CN107784276B - Microseismic event identification method and device - Google Patents
Microseismic event identification method and device Download PDFInfo
- Publication number
- CN107784276B CN107784276B CN201710955082.9A CN201710955082A CN107784276B CN 107784276 B CN107784276 B CN 107784276B CN 201710955082 A CN201710955082 A CN 201710955082A CN 107784276 B CN107784276 B CN 107784276B
- Authority
- CN
- China
- Prior art keywords
- event
- identified
- waveform
- channel
- waveform characteristics
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
Abstract
The invention provides a method and a device for identifying microseismic events, wherein the method comprises the following steps: s1, based on the waveform image of each channel of the event to be recognized, extracting the waveform characteristics of each channel of the event to be recognized by using a preset convolutional neural network model; s2, combining the waveform characteristics of all channels of the event to be identified to obtain the combined waveform characteristics of the event to be identified; and S3, classifying the event to be recognized by using a preset support vector machine model based on the combined waveform characteristics of the event to be recognized. The waveform features of all channels of the event to be recognized are extracted through a preset convolutional neural network, the waveform features of all the channels are combined into a whole, namely the waveform features are combined, a preset support vector machine model is input to realize the classification of the event to be recognized, and finally the recognition of the microseismic event in the event is realized. The method realizes automatic identification of the microseismic event, does not depend on the knowledge level and experience of operators, has high accuracy, is not influenced by application scenes, and has strong generalization capability.
Description
Technical Field
The embodiment of the invention relates to the technical field of geophysical exploration, in particular to a method and a device for identifying microseismic events.
Background
The microseism refers to the earthquake with the magnitude less than three levels, which can not be sensed by people and can only be monitored by using a specific instrument. The microseismic events produce a corresponding excitation of the subsurface medium, and such a shock may change the mechanical state of the subsurface medium. In the field of mine safety monitoring, the micro-earthquake is used as a precursor of mine dynamic disasters, real-time monitoring is carried out on the micro-earthquake, and the occurrence of the dynamic disasters can be effectively predicted and prevented. In addition, in the exploration and development process of unconventional oil gas such as shale gas, coal bed gas and the like, the crack monitoring technology based on microseismic becomes one of the most accurate fracture crack monitoring technologies at home and abroad. In the microseismic monitoring process, signals received by a monitoring instrument often include signals generated by blasting events, noise time and the like in addition to microseismic signals generated by microseismic events, so that the microseismic events are identified from a plurality of events in the microseismic monitoring process and are the basis for monitoring.
Microseismic events have the characteristic of single event multiple channels, and particularly, when a microseismic occurs, triggering of multiple sensors is usually caused, and the channels corresponding to the sensors acquire and store corresponding waveform data. Thus, caused by a microseismic event, multiple channels trigger the acquisition of a resulting waveform, referred to as a single-event multi-channel waveform. At present, microseismic events are mainly identified by information technicians, a microseismic monitoring instrument receives a large number of signals transmitted by a plurality of channels, the technicians extract waveform characteristics of the signals by a certain signal processing means, and then according to the waveform characteristics, theoretical knowledge and practical experience are utilized to judge whether the events corresponding to the received signals are microseismic events.
However, the method of manually extracting the waveform features of the signals to identify the microseismic events has a large workload, depends on the knowledge level and experience of operators, has low identification accuracy according to the manually extracted waveform features, is generally only suitable for specific application scenes, and has poor generalization capability.
Disclosure of Invention
The method aims at solving the problems of large workload, low recognition accuracy and poor generalization capability of the microseismic event recognition technology in the prior art. Embodiments of the present invention provide a method and apparatus for microseismic event identification that overcomes, or at least partially solves, the above-mentioned problems.
In one aspect, an embodiment of the present invention provides a method for identifying a microseismic event, where the method includes:
s1, based on the waveform image of each channel of the event to be recognized, extracting the waveform characteristics of each channel of the event to be recognized by using a preset convolutional neural network model;
s2, combining the waveform characteristics of all channels of the event to be identified to obtain the combined waveform characteristics of the event to be identified;
and S3, classifying the event to be recognized by using a preset support vector machine model based on the combined waveform characteristics of the event to be recognized.
Wherein, before step S1, the method further includes:
and converting the waveform signals of the channels of the event to be identified into an image form, and preprocessing the waveform image to obtain the waveform image.
