CN110058294A - A kind of tunnel micro seismic monitoring rock rupture event automatic identifying method - Google Patents
A kind of tunnel micro seismic monitoring rock rupture event automatic identifying method Download PDFInfo
- Publication number
- CN110058294A CN110058294A CN201910388659.1A CN201910388659A CN110058294A CN 110058294 A CN110058294 A CN 110058294A CN 201910388659 A CN201910388659 A CN 201910388659A CN 110058294 A CN110058294 A CN 110058294A
- Authority
- CN
- China
- Prior art keywords
- waveform
- event
- rupture
- sample
- seismic monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000011435 rock Substances 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012544 monitoring process Methods 0.000 title claims abstract description 45
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 19
- 238000013135 deep learning Methods 0.000 claims abstract description 13
- 239000000523 sample Substances 0.000 claims description 94
- 238000012360 testing method Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 2
- 230000004913 activation Effects 0.000 description 3
- 238000005422 blasting Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005553 drilling Methods 0.000 description 3
- 238000004880 explosion Methods 0.000 description 2
- 230000010358 mechanical oscillation Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000004575 stone Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009172 bursting Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 230000005641 tunneling Effects 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/01—Measuring or predicting earthquakes
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Remote Sensing (AREA)
- Acoustics & Sound (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Geophysics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The present invention provides a kind of tunnel micro seismic monitoring rock rupture event automatic identifying method, is related to tunnel On Microseismic Monitoring Technique field.This method establishes waveform sample library first with the tunnel micro seismic monitoring waveform of a large amount of known types, then statisticallys analyze the effective information of waveform in waveform sample library, determines the waveform sample length for being used for deep learning；Establish the tunnel micro seismic monitoring waveform recognition model based on depth convolutional neural networks；By a large amount of microseism Waveform Input waveform recognition models to be identified, its type of waveform recognition result is exported；Microseismic event type is finally judged according to type of waveform recognition result.Tunnel micro seismic monitoring rock rupture event automatic identifying method provided by the invention, the original waveform of Direct Recognition micro seismic monitoring, without carrying out waveshape feature abstraction, avoid the improper influence to signal identification accuracy rate of eigenvalue, it realizes from the identification recognized to microseismic event type to micro seismic monitoring type of waveform, recognition result can be directly used for rock burst microseism early warning.
Description
Technical field
The present invention relates to tunnel On Microseismic Monitoring Technique field more particularly to a kind of tunnel micro seismic monitoring rock rupture events certainly
Dynamic recognition methods.
Background technique
As the engineerings such as mine, tunnel (road) gradually extend to deep, the dynamic disasters such as rock burst take place frequently, On Microseismic Monitoring Technique
Gradually it is applied to the rock-burst monitoring in tunnel.It is different from mine microquake monitoring, tunnel micro seismic monitoring includes much noise signal, including
The characteristics of electrical noise, mechanical noise etc., and intertexture similar to the presentation of rock rupture signal, so tunnel micro seismic monitoring needs fastly
Speed accurately identifies rock rupture event, this is the premise of promptly and accurately early warning rockburst risk.
Microseismic event automatic identifying method mainly has at present: waveform frequency spectrum analytic approach, parameter statistic etc..In related microseism
In the research of signal recognition method, invention " a kind of microseism based on focal shock parameter and explosion events recognition methods ", the patent No.
201610537634.X；It invents " a kind of identification of nonlinearity method of rock masses fracturing signal and blasting vibration signal ", the patent No.
201610110718.5；Invention " mine microquake and blast signal recognition methods based on pre-and post-peaking waveform slope ", the patent No.
201510170565.9；It invents " microseismic event recognition methods and device ", the patent No. 201710955082.9.Foregoing invention is main
Method for distinguishing is known using characteristic value.However since tunnel microseismic event energy is smaller, wave character is unobvious, characteristic value identification
Method accuracy rate is bad.And the microseismic event recognition methods efficiency based on characteristic value identification is lower, seriously affects rock burst early warning
Timeliness.In addition, the method that most of engineering sites still carry out manual identified signal using experienced personnel.But manual identified
Method inefficiency is enriched degree by artificial experience and is limited, and is equally affected to the timeliness and accuracy of rock burst early warning.
Meanwhile tunnel micro seismic monitoring usually arranges multiple sensors, has the characteristics that the more waveforms of single event.Specifically, rock
Stone Surface Rupture Events can trigger multiple microseismic sensors, and only trigger multiple sensors, just can be considered as effective Surface Rupture Events,
Even for one small energy rock rupture event, it is also possible to which, containing a certain number of noise waveforms, this just determines microseism wave
Shape type and microseismic event the type concept that be entirely two different, the two cannot be equal, and it is broken to affect rock to a certain extent
Split the accuracy of event recognition.
It can be seen that existing tunnel micro seismic monitoring rock rupture event recognition method needs to get rid of feature there is also larger limitation
Value identification and the limitation of manual identified, provide the relationship of microseism type of waveform Yu microseismic event type, establish a kind of quickly identification
Rock rupture event methods.
Summary of the invention
The technical problem to be solved by the present invention is in view of the above shortcomings of the prior art, provide a kind of tunnel micro seismic monitoring rock
Stone Surface Rupture Events automatic identifying method realizes the automatic identification to rock rupture event, promotes rock rupture event recognition efficiency
And accuracy rate.
In order to solve the above technical problems, the technical solution used in the present invention is: a kind of tunnel micro seismic monitoring rock rupture
Event automatic identifying method, comprising the following steps:
Step 1 establishes waveform sample library with the tunnel micro seismic monitoring waveform of a large amount of known types；
The waveform sample library includes rupture waveform and all noise waveforms in the complete working procedure of Tunnel Engineering, waveform
Sample database quantity will reach ten thousand grades or more, and guarantee all kinds of waveform sample quantity differences within 3 times；
The effective information of waveform, determines that the waveform sample for deep learning is long in step 2, statistical analysis waveform sample library
Degree；
The waveform sample length for deep learning is identical, the sampling that waveform sample length includes by waveform sample
Point number；Rupture waveform is counted, the effective information segment length of waveform of the analysis sample length greater than 8000, in this, as
Sample length for deep learning；
Step 3 establishes the tunnel micro seismic monitoring waveform recognition model based on depth convolutional neural networks；It will be to be identified big
Microseism Waveform Input waveform recognition model is measured, its type of waveform recognition result is exported；
When establishing waveform recognition model, the time series x (n), n=1,2 for waveform sample, 3...N are inputted, wherein N
For waveform sample length；Depth convolutional neural networks include 2 convolutional layers, 1 pond layer, 3 full articulamentums and a decision
Layer；Decision-making level's output waveform type, wherein it is 0,1 that rupture waveform and noise waveform export respectively；Using waveform sample library to depth
Degree convolutional neural networks model is trained optimization, and according to the classification results of test sample, acquisition reaches waveform recognition accuracy rate
Highest model parameter obtains the microseism waveform recognition model based on depth convolutional neural networks；
Step 4 judges microseismic event type according to type of waveform recognition result；
In a microseismic event, when type of waveform recognition result meets following condition, which is rock rupture
Event, conversely, being then noise event；
Wherein, x is to be identified as the number of the waveform of rock rupture in a microseismic event, and X is of placement sensor
Number；
According to above formula, when placement sensor number is less than 8, there is the waveform recognition result of 4 and the above sensor to be broken
When splitting waveform, which is rock rupture event, conversely, being then noise event；When placement sensor number is greater than or waits
When 8, when having the waveform recognition result of 50% or more number of probes to rupture waveform, which is rock rupture thing
Part, conversely, being then noise event.
The beneficial effects of adopting the technical scheme are that a kind of tunnel micro seismic monitoring rock provided by the invention
Surface Rupture Events automatic identifying method, the original waveform of Direct Recognition micro seismic monitoring avoid spy without carrying out waveshape feature abstraction
Value indicative chooses the improper influence to signal identification accuracy rate.Automatic identification waveform reduces the dependence to manual identified, eliminates
Influence of the human factor to signal identification greatly improves efficiency and accuracy rate to micro seismic monitoring signal identification.It provides simultaneously
It is appropriate to reduce waveform invalid information and repeated and redundant information for the waveform sample length determining method of deep learning, promote fortune
Speed is calculated, accuracy rate is improved.It realizes from the identification recognized to microseismic event type to micro seismic monitoring type of waveform, identification
As a result it can be directly used for rock burst microseism early warning.
