judgment, judging the current water inrush or water permeation situation according to the following method to obtain the current judgment result:
h is to be1The water inrush or water penetration scene related to the scene data vector in the corresponding scene class is used as the scene in the current judgment result;
for each scene in the recognition result, determining the best scene moment of the scene in the recognition result and the recognition rate of the current scene according to the following method:
acquiring each scene data vector of the scene from the scene class;
h is calculated for each acquired scene data vector of the scene1Similarity with the scene data vector;
determining the sum of h1The scene data vector of the scene with the highest similarity is used as the judgment moment vector of the scene;
according to the judgment of the sceneThe time vector and h1Calculating the recognition rate of the scene according to the similarity;
and determining the scene time corresponding to the judgment time vector of the scene as the optimal scene time of the current scene.
Wherein, the said is according to h1Judging the current water inrush or water permeation situation according to the water inrush or water permeation situation related to the situation data vector in the corresponding situation class, specifically comprising:
h1if the scene exists in the previous judgment result, the scene is taken as the scene in the current judgment result, and the optimal scene time of the scene in the current judgment result and the judgment rate of the current scene are determined according to the following method:
from h1Selecting the scene data vector in the corresponding scene class, wherein the scene time is closest to t0+ Δ t of the scene data vector as the judgment time vector of the scene, and obtaining the scene time t of the scene data vector1；
Determining the best scene moment of the current scene in the current judgment result as (t)0+Δt+t1) /2.0, wherein t0For the optimal scene moment of the scene in the previous identification result, delta t is h1And h0Time difference, h, input to the classifier0A vector of monitoring data input to the classifier for the previous time;
and obtaining the judgment rate of the scene in the current judgment result by the iterative operation shown in the formula III according to the judgment rate of the scene in the previous judgment result:
pn＝pn-1×pa+smn×pb(formula three)
Wherein p isn-1Representing the recognition rate, p, of the scene in the previous recognition resultnIndicating the recognition rate, sm, of the scene in the calculated current recognition resultnIs h1Similarity between the recognition time vector and the scene, paTo be arranged asThe accumulated judgment rate contribution ratio value; p is a radical ofbAnd contributing a proportion value to the set current identification rate.
Wherein, the said is according to h1Judging the current water inrush or water permeation situation according to the water inrush or water permeation situation related to the situation data vector in the corresponding situation class, specifically comprising:
if h1If the water inrush or water permeability scenario related to the scenario data vector in the corresponding scenario class does not exist in the previous recognition result, taking the scenario as the scenario in the current recognition result, and then determining the best scenario time of the scenario currently in the current recognition result and the recognition rate of the scenario currently according to the following method:
from h1Acquiring each scene data vector of the scene in the corresponding scene class;
for each acquired context data vector, calculating h1Similarity with the scene data vector;
determining the sum of h1The scene data vector with the highest similarity;
according to the scene data vector and h1Calculating the judgment rate of the scene in the current judgment result according to the similarity;
and determining the scene time corresponding to the scene data vector as the optimal scene time of the current scene in the current identification result.
Wherein, the said is according to h1Judging the current water inrush or water permeation situation according to the water inrush or water permeation situation related to the situation data vector in the corresponding situation class, specifically comprising:
for the result existing in the previous recognition but h1And determining the optimal scene time of the scene in the current identification result and the identification rate of the current scene according to the following method:
determining the best scene moment of the current scene in the current identification result as t0+ Δ t, where t0Is that it isThe best scene moment of the scene in the previous identification result is h1And h0Time difference, h, input to the classifier0A vector of monitoring data input to the classifier for the previous time;
and obtaining the judgment rate of the scene in the current judgment result by the iterative operation shown in the formula III according to the judgment rate of the scene in the previous judgment result:
pn＝pn-1×pa+smn×pb(formula three)
Wherein p isn-1Representing the recognition rate, p, of the scene in the previous recognition resultnIndicating the recognition rate, sm, of the scene in the calculated current recognition resultn＝0，paFor a set cumulative recognition rate contribution ratio value, pbAnd contributing a proportion value to the set current identification rate.
The invention also provides an identification device for the scene of water penetration in the mine, which comprises:
a monitoring data acquisition module for acquiring current monitoring water flow data of each monitoring device deployed in each mine tunnel to form a current monitoring data vector h1；
A scene classification module for classifying h1Inputting the obtained data into a classifier, and obtaining h output by the classifier1A corresponding scene class;
a scene judging module for judging according to h1Judging the current water inrush or water permeation scene related to the scene data vector in the corresponding scene class;
the classifier is obtained by training scene data sample sets classified into different scene classes in advance; the scene data sample set comprises a plurality of scene data vectors
Wherein the content of the first and second substances,
representing acquisition at scene time t in water-inrush or water-breakthrough scene cThe scene data vector is composed of water flow data monitored by each monitoring device; c e p, t e t, p represents a set comprising various water-break, water-permeable scenes, t represents a period of scene simulation under water-break or water-permeable scenes c.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the method for identifying the water inrush situation in the mine.