Wherein, step S1 specifically includes:
respectively and randomly cutting the waveform image of each channel of the event to be identified into a plurality of small image blocks, and respectively extracting the waveform characteristics of each small image block by using the preset convolutional neural network model;
and solving the mean value of the waveform characteristics of the plurality of small image blocks corresponding to each channel of the event to be identified to obtain the waveform characteristics of each channel of the event to be identified.
Wherein, step S2 specifically includes:
converting the waveform characteristics of each channel of the event to be identified into 1 xM dimension, wherein M is an integer greater than zero;
and combining the waveform characteristics of all channels of the event to be identified to obtain a combined waveform characteristic with NxM dimensionality, wherein N is the number of the channels of the event to be identified.
Wherein the preset convolutional neural network model is obtained by the following steps:
constructing a convolutional neural network, wherein the input of the convolutional neural network is a waveform image of the event to be identified, and a softmax layer is connected behind a full connection layer;
training the convolutional neural network by utilizing a first training data set to obtain a trained convolutional neural network; wherein the first training data set comprises waveform images of the events to be recognized and corresponding event classes.
Wherein the preset support vector machine model is obtained by:
constructing a support vector machine, wherein the dimension of the input quantity of the support vector machine is NxM;
training the support vector machine by utilizing a second training data set to obtain a preset support vector machine model; wherein the second data set comprises combined waveform features of the events to be identified and corresponding categories of events.
The preset support vector machine model comprises a plurality of support vector machines with different input quantity dimensions N.
In another aspect, an embodiment of the present invention provides a microseismic event recognition apparatus, including:
the characteristic extraction module is used for extracting the waveform characteristics of each channel of the event to be identified by utilizing a preset convolutional neural network model based on the waveform image of each channel of the event to be identified;
the characteristic combination module is used for combining the waveform characteristics of all channels of the event to be identified to obtain the combined waveform characteristics of the event to be identified;
and the identification module is used for classifying the event to be identified by utilizing a preset support vector machine model based on the combined waveform characteristics of the event to be identified.
Third aspect embodiments of the present invention provide a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the microseismic event identification method.
A fourth aspect of the present invention provides a non-transitory computer-readable storage medium storing computer instructions that cause the computer to perform the microseismic event identification method.
According to the microseismic event identification method and device provided by the embodiment of the invention, the waveform characteristics of each channel of an event to be identified are extracted through a preset convolutional neural network, then the waveform characteristics of each channel are combined into a whole, namely the combined waveform characteristics, a preset support vector machine model is input to realize the classification of the event to be identified, and finally the identification of the microseismic event in the event is realized. The method realizes automatic identification of the microseismic event, does not depend on the knowledge level and experience of operators, has high accuracy, is not influenced by application scenes, and has strong generalization capability.
Drawings
FIG. 1 is a flow chart of a method for identifying microseismic events according to an embodiment of the present invention;
fig. 2 is a schematic diagram of obtaining the preset convolutional neural network model and the preset support vector machine model according to the embodiment of the present invention;
fig. 3 is a block diagram of a microseismic event recognition device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart of a method for identifying microseismic events according to an embodiment of the present invention, as shown in fig. 1, the method includes: s1, based on the waveform image of each channel of the event to be recognized, extracting the waveform characteristics of each channel of the event to be recognized by using a preset convolutional neural network model; s2, combining the waveform characteristics of all channels of the event to be identified to obtain the combined waveform characteristics of the event to be identified; and S3, classifying the event to be recognized by using a preset support vector machine model based on the combined waveform characteristics of the event to be recognized.
Convolutional Neural Networks (CNN) is an efficient recognition method that has been developed in recent years and is gaining wide attention. In general, the basic structure of CNN includes two layers, one of which is a feature extraction layer, and the input of each neuron is connected to a local acceptance domain of the previous layer and extracts the feature of the local. Once the local feature is extracted, the position relation between the local feature and other features is determined; the other is a feature mapping layer, each calculation layer of the network is composed of a plurality of feature mappings, each feature mapping is a plane, and the weights of all neurons on the plane are equal. The feature mapping structure adopts a nonlinear activation function as an activation function of the convolutional neural network, so that the feature mapping has displacement invariance, and preferably, a Relu activation function can be adopted. In addition, since the neurons on one mapping surface share the weight, the number of free parameters of the network is reduced. Each convolutional layer in the convolutional neural network is followed by a computation layer for local averaging and quadratic extraction, which reduces the feature resolution.
CNN is used primarily to identify two-dimensional graphs of displacement, scaling and other forms of distortion invariance. Since the feature detection layer of CNN learns from the training data, when using CNN, it avoids the feature extraction of the display, and implicitly learns from the training data; moreover, because the weights of the neurons on the same feature mapping surface are the same, the network can learn in parallel, which is also a great advantage of the convolutional network relative to the network in which the neurons are connected with each other. The convolution neural network has unique superiority in the aspects of voice recognition and image processing by virtue of a special structure with shared local weight, the layout of the convolution neural network is closer to that of an actual biological neural network, the complexity of the network is reduced by virtue of weight sharing, and particularly, the complexity of data reconstruction in the processes of feature extraction and classification is avoided by virtue of the characteristic that an image of a multi-dimensional input vector can be directly input into the network.
However, since the signal in the microseismic monitoring technology has the characteristic of single event and multiple channels, if a convolutional neural network is adopted to identify microseismic events, because the number of channels of each event is different, a plurality of different convolutional neural networks need to be constructed and trained. The training of the convolutional neural network is long in time consumption, and the requirement for rapidly identifying microseismic events cannot be met.
Support Vector Machine (SVM) was first proposed by cortex and Vapnik in 1995, and it shows many unique advantages in solving small sample, nonlinear and high-dimensional pattern recognition, and can be generalized and applied to other Machine learning problems such as function fitting. The support vector machine method is based on VC dimension theory and structure risk minimization principle of statistical learning theory, and seeks an optimal compromise between model complexity (namely learning precision of specific training samples) and learning capacity (namely capacity of identifying any sample without error) according to limited sample information so as to obtain the best popularization capacity (or generalization capacity).
The construction and training of the support vector machine are very convenient, so that in the process of identifying single-event multi-channel events, the events of the number of channels only need to be classified by constructing and training the support vector machine with corresponding dimensionality. The support vector machine well realizes the classification of events with different channel numbers, and simultaneously avoids the problem of long time consumption for constructing and training the convolutional neural network when the convolutional neural network is used for classifying the events.
Specifically, in microseismic monitoring, waveform signals of a plurality of channels are received in one event, corresponding to a plurality of waveform images. And after extracting the waveform characteristics of each channel by using the preset convolutional neural network model, combining the waveform characteristics of each channel to obtain the combined waveform characteristics of the event to be recognized, so that the waveform characteristics of each channel of the event to be recognized are combined into a whole to be used as the input of the preset vector machine, the classification of the event to be recognized is realized, and whether the event to be recognized is a microseismic event is judged.
According to the microseismic event identification method provided by the embodiment of the invention, the waveform characteristics of each channel of an event to be identified are extracted through a preset convolutional neural network, then the waveform characteristics of each channel are combined into a whole, namely the combined waveform characteristics, a preset support vector machine model is input to realize the classification of the event to be identified, and finally the identification of the microseismic event in the event is realized. The method realizes automatic identification of the microseismic event, does not depend on the knowledge level and experience of operators, has high accuracy, is not influenced by application scenes, and has strong generalization capability.
In the above embodiment, before step S1, the method further includes:
and converting the waveform signals of the channels of the event to be identified into an image form, and preprocessing the waveform image to obtain the waveform image.
In the above embodiment, step S1 specifically includes:
respectively and randomly cutting the waveform image of each channel of the event to be identified into a plurality of small image blocks, and respectively extracting the waveform characteristics of each small image block by using the preset convolutional neural network model;
and solving the mean value of the waveform characteristics of the plurality of small image blocks corresponding to each channel of the event to be identified to obtain the waveform characteristics of each channel of the event to be identified.
Preferably, the waveform image of each channel can be randomly cropped into 10 small tiles.
According to the embodiment of the invention, the waveform image of each channel is randomly cut and then the waveform characteristics are respectively extracted, and then the average value characteristics of the small image blocks are obtained, so that the extracted waveform characteristics of each channel can be more accurate.
In the above embodiment, step S2 specifically includes:
converting the waveform characteristics of each channel of the event to be identified into 1 xM dimension, wherein M is an integer greater than zero;
and combining the waveform characteristics of all channels of the event to be identified to obtain a combined waveform characteristic with NxM dimensionality, wherein N is the number of the channels of the event to be identified.