Detailed description of the invention
Fig. 1 is a kind of process of tunnel micro seismic monitoring rock rupture event automatic identifying method provided in an embodiment of the present invention
Figure；
Fig. 2 is the distribution schematic diagram of rupture waveform and Blast waveform sample validity feature provided in an embodiment of the present invention,
In, it (b) is Blast waveform that (a), which is rupture waveform,；
Fig. 3 is rupture waveform sample length statistical result schematic diagram provided in an embodiment of the present invention；
The wave character schematic diagram that Fig. 4 is sample length provided in an embodiment of the present invention when being 3000, wherein (a) is sample
Rupture waveform when this length is 3000, it is 3000 that (b) Blast waveform when be sample length being 3000, which is (c) sample length,
When mechanical oscillation waveform.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
The present embodiment is by taking the drilling and blasting method tunneling that certain rock burst takes place frequently as an example, using tunnel micro seismic monitoring rock of the invention
Surface Rupture Events automatic identifying method carries out automatic identification to the rock rupture event in the tunnel.
A kind of tunnel micro seismic monitoring rock rupture event automatic identifying method, as shown in Figure 1, comprising the following steps:
Step 1 establishes waveform sample library with the tunnel micro seismic monitoring waveform of a large amount of known types；
The waveform sample library includes rupture waveform and all noise waveforms in the complete working procedure of Tunnel Engineering, waveform
Sample database quantity will reach ten thousand grades or more, and guarantee all kinds of waveform sample quantity differences within 3 times；
It establishes abundant and accurately waveform sample library is the premise for realizing rock rupture event automatic identification.For creating tunnel
Road engineering selects the tunnel micro seismic monitoring sample of identical digging mode, due to lacking micro seismic monitoring sample with a large amount of known types
Tunnel micro seismic monitoring waveform establish waveform sample library.And after formal construction, sample is enriched to monitor the Sample Refreshment obtained
Library.For construction tunnel, then waveform sample library is established to add up sample early period.Sample database includes rupture sample and noise sample
This.Noise sample includes all noises that complete working procedure generates, this is the guarantee to noise signal identification correctness.Separately
Outside, waveform sample library is the bigger the better, but to guarantee that Different categories of samples quantity is closer to.Sample size gap is excessive to will lead to test
All waveforms of sample are judged as the biggish one kind of quantity, and accuracy rate is larger instead.
The effective information of waveform, determines that the waveform sample for deep learning is long in step 2, statistical analysis waveform sample library
Degree；
Deep learning sample length is identical, the number of sampling points that waveform sample length includes by waveform sample；To rupture
Waveform is counted, the effective information segment length of waveform of the analysis sample length greater than 8000, in this, as depth
The sample length of habit；
Waveform sample length for deep learning need to be consistent, and can generally realize this target by two methods: one
It is by carrying out a large amount of zero paddings to the waveform compared with small sample length；Second is that passing through the redundant information for deleting larger samples length.It is real
On border, all kinds of waveform samples all contain a large amount of invalid informations or even repeated and redundant information will affect recognition efficiency.A large amount of zero paddings
Mode but will seriously affect model to the learning effect of waveform characteristic feature.As shown in Fig. 2, spy of the rupture waveform for identification
Sign is distributed mainly on effective information section, and invalid information section is substantially without obvious characteristic.Blast waveform has great quantities of spare duplicate message,
Effective information section and rupture waveform have larger difference, can be used as basis of characterization.Therefore rupture waveform sample length is counted,
The effective information segment length for analyzing the biggish waveform of sample length, in this, as the sample length for deep learning, and is analyzed
The effective information distribution of noise waveform under the conditions of identical sample length.Guaranteeing that Wave data contains the premise of mass efficient information
Under, it is appropriate to reduce waveform invalid information and repeated and redundant information, facilitate improving operational speed, improves accuracy rate.
Step 3 establishes the tunnel micro seismic monitoring waveform recognition model based on depth convolutional neural networks；It will be to be identified big
Microseism Waveform Input waveform recognition model is measured, its type of waveform recognition result is exported；
Establish the tunnel micro seismic monitoring waveform recognition model based on depth convolutional neural networks.Depth convolutional neural networks
(CNN) it is a kind of comprising convolutional calculation and with the feedforward neural network of depth structure, is one of representative algorithm of deep learning.
Since the feature detection layer of CNN is learnt by training data, so when using CNN, without carrying out explicit characteristic value
It extracts, but is implicitly learnt from training data；When establishing waveform recognition model, input layer be waveform sample when
Between sequence x (n), n=1,2,3...N, wherein N be waveform sample length, the sampled point that sample length includes by waveform sample
Number；Depth convolutional neural networks include 2 convolutional layers, 1 pond layer, 3 full articulamentums and a decision-making level；Decision-making level is defeated
Type of waveform out, wherein it is 0,1 that rupture waveform and noise waveform export respectively；Using waveform sample library to depth convolutional Neural net
Network model is trained optimization, and according to the classification results of test sample, acquisition reaches the highest model ginseng of waveform recognition accuracy rate
Number, that is, obtain the microseism waveform recognition model based on depth convolutional neural networks；
Step 4 judges microseismic event type according to type of waveform recognition result；
In application process, by a large amount of microseism Waveform Input microseism waveform recognition models to be identified, its type of waveform is exported
Recognition result.One microseismic event usually contains multiple waveforms, it is contemplated that the demand of microseismic event positioning, so in a microseism
In event, when waveform recognition result meets following condition, which is rock rupture event, conversely, being then noise event；
Wherein, x is to be identified as the number of the waveform of rock rupture in a microseismic event, and X is of placement sensor
Number.
According to above formula, when placement sensor number is less than 8, there is the waveform recognition result of 4 and the above sensor to be broken
When splitting waveform, which is rock rupture event, conversely, being then noise event；When placement sensor number is greater than or waits
When 8, when having the waveform recognition result of 50% or more number of probes to rupture waveform, which is rock rupture thing
Part, conversely, being then noise event.
In the present embodiment, the tunnel rock burst which excavates takes place frequently, and has been carried out using IMS Microseismic monitoring system to it micro-
Shake monitoring, sample frequency 6000 arrange 8 microseismic sensors altogether, establish the rock rupture thing for being directed to the Microseismic monitoring system
Part recognition methods.
Using the data of the tunnel excavation process as sample, waveform sample library is established.Sample database includes rupture waveform and makes an uproar
Acoustic wave form.Since complete drill bursting construction process is including drilling, charge explosion, ventilation smoke exhaust, slag tap (this stage also row
Danger) and spray anchor etc..In the meantime, signal received by Microseismic monitoring system has: 1. rock rupture；2. sinking and blasting；3. electricity
Gas noise；4. drilling machine broken rock；5. mechanical oscillation (containing machinery such as loading machine, pulp shooting machines), so the waveform sample library such as table 1 established
It is shown.
The waveform sample library that table 1 is established
The present embodiment has carried out a large amount of statistics, statistical result such as Fig. 3 to this engineering micro seismic monitoring rupture waveform sample length
It is shown, it is known that rupture waveform sample length more concentrates on 2500~6000 or so, and waveform sample length is greater than 10000 waveform
Only 7.9%.From Fig. 2 a it is found that the rupture waveform that sample length is 10000, main waveform effective information is distributed in 0~
3000, so selecting sample length for 3000.When sample length takes 3000, it is special that rupture waveform sample contains waveform Main change
Sign, as shown in figure 4, and noise waveform and rupture waveform present larger difference, so this waveform sample length obtaining value method is can
Capable.
According to the classification results of test sample, acquisition reaches the optimal depth convolutional neural networks mould of waveform recognition accuracy rate
Shape parameter, concrete model parameter successively include: (1) convolutional layer according to network structure sequence, include 16 3 × 3 convolution kernels,
Convolution kernel moving step length is automatically determined by same-padding strategy, using ReLU as activation primitive；(2) pond layer uses
Maximum pondization strategy；(3) convolutional layer, includes 83 × 3 convolution kernels, convolution kernel moving step length by same-padding strategy from
It is dynamic to determine, using ReLU as activation primitive；(4) full articulamentum includes 64 neuron nodes, and uses probability for 0.1
Dropout strategy, using ReLU as activation primitive；(5) full articulamentum includes 16 neuron nodes；(6) full articulamentum,
It is corresponding with waveform classification number comprising 2 nodes；(7) decision-making level, export final waveform separation using Softmax function as a result,
It is 0,1 that wherein rupture waveform and noise waveform export respectively.
The recognition result of test sample is as shown in table 2, and as shown in Table 2, identification model is accurate for the identification for rupturing waveform
Rate reaches 93%, reaches 97.1% for the recognition accuracy of noise waveform, whole accuracy rate has reached 95.8%.Model measurement
Time is 0.208s.It can be seen that the waveform recognition model based on depth convolutional neural networks is a kind of quickly accurate microseism waveform
Recognition methods.
The test result statistical form of 2 deep learning waveform recognition model of table
The present embodiment also by 200 Waveform Input models of 43 microseismic events to be identified, obtains wave as shown in table 3
Shape type and event recognition result, wherein 0 represents Surface Rupture Events, and 1 represents noise event.Due to arranging 8 microseism sensings altogether
Device, then when determining rock rupture event, in a microseismic event, when there is 4 or more waveform recognition results to be broken
When splitting waveform, which is rock rupture event, conversely, being then noise event.As seen from table, microseismic event identification is quasi-
True rate has reached 97.7%, and elapsed time is within 1min.This recognition result has further demonstrated that tunnel microseism of the invention
The convenience and accuracy of rock rupture event recognition method are monitored, to realize that rock burst microseism accurate early warning in real time lays the foundation.
3 microseismic event recognition result of table
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify to technical solution documented by previous embodiment, or some or all of the technical features are equal
Replacement；And these are modified or replaceed, model defined by the claims in the present invention that it does not separate the essence of the corresponding technical solution
It encloses.
Claims (3)
1. a kind of tunnel micro seismic monitoring rock rupture event automatic identifying method, it is characterised in that: the following steps are included:
Step 1 establishes waveform sample library with the tunnel micro seismic monitoring waveform of a large amount of known types；
The waveform sample library includes rupture waveform and all noise waveforms in the complete working procedure of Tunnel Engineering, waveform sample
Library quantity will reach ten thousand grades or more, and guarantee all kinds of waveform sample quantity differences within 3 times；
The effective information of waveform, determines the waveform sample length for being used for deep learning in step 2, statistical analysis waveform sample library；
Step 3 establishes the tunnel micro seismic monitoring waveform recognition model based on depth convolutional neural networks；It will be to be identified a large amount of micro-
Seismic wave shape input waveform identification model, exports its type of waveform recognition result；
When establishing waveform recognition model, input is the time series x (n), n=1,2 of waveform sample, 3...N, and wherein N is wave
Shape sample length exports as waveform separation result；Depth convolutional neural networks model is trained using waveform sample library excellent
Change, according to the classification results of test sample, acquisition reaches the highest model parameter of waveform recognition accuracy rate, that is, obtains based on deep
Spend the microseism waveform recognition model of convolutional neural networks；
Step 4 judges microseismic event type according to type of waveform recognition result；
In a microseismic event, when type of waveform recognition result meets following condition, which is rock rupture event,
Conversely, being then noise event；
Wherein, x is to be identified as the number of the waveform of rock rupture in a microseismic event, and X is the number of placement sensor；
According to above formula, when placement sensor number is less than 8, having the waveform recognition result of 4 and the above sensor is rupture wave
When shape, which is rock rupture event, conversely, being then noise event；When placement sensor number is greater than or equal to 8
When, when having the waveform recognition result of 50% or more number of probes to rupture waveform, which is rock rupture event,
Conversely, being then noise event.
2. a kind of tunnel micro seismic monitoring rock rupture event automatic identifying method according to claim 1, it is characterised in that:
The waveform sample length for deep learning is identical, the number of sampling points that waveform sample length includes by waveform sample；
Rupture waveform is counted, the effective information segment length of waveform of the analysis sample length greater than 8000, in this, as deep
Spend the sample length of study.
3. a kind of tunnel micro seismic monitoring rock rupture event automatic identifying method according to claim 1, it is characterised in that:
The depth convolutional neural networks include 2 convolutional layers, 1 pond layer, 3 full articulamentums and a decision-making level；Decision-making level is defeated
Type of waveform out, wherein it is 0,1 that rupture waveform and noise waveform export respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910388659.1A CN110058294A (en) | 2019-05-10 | 2019-05-10 | A kind of tunnel micro seismic monitoring rock rupture event automatic identifying method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910388659.1A CN110058294A (en) | 2019-05-10 | 2019-05-10 | A kind of tunnel micro seismic monitoring rock rupture event automatic identifying method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110058294A true CN110058294A (en) | 2019-07-26 |
Family
ID=67322752
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910388659.1A Pending CN110058294A (en) | 2019-05-10 | 2019-05-10 | A kind of tunnel micro seismic monitoring rock rupture event automatic identifying method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110058294A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110632662A (en) * | 2019-09-25 | 2019-12-31 | 成都理工大学 | Algorithm for automatically identifying microseism signals by using DCNN-inclusion network |
| CN110910613A (en) * | 2019-12-10 | 2020-03-24 | 大连理工大学 | Rock micro-seismic wireless monitoring, receiving and early warning system |
| CN111123355A (en) * | 2020-01-07 | 2020-05-08 | 山东大学 | Rockburst prediction method and system based on microseismic monitoring data |
| CN111458746A (en) * | 2020-05-29 | 2020-07-28 | 东北大学 | Tunnel microseismic waveform arrival time picking method based on U-Net neural network |
| CN111562612A (en) * | 2020-05-20 | 2020-08-21 | 大连理工大学 | Deep learning microseismic event identification method and system based on attention mechanism |
| CN111636859A (en) * | 2020-07-09 | 2020-09-08 | 中煤科工集团重庆研究院有限公司 | Coal rock while-drilling self-identification method based on micro-fracture wave detection |
| CN112487952A (en) * | 2020-11-27 | 2021-03-12 | 东北大学 | Mine microseismic signal automatic identification method based on deep learning |
| CN112882091A (en) * | 2021-01-18 | 2021-06-01 | 长安大学 | Sensitivity-improved device of micro-seismic monitoring acceleration sensor |
| CN113031060A (en) * | 2021-03-19 | 2021-06-25 | 中国科学院武汉岩土力学研究所 | Near-field microseismic signal identification method, device, equipment and storage medium |
| CN113139681A (en) * | 2021-04-13 | 2021-07-20 | 合肥综合性国家科学中心能源研究院(安徽省能源实验室) | Neural network rock burst prediction method based on time series data |
| CN114994751A (en) * | 2022-07-21 | 2022-09-02 | 中国矿业大学(北京) | Coal mine microseismic signal identification and classification method based on model experiment |
| CN115421188A (en) * | 2022-08-23 | 2022-12-02 | 安徽省新近纪防灾科技有限公司 | Micro-seismic event real-time identification system and method based on artificial intelligence |
| CN116540299A (en) * | 2023-07-05 | 2023-08-04 | 煤炭科学研究总院有限公司 | Early warning method based on microseismic energy accumulation tendency for coal mine scene |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103777232A (en) * | 2014-02-20 | 2014-05-07 | 武汉大学 | Deep rock mass rock blasting forecasting and early warning method based on blast vibration monitoring |
| CN104062677A (en) * | 2014-07-03 | 2014-09-24 | 中国科学院武汉岩土力学研究所 | Multifunctional comprehensive integrated high-precision intelligent micro-seismic monitoring system |
| US20140334260A1 (en) * | 2013-05-09 | 2014-11-13 | Schlumberger Technology Corporation | Neural Network Signal Processing of Microseismic Events |
| CN108846307A (en) * | 2018-04-12 | 2018-11-20 | 中南大学 | A kind of microseism based on waveform image and explosion events recognition methods |
| CN109063687A (en) * | 2018-08-29 | 2018-12-21 | 长江大学 | A kind of microseism P wave recognition methods and system based on depth convolutional neural networks |
-
2019
- 2019-05-10 CN CN201910388659.1A patent/CN110058294A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140334260A1 (en) * | 2013-05-09 | 2014-11-13 | Schlumberger Technology Corporation | Neural Network Signal Processing of Microseismic Events |
| CN103777232A (en) * | 2014-02-20 | 2014-05-07 | 武汉大学 | Deep rock mass rock blasting forecasting and early warning method based on blast vibration monitoring |
| CN104062677A (en) * | 2014-07-03 | 2014-09-24 | 中国科学院武汉岩土力学研究所 | Multifunctional comprehensive integrated high-precision intelligent micro-seismic monitoring system |
| CN108846307A (en) * | 2018-04-12 | 2018-11-20 | 中南大学 | A kind of microseism based on waveform image and explosion events recognition methods |
| CN109063687A (en) * | 2018-08-29 | 2018-12-21 | 长江大学 | A kind of microseism P wave recognition methods and system based on depth convolutional neural networks |
Non-Patent Citations (3)
| Title |
|---|
| 伍梦蝶: ""岩石破裂信号辨识及自动识别方法研究"", 《中国优秀硕士学位论文全文数据库•基础科学辑》 * |
| 赵明 等: ""基于深度学习卷积神经网络的地震波形自动分类与识别"", 《地球物理学报》 * |
| 陈润航 等: "地震和爆破事件源波形信号的卷积神经网络分类研究", 《地球物理学进展》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110632662A (en) * | 2019-09-25 | 2019-12-31 | 成都理工大学 | Algorithm for automatically identifying microseism signals by using DCNN-inclusion network |
| CN110910613A (en) * | 2019-12-10 | 2020-03-24 | 大连理工大学 | Rock micro-seismic wireless monitoring, receiving and early warning system |
| CN110910613B (en) * | 2019-12-10 | 2022-04-05 | 大连理工大学 | Rock micro-seismic wireless monitoring, receiving and early warning system |
| CN111123355A (en) * | 2020-01-07 | 2020-05-08 | 山东大学 | Rockburst prediction method and system based on microseismic monitoring data |
| CN111562612A (en) * | 2020-05-20 | 2020-08-21 | 大连理工大学 | Deep learning microseismic event identification method and system based on attention mechanism |
| CN111562612B (en) * | 2020-05-20 | 2021-03-19 | 大连理工大学 | Deep learning microseismic event identification method and system based on attention mechanism |
| CN111458746A (en) * | 2020-05-29 | 2020-07-28 | 东北大学 | Tunnel microseismic waveform arrival time picking method based on U-Net neural network |
| CN111636859B (en) * | 2020-07-09 | 2022-08-16 | 中煤科工集团重庆研究院有限公司 | Coal rock while-drilling self-identification method based on micro-fracture wave detection |
| CN111636859A (en) * | 2020-07-09 | 2020-09-08 | 中煤科工集团重庆研究院有限公司 | Coal rock while-drilling self-identification method based on micro-fracture wave detection |
| CN112487952A (en) * | 2020-11-27 | 2021-03-12 | 东北大学 | Mine microseismic signal automatic identification method based on deep learning |
| CN112882091A (en) * | 2021-01-18 | 2021-06-01 | 长安大学 | Sensitivity-improved device of micro-seismic monitoring acceleration sensor |
| CN113031060A (en) * | 2021-03-19 | 2021-06-25 | 中国科学院武汉岩土力学研究所 | Near-field microseismic signal identification method, device, equipment and storage medium |
| CN113139681A (en) * | 2021-04-13 | 2021-07-20 | 合肥综合性国家科学中心能源研究院(安徽省能源实验室) | Neural network rock burst prediction method based on time series data |
| CN113139681B (en) * | 2021-04-13 | 2023-10-17 | 合肥综合性国家科学中心能源研究院(安徽省能源实验室) | Neural network rock burst prediction method based on time sequence data |
| CN114994751A (en) * | 2022-07-21 | 2022-09-02 | 中国矿业大学(北京) | Coal mine microseismic signal identification and classification method based on model experiment |
| CN114994751B (en) * | 2022-07-21 | 2023-01-31 | 中国矿业大学(北京) | Coal mine microseismic signal identification and classification method based on model experiment |
| CN115421188A (en) * | 2022-08-23 | 2022-12-02 | 安徽省新近纪防灾科技有限公司 | Micro-seismic event real-time identification system and method based on artificial intelligence |
| CN115421188B (en) * | 2022-08-23 | 2024-02-20 | 宿州学院 | Microseism event real-time identification system and method based on artificial intelligence |
| CN116540299A (en) * | 2023-07-05 | 2023-08-04 | 煤炭科学研究总院有限公司 | Early warning method based on microseismic energy accumulation tendency for coal mine scene |
| CN116540299B (en) * | 2023-07-05 | 2023-09-26 | 煤炭科学研究总院有限公司 | Early warning method based on microseismic energy accumulation tendency for coal mine scene |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110058294A (en) | A kind of tunnel micro seismic monitoring rock rupture event automatic identifying method | |
| CN110109895B (en) | Surrounding rock grading combined prediction method suitable for TBM tunneling tunnel and application | |
| US20210390230A1 (en) | Method for Quickly Optimizing Key Mining Parameters of Outburst Coal Seam | |
| CN110298503B (en) | Tunnel rock burst early warning method based on microseismic information and deep convolutional neural network | |
| CN106407649B (en) | Microseismic signals based on time recurrent neural network then automatic pick method | |
| CN110319982A (en) | Underground gas pipeline leak judgment method based on machine learning | |
| CN106707340A (en) | Method for predicting volcanic rock facies | |
| CN109100627A (en) | A kind of power equipment partial discharges fault diagnostic method based on end-to-end mode | |
| CN115291281B (en) | Real-time micro-earthquake magnitude calculation method and device based on deep learning | |
| CN104834004B (en) | Mine microquake based on pre-and post-peaking waveform slope and blast signal recognition methodss | |
| CN106973039A (en) | A kind of network security situation awareness model training method and device based on information fusion technology | |
| CN110501742A (en) | A method of seismic events are distinguished using Boosting Ensemble Learning Algorithms | |
| CN110308485A (en) | Microseismic signals classification method, device and storage medium based on deep learning | |
| CN110333074A (en) | Multi-measuring point drive failure diagnostic method and system based on convolutional neural networks | |
| CN115327616B (en) | Automatic positioning method for mine microseism focus driven by massive data | |
| CN111520192A (en) | Non-contact tunnel engineering construction rock burst real-time forecasting optimization method | |
| CN109975412A (en) | Rock core uniaxial compressive strength measuring method and device based on the study of ultrasonic spectrum depth migration | |
| CN107060714B (en) | Large-scale true triaxial physical model test method for researching thin interbed fracture extension rule | |
| Xu et al. | Accurate identification of microseismic waveforms based on an improved neural network model | |
| CN110259442B (en) | Coal measure stratum hydraulic fracturing fracture horizon identification method | |
| Si et al. | A Novel coal-gangue recognition method for top coal caving face based on IALO-VMD and improved MobileNetV2 network | |
| CN113158315A (en) | Rock-soil body parameter three-dimensional non-stationary condition random field modeling method based on static cone penetration data | |
| CN111155980B (en) | Water flow dominant channel identification method and device | |
| CN110118994A (en) | A kind of nonmarine source rock quantitative forecasting technique based on seismic inversion and machine learning | |
| CN116378769A (en) | Mine ground pressure activity monitoring system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190726 |
|
| RJ01 | Rejection of invention patent application after publication |