CN107784276A - Microseismic event recognition methods and device - Google Patents
Microseismic event recognition methods and device Download PDFInfo
- Publication number
- CN107784276A CN107784276A CN201710955082.9A CN201710955082A CN107784276A CN 107784276 A CN107784276 A CN 107784276A CN 201710955082 A CN201710955082 A CN 201710955082A CN 107784276 A CN107784276 A CN 107784276A
- Authority
- CN
- China
- Prior art keywords
- event
- identified
- passage
- convolutional neural
- wave character
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a kind of microseismic event recognition methods and device, methods described to include：S1, based on the waveform image of each passage of event to be identified, utilize the wave character of each passage of event to be identified described in default convolutional neural networks model extraction；S2, the wave character for combining all passages of event to be identified obtain the combined waveform feature of the event to be identified；S3, based on the combined waveform feature of the event to be identified, the event to be identified is classified using default supporting vector machine model.The wave character of each passage of event to be identified is extracted by presetting convolutional neural networks, the wave character of each passage is combined as an entirety i.e. combined waveform feature again, the default supporting vector machine model of input realizes the classification for treating identification events, finally realizes the identification to microseismic event in event.The automatic identification of microseismic event is realized, independent of the know-how and experience of operating personnel, the degree of accuracy is high, is not influenceed by application scenarios, generalization ability is strong.
Description
Technical field
The present embodiments relate to geophysical probing technique field, more particularly, to a kind of microseismic event identification side
Method and device.
Background technology
Microseism refers to that earthquake magnitude is less than the earthquake of three-level, and this kind of earthquake people is typically unable to perceive that, can only use specific
Instrument is monitored.Microseism can produce corresponding excitation to the medium of underground, and such fierceness may change the power of underground medium
State.Field is monitored in mine safety, omen of the microseism as mine power disaster, microseism is monitored in real time, can be had
Effect prediction and the generation of prevention dynamic disaster.In addition during the unconventionaloil pool exploration and development such as shale gas, coal bed gas, it is based on
The fracture monitoring technique of microseism has turned into domestic and international fracturing crack and has monitored one of most accurate technology.During micro seismic monitoring,
The signal that monitoring instrument receives includes explosion events, noise temporal except the microseismic signals as caused by microseismic event toward contact
The signal Deng caused by, therefore, during micro seismic monitoring, it is the basis of monitoring that microseismic event is identified in multiple affair of comforming.
Microseismic event has the characteristics of single event multichannel, specifically, when microseism occurs, it will usually cause multiple sensings
The triggering of device, the passage corresponding to these sensors will gather and store corresponding Wave data.So by a microseism thing
Caused by part, waveform that multiple passage triggering collections obtain, referred to as single event multi-channel waveform.At present, microseismic event is main
It is to be identified by information technologist, micro-seismic monitoring instrument receives a large amount of signals of multiple passage transmission, technical staff
The wave character of these signals is extracted by certain signal processing means, further according to these wave characters, utilizes knowwhy
Whether event corresponding to the signal for judging to receive with practical experience is microseismic event.
But using manual extraction signal waveform feature and then the method for identification microseismic event, workload is big, relies on operation
The know-how and experience of personnel, and according to the wave character manually extracted, the degree of accuracy of identification is low, is typically only applicable to specific
Application scenarios, generalization ability is poor.
The content of the invention
Big for workload existing for microseismic event identification technology in the prior art, the degree of accuracy of identification is low, and extensive
The problem of ability.Overcome above mentioned problem the embodiments of the invention provide a kind of or solve the above problems at least in part micro-
Shake event recognition method and device.
On the one hand the embodiments of the invention provide a kind of microseismic event recognition methods, methods described to include：
S1, based on the waveform image of each passage of event to be identified, treated using described in default convolutional neural networks model extraction
The wave character of each passage of identification events；
S2, the wave character for combining all passages of event to be identified obtain the combined waveform spy of the event to be identified
Sign；
S3, based on the combined waveform feature of the event to be identified, wait to know to described using default supporting vector machine model
Other event is classified.
Wherein, also include before step S1：
The waveform signal of each passage of event to be identified is converted into image format, and the ripple is obtained by pretreatment
Shape image.
Wherein, step S1 is specifically included：
It is several thumbnails by the waveform image of each passage of event to be identified difference random cropping, using described pre-
If convolutional neural networks model extracts the wave character of each thumbnail respectively；
Ask being worth to for the wave character of several thumbnails corresponding to each passage of event to be identified described
The wave character of each passage of event to be identified.