In the above embodiment, the preset convolutional neural network model is obtained by the following steps:
constructing a convolutional neural network, wherein the input of the convolutional neural network is a waveform image of the event to be identified, a softmax layer is connected behind a full connection layer, and the output of the convolutional neural network is a waveform feature of the event to be identified;
training the convolutional neural network by utilizing a first training data set to obtain a trained convolutional neural network; wherein the first training data set comprises waveform images of the events to be recognized and corresponding event classes.
The softmax layer is used for classifying events corresponding to waveform pictures input into the convolutional neural network, and the classification accuracy needs to be judged according to classification results in the training process so as to determine whether the trained convolutional neural network is obtained. After the trained convolutional neural network is obtained, only the trained convolutional neural network is needed to be used for extracting the characteristics of the waveform image, and when the microseismic event is identified, the waveform characteristics of each channel of the time to be detected are directly extracted from the convolutional layer corresponding to the trained convolutional neural network, so that the classification result of the time to be detected by utilizing the softmax layer in the trained neural network is not needed. Then, the preset convolutional neural network model not only utilizes the function of extracting waveform and graphic waveform characteristics of the convolutional neural network, but also avoids the problem that the preset convolutional neural network model is only suitable for events with specific channel numbers when classification is carried out by utilizing a softmax layer.
In addition, as shown in fig. 2, when the convolutional neural network is trained, a waveform image typical of known events is selected to train the convolutional neural network, for example, 3 ten thousand waveform images of known events are selected to train the convolutional neural network, and the classification accuracy of the trained convolutional neural network can reach 95.13%.
In the above embodiment, as shown in fig. 2, the preset support vector machine model is obtained by:
constructing a support vector machine, wherein the dimension of the input quantity of the support vector machine is NxM;
training the support vector machine by utilizing a second training data set to obtain a preset support vector machine model; wherein the second data set comprises combined waveform features of the events to be identified and corresponding categories of events.
The dimension of the input quantity of the constructed support vector machine is determined by the dimension of the combined feature of the event to be identified. The combined waveform features in the second data set are obtained from the first data set after the steps S1 and S2.
In the above embodiment, the preset support vector machine model includes a plurality of support vector machines with different input quantity dimensions N.
Because the support vector machine is convenient to construct and train, in order to conveniently identify the events with different channel numbers, the preset support vector machine model can comprise a plurality of support vector machines, and the events with different channel numbers can be classified when N values in the dimensionality of input quantity of each support vector machine are different.
An embodiment of the present invention provides a microseismic event recognition device, as shown in fig. 3, the device includes: the device comprises a feature extraction module 1, a feature combination module 2 and an identification module 3. Wherein:
the characteristic extraction module 1 is used for extracting the waveform characteristics of each channel of the event to be identified by utilizing a preset convolutional neural network model based on the waveform image of each channel of the event to be identified; the characteristic combination module 2 is used for combining the waveform characteristics of all channels of the event to be identified to obtain the combined waveform characteristics of the event to be identified; the recognition module 3 is configured to classify the event to be recognized by using a preset support vector machine model based on the combined waveform feature of the event to be recognized.
Because the signal in the microseismic monitoring technology has the characteristic of single event and multiple channels, if a convolutional neural network is adopted to identify microseismic events, because the number of the channels of each event is different, a plurality of different convolutional neural networks need to be constructed and trained. The training of the convolutional neural network is long in time consumption, and the requirement for rapidly identifying microseismic events cannot be met. The construction and training of the support vector machine are very convenient, so that in the process of identifying single-event multi-channel events, the events of the number of channels only need to be classified by constructing and training the support vector machine with corresponding dimensionality. The support vector machine well realizes the classification of events with different channel numbers, and simultaneously avoids the problem of long time consumption for constructing and training the convolutional neural network when the convolutional neural network is used for classifying the events.
Specifically, in microseismic monitoring, waveform signals of a plurality of channels are received in one event, corresponding to a plurality of waveform images. And after extracting the waveform characteristics of each channel by using the preset convolutional neural network model, combining the waveform characteristics of each channel to obtain the combined waveform characteristics of the event to be recognized, so that the waveform characteristics of each channel of the event to be recognized are combined into a whole to be used as the input of the preset vector machine, the classification of the event to be recognized is realized, and whether the event to be recognized is a microseismic event is judged.
According to the microseism event recognition device provided by the embodiment of the invention, the waveform characteristics of each channel of an event to be recognized are extracted through the characteristic extraction module, the waveform characteristics of each channel are combined into a whole through the characteristic combination module, namely, the waveform characteristics are combined, the integrated waveform characteristics are input into the classification module to realize the classification of the event to be recognized, and the identification of the microseism event in the event is finally realized. The method realizes automatic identification of the microseismic event, does not depend on the knowledge level and experience of operators, has high accuracy, is not influenced by application scenes, and has strong generalization capability.