According to the technical scheme, the current monitoring data vector h is formed by acquiring current monitoring water flow data of each monitoring device deployed in each roadway of a mine1(ii) a H is to be1Inputting the obtained data into a classifier, and obtaining h output by the classifier1A corresponding scene class; according to h1Judging the current water inrush or water permeation scene related to the scene data vector in the corresponding scene class; the classifier is obtained by training scene data sample sets classified into different scene classes in advance; therefore, the purpose of rapidly judging and identifying the water penetration scene in the mine based on the current monitoring water flow data of each monitoring device in the mine roadway is achieved, and corresponding emergency rescue and disposal can be carried out in time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart of a classifier training method according to an embodiment of the present invention;
fig. 2 is a flowchart of an identification method for a water inrush situation in a mine according to an embodiment of the present invention;
fig. 3 is a flowchart of a method for identifying a current water inrush or water penetration scenario according to an embodiment of the present invention;
fig. 4 is a flowchart of a method for determining an identification rate of a current scenario in an identification result and an optimal scenario time of the current scenario according to an embodiment of the present invention;
fig. 5 is a flowchart of a method for identifying a current water inrush or water permeability scenario of a mine according to a previous identification result in an embodiment of the present invention;
fig. 6 is a schematic diagram of a position of a monitoring device deployed in a mine according to an embodiment of the present invention;
fig. 7a is a schematic diagram of a change process of an identification result according to an embodiment of the present invention;
FIG. 7b is a schematic diagram illustrating the variation of burst (permeation) water amount for three burst (permeation) water scenarios provided by the embodiment of the present invention;
fig. 8 is a schematic diagram showing a roadway submerging range and predicting a water flow spreading process of a future roadway in a three-dimensional visualization manner according to an embodiment of the present invention;
fig. 9 is an internal structure block diagram of an identification device for a water inrush situation in a mine according to an embodiment of the present invention;
fig. 10 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to specific embodiments and the accompanying drawings.
It is to be noted that technical terms or scientific terms used in the embodiments of the present invention should have the ordinary meanings as understood by those having ordinary skill in the art to which the present disclosure belongs, unless otherwise defined. The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
The inventor considers that by means of information technology means such as three-dimensional geological modeling, roadway water flow numerical simulation and Internet of things, a mine water disaster emergency evacuation simulation system is firstly proposed in 2017, cloud computing and machine learning algorithms are fused in 2018, a mine water disaster 'one-map' and an intelligent emergency system are constructed, and a new research direction is provided for mine water disaster prevention and control.
Therefore, on the basis of the research of the emergency system, a 'quick emergency' framework is further organized, namely: firstly, analyzing possible water bursting (penetration) scenes of a mine according to mine geological and hydrogeological conditions, mining engineering and the like, and establishing a water bursting (penetration) scene library of the mine; then, calculating a water burst (penetration) spreading rule by using a roadway water flow numerical simulation technology, and constructing a mine water burst (penetration) spreading scenario library; then carrying out cluster analysis on the water outburst (penetration) spreading scenes to obtain different scene classes; and training a classifier by using a random forest algorithm based on the classified situation classes, and establishing a mine water burst (penetration) rapid identification model. The construction and the use of the quick identification are important links for playing the role of the intelligent emergency system, the analysis and research work before the water disaster accident and the emergency rescue and disposal after the accident are effectively connected, and the difficulty of the analysis and research work before the accident is greatly reduced.
Therefore, in the technical scheme of the invention, the current monitoring data vector h is formed by acquiring the current monitoring water flow data of each monitoring device deployed in each roadway of the mine1(ii) a H is to be1Inputting the obtained data into a classifier, and obtaining h output by the classifier1A corresponding scene class; according to h1Judging the current water inrush or water permeation scene related to the scene data vector in the corresponding scene class; the classifier is obtained by training scene data sample sets classified into different scene classes in advance; the number of scenesIncluding multiple context data vectors in a data sample set
Wherein the content of the first and second substances,
the scene data vector is composed of water flow data collected at scene time t and monitored by each monitoring device under the scene c of water inrush or water permeation; c ∈ Ρ, t ∈ Τ Ρ, Ρ represents a set comprising various water-break, water-permeable scenes, Τ represents a scene simulation period under water-break or water-permeable scenes. Therefore, the purpose of rapidly judging and identifying the water penetration scene in the mine based on the current monitoring water flow data of each monitoring device in the mine roadway is achieved, and corresponding emergency rescue and disposal can be carried out in time.
The technical solution of the embodiments of the present invention is described in detail below with reference to the accompanying drawings.
The classifier applied in the embodiment of the present invention can be obtained by training according to the following method, and the flow is shown in fig. 1, and includes the following steps:
step S101: a sample set of contextual data is generated.
Specifically, after analyzing data such as geological conditions of mining areas, hydrogeological conditions, mine excavation plans and the like, the water inrush (permeation) situation that may occur in mines, namely the water inrush (permeation) position and water inrush (permeation) quantity change, is proposed. The roadway water flow spreading process corresponding to the outburst (penetration) water situation scene is calculated by utilizing a roadway water flow numerical simulation method, and water flow data (water depth, flow speed, pressure measuring water head and the like) of each monitoring device arranged at different positions in each roadway of a mine at different time are marked as follows:
wherein the content of the first and second substances,
the water flow data value collected by the ith monitoring equipment is shown, T is time, i is the number of the monitoring equipment, and T is water inrush or water permeabilityAnd in the scene simulation period, omega represents the number range of the monitoring equipment. Data collected by all monitoring equipment in a mine at the same time are combined into a one-dimensional scene data vector for storage, namely:
wherein, among others,
the scene data vector is composed of water flow data collected at scene time t and monitored by each monitoring device under the scene c of water inrush or water permeation; that is to say that the position of the first electrode,
scene data vector of water inrush or water inrush scene c, c being scene data vector
The involved water inrush or breakthrough scenarios, t being scenario data vector
Corresponding scene time; c ∈ Ρ, t ∈ Τ Ρ, Ρ represents a set comprising various water-break, water-permeable scenes, Τ represents a scene simulation period under water-break or water-permeable scenes.
Respectively representing water flow data collected by 1 st to nth monitoring devices in a mine at the scene moment t; and n is the total number of monitoring equipment in the mine.
And under various water inrush or water penetration scenes, the acquired scene data vectors at different scene moments form a scene data sample set.
Step S102: and clustering the scene data vectors in the scene data sample set, and classifying the scene data vectors into different scene classes.
Specifically, hierarchical clustering or a K-means clustering method may be adopted to cluster the scene data vectors in the scene data sample set, and classify the scene data vectors in the scene data sample set into different scene classes. In the clustering process, the similarity between two scene data vectors can be calculated according to the following formula I:
in formula one, sm represents a normalized similarity metric of a scene data vector a and a scene data vector b, and i represents an element number in the scene data vector.
Step S103: based on the scene data sample sets classified into different scene classes, a classifier is trained by a random forest method.
Specifically, based on the scene data vectors in the scene data sample set classified into different scene classes, the classifier may be trained by a random forest method: establishing a random forest by using a sampling mode with putting back; in the classification calculation process, all binary trees in the random forest are used for classifying a certain scene data vector, and the probability of the scene data vector belonging to a certain class is calculated by dividing the number of the binary trees classified into the class by the total number of the binary trees in the random forest.
After the trained classifier is obtained, the method for identifying the water inrush situation in the mine based on the classifier provided by the invention has the specific flow shown in fig. 2, and comprises the following steps:
step S201: acquiring current monitoring water flow data of each monitoring device deployed in each roadway of a mine to form a current monitoring data vector h1。
Specifically, the data currently acquired by all monitoring devices in the mine are combined into a one-dimensional monitoring data vector h1＝[v1,…,vn]，v1,…,vnRespectively representing current water flow data collected by 1 st to nth monitoring equipment in a mine; and n is the total number of monitoring equipment in the mine.
Step S202: h is to be1Inputting the obtained data into a classifier, and obtaining h output by the classifier1Corresponding scene class.
Step (ii) ofS203: according to h1And judging the current water inrush or water permeation scene related to the scene data vector in the corresponding scene class.
Specifically, if the current judgment is the first judgment, i.e. h1For the monitoring data vector input to the classifier for the first time, the current water inrush or water permeation situation may be identified according to the following method to obtain the current identification result, and the specific flow is shown in fig. 3, and includes the following steps:
step S301: h is to be1The water inrush or water penetration scene related to the scene data vector in the corresponding scene class is used as the scene in the current judgment result;
step S302: for each scenario in the current recognition result, according to the method shown in the flow of fig. 4, the recognition rate of the scenario currently in the current recognition result and the best scenario time of the scenario currently in the current recognition result are further determined, which specifically includes the following sub-steps:
substep S401: from h1Acquiring each scene data vector of the scene in the corresponding scene class;
substep S402: for each acquired context data vector, calculating h1Similarity with the scene data vector;
specifically, h can be calculated according to the calculation mode of the above formula one1Similarity with the scene data vector.
Substep S403: determining the sum of h1The scene data vector of the scene with the highest similarity is used as the judgment moment vector of the scene;
substep S404: according to the judgment time vector and h of the scene1Calculating the recognition rate of the scene according to the similarity;
specifically, the recognition rate p of the scene may be calculated according to the following formula two0：
p0＝sm0×pini(formula two)
In the second formula, sm0Identify the time vector and h for the scene1Similarity of (2), piniFor judging the settingAnd (4) a rate initial value.
Substep S405: and determining the scene time corresponding to the judgment time vector of the scene as the optimal scene time of the current scene.
Substep S406: and adding the determined recognition rate of the scene and the current optimal scene moment of the scene into the current recognition result.
If the current identification is not the first identification, i.e. h1Is a monitoring data vector h formed by the water flow data monitored before each monitoring device in the mine and is not input into the classifier for the first time0Earlier than h1Is input into the classifier, and h is output from the classifier0After the corresponding scene class, can be according to h0The water inrush or water permeability scenario related to the scenario data vector in the corresponding scenario class obtains the identification result (i.e., the previous identification result) of the water inrush or water permeability scenario before the mine, and then the current identification result can be obtained by identifying the current water inrush or water permeability scenario of the mine in combination with the previous identification result, and the specific flow is shown in fig. 5, and the method includes the following steps:
step S501: judgment h1Whether the water inrush or water permeation scene related to the scene data vector in the corresponding scene class exists in the previous judgment result or not; if yes, the following step S502 is executed; otherwise, the following step S503 is performed.
Step S502: for h existing in the previous recognition result1And determining the relevant information of the scene in the current judgment result by combining each water inrush or water permeation scene related to the scene data vector in the corresponding scene class and the previous judgment result through iterative operation.
Specifically, for h existing in the previous recognition result1Taking each water inrush or water penetration scene related to the scene data vector in the corresponding scene class as a scene in the current identification result, and then determining the best scene time of the current scene in the current identification result and the identification rate of the current scene according to the following method:
from h1Corresponding scene classIn the scene data vector, selecting the closest t of the scene time0The scene data vector of the scene of + Δ t is used as the judgment time vector of the scene, and the scene time t of the scene data vector is obtained1；
Determining the best scene moment of the current scene in the current judgment result as (t)0+Δt+t1) /2.0, wherein t0For the optimal scene moment of the scene in the previous identification result, delta t is h1And h0Time difference, h, input to the classifier0A vector of monitoring data input to the classifier for the previous time;
and obtaining the judgment rate of the scene in the current judgment result by the iterative operation shown in the following formula three according to the judgment rate of the scene in the previous judgment result:
pn＝pn-1×pa+smn×pb(formula three)
Wherein p isn-1Representing the recognition rate, p, of the scene in the previous recognition resultnIndicating the recognition rate, sm, of the scene in the calculated current recognition resultnIs h1Similarity between the recognition time vector and the scene, paFor the set cumulative recognition rate contribution ratio value, for example, it may be set to 0.9; p is a radical ofbThe value of the current recognition rate contribution ratio set may be set to 0.1, for example.
Step S503: h is not present in the previous identification result1And directly calculating the relevant information of each scene in the current judgment result according to each water inrush or water penetration scene related to the scene data vector in the corresponding scene class.
Specifically, for h not existing in the previous recognition result1After each water inrush or water breakthrough scenario related to the scenario data vector in the corresponding scenario class is used as a scenario in the current recognition result, the best scenario time of the scenario currently in the current recognition result and the recognition rate of the scenario currently can be determined according to the methods of the steps in the flow shown in fig. 4, and the scenario is no longer marked hereThe above-mentioned processes are described.
Step S504: judging whether the current identification exists in the previous identification result, but h1The scene data vectors in the corresponding scene classes do not relate to water inrush or water penetration scenes; if yes, the following step S505 is executed; otherwise, ending.
Step S505: for the result existing in the previous recognition but h1And (4) the scene data vector in the corresponding scene class does not relate to the water inrush or water permeation scene, and the related information of the scene in the current judgment result is deduced according to the previous judgment result.
Specifically, for h existing in the previous recognition result1And after the scene is taken as the scene in the current identification result, determining the optimal scene time of the current scene in the current identification result and the identification rate of the current scene according to the following method:
determining the best scene moment of the current scene in the current identification result as t0+ Δ t, where t0For the optimal scene moment of the scene in the previous identification result, delta t is h1And h0Time difference, h, input to the classifier0A vector of monitoring data input to the classifier for the previous time;
obtaining the current judgment result in the current judgment result by the iterative operation of the formula III according to the judgment rate of the scene in the previous judgment result; wherein, since the scene is not h1Water inrush or water breakthrough scenarios related to scenario data vectors in the corresponding scenario class, and therefore sm is calculatedn0, i.e. h1The similarity with the scene data vector of the scene is 0.
For example, a mine with 35 monitoring devices deployed, each monitoring device located as shown in fig. 6. And selecting a water penetration scene to simulate the operation condition of monitoring equipment after water damage occurs in a mine. Monitoring the occurrence of water burst (penetration) of the mine from a monitoring device to record data and generate an identification result; selecting three scenes as representatives from the judgment result, and analyzing the variation of the judgment resultThe formation process is shown in FIG. 7 a. Given piniThe value of (a) is less than 50%, the recognition rates of the three water inrush (breakthrough) scenes show different change trends, and as can be seen from fig. 7 a: after the recognition rate of the scene a fluctuates slightly, the recognition rate is stably increased by over 90 percent; the scene b gradually decreases to below 50% after the fluctuation increases; scenario c then drops sharply below 10% after the surge increases. The judgment result shows that the scene a has higher scene similarity with the data of the simulation monitoring equipment. Essentially, scenario a is the scenario where the data of the analog monitoring device is selected; the position of the scene b is the same as that of the scene a, but the water burst (permeation) amount is smaller; the scene c is the same as the scene a in the amount of burst (permeation) water, but the position of the burst (permeation) water is different. The change in burst (through) water volume for the three burst (through) water scenarios is shown in fig. 7 b. Therefore, by applying the technical scheme of the invention, after the judgment time 41, the situation of the mine can be predicted to be the situation a, and a basis is provided for emergency rescue and disposal of the water disaster of the mine.
After the mine water disaster accident information is obtained by utilizing the rapid identification, the roadway submerging range can be displayed in a three-dimensional visual mode, and the future roadway water flow spreading process can be predicted, as shown in fig. 8, the change of the side pressure water head from small (0m) to large (>1.5m) is plotted from deep to shallow in roadway coloring. Fig. 8 shows the change situation of the mine flooding range when the mine water disaster accident of the scene a occurs for 5min, 10min, 20min, 30min, 1h and 2h, and provides a basis for emergency rescue and disposal of the mine water disaster.
Based on the identification method for the situation of penetration through water in the mine, the identification device for the situation of penetration through water in the mine provided by the embodiment of the invention has a structure shown in fig. 9, and comprises: a monitoring data obtaining module 901, a scene classification module 902, and a scene identification module 903.
The monitoring data obtaining module 901 is configured to obtain current water flow data monitored by each monitoring device deployed in each roadway of the mine to form a current monitoring data vector h1；
The scene classification module 902 is used for classifying h1Inputting the obtained data into a classifier, and obtaining h output by the classifier1A corresponding scene class; wherein the classifier is a scene classified into different scene classes in advanceTraining a data sample set;
the scene judgment module 903 is used for judging the scene according to h1And judging the current water inrush or water permeation scene related to the scene data vector in the corresponding scene class to obtain a current judgment result. Specifically, the scenario judgment module 903 may judge the current water inrush or water breakthrough scenario according to the method in each step of the flow shown in fig. 3, so as to obtain a current judgment result, which is not described herein again.
Further, the device for identifying a water inrush situation in a mine provided by the embodiment of the present invention may further include: a classifier training module 904.
The classifier training module 904 is configured to train classifiers by sets of contextual data samples classified into different contextual classes. Specifically, the classifier training module 904 may train the classifier according to the method in each step of the flow shown in fig. 1, which is not described herein again.
The apparatus of the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Fig. 10 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute a related program to implement the method for identifying the water inrush situation in the mine provided in the embodiment of the present disclosure.
The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called to be executed by the processor 1010.
The input/output interface 1030 is used for connecting an input/output module to input and output information. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present apparatus and other apparatuses. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).
It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
According to the technical scheme, the current monitoring data vector h is formed by acquiring current monitoring water flow data of each monitoring device deployed in each roadway of a mine1(ii) a H is to be1Inputting the obtained data into a classifier, and obtaining h output by the classifier1A corresponding scene class; according to h1Judging the current water inrush or water permeation scene related to the scene data vector in the corresponding scene class; wherein the classificationThe device is obtained by training scene data sample sets classified into different scene classes in advance; therefore, the purpose of rapidly judging and identifying the water penetration scene in the mine based on the current monitoring water flow data of each monitoring device in the mine roadway is achieved, and corresponding emergency rescue and disposal can be carried out in time.
Computer-readable media of the present embodiments, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the idea of the invention, also features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
In addition, well known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures for simplicity of illustration and discussion, and so as not to obscure the invention. Furthermore, devices may be shown in block diagram form in order to avoid obscuring the invention, and also in view of the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the present invention is to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the invention, it should be apparent to one skilled in the art that the invention can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.
The embodiments of the invention are intended to embrace all such alternatives, modifications and variances that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements and the like that may be made without departing from the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. A method for judging and identifying a water penetration scene in a mine is characterized by comprising the following steps:
acquiring current monitoring water flow data of each monitoring device deployed in each roadway of a mine to form a current monitoring data vector h1；
H is to be1Inputting the obtained data into a classifier, and obtaining h output by the classifier1A corresponding scene class;
according to h1Judging the current water inrush or water permeation scene related to the scene data vector in the corresponding scene class;
the classifier is obtained by training scene data sample sets classified into different scene classes in advance; the scene data sample set comprises a plurality of scene data vectors
Wherein the content of the first and second substances,
the scene data vector is composed of water flow data collected at scene time t and monitored by each monitoring device under the scene c of water inrush or water permeation; c ∈ Ρ, t ∈ Τ Ρ, Ρ represents a set comprising various water-break, water-permeable scenes, Τ represents a scene simulation period under water-break or water-permeable scenes.
2. The method of claim 1, wherein the function h is based on1Judging the current water inrush or water permeation situation according to the water inrush or water permeation situation related to the situation data vector in the corresponding situation class, specifically comprising:
if the current judgment is the first judgment, judging the current water inrush or water permeation situation according to the following method to obtain the current judgment result:
h is to be1The water inrush or water penetration scene related to the scene data vector in the corresponding scene class is used as the scene in the current judgment result;
for each scene in the recognition result, determining the best scene moment of the scene in the recognition result and the recognition rate of the current scene according to the following method:
acquiring each scene data vector of the scene from the scene class;
h is calculated for each acquired scene data vector of the scene1Similarity with the scene data vector;
determining the sum of h1The scene data vector of the scene with the highest similarity is used as the judgment moment vector of the scene;
according to the judgment time vector and h of the scene1Calculating the recognition rate of the scene according to the similarity;
and determining the scene time corresponding to the judgment time vector of the scene as the optimal scene time of the current scene.
3. The method of claim 1, wherein the step of applying the coating comprises applying a coating to the substrateAccording to h1Judging the current water inrush or water permeation situation according to the water inrush or water permeation situation related to the situation data vector in the corresponding situation class, specifically comprising:
h1if the scene exists in the previous judgment result, the scene is taken as the scene in the current judgment result, and the optimal scene time of the scene in the current judgment result and the judgment rate of the current scene are determined according to the following method:
from h1Selecting the scene data vector in the corresponding scene class, wherein the scene time is closest to t0+ Δ t of the scene data vector as the judgment time vector of the scene, and obtaining the scene time t of the scene data vector1；
Determining the best scene moment of the current scene in the current judgment result as (t)0+Δt+t1) /2.0, wherein t0For the optimal scene moment of the scene in the previous identification result, delta t is h1And h0Time difference, h, input to the classifier0A vector of monitoring data input to the classifier for the previous time;
and obtaining the judgment rate of the scene in the current judgment result by the iterative operation shown in the formula III according to the judgment rate of the scene in the previous judgment result:
pn＝pn-1×pa+smn×pb(formula three)
Wherein p isn-1Representing the recognition rate, p, of the scene in the previous recognition resultnIndicating the recognition rate, sm, of the scene in the calculated current recognition resultnIs h1Similarity between the recognition time vector and the scene, paContributing a proportion value for the set accumulated recognition rate; p is a radical ofbAnd contributing a proportion value to the set current identification rate.
4. The method of claim 1, wherein the function h is based on1Corresponding toJudging the current water inrush or water permeation situation according to the water inrush or water permeation situation related to the situation data vector in the situation class, and specifically comprising the following steps:
if h1If the water inrush or water permeability scenario related to the scenario data vector in the corresponding scenario class does not exist in the previous recognition result, taking the scenario as the scenario in the current recognition result, and then determining the best scenario time of the scenario currently in the current recognition result and the recognition rate of the scenario currently according to the following method:
from h1Acquiring each scene data vector of the scene in the corresponding scene class;
for each acquired context data vector, calculating h1Similarity with the scene data vector;
determining the sum of h1The scene data vector with the highest similarity;
according to the scene data vector and h1Calculating the judgment rate of the scene in the current judgment result according to the similarity;
and determining the scene time corresponding to the scene data vector as the optimal scene time of the current scene in the current identification result.
5. The method of claim 1, wherein the function h is based on1Judging the current water inrush or water permeation situation according to the water inrush or water permeation situation related to the situation data vector in the corresponding situation class, specifically comprising:
for the result existing in the previous recognition but h1And determining the optimal scene time of the scene in the current identification result and the identification rate of the current scene according to the following method:
determining the best scene moment of the current scene in the current identification result as t0+ Δ t, where t0For the optimal scene moment of the scene in the previous identification result, delta t is h1And h0Time difference, h, input to the classifier0A vector of monitoring data input to the classifier for the previous time;
and obtaining the judgment rate of the scene in the current judgment result by the iterative operation shown in the formula III according to the judgment rate of the scene in the previous judgment result:
pn＝pn-1×pa+smn×pb(formula three)
Wherein p isn-1Representing the recognition rate, p, of the scene in the previous recognition resultnIndicating the recognition rate, sm, of the scene in the calculated current recognition resultn＝0，paFor a set cumulative recognition rate contribution ratio value, pbAnd contributing a proportion value to the set current identification rate.
6. The method of claim 1, wherein the scene data vectors in the scene data sample set are classified into different scene classes by hierarchical clustering or K-means clustering.
7. The method of claim 1, wherein the classifier is trained by a random forest method based on a sample set of scene data classified into different scene classes.
8. The utility model provides a device is discerned to judgement of abrupt permeable scene in mine which characterized in that includes:
a monitoring data acquisition module for acquiring current monitoring water flow data of each monitoring device deployed in each mine tunnel to form a current monitoring data vector h1；
A scene classification module for classifying h1Inputting the obtained data into a classifier, and obtaining h output by the classifier1A corresponding scene class;
a scene judging module for judging according to h1Judging the current water inrush or water permeation scene related to the scene data vector in the corresponding scene class;
wherein the classifierThe scene data is obtained by training scene data sample sets classified into different scene classes in advance; the scene data sample set comprises a plurality of scene data vectors
Wherein the content of the first and second substances,
the scene data vector is composed of water flow data collected at scene time t and monitored by each monitoring device under the scene c of water inrush or water permeation; c e p, t e t, p represents a set comprising various water-break, water-permeable scenes, t represents a period of scene simulation under water-break or water-permeable scenes c.
9. The apparatus of claim 8, further comprising:
and the classifier training module is used for training the classifier through the scene data sample set classified into different scene classes.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1-7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010183067.9A CN113408322B (en) | 2020-03-16 | 2020-03-16 | Method and device for identifying sudden permeable scene in mine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010183067.9A CN113408322B (en) | 2020-03-16 | 2020-03-16 | Method and device for identifying sudden permeable scene in mine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113408322A true CN113408322A (en) | 2021-09-17 |
| CN113408322B CN113408322B (en) | 2022-12-02 |
Family
ID=77676743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010183067.9A Active CN113408322B (en) | 2020-03-16 | 2020-03-16 | Method and device for identifying sudden permeable scene in mine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113408322B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160070828A1 (en) * | 2013-04-08 | 2016-03-10 | China University of Mining & Technology, Beijng | Vulnerability Assessment Method of Water Inrush from Aquifer Underlying Coal Seam |
| CN106095990A (en) * | 2016-06-21 | 2016-11-09 | 山东科技大学 | A kind of method of discrimination for deep-well Water Inrush degree of risk |
| CN106194262A (en) * | 2016-08-03 | 2016-12-07 | 太原理工大学 | Mine floor Austria limestone gushing water on-line monitoring intelligent early-warning system |
| CN106683728A (en) * | 2016-12-21 | 2017-05-17 | 中国核电工程有限公司 | Accident diagnosis method based on unit state |
| CN106910139A (en) * | 2017-02-22 | 2017-06-30 | 北京石油化工学院 | A kind of prominent flooding disaster emergency evacuation analogy method in colliery |
| CN108832630A (en) * | 2018-07-17 | 2018-11-16 | 东北大学 | A kind of power grid CPS prevention and control method based on forecast accident scene |
| CN109063230A (en) * | 2018-06-11 | 2018-12-21 | 中国矿业大学(北京) | Different gushing waters or permeable condition go down into a mine the evaluation method of the process of flooding |
| CN110288501A (en) * | 2019-07-05 | 2019-09-27 | 华北科技学院 | A kind of mine water disaster accident emergency decision-making technique and system |
| CN110781807A (en) * | 2019-10-23 | 2020-02-11 | 泰康保险集团股份有限公司 | Disaster information processing method and device |
| 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 |
-
2020
- 2020-03-16 CN CN202010183067.9A patent/CN113408322B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160070828A1 (en) * | 2013-04-08 | 2016-03-10 | China University of Mining & Technology, Beijng | Vulnerability Assessment Method of Water Inrush from Aquifer Underlying Coal Seam |
| CN106095990A (en) * | 2016-06-21 | 2016-11-09 | 山东科技大学 | A kind of method of discrimination for deep-well Water Inrush degree of risk |
| CN106194262A (en) * | 2016-08-03 | 2016-12-07 | 太原理工大学 | Mine floor Austria limestone gushing water on-line monitoring intelligent early-warning system |
| CN106683728A (en) * | 2016-12-21 | 2017-05-17 | 中国核电工程有限公司 | Accident diagnosis method based on unit state |
| CN106910139A (en) * | 2017-02-22 | 2017-06-30 | 北京石油化工学院 | A kind of prominent flooding disaster emergency evacuation analogy method in colliery |
| CN109063230A (en) * | 2018-06-11 | 2018-12-21 | 中国矿业大学(北京) | Different gushing waters or permeable condition go down into a mine the evaluation method of the process of flooding |
| CN108832630A (en) * | 2018-07-17 | 2018-11-16 | 东北大学 | A kind of power grid CPS prevention and control method based on forecast accident scene |
| CN110288501A (en) * | 2019-07-05 | 2019-09-27 | 华北科技学院 | A kind of mine water disaster accident emergency decision-making technique and system |
| CN110781807A (en) * | 2019-10-23 | 2020-02-11 | 泰康保险集团股份有限公司 | Disaster information processing method and device |
| 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 |
Non-Patent Citations (9)
| Title |
|---|
| DAN MA等: "A Global Optimization-Based Method for the Prediction of Water Inrush Hazard from Mining Floor", 《WATER》 * |
| DEKANG ZHAO等: "Using random forest for the risk assessment of coal-floor water inrush in Panjiayao Coal Mine, northern China", 《HYDROGEOLOGY JOURNAL》 * |
| QIN LIU等: "Application of the comprehensive identification model in analyzing the source of water inrush", 《ARABIAN JOURNAL OF GEOSCIENCES》 * |
| SHICHUAN ZHANG等: "Experimental Simulation of Fault Water Inrush Channel Evolution in a Coal Mine Floor", 《MINE WATER ENVIRON》 * |
| YINGWANG ZHAO等: "Location and flux discrimination of water inrush using its spreading process in underground coal mine", 《SAFETY SCIENCE》 * |
| 武强等: "矿井巷道突(透)水蔓延模型研究及应用", 《煤炭工程》 * |
| 赵颖旺等: "基于人工智能的矿井水害灾情研判及预测研究", 《中国矿业大学学报》 * |
| 连会青等: "基于"情景–应对"的矿井水灾事故应急决策机制", 《煤田地质与勘探》 * |
| 陈秦生等: "用模式识别方法预测煤矿突水", 《煤炭学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113408322B (en) | 2022-12-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Classification of rockburst in underground projects: comparison of ten supervised learning methods | |
| Talagala et al. | Anomaly detection in streaming nonstationary temporal data | |
| e Sousa et al. | The use of data mining techniques in rockburst risk assessment | |
| Hung et al. | Methods for assessing the credibility of volunteered geographic information in flood response: A case study in Brisbane, Australia | |
| CN111242521A (en) | Track anomaly detection method and system | |
| US10073908B2 (en) | Functional space-time trajectory clustering | |
| Lind et al. | Artificial neural networks in drilling troubles prediction | |
| CN107366534B (en) | Method and device for determining coarsening permeability | |
| CN113688532B (en) | Mine disaster early warning method and device, storage medium and electronic device | |
| Asencio-Cortés et al. | Improving earthquake prediction with principal component analysis: application to Chile | |
| US20210064848A1 (en) | Method and System for Prediction and Mitigation of Spontaneous Combustion in Coal Stock Piles | |
| CN112031839B (en) | Mine pressure space-time bi-periodic prediction method, device and equipment under limited data condition | |
| CN115861400B (en) | Target object detection method, training device and electronic equipment | |
| Tordesillas et al. | Spatiotemporal slope stability analytics for failure estimation (SSSAFE): linking radar data to the fundamental dynamics of granular failure | |
| Kumar et al. | BS-LSTM: an ensemble recurrent approach to forecasting soil movements in the real world | |
| CN111815576A (en) | Method, device, equipment and storage medium for detecting corrosion condition of metal part | |
| Mahurkar | Integrating yolo object detection with augmented reality for ios apps | |
| CN116028798A (en) | Water damage early warning data processing method, device, computer equipment and storage medium | |
| Zhao et al. | A hybrid recognition model of microseismic signals for underground mining based on CNN and LSTM networks | |
| Chen et al. | Association mining of near misses in hydropower engineering construction based on convolutional neural network text classification | |
| CN114251125A (en) | Intelligent early warning system for water damage of coal mine | |
| CN113408322B (en) | Method and device for identifying sudden permeable scene in mine | |
| KR20220029396A (en) | Automation device and method for evaluating Rock Mass Rating(RMR) using deep learning models | |
| JP7348575B2 (en) | Deterioration detection device, deterioration detection system, deterioration detection method, and program | |
| Devi et al. | Exploration of multiple linear regression with ensembling schemes for roof fall assessment using machine learning |
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 |