Wherein, step S2 is specifically included：
The wave character of each passage of event to be identified is converted into 1 × M dimensions, wherein M is the integer more than zero；
The wave character of all passages of event to be identified is combined to obtain the combined waveform feature of N × M dimensions,
Wherein N is the port number of the event to be identified.
Wherein, the default convolutional neural networks model is obtained by following steps：
Convolutional neural networks are built, wherein, the input of the convolutional neural networks is the oscillogram of the event to be identified
Picture, softmax layers are connected after full articulamentum；
The convolutional neural networks trained are trained using convolutional neural networks described in the first training data set pair；
Wherein, first training dataset includes the waveform image of the event to be identified and corresponding event category.
Wherein, the default supporting vector machine model is obtained by following steps：
SVMs is built, the input quantity dimension of the SVMs is N × M；
It is trained using SVMs described in the second training data set pair, obtains default supporting vector machine model；Its
In, second data set includes the combined waveform feature of the event to be identified and the classification of corresponding event.
Wherein, the default supporting vector machine model includes the different SVMs of multiple input quantity dimension N.
On the other hand the embodiments of the invention provide a kind of microseismic event identification device, described device to include：
Characteristic extracting module, for the waveform image based on each passage of event to be identified, utilize default convolutional neural networks
The wave character of each passage of event to be identified described in model extraction；
Feature combination module, the wave character for combining all passages of event to be identified obtain the thing to be identified
The combined waveform feature of part；
Identification module, for the combined waveform feature based on the event to be identified, utilize default supporting vector machine model
The event to be identified is classified.
The embodiments of the invention provide a kind of computer program product, the computer program product includes depositing the third aspect
The computer program on non-transient computer readable storage medium storing program for executing is stored up, the computer program includes programmed instruction, when described
When programmed instruction is computer-executed, the computer is set to perform the microseismic event recognition methods.
The embodiments of the invention provide a kind of non-transient computer readable storage medium storing program for executing, the non-transient calculating for fourth aspect
Machine readable storage medium storing program for executing stores computer instruction, and the computer instruction makes the computer perform the microseismic event identification side
Method.
A kind of microseismic event recognition methods provided in an embodiment of the present invention and device, extracted by default convolutional neural networks
The wave character of each passage of event to be identified, then the wave character of each passage is combined as an entirety i.e. combined waveform feature,
The default supporting vector machine model of input realizes the classification for treating identification events, finally realizes the identification to microseismic event in event.
The automatic identification of microseismic event is realized, independent of the know-how and experience of operating personnel, the degree of accuracy is high, not by application scenarios
Influence, generalization ability is strong.
Brief description of the drawings
Fig. 1 is a kind of flow chart of microseismic event recognition methods provided in an embodiment of the present invention；
Fig. 2 is that the default convolutional neural networks model and default supporting vector machine model are obtained in the embodiment of the present invention
Schematic diagram；
Fig. 3 is a kind of structured flowchart of microseismic event identification device provided in an embodiment of the present invention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is explicitly described, it is clear that described embodiment be the present invention
Part of the embodiment, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not having
The every other embodiment obtained under the premise of creative work is made, belongs to the scope of protection of the invention.
Fig. 1 is a kind of flow chart of microseismic event recognition methods provided in an embodiment of the present invention, as shown in figure 1, the side
Method includes：S1, based on the waveform image of each passage of event to be identified, wait to know using described in default convolutional neural networks model extraction
The wave character of other each passage of event；S2, combine all passages of event to be identified wave character obtain it is described to be identified
The combined waveform feature of event；S3, based on the combined waveform feature of the event to be identified, utilize default supporting vector machine model
The event to be identified is classified.
Convolutional neural networks (Convolutional Neural Networks, CNN) are developed recentlies, and are caused
A kind of efficient identification method paid attention to extensively.Usually, CNN basic structure includes two layers, and one is characterized extract layer, each
The input of neuron is connected with the local acceptance region of preceding layer, and extracts the local feature.Once the local feature is extracted
Afterwards, its position relationship between further feature is also decided therewith；The second is Feature Mapping layer, each computation layer of network by
Multiple Feature Mappings composition, each Feature Mapping are a planes, and the weights of all neurons are equal in plane.Feature Mapping knot
Structure uses activation primitive of the nonlinear activation function as convolutional neural networks so that Feature Mapping has shift invariant, excellent
Selection of land, Relu activation primitives can be used.Further, since the neuron on a mapping face shares weights, thus reduce network
The number of free parameter.Each convolutional layer followed by one in convolutional neural networks is used for asking local average to carry with secondary
The computation layer taken, this distinctive structure of feature extraction twice reduce feature resolution.
CNN is mainly used to identify the X-Y scheme of displacement, scaling and other forms distortion consistency.Due to CNN feature
Detection layers are learnt by training data, so when using CNN, avoid the feature extraction of display, and implicitly from instruction
Practice and learnt in data；Furthermore because the neuron weights on same Feature Mapping face are identical, so network can be learned parallel
Practise, this is also that convolutional network is connected with each other a big advantage of network relative to neuron.Convolutional neural networks are with its local weight
Shared special construction has the superiority of uniqueness in terms of speech recognition and image procossing, and it is laid out the life closer to reality
Thing neutral net, the shared complexity for reducing network of weights, the image of particularly more dimensional input vectors can directly input net
This feature of network avoids the complexity of data reconstruction in feature extraction and assorting process.
But because the signal in On Microseismic Monitoring Technique has the characteristics of single event multichannel, according to convolutional neural networks pair
Microseismic event is identified, because the port number difference of each event is, it is necessary to build and train multiple different convolutional Neural nets
Network.The time consumption for training of convolutional neural networks is longer, can not meet the requirement of quick identification microseismic event.
SVMs SVMs (Support Vector Machine, SVM) be Cortes and Vapnik in
What nineteen ninety-five proposed first, it shows many distinctive advantages in solving small sample, the identification of non-linear and high dimensional pattern, and
It can promote the use of in the other machines problem concerning study such as Function Fitting.Support vector machine method is built upon Statistical Learning Theory
VC dimensions are theoretical and Structural risk minization basis on, according to limited sample information model complexity (i.e. to spy
Determine the study precision of training sample, Accuracy) sought between learning ability (ability for identifying arbitrary sample without error)
Optimal compromise is sought, to obtain best Generalization Ability (or generalization ability).
The structure of SVMs and training are very convenient, so process is being identified to single event multichannel event
In, for port number number event we only need to build and train the SVMs of respective dimensions to be classified i.e.
Can.SVMs realizes well while classify to the event of different port numbers, avoids using convolutional Neural
Network carries out structure and training convolutional neural networks the problem of time-consuming during event category.
Specifically, in micro seismic monitoring, the waveform signal of multiple passages is received in an event, corresponding to multiple waveforms
Image.After wave character using default each passage of convolutional neural networks model extraction, the wave character of each passage is entered
Row combination obtains the combined waveform feature of the event to be identified, thus by the wave character of each passage of event to be identified
Input of the entirety as the default vector machine is combined into, realizes the classification to the event to be identified, judges to wait to know
Whether other event is microseismic event.
A kind of microseismic event recognition methods provided in an embodiment of the present invention, extracted by default convolutional neural networks to be identified
The wave character of each passage of event, then the wave character of each passage is combined as an entirety i.e. combined waveform feature, input is pre-
If supporting vector machine model realizes the classification for treating identification events, the identification to microseismic event in event is finally realized.Realize
The automatic identification of microseismic event, independent of the know-how and experience of operating personnel, the degree of accuracy is high, not by the shadow of application scenarios
Ring, generalization ability is strong.
In the above-described embodiments, also include before step S1：
The waveform signal of each passage of event to be identified is converted into image format, and the ripple is obtained by pretreatment
Shape image.
In the above-described embodiments, step S1 is specifically included：
It is several thumbnails by the waveform image of each passage of event to be identified difference random cropping, using described pre-
If convolutional neural networks model extracts the wave character of each thumbnail respectively；
Ask being worth to for the wave character of several thumbnails corresponding to each passage of event to be identified described
The wave character of each passage of event to be identified.
Preferably, can be 10 thumbnails by the waveform image random cropping of each passage.
The embodiment of the present invention by extracting wave character respectively after the waveform image random cropping by each passage, then asks for this
The characteristics of mean of a little thumbnails, the wave character of each passage that extracts can be made more accurate.
In the above-described embodiments, step S2 is specifically included：
The wave character of each passage of event to be identified is converted into 1 × M dimensions, wherein M is the integer more than zero；
The wave character of all passages of event to be identified is combined to obtain the combined waveform feature of N × M dimensions,
Wherein N is the port number of the event to be identified.
In the above-described embodiments, the default convolutional neural networks model is obtained by following steps：
Convolutional neural networks are built, wherein, the input of the convolutional neural networks is the oscillogram of the event to be identified
Picture, softmax layers are connected after full articulamentum, are exported as the wave character of the event to be identified；
The convolutional neural networks trained are trained using convolutional neural networks described in the first training data set pair；
Wherein, first training dataset includes the waveform image of the event to be identified and corresponding event category.
Wherein, the softmax layers are used to classify to event corresponding to the waveform picture of input convolutional neural networks,
Need to judge the accuracy classified by classification results in the training process, to determine whether to draw the convolutional Neural trained
Network.After the convolutional neural networks trained, because only needing using the convolutional neural networks trained to oscillogram
As carrying out feature extraction, when identifying microseismic event, directly extracted in the corresponding convolutional layer of convolutional neural networks trained
The wave character of time each passage to be detected, without using softmax layers in the neutral net that trains to be checked
Survey the classification results of time.So, presetting convolutional neural networks model both make use of convolutional neural networks to extract waveform graph ripple
The function of shape feature, when it also avoid being classified using softmax layers, the problem of being only applicable to the event of special modality number.
In addition, as shown in Fig. 2 when being trained to convolutional neural networks, typical oscillogram in known event is chosen
As being trained to convolutional neural networks, for example, the waveform image for choosing 30,000 known events is instructed to convolutional neural networks
Practice, the nicety of grading of the convolutional neural networks trained is up to 95.13%.
In the above-described embodiments, as shown in Fig. 2 the default supporting vector machine model is obtained by following steps：
SVMs is built, the input quantity dimension of the SVMs is N × M；
It is trained using SVMs described in the second training data set pair, obtains default supporting vector machine model；Its
In, second data set includes the combined waveform feature of the event to be identified and the classification of corresponding event.
Wherein, the dimension of the input quantity of the SVMs of structure is determined by the dimension of the assemblage characteristic of event to be identified.
Combined waveform feature in second data set is obtained by first data set after step S1 and step S2.
In the above-described embodiments, the default supporting vector machine model include the different supports of multiple input quantity dimension N to
Amount machine.
Due to SVMs build and train it is more convenient, for the ease of knowing to the event of different port numbers
Not, the default supporting vector machine model can include multiple SVMs, N in the dimension of each SVMs input quantity
Value is different, and the event of different port numbers can be classified.
The embodiments of the invention provide a kind of microseismic event identification device, as shown in figure 3, described device includes：Feature carries
Modulus block 1, feature combination module 2 and identification module 3.Wherein：
Characteristic extracting module 1 is used for the waveform image based on each passage of event to be identified, utilizes default convolutional neural networks
The wave character of each passage of event to be identified described in model extraction；Feature combination module 2 is used to combine the event institute to be identified
The wave character for having passage obtains the combined waveform feature of the event to be identified；Identification module 3 is used for based on described to be identified
The combined waveform feature of event, the event to be identified is classified using default supporting vector machine model.
Because the signal in On Microseismic Monitoring Technique has the characteristics of single event multichannel, according to convolutional neural networks to micro-
Shake event is identified, because the port number difference of each event is, it is necessary to build and train multiple different convolutional neural networks.
The time consumption for training of convolutional neural networks is longer, can not meet the requirement of quick identification microseismic event.The structure of SVMs and
Training is very convenient, so during single event multichannel event is identified, for port number number event we
Structure and the SVMs of training respective dimensions is only needed to be classified.SVMs realizes to not well
While classification with the event of port number, structure and training volume when carrying out event category using convolutional neural networks are avoided
Product neutral net the problem of time-consuming.
Specifically, in micro seismic monitoring, the waveform signal of multiple passages is received in an event, corresponding to multiple waveforms
Image.After wave character using default each passage of convolutional neural networks model extraction, the wave character of each passage is entered
Row combination obtains the combined waveform feature of the event to be identified, thus by the wave character of each passage of event to be identified
Input of the entirety as the default vector machine is combined into, realizes the classification to the event to be identified, judges to wait to know
Whether other event is microseismic event.
A kind of microseismic event identification device provided in an embodiment of the present invention, event to be identified is extracted by characteristic extracting module
The wave character of each passage, then the wave character of each passage is combined as by an entirety i.e. combined waveform by feature combination module
Feature, input sort module realize the classification for treating identification events, finally realize the identification to microseismic event in event.Realize
The automatic identification of microseismic event, independent of the know-how and experience of operating personnel, the degree of accuracy is high, not by the shadow of application scenarios
Ring, generalization ability is strong.
The embodiment of the present invention discloses a kind of computer program product, and the computer program product is non-transient including being stored in
Computer program on computer-readable recording medium, the computer program include programmed instruction, when described program instructs quilt
When computer performs, computer is able to carry out the method that above-mentioned each method embodiment is provided, such as including：Based on thing to be identified
The waveform image of each passage of part, it is special using the waveform of each passage of event to be identified described in default convolutional neural networks model extraction
Sign；The wave character for combining all passages of event to be identified obtains the combined waveform feature of the event to be identified；It is based on
The combined waveform feature of the event to be identified, the event to be identified is classified using default supporting vector machine model.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium storing program for executing, the non-transient computer readable storage
Medium storing computer instructs, and the computer instruction makes the computer perform the side that above-mentioned each method embodiment is provided
Method, such as including：Based on the waveform image of each passage of event to be identified, treated using described in default convolutional neural networks model extraction
The wave character of each passage of identification events；The wave character for combining all passages of event to be identified obtains the thing to be identified
The combined waveform feature of part；Based on the combined waveform feature of the event to be identified, using default supporting vector machine model to institute
Event to be identified is stated to be classified.
One of ordinary skill in the art will appreciate that：Realizing all or part of step of above method embodiment can pass through
Programmed instruction related hardware is completed, and foregoing program can be stored in a computer read/write memory medium, the program
Upon execution, the step of execution includes above method embodiment；And foregoing storage medium includes：ROM, RAM, magnetic disc or light
Disk etc. is various can be with the medium of store program codes.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
Realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on such understanding, on
The part that technical scheme substantially in other words contributes to prior art is stated to embody in the form of software product, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including some fingers
Make to cause a computer equipment (can be personal computer, server, or network equipment etc.) to perform each implementation
Method described in some parts of example or embodiment.
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
The present invention is described in detail with reference to the foregoing embodiments, it will be understood by those within the art that：It still may be used
To be modified to the technical scheme described in foregoing embodiments, or equivalent substitution is carried out to which part technical characteristic；
And these modification or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (10)
1. a kind of microseismic event recognition methods, it is characterised in that methods described includes：
S1, based on the waveform image of each passage of event to be identified, using to be identified described in default convolutional neural networks model extraction
The wave character of each passage of event；
S2, the wave character for combining all passages of event to be identified obtain the combined waveform feature of the event to be identified；
S3, based on the combined waveform feature of the event to be identified, using default supporting vector machine model to the thing to be identified
Part is classified.
2. method according to claim 1, it is characterised in that also include before step S1：
The waveform signal of each passage of event to be identified is converted into image format, and the oscillogram is obtained by pretreatment
Picture.
3. method according to claim 1, it is characterised in that step S1 is specifically included：
It is several thumbnails by the waveform image difference random cropping of each passage of event to be identified, utilizes the default volume
Product neural network model extracts the wave character of each thumbnail respectively；
Being worth to for the wave character of several thumbnails is asked corresponding to each passage of event to be identified described to wait to know
The wave character of other each passage of event.
4. method according to claim 1, it is characterised in that step S2 is specifically included：
The wave character of each passage of event to be identified is converted into 1 × M dimensions, wherein M is the integer more than zero；
The wave character of all passages of event to be identified is combined to obtain the combined waveform feature of N × M dimensions, wherein
N is the port number of the event to be identified.
5. method according to claim 1, it is characterised in that the default convolutional neural networks model is obtained by following steps
：
Convolutional neural networks are built, wherein, the input of the convolutional neural networks is the waveform image of the event to be identified, entirely
Softmax layers are connected after articulamentum；
The convolutional neural networks trained are trained using convolutional neural networks described in the first training data set pair；Its
In, first training dataset includes the waveform image of the event to be identified and corresponding event category.