An embodiment of the present invention discloses a computer program product, which includes a computer program stored on a non-transitory computer readable storage medium, the computer program including program instructions, when the program instructions are executed by a computer, the computer can execute the methods provided by the above method embodiments, for example, the method includes: based on the waveform image of each channel of the event to be identified, extracting the waveform characteristics of each channel of the event to be identified by utilizing a preset convolutional neural network model; combining the waveform characteristics of all channels of the event to be identified to obtain the combined waveform characteristics of the event to be identified; and classifying the event to be recognized by utilizing a preset support vector machine model based on the combined waveform characteristics of the event to be recognized.
Embodiments of the present invention provide a non-transitory computer-readable storage medium, which stores computer instructions, where the computer instructions cause the computer to perform the methods provided by the above method embodiments, for example, the methods include: based on the waveform image of each channel of the event to be identified, extracting the waveform characteristics of each channel of the event to be identified by utilizing a preset convolutional neural network model; combining the waveform characteristics of all channels of the event to be identified to obtain the combined waveform characteristics of the event to be identified; and classifying the event to be recognized by utilizing a preset support vector machine model based on the combined waveform characteristics of the event to be recognized.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A method of microseismic event identification, the method comprising:
s1, based on the waveform image of each channel of the event to be recognized, extracting the waveform characteristics of each channel of the event to be recognized by using a preset convolutional neural network model; the method comprises the following steps: respectively and randomly cutting the waveform image of each channel of the event to be identified into a plurality of small image blocks, and respectively extracting the waveform characteristics of each small image block by using the preset convolutional neural network model; solving the mean value of the waveform characteristics of the plurality of small image blocks corresponding to each channel of the event to be identified to obtain the waveform characteristics of each channel of the event to be identified;
s2, combining the waveform characteristics of all channels of the event to be identified to obtain the combined waveform characteristics of the event to be identified; the method comprises the following steps: converting the waveform characteristics of each channel of the event to be identified into 1 xM dimension, wherein M is an integer greater than zero; combining the waveform characteristics of all channels of the event to be identified to obtain a combined waveform characteristic with NxM dimensionality, wherein N is the number of the channels of the event to be identified;
s3, classifying the event to be recognized by using a preset support vector machine model based on the combined waveform characteristics of the event to be recognized;
the step S2 of combining the waveform features of all channels of the event to be identified to obtain a combined waveform feature of the event to be identified; and S3, classifying the event to be recognized by using a preset support vector machine model based on the combined waveform features of the event to be recognized, wherein the classification comprises the step of combining the waveform features of all channels of the event to be recognized into a whole as the input of the preset support vector machine model.
2. The method according to claim 1, further comprising, before step S1:
and converting the waveform signals of the channels of the event to be identified into an image form, and preprocessing the waveform image to obtain the waveform image.
3. The method of claim 1, wherein the predetermined convolutional neural network model is obtained by:
constructing a convolutional neural network, wherein the input of the convolutional neural network is a waveform image of the event to be identified, and a softmax layer is connected behind a full connection layer;
training the convolutional neural network by utilizing a first training data set to obtain a trained convolutional neural network; wherein the first training data set comprises waveform images of the events to be recognized and corresponding event classes.
4. The method of claim 1, wherein the preset support vector machine model is obtained by:
constructing a support vector machine, wherein the dimension of the input quantity of the support vector machine is NxM;
training the support vector machine by utilizing a second training data set to obtain a preset support vector machine model; wherein the second training data set comprises combined waveform features of the events to be identified and corresponding categories of events.
5. The method of claim 4, wherein the preset support vector machine model comprises a plurality of support vector machines with different input quantity dimensions N.
6. A microseismic event identification device wherein the device comprises:
the characteristic extraction module is used for extracting the waveform characteristics of each channel of the event to be identified by utilizing a preset convolutional neural network model based on the waveform image of each channel of the event to be identified; the method comprises the following steps: respectively and randomly cutting the waveform image of each channel of the event to be identified into a plurality of small image blocks, and respectively extracting the waveform characteristics of each small image block by using the preset convolutional neural network model; solving the mean value of the waveform characteristics of the plurality of small image blocks corresponding to each channel of the event to be identified to obtain the waveform characteristics of each channel of the event to be identified;
the characteristic combination module is used for combining the waveform characteristics of all channels of the event to be identified to obtain the combined waveform characteristics of the event to be identified; the method comprises the following steps: converting the waveform characteristics of each channel of the event to be identified into 1 xM dimension, wherein M is an integer greater than zero; combining the waveform characteristics of all channels of the event to be identified to obtain a combined waveform characteristic with NxM dimensionality, wherein N is the number of the channels of the event to be identified;
and the identification module is used for classifying the event to be identified by utilizing a preset support vector machine model based on the combined waveform characteristics of the event to be identified.
7. A computer program product, characterized in that the computer program product comprises a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to carry out the method according to any one of claims 1 to 5.
8. A non-transitory computer-readable storage medium storing computer instructions that cause a non-transitory computer to perform the method of any one of claims 1 to 5.
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 CN107784276A (en) | 2018-03-09 |
| CN107784276B true 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) |
Families Citing this family (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 |
| 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 |
| CN110322894B (en) * | 2019-06-27 | 2022-02-11 | 电子科技大学 | Sound-based oscillogram generation and panda detection method |
| CN110308485B (en) * | 2019-07-05 | 2022-02-11 | 中南大学 | Microseismic signal classification method and device based on deep learning and storage medium |
| 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 |
| 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 |
| CN110910613B (en) * | 2019-12-10 | 2022-04-05 | 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 |
| CN111123355B (en) * | 2020-01-07 | 2020-12-11 | 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 |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (2)
| 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 |
| CN106405640B (en) * | 2016-08-26 | 2018-07-10 | 中国矿业大学(北京) | Microseismic signals based on depth conviction neural network then automatic pick method |
-
2017
- 2017-10-13 CN CN201710955082.9A patent/CN107784276B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 (1)
| Title |
|---|
| SGRAPH (SeismoGRAPHer): Seismic waveform analysis and integrated tools in seismology;Author links open overlay panelMohamed F.Abdelwahed;《Computers & Geosciences》;20110722;第40卷;第153-165页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107784276A (en) | 2018-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107784276B (en) | Microseismic event identification method and device | |
| Ross et al. | P wave arrival picking and first‐motion polarity determination with deep learning | |
| CN106295502B (en) | A kind of method for detecting human face and device | |
| CN108737406A (en) | A kind of detection method and system of abnormal flow data | |
| CN112673381B (en) | Method and related device for identifying confrontation sample | |
| CN115758212B (en) | Mechanical equipment fault diagnosis method based on parallel network and transfer learning | |
| CN109165660A (en) | A kind of obvious object detection method based on convolutional neural networks | |
| CN111738054B (en) | Behavior anomaly detection method based on space-time self-encoder network and space-time CNN | |
| CN104636449A (en) | Distributed type big data system risk recognition method based on LSA-GCC | |
| CN109190698B (en) | Classification and identification system and method for network digital virtual assets | |
| CN102156873A (en) | Chaos-based method for detecting and classifying early single-point faults of mechanical component | |
| CN113095370A (en) | Image recognition method and device, electronic equipment and storage medium | |
| Dickey et al. | Beyond correlation: A path‐invariant measure for seismogram similarity | |
| CN106935038B (en) | Parking detection system and detection method | |
| CN106251375A (en) | A kind of degree of depth study stacking-type automatic coding of general steganalysis | |
| CN110398775B (en) | Tunnel water burst disaster micro-seismic event signal fluctuation first arrival pickup method and system | |
| CN115830449A (en) | Remote sensing target detection method with explicit contour guidance and spatial variation context enhancement | |
| CN114547365A (en) | Image retrieval method and device | |
| CN109726637A (en) | The parking site detecting system and method in parking stall region are indicated with resilient polygonal | |
| CN112966815A (en) | Target detection method, system and equipment based on impulse neural network | |
| TWI636276B (en) | Method of determining earthquake with artificial intelligence and earthquake detecting system | |
| CN116541771A (en) | Unbalanced sample bearing fault diagnosis method based on multi-scale feature fusion | |
| Castro-Cabrera et al. | Adaptive classification using incremental learning for seismic-volcanic signals with concept drift | |
| CN115314239A (en) | Analysis method and related equipment for hidden malicious behaviors based on multi-model fusion | |
| Kouadri et al. | Blind source separation filters-based-fault detection and isolation in a three tank 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |