CN115526036A - Method and system for judging rock burst scale grade - Google Patents
Method and system for judging rock burst scale grade Download PDFInfo
- Publication number
- CN115526036A CN115526036A CN202211136433.0A CN202211136433A CN115526036A CN 115526036 A CN115526036 A CN 115526036A CN 202211136433 A CN202211136433 A CN 202211136433A CN 115526036 A CN115526036 A CN 115526036A
- Authority
- CN
- China
- Prior art keywords
- rock burst
- microseismic
- rockburst
- scale
- predicted
- 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.)
- Pending
Links
- 239000011435 rock Substances 0.000 title claims abstract description 312
- 238000000034 method Methods 0.000 title claims abstract description 98
- 238000012544 monitoring process Methods 0.000 claims abstract description 63
- 238000010276 construction Methods 0.000 claims abstract description 31
- 238000010586 diagram Methods 0.000 claims abstract description 28
- 238000007417 hierarchical cluster analysis Methods 0.000 claims abstract description 16
- 238000011081 inoculation Methods 0.000 claims abstract description 16
- 238000009826 distribution Methods 0.000 claims description 37
- 230000001186 cumulative effect Effects 0.000 claims description 36
- 230000006378 damage Effects 0.000 claims description 35
- 230000002776 aggregation Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000005054 agglomeration Methods 0.000 claims description 6
- 238000004220 aggregation Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000003672 processing method Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 238000009412 basement excavation Methods 0.000 description 5
- 238000007621 cluster analysis Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 241000239290 Araneae Species 0.000 description 3
- 230000003321 amplification Effects 0.000 description 3
- 238000005422 blasting Methods 0.000 description 3
- 238000003199 nucleic acid amplification method Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005553 drilling Methods 0.000 description 2
- 230000005486 microgravity Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000005670 electromagnetic radiation Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/288—Event detection in seismic signals, e.g. microseismics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/30—Analysis
- G01V1/306—Analysis for determining physical properties of the subsurface, e.g. impedance, porosity or attenuation profiles
-
- 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
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Acoustics & Sound (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Geophysics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a method and a system for judging rock burst scale levels, which relate to the technical field of rock burst scale prediction, wherein the method for dividing and judging the rock burst scale levels comprises the following steps: constructing a rock burst case information and a sample library of microseismic monitoring information of the region to be predicted in the rock burst inoculation process; selecting a plurality of microseismic parameter data as a basis for hierarchical clustering analysis, and carrying out comprehensive clustering on the rock burst case information in the sample library; obtaining a threshold value of rock burst scale grade division according to a clustering result of rock burst case information in a sample library, determining a threshold value of a single microseismic parameter corresponding to each rock burst scale grade, drawing a spider-web diagram of the microseismic parameter of the rock burst scale grade, and determining a basic principle of potential rock burst scale grade of a region to be predicted, which is judged based on the spider-web diagram; and judging the scale grade of the potential rock burst of the area to be predicted. The rock burst scale grade prediction in the deep tunnel construction process is realized, and the fine prediction early warning level of the rock burst disaster risk is improved.
Description
Technical Field
The invention relates to the technical field of rockburst scale prediction, in particular to a method and a system for judging rockburst scale grades.
Background
Rock burst is a phenomenon that under the condition of high ground stress, elastic potential energy accumulated in hard rock is suddenly and violently released due to engineering excavation, so that a rock body bursts and is ejected. The rock burst disaster problem is more and more prominent along with the gradual extension of tunnel (road) engineering related to mines, water conservancy and hydropower, traffic and the like to the deep part. Frequent rockburst disasters in the process of excavating deep tunnels often cause a great amount of casualties and huge property loss. Therefore, the prediction of the rock burst disaster has very important significance for the safe construction of deep underground engineering.
Based on the priori knowledge of rock physical mechanical parameters, stress states and rock burst risk levels, the rock burst tendency can be predicted and evaluated, a basis is provided for engineering design, in the construction stage, along with the refinement of geological conditions and stress state data, the accuracy of rock burst tendency prediction is improved to a certain extent, but the parameters are difficult to obtain, and dynamic real-time early warning of the rock burst risk in the tunnel construction process is difficult to realize. The prediction method based on the field monitoring is characterized in that the data monitored in the excavation process are analyzed, relevant parameters can be directly obtained in real time, and rock burst risks can be predicted and evaluated in time.
Common in-situ monitoring methods include conventional monitoring (stress, displacement, etc.), acoustic emission methods (AE), microseismic monitoring Methods (MS), electromagnetic radiation methods (EMR), microgravity Methods (MC), resistivity methods, and drilling cuttings methods, among others. Because the acoustic emission method monitors high-frequency low-energy events (energy attenuation is fast, propagation distance is limited), only local small-range rock mass can be monitored. The microgravity monitoring method and the resistivity method are easily interfered by the outside, the precision is difficult to ensure, and the forecasting range of the drilling cutting method is very limited. The principle of microseismic monitoring is to receive the elastic waves generated by the rock fracturing process through sensors arranged in space. As is well known, rock damage and failure are a series of rock fracture evolution processes, and microseismic data contains information of stress and fracture change development trend in rock.
The former provides the relation between the space-time evolution of the micro-earthquake and the rock burst on the basis of comparing the monitoring result with the field reality, and summarizes micro-earthquake monitoring index rules such as a micro-earthquake density cloud chart, the relation between the micro-earthquake magnitude and the frequency, the micro-earthquake magnitude, the energy concentration and the like. With the development of scientific technology, the microseismic monitoring technology develops a complete set of rock burst prediction and early warning method, can realize the real-time monitoring of rock burst disasters in the tunnel excavation process, and obtains practice verification by using microseismic information obtained by microseismic monitoring as a precursor of rock burst. The microseismic monitoring technology has become one of the relatively widely applied methods at present.
The rock burst prediction method and the engineering application based on the microseismic monitoring information are developed greatly in recent years, and in general, the current rock burst disaster prediction mainly stays in the rock burst intensity grade prediction, the intensity grade determination takes the rock burst pit depth as a main prediction index, the rock burst depth is easy to obtain in engineering practice and can reflect the scale of rock burst to a certain extent, however, compared with the damage depth, the rock burst damage scale (the volume of the rock burst pit and the damage surface area of surrounding rocks) can represent the intensity of rock burst damage from a more comprehensive dimension, and the hazard of the rock burst and the scale of the rock mass thrown by the rock burst have obvious correlation. Engineering practice shows that for rock bursts with the same intensity grade, the scales of the caused rock bursts are different, even different, namely the corresponding rock burst risk levels under the same prediction intensity grade are possibly different, but the prior determination and prediction technical method related to the rock burst scale grade is deficient.
The microseism monitoring technology can acquire information such as the time, the position, the energy release and the like of the occurrence of a microseism event in the whole stress adjustment process after rock mass excavation in real time, and is considered to be one of the most effective means for carrying out rock burst monitoring and early warning at present.
In view of this, a scheme for dividing the rock burst scale grade based on the microseismic monitoring information needs to be developed to supplement and perfect the defects of the existing prediction method in predicting the rock burst risk level. However, how to determine the division threshold of the rock burst scale grade and determine the rock burst potential scale grade judgment based on the microseismic parameters is a technical difficulty for rock burst prediction.
Disclosure of Invention
The invention aims to provide a method and a system for judging rock burst scale grade.
The invention provides a method for judging rock burst scale grade, which comprises the following steps:
constructing a rock burst case information and a sample library of microseismic monitoring information of the region to be predicted in the rock burst inoculation process;
selecting a plurality of microseismic parameter data from the microseismic monitoring information as a basis for hierarchical clustering analysis, and carrying out comprehensive clustering on the rock burst case information in the sample library;
obtaining a threshold value of rock burst scale grade division according to a clustering result of rock burst case information in a sample library;
determining the threshold of the single microseismic parameter corresponding to each rock burst scale grade according to the threshold of the rock burst scale grade division; drawing a spider-web diagram of the microseismic parameter of the rock burst scale grade according to the threshold value of each single microseismic parameter, and determining a basic principle of the potential rock burst scale grade of the region to be predicted, which is judged based on the spider-web diagram;
and judging the potential rockburst scale grade of the area to be predicted according to the basic principle of judging the potential rockburst scale grade of the area to be predicted based on the spider-web diagram and a plurality of microseismic parameter information obtained by actually monitoring the area to be predicted.
Further, when constructing a sample library of rockburst case information and microseismic monitoring information of the area to be predicted in the rockburst inoculation process, the method comprises the following steps:
for the newly-built project of the area to be predicted, before construction, a sample library is constructed by adopting rock burst cases and microseismic monitoring information thereof in the built or under-construction project with similar construction conditions and the same construction mode;
after the new construction of the area to be predicted is constructed, supplementing and updating a sample library by using a rock burst case newly generated in the construction and microseismic monitoring information thereof;
for the construction project of the area to be predicted, constructing a sample library by using a large number of rock explosion cases accumulated in the early stage of the project and microseismic monitoring information thereof;
the rockburst case information of the area to be predicted in the rockburst inoculation process comprises the following steps: information of intensity grade of rock burst, information of volume of a rock burst pit area or damage surface area of surrounding rocks, and information of photos of rock burst;
the microseismic monitoring information of the rock burst case comprises the following information: the number of microseismic cumulative events, microseismic cumulative released energy, microseismic cumulative apparent volume, cumulative event rate, cumulative released energy rate, cumulative apparent volume rate;
preprocessing the microseismic monitoring information of the rock burst case information, comprising: respectively taking logarithms of the microseismic accumulated release energy, the microseismic accumulated visual volume, the accumulated release energy rate and the accumulated visual volume rate.
Further, the selected multiple microseismic parameters in the microseismic monitoring information are respectively: the number of microseismic cumulative events, the microseismic cumulative released energy, the microseismic cumulative apparent volume, the cumulative event rate, the cumulative released energy rate, the cumulative apparent volume rate.
Further, the comprehensive clustering of the rockburst case information in the sample library is carried out by taking the plurality of microseismic parameter data as the basis of hierarchical clustering analysis, and the comprehensive clustering comprises the following steps:
respectively carrying out standardization processing on each microseismic parameter, wherein the standardization processing method is standard deviation standardization, and the conversion formula is as follows:
wherein, X is the original data,
is the mean, S is the standard deviation;
and clustering the rock burst case information in the sample library by adopting an agglomeration hierarchical clustering method.
Further, the clustering the rockburst case information in the sample library by using the cohesive hierarchical clustering method includes:
respectively taking each rockburst case sample in the sample library as a clustered individual, and taking the individual as a rockburst case atomic cluster;
combining the rock burst case clusters to form a small set of rock burst cases according to the degree of affinity and sparseness among individuals;
and combining the rockburst case atomic clusters and the small collection classes to form a larger case set class according to the degree of affinity and sparseness between the individuals and the small collection classes and between the small collection classes.
Further, the measure rule of the degree of affinity between the individuals is as follows:
measuring the distance between the individual rock burst case sample by using a squared Euclidean distance, wherein the calculation formula is as follows:
the measuring rule of the degree of affinity between the individuals and the small set classes and between the small set classes is as follows:
measuring the distances between the individuals and the subclasses of the sets and between the subclasses of the sets by adopting the average inter-group chain distance, wherein the calculation formula is as follows:
wherein x and y are different rock burst case sample individuals respectively;
x 1 ,x 2 ,...x i ,...x n ，y 1 ,y 2 ,...y i ,...y n ，z 1 ,z 2 ,...z i ,...z n the evaluation indexes corresponding to the individual x, y and z, namely the microseismic parameters, are respectively;
(y, z) is a subclass of sets of individuals y and z.
Further, the obtaining of the threshold value of the rock burst scale grade division according to the clustering result of the rock burst case information in the sample library includes:
calculating the aggregation state parameters of the rockburst case information in the sample library during hierarchical clustering, wherein the aggregation state parameters comprise the currently executed step number in the hierarchical clustering process, the numbers of two objects clustered into a class, the clustering coefficient between the two objects participating in clustering, the identifiers of the two objects participating in clustering and the step number subsequently participating in further clustering;
determining the dividing quantity of the rock burst scale grade according to the sudden increase condition of the clustering coefficient in the hierarchical clustering process of the rock burst case information in the sample library and the combination of actual working conditions;
establishing rock burst case sample sets under different rock burst scale levels according to the clustering result of the rock burst case information in the sample library and the actual construction working conditions;
determining a confidence interval of the volume of the rock burst pit area or the distribution range of the surrounding rock damage surface area based on the volume of the rock burst pit area or the distribution range of the surrounding rock damage surface area in the rock burst case sample set;
and determining a threshold value of the rock burst pit volume or the surrounding rock damage surface area based on the confidence interval of the rock burst pit volume or the surrounding rock damage surface area distribution range, and establishing a rock burst scale grade division table.
Further, the determining the threshold of the single microseismic parameter corresponding to each rock burst scale grade according to the threshold divided by the rock burst scale grade includes:
determining the distribution range of each microseismic parameter data corresponding to each rock burst case set one by one according to the clustering result of the rock burst case information in the sample library and the rock burst case sample sets under different rock burst scale levels;
determining distribution confidence intervals of the microseismic parameters under different rock burst scale levels according to the distribution range of the microseismic parameter data corresponding to each rock burst case set;
and determining the threshold value of the single microseismic parameter corresponding to each rock burst scale grade based on the distribution confidence interval of each microseismic parameter under different rock burst scale grades.
Further, the basic principle of the classification of the potential rockburst scale of the region to be predicted based on the spider diagram includes:
determining the potential scale grade of the rockburst of the risk area by utilizing the landing point distribution position of the microseismic parameter information of the area to be predicted, which is obtained by monitoring;
when the values of four or more single microseismic parameters of the monitored area to be predicted fall in the same rockburst scale grade interval, the predicted rockburst scale is the grade;
when the rock burst scale level determined according to the value of the microseismic parameter has two levels, the predicted rock burst scale takes the higher level of the two levels;
and when the rockburst scale level determined according to the value of the microseismic parameter has three levels, taking the middle level of the three levels as the predicted rockburst scale level.
The invention also provides a system for dividing and distinguishing the rock burst scale grade, which comprises the following steps:
the data construction module is used for constructing rockburst case information of the area to be predicted in the rockburst inoculation process and a sample library of microseismic monitoring information of the area to be predicted;
the data clustering module is used for selecting a plurality of microseismic parameter data from the microseismic monitoring information as the basis of hierarchical clustering analysis and comprehensively clustering the rockburst case information in the sample library;
the grading module is used for obtaining a threshold value of rock burst scale grading according to the clustering result of the rock burst case information in the sample library;
the judgment principle establishing module is used for determining the threshold of the single microseismic parameter corresponding to each rock burst scale grade according to the threshold of the rock burst scale grade division; drawing a spider-web diagram of the microseismic parameter of the rockburst scale grade according to the threshold value of each single microseismic parameter, and determining a basic principle of the potential rockburst scale grade of the region to be predicted, which is judged based on the spider-web diagram;
and the actual judging module is used for judging the potential rockburst scale grade of the area to be predicted according to the basic principle of judging the potential rockburst scale grade of the area to be predicted based on the spider-web diagram and a plurality of microseismic parameter information obtained by actually monitoring the area to be predicted.
Compared with the prior art, the invention has the beneficial effects that:
the rockburst scale grading and judging method based on microseismic information and cluster analysis provided by the invention realizes the deep-buried tunnel (tunnel) rockburst scale grading and the judgment of the rockburst potential scale grade in the construction process, and is beneficial to improving the fine prediction early warning level of the tunnel rockburst disaster risk, so that the rockburst disaster risk prevention and control under the high stress condition has higher pertinence and effectiveness. In addition, the method has important significance for scientifically grasping the rock burst scale and the corresponding characteristics of microseismic activity and determining the specific quantification of each microseismic parameter under different rock burst scale levels.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic flow chart of a method for discriminating the scale grade of the rockburst according to the present invention;
FIG. 2 is a schematic diagram of the number of hierarchical clustering steps of the rock burst case in the embodiment of the present invention;
FIG. 3 is a volume distribution range of a rockburst pit corresponding to a case set of a level 2 rockburst scale in an embodiment of the present invention;
FIG. 4 is a volume distribution range of a rockburst pit corresponding to a case set of a grade 3 rockburst scale in an embodiment of the present invention;
FIG. 5 is a volume distribution range of a rockburst pit corresponding to a case set of a class 4 rockburst scale in an embodiment of the present invention;
FIG. 6 is a wall rock failure surface area distribution range corresponding to a class 2 rockburst scale case set in an embodiment of the present invention;
FIG. 7 is a wall rock failure surface area distribution range corresponding to a class 3 rockburst scale case set in an embodiment of the present invention;
FIG. 8 is a wall rock failure surface area distribution range corresponding to a class 4 rockburst scale case set in an embodiment of the present invention;
fig. 9 is a spider-web diagram of rock burst scale discrimination in the example of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings in the embodiments of the present invention, but it should be understood that the scope of the present invention is not limited by the specific embodiments.
Example 1
Fig. 1 is a basic idea of a method for grading and discriminating a rockburst scale according to the present invention, and provides an operation flow for finely grading and discriminating the rockburst scale, wherein the method for grading and discriminating the rockburst scale specifically includes the following steps:
step S1: constructing a rock burst case information and a sample library of microseismic monitoring information of the region to be predicted in the rock burst inoculation process;
step S2: selecting a plurality of microseismic parameter data from the microseismic monitoring information as a basis for hierarchical clustering analysis, and carrying out comprehensive clustering on the rock burst case information in the sample library;
and step S3: obtaining a threshold value of rock burst scale grade division according to a clustering result of rock burst case information in a sample library;
and step S4: determining the threshold of the single microseismic parameter corresponding to each rock burst scale grade according to the threshold of the rock burst scale grade division; drawing a spider-web diagram of the microseismic parameter of the rock burst scale grade according to the threshold value of each single microseismic parameter, and determining a basic principle of the potential rock burst scale grade of the region to be predicted, which is judged based on the spider-web diagram;
step S5: and judging the potential rockburst scale grade of the area to be predicted according to the basic principle of judging the potential rockburst scale grade of the area to be predicted based on the spider-web diagram and a plurality of microseismic parameter information obtained by actually monitoring the area to be predicted.
In step S1, when constructing a sample library of rockburst case information and microseismic monitoring information of the area to be predicted in the rockburst inoculation process, the method includes:
for a newly-built project of an area to be predicted, before construction, a sample library is constructed by adopting rock burst cases and microseismic monitoring information thereof in the built or under-built project with similar construction conditions and the same construction mode;
after the construction of a newly-built project of an area to be predicted, supplementing and updating a sample library by using a rock burst case newly generated in the project and microseismic monitoring information thereof;
for the construction project of the area to be predicted, a sample library is constructed by using a large number of rock burst cases accumulated in the early stage of the project and microseismic monitoring information of the rock burst cases.
The rockburst case information of the area to be predicted in the rockburst inoculation process comprises the following steps: intensity grade information of rockburst, volume of rockburst pit area or surface area of surrounding rock damage, and picture information of rockburst;
wherein, the microseismic monitoring information of the rock burst case includes: the number of microseismic cumulative events, microseismic cumulative released energy, microseismic cumulative apparent volume, cumulative event rate, cumulative released energy rate, cumulative apparent volume rate;
preprocessing microseismic monitoring information of rock burst case information, which comprises the following steps: respectively taking logarithms of the microseismic accumulated release energy, the microseismic accumulated visual volume, the accumulated release energy rate and the accumulated visual volume rate.
In step S2, the plurality of microseismic parameters in the selected microseismic monitoring information are respectively: number of microseismic cumulative events, microseismic cumulative released energy, microseismic cumulative apparent volume, cumulative event rate, cumulative released energy rate, cumulative apparent volume rate.
Taking a plurality of microseismic parameter data as the basis of hierarchical clustering analysis, and comprehensively clustering the rockburst case information in the sample library, wherein the method comprises the following steps:
step S2.1: respectively carrying out standardization processing on each microseismic parameter, wherein the standardization processing method is standard deviation standardization, and the conversion formula is as follows:
wherein, X is the original data,
mean, S is standard deviation.
Step S2.2: clustering the rockburst case information in the sample library by adopting an agglomeration hierarchical clustering method, wherein the clustering method comprises the following steps:
respectively taking each rockburst case sample in the sample library as a clustered individual, and taking the individual as a rockburst case atomic cluster;
combining the rock burst case clusters to form a small set of rock burst cases according to the degree of affinity and sparseness among individuals;
and combining the rockburst case atomic clusters and the small collection classes to form a larger case set class according to the degree of affinity and sparseness between the individuals and the small collection classes and between the small collection classes.
Wherein, the measuring rule of the affinity and the sparsity among individuals is as follows:
measuring the distance between individual rock burst case samples by using the squared Euclidean distance, wherein the calculation formula is as follows:
the measuring rule of the degree of affinity and sparseness between individuals and the small set classes and between the small set classes is as follows:
measuring the distances between the individual and the small set, and between the small set and the small set by using the average inter-group chain distance, wherein the calculation formula is as follows:
wherein x and y are different rock burst case sample individuals respectively;
x 1 ,x 2 ,...x i ,...x n ，y 1 ,y 2 ,...y i ,...y n ，z 1 ,z 2 ,...z i ,...z n the evaluation indexes corresponding to the individual x, y and z, namely the microseismic parameters, are respectively; (y, z) is a subclass of sets of individuals y and z.
In step S3, obtaining a threshold value for rock burst scale classification according to the clustering result of the rock burst case information in the sample library, including:
step S3.1: calculating the aggregation state parameters of the rockburst case information in the sample library during hierarchical clustering, wherein the aggregation state parameters comprise the currently executed step number in the hierarchical clustering process, the numbers of two objects clustered into a class, the clustering coefficient between the two objects participating in clustering, the identifiers of the two objects participating in clustering and the step number subsequently participating in further clustering; wherein, the clustering coefficient refers to the distance between two objects participating in clustering.
Step S3.2: determining the dividing quantity of the rock burst scale grade according to the sudden increase condition of the clustering coefficient in the hierarchical clustering process of the rock burst case information in the sample library and the combination of the actual working condition;
step S3.3: establishing rock burst case sample sets under different rock burst scale levels according to the clustering result of the rock burst case information in the sample library and the actual construction working conditions;
step S3.4: determining a confidence interval of the volume of the rock burst pit area or the distribution range of the surrounding rock damage surface area based on the volume of the rock burst pit area or the distribution range of the surrounding rock damage surface area in the rock burst case sample set;
step S3.5: and determining a threshold value of the rock burst pit volume or the surrounding rock damage surface area based on the confidence interval of the rock burst pit volume or the surrounding rock damage surface area distribution range, and establishing a rock burst scale grade division table.
The rock burst scale grade division table established in the method is shown in table 1:
table 1 quantitative grading result for representing rock burst scale by adopting volume of rock burst pit area
| Grade of |
1 | 2 | 3 | ··· | k |
| Volume of blasting pit in rockburst area (v) i /m 3 ) | 0 | (0，v 2 ] | (v 2 ，v 3 ] | ··· | >v k |
| Description of the invention | Is free of | Light and slight | Medium grade | ··· | Extremely strong |
Note: when the volume of the blasting pit is equal to the threshold value for dividing the boundary, the principle of low grade is adopted, for example, the volume of the blasting pit is v 2 m 3 Meanwhile, the rockburst scale is divided into 2 grades, which is a slight rockburst scale.
Table 2 shows quantitative grading results of rock burst scale by adopting surrounding rock destruction surface area of rock burst pit area
| Grade of |
1 | 2 | 3 | ··· | k |
| Area of destruction of surrounding rock in rockburst zone(s) i /m 2 ) | 0 | (0，s 2 ] | (s 2 ，s 3 ] | ··· | >s k |
| Description of the invention | Is free of | Light and slight | Medium grade | ··· | Extremely strong |
Note: when the damage surface area of the surrounding rock is equal to the threshold value for dividing the boundary, the principle of 'low grade' is recommended, for example, the damage surface area of the surrounding rock is s 2 m 3 Meanwhile, the rockburst scale is divided into 2 grades, which is a slight rockburst scale.
In step S4, determining the threshold of the single microseismic parameter corresponding to each rock burst scale level includes:
step S4.1: determining the distribution range of each microseismic parameter data corresponding to each rock burst case set one by one according to the clustering result of the rock burst case information in the sample library and the rock burst case sample sets under different rock burst scale levels;
step S4.2: determining the distribution confidence interval of each microseismic parameter under different rock burst scale levels according to the distribution range of each microseismic parameter data corresponding to each rock burst case set;
step S4.3: and determining the threshold value of the single microseismic parameter corresponding to each rock burst scale grade based on the distribution confidence interval of each microseismic parameter under different rock burst scale grades.
In step S5, the basic principle of the classification of the potential rockburst scale of the region to be predicted, which is determined based on the spider-web diagram, includes:
determining the potential scale grade of the rockburst of the risk area by utilizing the landing point distribution position of the microseismic parameter information of the area to be predicted, which is obtained by monitoring;
when the values of four or more single microseismic parameters of the monitored area to be predicted fall in the same rockburst scale grade interval, the predicted rockburst scale is the grade;
when the rock burst scale level determined according to the microseismic parameter value is stored in two levels, the predicted rock burst scale is the higher level of the two levels;
and when the rock burst scale level determined according to the microseismic parameter value has three levels, taking the middle level of the three levels as the predicted rock burst scale level.
Example 2
The invention provides a system for dividing and distinguishing rock burst scale grades, which comprises:
the data construction module is used for constructing rockburst case information of the area to be predicted in the rockburst inoculation process and a sample library of microseismic monitoring information of the area to be predicted;
the data clustering module is used for selecting a plurality of microseismic parameter data from the microseismic monitoring information as the basis of hierarchical clustering analysis and comprehensively clustering the rockburst case information in the sample library;
the grading module is used for obtaining a threshold value of rock burst scale grading according to the clustering result of the rock burst case information in the sample library;
the judgment principle establishing module is used for determining the threshold of the single microseismic parameter corresponding to each rock burst scale grade according to the threshold of the rock burst scale grade division; drawing a spider-web diagram of the microseismic parameter of the rock burst scale grade according to the threshold value of each single microseismic parameter, and determining a basic principle of the potential rock burst scale grade of the region to be predicted, which is judged based on the spider-web diagram;
and the actual judging module is used for judging the potential rockburst scale grade of the area to be predicted according to a basic principle of judging the potential rockburst scale grade of the area to be predicted based on the spider web diagram and a plurality of microseismic parameter information obtained by actually monitoring the area to be predicted.
In order to make the objects, technical solutions and advantages of the present invention more clear, the following description of the embodiments of the present invention is made with reference to the specific calculation examples and 8 drawings.
Selecting a certain tunnel project, and carrying out rock burst scale dynamic classification, wherein the calculation example is as follows:
1. and characterizing the damage scale of the rock burst by adopting the volume of a rock burst pit area or the damage surface area of surrounding rocks, and constructing a rock burst case and a sample library of microseismic monitoring information thereof in the tunnel construction process.
Carrying out rockburst microseismic monitoring in the tunnel excavation process of certain tunnel engineering, acquiring multi-parameter microseismic monitoring information and rockburst scale information in the rockburst inoculation process, and constructing rockburst cases and a sample library corresponding to the microseismic monitoring information and the rockburst scale information, wherein the total number of the rockburst cases is 111. The total number of rock burst-free samples is 32, the scale of the rock burst is 1 grade, and the cluster analysis is not participated.
2. Based on the micro-seismic activity characteristics in the rockburst inoculation process and the correlation between the micro-seismic activity characteristics and the rockburst scale, taking multiple micro-seismic parameters as rockburst scale grade division and risk judgment indexes, carrying out standardized processing on each micro-seismic parameter in a sample library, and constructing atomic clusters required by hierarchical clustering analysis;
2.1, selecting six key microseismic parameters such as microseismic accumulated event number, microseismic accumulated release energy, microseismic accumulated visual volume, accumulated event rate, accumulated release energy rate, accumulated visual volume rate and the like as indexes for dividing and judging rock burst scale grades according to the characteristics of surrounding rock microseismic activities accompanied in the rock burst inoculation process;
2.2, carrying out standardized processing on each microseismic parameter of a plurality of rockburst cases in the sample library, and constructing an atomic cluster required by hierarchical clustering analysis.
The standardization processing method adopts standard deviation standardization, and the conversion formula is as follows:
wherein, X is the original data,
is the mean and S is the standard deviation.
3. Carrying out comprehensive hierarchical clustering analysis on the rockburst sample library by taking the microseismic parameters as the basis of clustering analysis;
3.1, adopting a cohesive hierarchical clustering method, taking rockburst case samples as clustered individuals through a bottom-up strategy from one to one, enabling the individuals to be used as an atomic cluster to form a class by themselves, combining the atomic clusters according to the degree of closeness to form a rockburst case set subclass, combining the rockburst case atomic cluster and the set subclass to form a larger case set class, and repeating the process until all rockburst case individuals are clustered into one class; when hierarchical clustering is carried out on the rock burst scale, the measuring rule of the degree of intimacy and phobicity is as follows:
the distance between rock burst cases is mainly measured by a squared Euclidean distance, and the calculation formula is as follows:
the distances between individuals and the subclasses of collections and between the subclasses of collections are mainly measured by using the average inter-group chain distance, and the basic calculation formula is as follows:
wherein x 1 ,x 2 ,...x i ,...x n ，y 1 ,y 2 ,...y i ,...y n ，z 1 ,z 2 ,...z i ,...z n The evaluation indexes corresponding to the individual x, y and z, namely the microseismic parameters, are respectively; (y, z) is a subclass of sets of individuals y and z.
3.2, calculating the corresponding agglomeration state of the rock burst scale hierarchical clustering, wherein the result is shown in the table 1:
TABLE 1 agglomeration states corresponding to rockburst scale hierarchical clustering
The state parameters comprise the step number currently executed by hierarchical clustering analysis, the numbers of two objects grouped into one class, a clustering coefficient between the two objects participating in clustering, the identifications of the two objects participating in clustering, the step number subsequently participating in further clustering and the like; the clustering coefficient refers to the distance between two objects participating in clustering; for the identification of the hierarchical clustering object, 0 represents that the current participating hierarchical clustering is an individual, and non-0 represents that the current participating hierarchical clustering is a set subclass.
And 3.3, analyzing the change condition of the clustering coefficient in the hierarchical clustering process, and determining the dividing quantity of the rock burst scale grade according to the sudden increase condition of the clustering coefficient and by combining with the actual working condition.
Under the condition of hierarchical clustering of the rock burst cases, as can be seen from fig. 2: in the first 76 steps of clustering process, the distance between individuals or subclasses is increased slightly, the minimum amplification is 0.0000046, the maximum amplification is 0.015, and the average amplification is 0.101; in the 76 th clustering process, the distance between the subclasses is 0.1014, compared with the distance increase of the 75 th clustering process, the distance increase is 0.001; in the 77 step of clustering process, the distance between an individual and a subclass is 0.137, and compared with the distance of the 76 step of clustering, the distance is increased by 0.036; because the hierarchical clustering process has the condition that the clustering coefficient is suddenly increased between the step 76 and the step 77, the rockburst case clustering analysis process can be completed at the step 76, and finally 79 rockburst case samples are clustered into 3 types. The rock burst scale can be divided into 5 grades by combining the actual working conditions.
4. Determining a threshold value for grading the rock burst scale;
4.1, establishing case sample sets under different rock burst scale levels based on hierarchical clustering analysis of a rock burst sample library and combining actual working conditions, wherein the results are as follows;
number set of grade 1 rockburst scale cases: {46, 47, 48, 49, …,85, 86, 87, 111}, 32 rock burst-free cases in total, namely that the volume of a rock burst pit and the surface area of damage of surrounding rocks are both 0;
number set of grade 2 rockburst size cases: {11, 12, 13, 14, …,102, 103, 104, 108}, for a total of 56 cases;
number set of grade 3 rockburst size cases: {1,2,3,8, …,77, 79, 105, 106}, for a total of 13 cases;
number set of 4-grade rockburst-scale cases: {4,5,6,7, …,107, 109, 110}, for a total of 10 cases;
4.2, determining a confidence interval of the distribution range of the volume of the rock burst pit area or the damage surface area of the surrounding rock based on the distribution range of the volume of the rock burst pit area or the damage surface area of the surrounding rock in the case sample set, wherein the result is shown in fig. 3 and 4;
and 4.3, determining a threshold value of the volume of the rock burst pit or the damage surface area of the surrounding rock based on the confidence interval of the volume of the rock burst pit or the damage surface area distribution range of the surrounding rock, and establishing rock burst scale grade division as shown in tables 2 and 3.
TABLE 2 rockburst scale quantitative grading results based on rockburst pit area volume characterization
| Grade of |
1 | 2 | 3 | 4 | 5 |
| Volume of blast pit (v) i /m 3 ) | 0 | (0，5] | (5,25] | (25,60] | >60 |
| Description of the invention | Is free of | Light and slight | Medium and high grade | Is strong and strong | Extremely strong |
Note: for the volume of the blast pit equal to the threshold value for dividing the boundary, the principle of 'low grade' is recommended, such as the volume of the blast pit is 5m 3 Meanwhile, the rockburst scale is divided into 2 grades, which is a slight rockburst scale.
Table 3 rock burst scale quantitative grading result based on rock burst pit area surrounding rock damage surface area representation
| Grade of |
1 | 2 | 3 | 4 | 5 |
| Surface area of wall rock failure(s) i /m 2 ) | 0 | (0,15] | (15,45] | (45,75] | >75 |
| Description of the invention | Is free of | Light and slight | Medium and high grade | Is strong and strong | Extremely strong |
Note: when the damage surface area of the surrounding rock is equal to the threshold value for dividing the boundary, the principle of 'low grade' is recommended, for example, the damage surface area of the surrounding rock is s 2 m 3 Meanwhile, the rockburst scale is divided into 2 grades, which is a slight rockburst scale.
In specific application, after the set of the same-level rock burst scale cases is obtained through cluster analysis, the threshold of the volume of a rock burst pit or the damage surface area of surrounding rock can be determined through a method of solving a confidence interval, and the method can be specifically realized by using related statistical analysis software. If the result can not be automatically obtained, the result can be obtained by a manual delineation method. See fig. 3 and 4 for a schematic diagram of threshold determination.
5. Determining a threshold value of a single microseismic parameter corresponding to each rockburst scale grade;
5.1, determining the distribution range of the microseismic parameter data corresponding to the rock burst case one by one aiming at the rock burst scale sample set of each class on the basis of hierarchical clustering analysis, and determining the distribution confidence interval of each microseismic parameter under different rock burst scale classes;
and 5.2, determining a single microseismic parameter threshold value corresponding to each rock burst scale grade based on the distribution confidence interval of each microseismic parameter under different rock burst scale grades.
6. Constructing a microseismic parameter spider-web diagram of the rock burst scale grade, and determining a basic principle of the risk area rock burst scale grade judged based on the spider-web diagram.
6.1, integrating the division results of the single microseismic parameter threshold values corresponding to the rock burst scale grades, and constructing a spider graph for rock burst scale grade judgment, wherein the results are shown in fig. 5 and 6;
and 6.2, determining a rock burst potential scale grade basic principle based on spider-web graph discrimination.
Basic principle of discrimination: and drawing a spider-web graph according to each microseismic parameter index of the rock burst case, and determining the potential scale grade of the rock burst in the risk area by utilizing the landing point distribution position of the microseismic parameter information in the spider-web graph according to the monitored microseismic parameter information aiming at risk prediction.
Specifically, when four or more single microseismic parameter index values fall in the same rockburst scale grade interval, the predicted rockburst scale is the grade; when two rock burst scale levels are determined according to the values of the microseismic parameters (namely three microseismic parameters point to a certain level), the predicted rock burst scale is the higher level of the two levels; and when three rockburst scale grades pointed by the microseismic parameter index exist, taking the middle grade of the three grades as the predicted rockburst scale grade.
Based on the judgment principle, the 111 cases collected were subjected to the judgment back verification, and the results are shown in table 4.
TABLE 4 comparison of rockburst size discrimination results with actual conditions of sample library
As can be seen from Table 4, the back judgment accuracy rate reaches 82.88%, and the verification result shows that the rockburst scale grading and judging method based on microseismic information and cluster analysis provided by the invention has higher practicability and accuracy rate, can realize the grading of rockburst scale and the risk judgment, and can provide scientific basis for formulating targeted rockburst prevention and control measures.
Finally, the following is explained: the above disclosure is only one specific embodiment of the present invention, however, the present invention is not limited thereto, and any variations that can be made by those skilled in the art are intended to fall within the scope of the present invention.
Claims (10)
1. A method for judging the scale grade of rock burst is characterized by comprising the following steps:
constructing a sample library of rockburst case information and microseismic monitoring information of the area to be predicted in the rockburst inoculation process;
selecting a plurality of microseismic parameter data from the microseismic monitoring information as a basis for hierarchical clustering analysis, and carrying out comprehensive clustering on the rock burst case information in the sample library;
obtaining a threshold value of rock burst scale grade division according to a clustering result of rock burst case information in a sample library;
determining the threshold of the single microseismic parameter corresponding to each rock burst scale grade according to the threshold of the rock burst scale grade division; drawing a spider-web diagram of the microseismic parameter of the rock burst scale grade according to the threshold value of each single microseismic parameter, and determining a basic principle of the potential rock burst scale grade of the region to be predicted, which is judged based on the spider-web diagram;
and judging the potential rockburst scale grade of the area to be predicted according to the basic principle of judging the potential rockburst scale grade of the area to be predicted based on the spider-web diagram and a plurality of microseismic parameter information obtained by actually monitoring the area to be predicted.
2. A method for discriminating a grade of a rockburst size according to claim 1, wherein: when constructing a sample library of rockburst case information and microseismic monitoring information of the area to be predicted in the rockburst inoculation process, the method comprises the following steps:
for the newly-built project of the area to be predicted, before construction, a sample library is constructed by adopting rock burst cases and microseismic monitoring information thereof in the built or under-construction project with similar construction conditions and the same construction mode;
after the new construction of the area to be predicted is constructed, supplementing and updating a sample library by using a rock burst case newly generated in the construction and microseismic monitoring information thereof;
for the construction project of the area to be predicted, constructing a sample library by using a large number of rock burst cases accumulated in the early stage of the project and microseismic monitoring information of the rock burst cases;
the rockburst case information of the area to be predicted in the rockburst inoculation process comprises the following steps: intensity grade information of rockburst, volume of rockburst pit area or surface area of surrounding rock damage, and picture information of rockburst;
the microseismic monitoring information of the rock burst case comprises the following information: the number of microseismic cumulative events, microseismic cumulative released energy, microseismic cumulative apparent volume, cumulative event rate, cumulative released energy rate, cumulative apparent volume rate;
preprocessing the microseismic monitoring information of the rock burst case information, comprising: respectively taking logarithms of the microseismic accumulated released energy, the microseismic accumulated visual volume, the accumulated released energy rate and the accumulated visual volume rate.
3. The method for discriminating the rock burst scale grade according to claim 2, wherein: the selected multiple microseismic parameters in the microseismic monitoring information are respectively as follows: number of microseismic cumulative events, microseismic cumulative released energy, microseismic cumulative apparent volume, cumulative event rate, cumulative released energy rate, cumulative apparent volume rate.
4. A method for discriminating a rockburst scale grade according to claim 3, wherein: taking the microseismic parameter data as the basis of hierarchical clustering analysis to comprehensively cluster the rock burst case information in the sample library, wherein the comprehensive clustering comprises the following steps:
respectively carrying out standardization processing on each microseismic parameter, wherein the standardization processing method is standard deviation standardization, and the conversion formula is as follows:
wherein, X is the original data,
is the mean, S is the standard deviation;
and clustering the rockburst case information in the sample library by adopting an agglomeration hierarchical clustering method.
5. The method for discriminating the rock burst scale grade according to claim 4, wherein: the method for clustering the rock burst case information in the sample library by adopting the agglomeration hierarchical clustering method comprises the following steps:
respectively taking each rockburst case sample in the sample library as a clustered individual, and taking the individual as a rockburst case atomic cluster;
combining the rock burst case clusters to form a small set of rock burst cases according to the degree of affinity and sparseness among individuals;
and combining the rockburst case atomic clusters and the small assembly classes to form a larger case assembly class according to the intimacy degree between the individuals and the small assembly classes and between the small assembly classes.
6. The method for discriminating the grade of the rockburst size according to claim 5, wherein: the rule for measuring the degree of affinity and sparseness between the individuals is as follows:
measuring the distance between the individual rock burst case sample by using a squared Euclidean distance, wherein the calculation formula is as follows:
the measuring rule of the degree of affinity between the individuals and the small set classes and between the small set classes is as follows:
measuring the distances between the individuals and the subclasses of the sets and between the subclasses of the sets by adopting the average inter-group chain distance, wherein the calculation formula is as follows:
wherein x and y are different rock burst case sample individuals respectively;
x 1 ,x 2 ,...x i ,...x n ，y 1 ,y 2 ,...y i ,...y n ，z 1 ,z 2 ,...z i ,...z n the evaluation indexes corresponding to the individual x, y and z, namely the microseismic parameters, are respectively;
(y, z) is a subclass of sets of individuals y and z.
7. The method for discriminating the grade of the rockburst size according to claim 6, wherein: the obtaining of the threshold value of rock burst scale grade division according to the clustering result of the rock burst case information in the sample library comprises the following steps:
calculating the aggregation state parameters of the rockburst case information in the sample library during hierarchical clustering, wherein the aggregation state parameters comprise the currently executed step number in the hierarchical clustering process, the number of two objects which are clustered into a class, a clustering coefficient between the two objects which participate in clustering, the identification of the two objects which participate in clustering and the subsequent step number which participate in further clustering;
determining the dividing quantity of rock burst scale grades according to the sudden increase condition of the clustering coefficients of the rock burst case information in the sample library in the hierarchical clustering process and in combination with the actual working condition;
establishing rock burst case sample sets under different rock burst scale levels according to the clustering result of the rock burst case information in the sample library and the actual construction working conditions;
determining a confidence interval of the volume of the rock burst pit area or the distribution range of the surrounding rock damage surface area based on the volume of the rock burst pit area or the distribution range of the surrounding rock damage surface area in the rock burst case sample set;
and determining a threshold value of the rock burst pit volume or the surrounding rock damage surface area based on the confidence interval of the rock burst pit volume or the surrounding rock damage surface area distribution range, and establishing a rock burst scale grade division table.
8. The method for discriminating the rock burst scale grade according to claim 7, wherein: the determining the threshold of the single microseismic parameter corresponding to each rock burst scale grade according to the threshold divided by the rock burst scale grade comprises the following steps:
determining the distribution range of each microseismic parameter data corresponding to each rock burst case set one by one according to the clustering result of the rock burst case information in the sample library and the rock burst case sample sets under different rock burst scale levels;
determining distribution confidence intervals of the microseismic parameters under different rock burst scale levels according to the distribution range of the microseismic parameter data corresponding to each rock burst case set;
and determining the threshold value of the single microseismic parameter corresponding to each rock burst scale grade based on the distribution confidence interval of each microseismic parameter under different rock burst scale grades.
9. The method for discriminating the rock burst scale grade according to claim 7, wherein: the basic principle of the potential rockburst scale grade of the region to be predicted, which is judged based on the spider-web diagram, comprises the following steps:
determining the potential scale grade of the rockburst of the risk area by utilizing the landing point distribution position of the microseismic parameter information of the area to be predicted, which is obtained by monitoring;
when the values of four or more single microseismic parameters of the monitored area to be predicted fall in the same rockburst scale grade interval, the predicted rockburst scale is the grade;
when the rock burst scale level determined according to the microseismic parameter value is stored in two levels, the predicted rock burst scale is the higher level of the two levels;
and when the rock burst scale level determined according to the microseismic parameter value has three levels, taking the middle level of the three levels as the predicted rock burst scale level.
10. A system for discriminating the scale grade of rock burst is characterized in that: the method comprises the following steps:
the data construction module is used for constructing a sample library of rockburst case information and microseismic monitoring information of the area to be predicted in the rockburst inoculation process;
the data clustering module is used for selecting a plurality of microseismic parameter data from the microseismic monitoring information as the basis of hierarchical clustering analysis and comprehensively clustering the rockburst case information in the sample library;
the grading module is used for obtaining a threshold value of rock burst scale grading according to the clustering result of the rock burst case information in the sample library;
the judgment principle establishing module is used for determining the threshold of the single microseismic parameter corresponding to each rock burst scale grade according to the threshold of the rock burst scale grade division; drawing a spider-web diagram of the microseismic parameter of the rock burst scale grade according to the threshold value of each single microseismic parameter, and determining a basic principle of the potential rock burst scale grade of the region to be predicted, which is judged based on the spider-web diagram;
and the actual judging module is used for judging the potential rockburst scale grade of the area to be predicted according to the basic principle of judging the potential rockburst scale grade of the area to be predicted based on the spider-web diagram and a plurality of microseismic parameter information obtained by actually monitoring the area to be predicted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211136433.0A CN115526036A (en) | 2022-09-19 | 2022-09-19 | Method and system for judging rock burst scale grade |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211136433.0A CN115526036A (en) | 2022-09-19 | 2022-09-19 | Method and system for judging rock burst scale grade |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115526036A true CN115526036A (en) | 2022-12-27 |
Family
ID=84697509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211136433.0A Pending CN115526036A (en) | 2022-09-19 | 2022-09-19 | Method and system for judging rock burst scale grade |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115526036A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118068412A (en) * | 2023-12-29 | 2024-05-24 | 北京科技大学 | Rock burst early warning method and device based on microseismic source parameter space partitioning |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104732070A (en) * | 2015-02-27 | 2015-06-24 | 广西大学 | Rockburst grade predicting method based on information vector machine |
| CN110298503A (en) * | 2019-06-26 | 2019-10-01 | 东北大学 | Tunnel rock burst method for early warning based on microseism information and depth convolutional neural networks |
| CN110488352A (en) * | 2019-08-20 | 2019-11-22 | 中国科学院武汉岩土力学研究所 | A kind of determination method of the microseism parameter threshold for rock burst grade early warning |
| CN110609324A (en) * | 2019-09-30 | 2019-12-24 | 东北大学 | Method for screening rock burst early warning micro-seismic events of deep-buried tunnel |
| CN111079342A (en) * | 2019-11-29 | 2020-04-28 | 中铁工程装备集团有限公司 | TBM tunneling performance prediction method based on online rock mass grade classification |
| CN112699553A (en) * | 2020-12-29 | 2021-04-23 | 昆明理工大学 | Intelligent prediction system method for rock burst intensity level |
| CN113378116A (en) * | 2021-05-26 | 2021-09-10 | 中国人民解放军陆军航空兵学院 | Method for determining load grade critical value of aeroengine load spectrum |
| CN114723204A (en) * | 2021-01-05 | 2022-07-08 | 华北电力大学 | Power transmission line galloping grading early warning method based on supervised learning |
-
2022
- 2022-09-19 CN CN202211136433.0A patent/CN115526036A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104732070A (en) * | 2015-02-27 | 2015-06-24 | 广西大学 | Rockburst grade predicting method based on information vector machine |
| CN110298503A (en) * | 2019-06-26 | 2019-10-01 | 东北大学 | Tunnel rock burst method for early warning based on microseism information and depth convolutional neural networks |
| CN110488352A (en) * | 2019-08-20 | 2019-11-22 | 中国科学院武汉岩土力学研究所 | A kind of determination method of the microseism parameter threshold for rock burst grade early warning |
| CN110609324A (en) * | 2019-09-30 | 2019-12-24 | 东北大学 | Method for screening rock burst early warning micro-seismic events of deep-buried tunnel |
| CN111079342A (en) * | 2019-11-29 | 2020-04-28 | 中铁工程装备集团有限公司 | TBM tunneling performance prediction method based on online rock mass grade classification |
| CN112699553A (en) * | 2020-12-29 | 2021-04-23 | 昆明理工大学 | Intelligent prediction system method for rock burst intensity level |
| CN114723204A (en) * | 2021-01-05 | 2022-07-08 | 华北电力大学 | Power transmission line galloping grading early warning method based on supervised learning |
| CN113378116A (en) * | 2021-05-26 | 2021-09-10 | 中国人民解放军陆军航空兵学院 | Method for determining load grade critical value of aeroengine load spectrum |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118068412A (en) * | 2023-12-29 | 2024-05-24 | 北京科技大学 | Rock burst early warning method and device based on microseismic source parameter space partitioning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Guo et al. | Assessment of rockburst risk using multivariate adaptive regression splines and deep forest model | |
| Farhadian | A new empirical chart for rockburst analysis in tunnelling: Tunnel rockburst classification (TRC) | |
| Hudyma et al. | An engineering approach to seismic risk management in hardrock mines | |
| Zhao et al. | Classification of mine blasts and microseismic events using starting-up features in seismograms | |
| Hudaverdi et al. | Prediction of blast fragmentation using multivariate analysis procedures | |
| Kulatilake et al. | New prediction models for mean particle size in rock blast fragmentation | |
| CN111339486A (en) | Deep foundation pit blasting vibration velocity risk level big data evaluation method | |
| CN105572747B (en) | A method of identification waterflooding reservoir clastic rock lithology in the areas Fu Jia with high salt | |
| CA2873816C (en) | Systems and methods for processing geophysical data | |
| Kabiesz et al. | Application of rule-based models for seismic hazard prediction in coal mines. | |
| CN110286416B (en) | Fast two-dimensional density inversion method based on physical property function | |
| CN104239743B (en) | The method and apparatus for determining lithologic reservoir forming probability | |
| Hartley et al. | Summary of discrete fracture network modelling as applied to hydrogeology of the Forsmark and Laxemar sites | |
| CN110306978A (en) | A kind of heterogeneous reservoir reservoir physical parameter prediction technique | |
| CN112270093B (en) | Reservoir natural fracture modeling method based on microseism moment tensor inversion | |
| CN116842411A (en) | Coal mine microseismic platform network monitoring capability evaluation method based on vibration wave detection probability | |
| CN110968840A (en) | Method for judging grade of tunnel surrounding rock based on magnetotelluric sounding resistivity | |
| Li et al. | Hydraulic fractures evaluation of the glutenite and the effects of gravel heterogeneity based on cores | |
| Lin et al. | A machine learning method for soil conditioning automated decision-making of EPBM: Hybrid GBDT and Random Forest Algorithm | |
| CN115526036A (en) | Method and system for judging rock burst scale grade | |
| CN112052274A (en) | Data mining method for rock stratum subway shield construction ground surface settlement rule | |
| CN115754220B (en) | Regional soil heavy metal source analysis and evaluation method based on geological background | |
| CN113901939B (en) | Rock burst danger level prediction method based on fuzzy correction, storage medium and equipment | |
| CN112285773B (en) | Quantitative characterization method for binary structure of buried fault | |
| Woodward et al. | Seismic hazard estimation using databases with bimodal frequency–magnitude behaviour |
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 |