6. method according to claim 4, it is characterised in that the default supporting vector machine model is obtained by following steps
：
SVMs is built, the input quantity dimension of the SVMs is N × M；
It is trained using SVMs described in the second training data set pair, obtains default supporting vector machine model；Wherein, institute
Stating the second data set includes the combined waveform feature of the event to be identified and the classification of corresponding event.
7. method according to claim 6, it is characterised in that the default supporting vector machine model is tieed up including multiple input quantities
Spend the different SVMs of N.
8. a kind of microseismic event identification device, it is characterised in that described device includes：
Characteristic extracting module, for the waveform image based on each passage of event to be identified, utilize default convolutional neural networks model
Extract the wave character of each passage of event to be identified；
Feature combination module, the wave character for combining all passages of event to be identified obtain the event to be identified
Combined waveform feature；
Identification module, for the combined waveform feature based on the event to be identified, using default supporting vector machine model to institute
Event to be identified is stated to be classified.
9. a kind of computer program product, it is characterised in that the computer program product includes being stored in non-transient computer
Computer program on readable storage medium storing program for executing, the computer program include programmed instruction, when described program is instructed by computer
During execution, the computer is set to perform the method as described in claim 1 to 7 is any.
10. a kind of non-transient computer readable storage medium storing program for executing, it is characterised in that the non-transient computer readable storage medium storing program for executing is deposited
Computer instruction is stored up, the computer instruction makes the computer perform the method as described in claim 1 to 7 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710955082.9A CN107784276B (en) | 2017-10-13 | 2017-10-13 | Microseismic event identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710955082.9A CN107784276B (en) | 2017-10-13 | 2017-10-13 | Microseismic event identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107784276A true CN107784276A (en) | 2018-03-09 |
| CN107784276B CN107784276B (en) | 2021-03-19 |
Family
ID=61434765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710955082.9A Active CN107784276B (en) | 2017-10-13 | 2017-10-13 | Microseismic event identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107784276B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086872A (en) * | 2018-07-30 | 2018-12-25 | 东北大学 | Seismic wave recognizer based on convolutional neural networks |
| CN110308485A (en) * | 2019-07-05 | 2019-10-08 | 中南大学 | Microseismic signals classification method, device and storage medium based on deep learning |
| CN110322894A (en) * | 2019-06-27 | 2019-10-11 | 电子科技大学 | A kind of waveform diagram generation and giant panda detection method based on sound |
| CN110361779A (en) * | 2019-07-14 | 2019-10-22 | 广东石油化工学院 | A kind of microseismic event detection method and system based on chi square distribution |
| 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 |
| CN111126471A (en) * | 2019-12-18 | 2020-05-08 | 中国石油大学(华东) | Microseism event detection method and system |
| CN111160516A (en) * | 2018-11-07 | 2020-05-15 | 杭州海康威视数字技术股份有限公司 | Convolutional layer sparsization method and device of deep neural network |
| CN114048669A (en) * | 2021-09-27 | 2022-02-15 | 吉林大学 | Hot dry rock microseism event detection method based on neural network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102650702A (en) * | 2012-05-03 | 2012-08-29 | 中国石油天然气股份有限公司 | Seismic waveform analysis and reservoir prediction method and device |
| CN106405640A (en) * | 2016-08-26 | 2017-02-15 | 中国矿业大学(北京) | Automatic microseismic signal arrival time picking method based on depth belief neural network |
| CN106526668A (en) * | 2016-11-14 | 2017-03-22 | 中国石油化工股份有限公司 | Original waveform extraction and imaging method |
-
2017
- 2017-10-13 CN CN201710955082.9A patent/CN107784276B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102650702A (en) * | 2012-05-03 | 2012-08-29 | 中国石油天然气股份有限公司 | Seismic waveform analysis and reservoir prediction method and device |
| CN106405640A (en) * | 2016-08-26 | 2017-02-15 | 中国矿业大学(北京) | Automatic microseismic signal arrival time picking method based on depth belief neural network |
| CN106526668A (en) * | 2016-11-14 | 2017-03-22 | 中国石油化工股份有限公司 | Original waveform extraction and imaging method |
Non-Patent Citations (4)
| Title |
|---|
| AUTHOR LINKS OPEN OVERLAY PANELMOHAMED F.ABDELWAHED: "SGRAPH (SeismoGRAPHer): Seismic waveform analysis and integrated tools in seismology", 《COMPUTERS & GEOSCIENCES》 * |
| 姜福兴 等: "单事件多通道微震波形的特征提取与联合识别研究", 《煤炭学报》 * |
| 曾建雄 等: "基于支持向量机的矿山微震波形识别和分类研究", 《化工矿物与加工》 * |
| 谭智勇 等: "基于深度卷积神经网络的人群密度估计方法", 《计算机应用与软件》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086872A (en) * | 2018-07-30 | 2018-12-25 | 东北大学 | Seismic wave recognizer based on convolutional neural networks |
| CN111160516A (en) * | 2018-11-07 | 2020-05-15 | 杭州海康威视数字技术股份有限公司 | Convolutional layer sparsization method and device of deep neural network |
| CN111160516B (en) * | 2018-11-07 | 2023-09-05 | 杭州海康威视数字技术股份有限公司 | Convolutional layer sparsification method and device for deep neural network |
| CN110322894A (en) * | 2019-06-27 | 2019-10-11 | 电子科技大学 | A kind of waveform diagram generation and giant panda detection method based on sound |
| CN110322894B (en) * | 2019-06-27 | 2022-02-11 | 电子科技大学 | Sound-based oscillogram generation and panda detection method |
| CN110308485A (en) * | 2019-07-05 | 2019-10-08 | 中南大学 | Microseismic signals classification method, device and storage medium based on deep learning |
| CN110361779B (en) * | 2019-07-14 | 2021-10-01 | 广东石油化工学院 | Microseismic event detection method and system based on chi-square distribution |
| CN110361779A (en) * | 2019-07-14 | 2019-10-22 | 广东石油化工学院 | A kind of microseismic event detection method and system based on chi square distribution |
| 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 |
| CN111126471A (en) * | 2019-12-18 | 2020-05-08 | 中国石油大学(华东) | Microseism event detection method and system |
| CN111123355A (en) * | 2020-01-07 | 2020-05-08 | 山东大学 | Rockburst prediction method and system based on microseismic monitoring data |
| CN114048669A (en) * | 2021-09-27 | 2022-02-15 | 吉林大学 | Hot dry rock microseism event detection method based on neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107784276B (en) | 2021-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107784276A (en) | Microseismic event recognition methods and device | |
| US11397272B2 (en) | Data augmentation for seismic interpretation systems and methods | |
| Kannojia et al. | Effects of varying resolution on performance of CNN based image classification: An experimental study | |
| CN107678059B (en) | A kind of method, apparatus and system of reservoir gas-bearing identification | |
| US6993434B2 (en) | Method for multi-region data processing and visualization | |
| CN106295502A (en) | A kind of method for detecting human face and device | |
| CN103279744B (en) | Imitation fingerprint detection methods based on multiple dimensioned three mode texture feature and system | |
| Jung et al. | Training image-based scenario modeling of fractured reservoirs for flow uncertainty quantification | |
| CN114238488B (en) | Multi-professional digital fruit integration and data interaction method and system | |
| US20130226968A1 (en) | Method and system of subsurface horizon assignment | |
| US20220206176A1 (en) | System and method for identifying subsurface structures | |
| Zheng et al. | Deep neural networks design and analysis for automatic phase pickers from three-component microseismic recordings | |
| CN112990320A (en) | Lithology classification method and device, electronic equipment and storage medium | |
| Song et al. | MEANet: Magnitude estimation via physics-based features time series, an attention mechanism, and neural networks | |
| Li et al. | A study on small magnitude seismic phase identification using 1D deep residual neural network | |
| Liu et al. | Automatic fracture segmentation and detection from image logging using mask R-CNN | |
| CN112966815A (en) | Target detection method, system and equipment based on impulse neural network | |
| Lu et al. | Multi-scale Fusion Network with SR-attention for seismic velocity model building | |
| Consolvo et al. | Microseismic event or noise: Automatic classification with convolutional neural networks | |
| CN106503070A (en) | A kind of engine test data three-dimensional Waterfall plot method for reconstructing | |
| CN112801073A (en) | Acoustic emission first-break signal classification and identification method based on deep neural network | |
| Abadicio et al. | Ground-level Post-Disaster Image Classification using DenseNet201 for Disaster Damage Assessment | |
| Wang et al. | A two-stage fake face image detection algorithm with expanded attention | |
| Ganesan et al. | Lung Cancer Classification Using Improvised CNN | |
| CN113887567B (en) | Vegetable quality detection method, system, medium and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |