CN114154542A - Microseism event classification method, device, equipment and readable storage medium - Google Patents
Microseism event classification method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN114154542A CN114154542A CN202111457860.4A CN202111457860A CN114154542A CN 114154542 A CN114154542 A CN 114154542A CN 202111457860 A CN202111457860 A CN 202111457860A CN 114154542 A CN114154542 A CN 114154542A
- Authority
- CN
- China
- Prior art keywords
- effective signal
- effective
- seismic
- signal
- micro
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000007621 cluster analysis Methods 0.000 claims abstract description 23
- 230000008859 change Effects 0.000 claims description 19
- 239000003245 coal Substances 0.000 claims description 13
- 238000000354 decomposition reaction Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 230000033001 locomotion Effects 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 239000011435 rock Substances 0.000 claims description 9
- 239000012530 fluid Substances 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 238000007417 hierarchical cluster analysis Methods 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 238000005054 agglomeration Methods 0.000 claims description 2
- 230000002776 aggregation Effects 0.000 claims description 2
- 230000001427 coherent effect Effects 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 7
- 239000003129 oil well Substances 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000005065 mining Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000000630 rising effect Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
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
- G06F2218/08—Feature extraction
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Geophysics And Detection Of Objects (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Tests Of Electronic Circuits (AREA)
Abstract
The invention discloses a microseism event classification method, which comprises the following steps: acquiring a microseism signal and identifying a plurality of effective signal sections in the microseism signal; extracting the characteristics of each effective signal segment to obtain the characteristic data of each effective signal segment; performing cluster analysis on each effective signal according to the characteristic data to obtain effective signal segments belonging to the same class; and determining the micro-seismic event corresponding to each effective signal segment according to the waveform rule to be followed in the probability of the effective signal corresponding to each micro-seismic time. According to the method and the device, clustering analysis is carried out on the characteristic data of the effective signal segments in the micro-seismic signals as a basis, the micro-seismic event types to which various effective signals belong are finally identified according to the waveform characteristics belonging to the same type of effective signal segments, and the accuracy and effectiveness of micro-seismic event identification are improved to a certain extent. The application also provides a microseism event classification device, equipment and a computer readable storage medium, which have the beneficial effects.
Description
Technical Field
The invention relates to the technical field of microseism event analysis, in particular to a microseism event classification method, a microseism event classification device, microseism event classification equipment and a computer readable storage medium.
Background
In an oil well for collecting oil and natural gas, with the process of oil and gas exploitation, the stratum environment is changed due to the geological structure, coal bed and the like of the oil well, and then the stratum generates a micro seismic event. The causes of microseismic events can be largely classified into three types: coal bed fracturing, formation activation, and groundwater movement; and the method has important significance for safety prediction and alarm of the oil well by identifying coal bed fracture, stratum structure activation and underground water movement through microseism events.
At present, the micro-seismic signal is mainly identified by monitoring and analyzing the micro-seismic signal, and whether the micro-seismic signal has the signal caused by coal seam breakage, stratum structure activation, underground water movement and the like is identified, but how to specifically analyze the micro-seismic signal is one of the directions of popular research in the industry.
Disclosure of Invention
The invention aims to provide a method, a device and equipment for classifying microseism events and a computer readable storage medium, which can improve the accuracy of identifying and classifying the microseism events.
In order to solve the technical problem, the invention provides a microseism event classification method, which comprises the following steps:
acquiring a microseismic signal and identifying a plurality of effective signal segments in the microseismic signal;
extracting the characteristics of each effective signal segment to obtain the characteristic data of each effective signal segment;
performing cluster analysis on each effective signal segment according to the characteristic data to obtain effective signal segments belonging to the same class;
when a preset proportion of effective signals in the same type of effective signal section meet a first waveform condition, the same type of effective signal section is a seismic signal corresponding to underground fluid movement; when a preset proportion of effective signals in the same type of effective signal segment meet a second waveform condition, the same type of effective signal segment is a seismic signal corresponding to stress change of an underground structure; when a preset proportion of effective signals in the same type of effective signal segment meet a third waveform condition, the same type of effective signal segment is a seismic signal corresponding to coal rock layer fracture;
wherein the first waveform condition is that P waves are included and S waves are not included; the second waveform condition is to include both an S wave and a P wave; the third waveform condition is a second largest amplitude for which a difference between the plurality of second largest amplitudes and the maximum amplitude is smaller than a preset difference.
Optionally, the performing feature extraction on each effective signal segment to obtain feature data of each effective signal segment includes:
and extracting a plurality of characteristic data in the characteristic data comprising total energy, average energy, total entropy, average entropy, total ringing, average ringing, rise time, duration, main frequency, maximum amplitude absolute value, P wave S wave time difference and P wave S wave amplitude ratio for each effective signal segment.
Optionally, acquiring a microseismic signal and identifying a plurality of valid signal segments in the microseismic signal comprises:
and carrying out multi-scale morphological decomposition on the micro-seismic signals, comparing a decomposition section corresponding to the decomposed micro-seismic signals with a preset threshold value, and taking a micro-seismic signal section corresponding to the decomposition section larger than the preset threshold value as an effective signal section.
Optionally, after performing cluster analysis on each effective signal segment according to the feature data to obtain effective signal segments belonging to the same class, the method further includes:
and carrying out normalization operation on the amplitude values of the effective signal segments of the same class so as to judge whether the effective signal segments after the normalization operation meet the first waveform condition, the second waveform condition and the third waveform condition.
Optionally, performing cluster analysis on each effective signal segment according to the feature data to obtain effective signal segments belonging to the same class, including:
and operating the characteristic data of each effective signal segment by adopting an agglomeration hierarchical clustering analysis algorithm to obtain the effective signal segments belonging to the same class.
Optionally, comprising:
the signal acquisition module is used for acquiring the micro-seismic signals and identifying a plurality of effective signal sections in the micro-seismic signals;
the characteristic extraction module is used for extracting the characteristics of each effective signal segment to obtain the characteristic data of each effective signal segment;
the cluster analysis module is used for carrying out cluster analysis on each effective signal segment according to the characteristic data to obtain the effective signal segments belonging to the same class;
the signal classification module is used for judging whether the effective signals of the same type meet the first waveform condition or not when the effective signals of the same type meet the first waveform condition; when a preset proportion of effective signals in the same type of effective signal segment meet a second waveform condition, the same type of effective signal segment is a seismic signal corresponding to stress change of an underground structure; when a preset proportion of effective signals in the same type of effective signal segment meet a third waveform condition, the same type of effective signal segment is a seismic signal corresponding to coal rock layer fracture;
wherein the first waveform condition is that P waves are included and S waves are not included; the second waveform condition is to include both an S wave and a P wave; the third waveform condition is a second largest amplitude for which a difference between the plurality of second largest amplitudes and the maximum amplitude is smaller than a preset difference.
Optionally, the feature extraction module is specifically configured to extract, for each effective signal segment, multiple pieces of feature data in feature data that includes total energy, average energy, total entropy, average entropy, total ringing, average ringing, rise time, duration, dominant frequency, maximum amplitude absolute value, P-wave-S-wave time difference, and P-wave-S-wave amplitude ratio.
Optionally, the cluster analysis module is specifically configured to calculate the feature data of each effective signal segment by using an agglomerative hierarchical cluster analysis algorithm to obtain effective signal segments belonging to the same class.
A microseismic event classification device comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of the method of microseismic event classification as defined in any one of the above.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of microseismic event classification as set forth in any of the above.
The invention provides a microseism event classification method, which comprises the following steps: acquiring a microseism signal and identifying a plurality of effective signal sections in the microseism signal; extracting the characteristics of each effective signal segment to obtain the characteristic data of each effective signal segment; performing cluster analysis on each effective signal according to the characteristic data to obtain effective signal segments belonging to the same class; when the effective signals in the same class meet the first waveform condition in a preset proportion, the effective signals in the same class are seismic signals corresponding to the underground fluid motion; when the effective signals in the same class meet the second waveform condition in a preset proportion, the effective signals in the same class are seismic signals corresponding to the stress change of the underground structure; when the effective signals in the same class meet the third waveform condition in a preset proportion, the effective signals in the same class are seismic signals corresponding to coal rock layer fracture; wherein, the first waveform condition comprises P wave and not comprises S wave; the second waveform condition is to include both S-wave and P-wave; the third waveform condition is a second largest amplitude for which the difference between the plurality of amplitudes and the maximum amplitude is less than a preset difference.
When the microseism events are classified, effective signal sections in the microseism signals are extracted, and characteristic data corresponding to each effective signal section are obtained; and performing cluster analysis by taking the characteristic data of each effective signal segment as a basis, and finally identifying the micro-seismic event type to which each type of effective signal belongs according to the waveform characteristics of the effective signal segments belonging to the same type. The characteristic range or standard does not need to be planned for the micro-seismic signal corresponding to each micro-seismic event in advance in the micro-seismic event identification process, the problem that the defined characteristic range or standard is inaccurate due to terrain change, and further the micro-seismic event identified is inaccurate is avoided, and the accuracy and the effectiveness of micro-seismic event identification are improved to a certain extent.
The application also provides a microseism event classification device, equipment and a computer readable storage medium, which have the beneficial effects.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for classifying seismic events according to an embodiment of the present application;
fig. 2 is a block diagram of a microseismic event classification device according to an embodiment of the present invention.
Detailed Description
At present, most of classification modes based on signal data are data analysis based on a big data statistics principle according to signal feature samples, a range standard is defined for each class of data, and the subsequently acquired data correspond to which range standard, namely which class; or performing data learning training on the signal characteristic samples according to the neural network model to obtain the recognition model.
However, for micro-seismic signals, effective signal data which contribute to micro-seismic event identification in the micro-seismic signals are relatively few, and therefore, the requirements of large data analysis are often difficult to meet, and the signal range standard of each micro-seismic event is more difficult to define in sequence. For neural network training, the problem of insufficient samples also exists. In addition, no matter whether the data is analyzed based on the statistical principle to determine the signal range standard or the recognition model is determined based on the neural network training, the problem that signals of various micro-seismic events change to a certain degree due to the change of the oil well environment cannot be avoided, and the problem that the signal range standard determined by the previous sample and the recognition model are inaccurate in micro-seismic event recognition is caused.
Therefore, the technical scheme capable of ensuring the accuracy of identifying and classifying the microseism event to a certain extent is provided.
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the 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.
As shown in fig. 1, fig. 1 is a schematic flow chart of a method for classifying seismic events according to an embodiment of the present application. The microseismic event classification method may include:
s11: the microseismic signals are acquired and a plurality of valid signal segments in the microseismic signals are identified.
Because the micro-seismic event has unpredictability, the micro-seismic signal is obtained by monitoring the formation vibration condition in real time when the micro-seismic signal is acquired. In general, when performing microseismic event identification and analysis based on microseismic signals, the microseismic signals detected by a plurality of signal detectors in the same oil field well site are collected for a period of time.
It can be understood that in the process of continuously detecting and acquiring the micro-seismic signals, the micro-seismic events are not generated all the time, so that only the corresponding signals in the micro-seismic signals have value in identifying the micro-seismic events when the micro-seismic events occur; for this purpose, in this embodiment, it is necessary to screen out the effective signal segment collected when the micro-seismic event occurs in the micro-seismic signal.
The intensity of the micro-seismic signals detected and obtained in the time period when the micro-seismic event occurs is obviously stronger than the signal intensity corresponding to the time period when the micro-seismic event does not occur, so that the effective signal segment corresponding to the time period when the micro-seismic event occurs can be determined according to the intensity. For example, a signal period with a generally large amplitude may be determined as the effective time directly according to the amplitude of the micro-seismic signal.
For example, the micro-seismic signal may be subjected to multi-scale morphological decomposition, and a decomposition section corresponding to the decomposed micro-seismic signal is compared with a preset threshold, so as to decompose a micro-seismic signal segment, which has a section larger than the preset threshold, and serve as an effective signal segment.
It can be understood that, after the micro-seismic signals are decomposed by the multi-scale morphology, a plurality of decomposition sections exist correspondingly, and in practical application, data of one of the decomposition sections can be selected to be compared with a preset threshold.
S12: and extracting the characteristics of each effective signal segment to obtain the characteristic data of each effective signal segment.
It should be noted that, in order to ensure the accuracy of the subsequent identification of the micro-seismic event corresponding to the effective signal segment, more feature data should be extracted from various aspects as much as possible when performing feature extraction on the effective signal.
For example, the feature data extracted from each valid signal segment in this embodiment may include: total energy, average energy, total entropy, average entropy, total ringing, average ringing, rise time, duration, dominant frequency, absolute value of maximum amplitude, P-wave S-wave time difference, P-wave S-wave amplitude ratio, or may further include all of the above characteristic data.
Each feature data will be described in detail below.
1) Regarding total energy and average energy: energy is expressed by the square of the amplitude corresponding to the active signal segment
The mean energy being the arithmetic mean of the total energy
Wherein N is the number of sampling points in the effective signal segment, AiIndicating the amplitude value of the effective signal at the ith sample point.
2) Regarding total entropy and mean entropy: entropy is a parameter used to describe the disorder of things, and the larger the entropy, the more chaotic it is. In the information theory, entropy represents the uncertainty of a random variable, and for the random variable of the amplitude value of the effective signal, the value of the random variable is x1、x2、x3......xmThe probability corresponding to each value is p1,p2,p3,......,pmThen the expressions for total entropy and average entropy are respectively:
3) regarding total and average ringing: the overshoot and continuous ripple generated when the effective signal oscillates back and forth around a steady state are called ringing effect, and are physical quantities representing the stability of the signal. For a valid signal of a microseismic event, the number of ringing effects, i.e., the total ringing, can be represented by the number of zero crossings of the valid signal: length (find (a)iAi+1Less than or equal to 0)); the corresponding average ringing may be
AiAnd Ai+1Is the amplitude of two adjacent samples, and N is the number of samples within the active signal segment.
4) Rise time and duration; the time interval from the first arrival moment of the sampling point of the starting point of the effective signal segment to the sampling point of the effective signal with the maximum amplitude is the rising time; the duration corresponding to the effective signal time period is the duration.
5) Maximum amplitude absolute value and dominant frequency: and performing effective value operation on the amplitude value of each effective signal to obtain a maximum absolute value, namely a maximum positive and negative absolute value, wherein the frequency value corresponding to the signal with the maximum amplitude value absolute value is called a dominant frequency: fmax＝f(|Amax|)。
6) P-wave S-wave time difference:
seismic waves are mainly classified into two types, one is surface waves and the other is body waves. Surface waves are transmitted only at the earth surface, and body waves can pass through the earth. Solid Wave (Body Wave): transmitted inside the earth and divided into two types, P-wave and S-wave. P wave: p represents Primary or compressional, which is a longitudinal wave with the particle vibration direction parallel to the wave front travel, and among all seismic waves, the travel speed is fastest and the arrival is earliest. P-wave energy is transferred in solids, liquids or gases. S wave: s means Secondary (Secondary) or Shear force (Shear), the forward velocity is second only to the P wave, and the particle vibration direction is perpendicular to the forward direction of the wave, which is a transverse wave. The S-wave can only be transmitted in a solid, but not through the liquid outer core. Simple earthquake positioning can be carried out by utilizing the difference of the transmission speeds of the P wave and the S wave and the travel time difference between the P wave and the S wave.
In this embodiment, the time difference of the P-wave S-wave, i.e. the first arrival time difference of the S-wave and the P-wave, can be determined by a formula
It is determined that st (S) represents the first arrival time of the S wave, and st (P) represents the first arrival time of P.
7) P-wave to S-wave amplitude ratio: i.e. the absolute value of the maximum amplitude ratio of the S wave and the P wave, can be obtained by the formula
Determination of Amax(S) represents the maximum amplitude of the S wave, Amax(P) represents the maximum amplitude of the P-wave.
S13: and carrying out cluster analysis on each effective signal according to the characteristic data to obtain effective signal segments belonging to the same class.
The cluster analysis algorithm is a method for dividing a data set into a plurality of clusters under a certain standard (such as shortest distance) by extracting and analyzing certain characteristics of data in the data set and utilizing the relation (such as similarity) between the characteristics of different data. The mahalanobis distance between the events is then calculated on the basis of the above features:
representing any two events xiAnd xjMahalanobis distance, Σ between-1The inverse of the covariance matrix is represented. The average distance is chosen to measure the distance between two clusters:
naand nbRespectively representing the number of objects in cluster A and cluster B, Da,bRepresenting the distance of any two objects in any cluster a and cluster B.
In this embodiment, the plurality of feature data of each effective signal are used as data representing characteristics of the effective signal, so that the feature data of each effective signal can be subjected to cluster analysis through a clustering algorithm, and effective signals with the feature data closer to each other are classified into the same class.
Classification of valid signals may be achieved, for example, using a agglomerative hierarchical clustering analysis algorithm. The method is characterized in that feature data corresponding to each effective signal are regarded as a cluster (one class, N classes in total), similarity operation or Mahalanobis distance operation is carried out between the feature data of each effective signal, two effective signal segments with highest similarity or minimum distance are found and combined into the same cluster, then the process is iterated, and all clusters are combined continuously until all objects are located in one cluster or a certain iteration termination condition is met. For a clustering operation containing N effective signal segments, the sum of the number m of object types and the clustering times N in the final clustering result is the same as the number of the effective signal segments.
S14: when the preset proportion of effective signals in the same type of effective signal section meet the first waveform condition, the same type of effective signal section is the seismic signal corresponding to the underground fluid motion.
The first waveform condition is that the P-wave is included and the S-wave is not included.
For the seismic signal waveform corresponding to the underground fluid motion, the waveform characteristics show that the maximum amplitude value of the signal is obviously higher than other amplitude values, the rise time and the duration corresponding to the effective signal segment are shorter, and the total number of ringing is also smaller.
S15: and when the preset proportion of effective signals in the same type of effective signal section meet the second waveform condition, the same type of effective signal section is the seismic signal corresponding to the stress change of the underground structure.
The second waveform condition is to include both S-waves and P-waves.
The seismic signal waveform corresponding to the stress change of the underground structure comprises two obvious wave crests, namely P waves and S waves, the rising time of the P waves and the rising time of the S waves are short, the duration of an effective signal segment is long, and the total number of ringing is small.
S16: and when the preset proportion of effective signals in the same type of effective signal section meet the third waveform condition, the same type of effective signal section is the seismic signal corresponding to the coal rock layer fracture.
The third waveform condition is a second largest amplitude for which the difference between the plurality of amplitudes and the maximum amplitude is less than a preset difference.
For the seismic signal waveform corresponding to the coal rock stratum fracture, a plurality of amplitude values are close to the maximum amplitude value, the rise time and the duration time of the signal are longer, and the total number of ringing is also larger.
It should be noted that, after performing cluster analysis on each effective signal segment to perform class division, for better analyzing and identifying the waveform characteristics of the effective signal segments corresponding to each class, so as to determine the seismic event to which the effective signal segments of the same class belong, the amplitude values of the effective signals in each effective signal segment can be normalized, so that the amplitude values of the effective signals in each effective signal segment are all converted into the same magnitude, and comparison between the effective signals in each effective signal segment is facilitated.
In the application, the size of the effective signal which can be collected to a certain extent is more or less considered for different regions or reasons such as change of stratum structure along with the process of oil well exploitation when the corresponding micro-seismic event is identified and analyzed based on the effective signal in the effective signal section. That is, in the well sites with different mining degrees in different regions, the effective signals corresponding to the same micro-seismic time may all be different. If the microseism event corresponding to the effective signal is classified and judged, a signal standard for dividing the effective signal into the corresponding microseism events is determined based on a statistical principle according to a large amount of historical effective signal data serving as samples, for example, an effective signal section changing according to a certain change rule is set to correspond to a certain type of microseism event, and the like, but the change rule may change for different mining degrees lower than different mining degrees, and the effectiveness of the predetermined change rule standard for judging the microseism event is relatively low. For example, the neural network training based on a large amount of historical effective signal data obtains a recognition model, which is essentially to determine the recognition model based on the intrinsic connection between the historical effective signals, but the intrinsic connection may also change for different mining degrees, and the accuracy of the recognition model may be reduced.
Another problem is that the frequency of occurrence of micro-seismic events is relatively low, and it is often difficult to obtain enough samples, and it is obvious that determining the identification criteria or identification model for a seismic event based on a small amount of sample data further reduces the accuracy of the identification result.
Therefore, the method does not depend on learning training of data samples, and cluster analysis is directly carried out according to the feature data of the effective signals in the effective signal sections obtained through collection, namely the classification of the effective signals is divided based on the characteristics of the effective data collected currently, but not according to the standard determined by sample data, on the basis, the micro-seismic events corresponding to each type of effective signal sections are determined according to the more definite waveform rule basically followed by the effective signals corresponding to each type of micro-seismic events, and the difficulty in classifying the micro-seismic events corresponding to the effective signals with the partially inconspicuous waveform rule is reduced to a great extent; and the interference generated by the fact that factors such as regional strata change to the definition of the micro-seismic event is also used to a certain extent, so that the accuracy and the effectiveness of the micro-seismic event identification are improved.
In the following, the microseism event classification device provided by the embodiment of the invention is introduced, and the microseism event classification device described below and the microseism event classification method described above can be referred to correspondingly.
Fig. 2 is a block diagram of a microseismic event classification device according to an embodiment of the present invention, and the microseismic event classification device according to fig. 2 may include:
a signal acquisition module 100 for acquiring a micro-seismic signal and identifying a plurality of valid signal segments in the micro-seismic signal;
the feature extraction module 200 is configured to perform feature extraction on each effective signal segment to obtain feature data of each effective signal segment;
the cluster analysis module 300 is configured to perform cluster analysis on each effective signal segment according to the feature data to obtain effective signal segments belonging to the same class;
the signal classification module 400 is configured to, when a preset proportion of effective signals in the same type of effective signal segment satisfy a first waveform condition, determine that the same type of effective signal segment is a seismic signal corresponding to underground fluid motion; when a preset proportion of effective signals in the same type of effective signal segment meet a second waveform condition, the same type of effective signal segment is a seismic signal corresponding to stress change of an underground structure; when a preset proportion of effective signals in the same type of effective signal segment meet a third waveform condition, the same type of effective signal segment is a seismic signal corresponding to coal rock layer fracture;
wherein the first waveform condition is that P waves are included and S waves are not included; the second waveform condition is to include both an S wave and a P wave; the third waveform condition is a second largest amplitude for which a difference between the plurality of second largest amplitudes and the maximum amplitude is smaller than a preset difference.
In an optional embodiment of the present application, the feature extraction module 200 is specifically configured to extract, for each of the effective signal segments, a plurality of feature data in feature data including total energy, average energy, total entropy, average entropy, total ringing, average ringing, rise time, duration, dominant frequency, absolute value of maximum amplitude, time difference of P-wave and S-wave, and amplitude ratio of P-wave and S-wave.
In an optional embodiment of the present application, the signal acquisition module 100 is configured to perform multi-scale morphological decomposition on the micro-seismic signal, and compare a decomposition profile corresponding to the decomposed micro-seismic signal with a preset threshold, where a micro-seismic signal segment corresponding to the decomposition profile larger than the preset threshold is used as an effective signal segment.
In an optional embodiment of the present application, the apparatus further includes a normalization operation module, configured to perform a normalization operation on the amplitude values of the effective signal segments of the same class, so as to determine whether the effective signal segments after the normalization operation satisfy the first waveform condition, the second waveform condition, and the third waveform condition.
In an optional embodiment of the present application, the cluster analysis module is specifically configured to calculate the feature data of each effective signal segment by using an agglomerative hierarchical cluster analysis algorithm, so as to obtain effective signal segments belonging to the same class.
The microseism event classification device of the embodiment is used for implementing the microseism event classification method, so the specific implementation manner in the microseism event classification device can be found in the embodiment section of the microseism event classification method in the foregoing, and details are not repeated here.
The present application also provides embodiments of a microseismic event classification device, which may include:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of the method of microseismic event classification as defined in any one of the above.
The processor of the present application executing the computer program implemented method of classifying microseismic events may comprise:
acquiring a microseismic signal and identifying a plurality of effective signal segments in the microseismic signal;
extracting the characteristics of each effective signal segment to obtain the characteristic data of each effective signal segment;
performing cluster analysis on each effective signal segment according to the characteristic data to obtain effective signal segments belonging to the same class;
when a preset proportion of effective signals in the same type of effective signal section meet a first waveform condition, the same type of effective signal section is a seismic signal corresponding to underground fluid movement; when a preset proportion of effective signals in the same type of effective signal segment meet a second waveform condition, the same type of effective signal segment is a seismic signal corresponding to stress change of an underground structure; when a preset proportion of effective signals in the same type of effective signal segment meet a third waveform condition, the same type of effective signal segment is a seismic signal corresponding to coal rock layer fracture;
wherein the first waveform condition is that P waves are included and S waves are not included; the second waveform condition is to include both an S wave and a P wave; the third waveform condition is a second largest amplitude for which a difference between the plurality of second largest amplitudes and the maximum amplitude is smaller than a preset difference.
The present application also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of micro-seismic event classification as described in any of the above.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include elements inherent in the list. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element. In addition, parts of the above technical solutions provided in the embodiments of the present application, which are consistent with the implementation principles of corresponding technical solutions in the prior art, are not described in detail so as to avoid redundant description.
The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (10)
1. A method of microseismic event classification; it is characterized by comprising:
acquiring a microseismic signal and identifying a plurality of effective signal segments in the microseismic signal;
extracting the characteristics of each effective signal segment to obtain the characteristic data of each effective signal segment;
performing cluster analysis on each effective signal segment according to the characteristic data to obtain effective signal segments belonging to the same class;
when a preset proportion of effective signals in the same type of effective signal section meet a first waveform condition, the same type of effective signal section is a seismic signal corresponding to underground fluid movement; when a preset proportion of effective signals in the same type of effective signal segment meet a second waveform condition, the same type of effective signal segment is a seismic signal corresponding to stress change of an underground structure; when a preset proportion of effective signals in the same type of effective signal segment meet a third waveform condition, the same type of effective signal segment is a seismic signal corresponding to coal rock layer fracture;
wherein the first waveform condition is that P waves are included and S waves are not included; the second waveform condition is to include both an S wave and a P wave; the third waveform condition is a second largest amplitude for which a difference between the plurality of second largest amplitudes and the maximum amplitude is smaller than a preset difference.
2. The method of classifying a microseismic event of claim 1 wherein the extracting features of each of the valid signal segments to obtain feature data for each of the valid signal segments comprises:
and extracting a plurality of characteristic data in the characteristic data comprising total energy, average energy, total entropy, average entropy, total ringing, average ringing, rise time, duration, main frequency, maximum amplitude absolute value, P wave S wave time difference and P wave S wave amplitude ratio for each effective signal segment.
3. The method of microseismic event classification as recited in claim 1 wherein acquiring microseismic signals and identifying a plurality of valid signal segments in the microseismic signals comprises:
and carrying out multi-scale morphological decomposition on the micro-seismic signals, comparing a decomposition section corresponding to the decomposed micro-seismic signals with a preset threshold value, and taking a micro-seismic signal section corresponding to the decomposition section larger than the preset threshold value as an effective signal section.
4. The method for classifying a microseismic event according to claim 1 wherein after performing cluster analysis on each of the valid signal segments according to the feature data to obtain valid signal segments belonging to the same class, the method further comprises:
and carrying out normalization operation on the amplitude values of the effective signal segments of the same class so as to judge whether the effective signal segments after the normalization operation meet the first waveform condition, the second waveform condition and the third waveform condition.
5. The method for classifying microseismic events according to any one of claims 1 to 4 wherein clustering each of the valid signal segments based on the signature data to obtain valid signal segments belonging to the same class comprises:
and operating the characteristic data of each effective signal segment by adopting an agglomeration hierarchical clustering analysis algorithm to obtain the effective signal segments belonging to the same class.
6. A microseismic event classification device comprising:
the signal acquisition module is used for acquiring the micro-seismic signals and identifying a plurality of effective signal sections in the micro-seismic signals;
the characteristic extraction module is used for extracting the characteristics of each effective signal segment to obtain the characteristic data of each effective signal segment;
the cluster analysis module is used for carrying out cluster analysis on each effective signal segment according to the characteristic data to obtain the effective signal segments belonging to the same class;
the signal classification module is used for judging whether the effective signals of the same type meet the first waveform condition or not when the effective signals of the same type meet the first waveform condition; when a preset proportion of effective signals in the same type of effective signal segment meet a second waveform condition, the same type of effective signal segment is a seismic signal corresponding to stress change of an underground structure; when a preset proportion of effective signals in the same type of effective signal segment meet a third waveform condition, the same type of effective signal segment is a seismic signal corresponding to coal rock layer fracture;
wherein the first waveform condition is that P waves are included and S waves are not included; the second waveform condition is to include both an S wave and a P wave; the third waveform condition is a second largest amplitude for which a difference between the plurality of second largest amplitudes and the maximum amplitude is smaller than a preset difference.
7. The microseismic event classification device of claim 6 wherein the feature extraction module is specifically configured to extract a plurality of feature data of the feature data including total energy, average energy, total entropy, average entropy, total ringing, average ringing, rise time, duration, dominant frequency, maximum amplitude absolute value, P-wave S-wave time difference, P-wave S-wave amplitude ratio for each of the active signal segments.
8. The microseismic event classification device according to claim 6 or 7 wherein the cluster analysis module is specifically configured to perform an operation on the feature data of each of the valid signal segments by using a coherent hierarchical cluster analysis algorithm to obtain valid signal segments belonging to the same class.
9. A microseismic event classification device comprising:
a memory for storing a computer program;
a processor for executing the computer program to carry out the steps of the method of micro-seismic event classification according to any of claims 1 to 5.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of micro-seismic event classification according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111457860.4A CN114154542B (en) | 2021-12-01 | 2021-12-01 | Microseism event classification method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111457860.4A CN114154542B (en) | 2021-12-01 | 2021-12-01 | Microseism event classification method, device, equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114154542A true CN114154542A (en) | 2022-03-08 |
| CN114154542B CN114154542B (en) | 2024-09-27 |
Family
ID=80455774
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111457860.4A Active CN114154542B (en) | 2021-12-01 | 2021-12-01 | Microseism event classification method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114154542B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115616659A (en) * | 2022-10-10 | 2023-01-17 | 中国矿业大学(北京) | Method and device for determining type of microseism event and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5373486A (en) * | 1993-02-03 | 1994-12-13 | The United States Department Of Energy | Seismic event classification system |
| US20180059272A1 (en) * | 2016-08-26 | 2018-03-01 | Baker Hughes Incorporated | System for automatically locating microseismic events |
| CN111126471A (en) * | 2019-12-18 | 2020-05-08 | 中国石油大学(华东) | Microseism event detection method and system |
-
2021
- 2021-12-01 CN CN202111457860.4A patent/CN114154542B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5373486A (en) * | 1993-02-03 | 1994-12-13 | The United States Department Of Energy | Seismic event classification system |
| US20180059272A1 (en) * | 2016-08-26 | 2018-03-01 | Baker Hughes Incorporated | System for automatically locating microseismic events |
| CN111126471A (en) * | 2019-12-18 | 2020-05-08 | 中国石油大学(华东) | Microseism event detection method and system |
Non-Patent Citations (5)
| Title |
|---|
| JIA, J: "Research on the spatial analysis method of seismic hazard for island", 《 12TH INTERNATIONAL CONFERENCE ON DAMAGE ASSESSMENT OF STRUCTURES》, 19 November 2017 (2017-11-19) * |
| R.K. LENNARTSSON: "Classification of acoustic and seismic data using nonlinear dynamical signal models", 《 PROCEEDINGS OF THE TENTH IEEE WORKSHOP ON STATISTICAL SIGNAL AND ARRAY PROCESSING》, 6 August 2002 (2002-08-06) * |
| 刘超;唐春安;薛俊华;余国锋;: "煤岩体微震事件属性识别与标定综合分析方法", 采矿与安全工程学报, no. 01, 15 March 2011 (2011-03-15) * |
| 贾靖: "微震监测技术在煤矿防治水中的应用研究", 《煤炭与化工》, 26 January 2017 (2017-01-26) * |
| 黄志辉: "爆破地震的研究与减震方法初探", 《全国首届防震减灾工程学术研讨会 》, 31 December 2004 (2004-12-31) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115616659A (en) * | 2022-10-10 | 2023-01-17 | 中国矿业大学(北京) | Method and device for determining type of microseism event and electronic equipment |
| CN115616659B (en) * | 2022-10-10 | 2023-06-30 | 中国矿业大学(北京) | Microseism event type determining method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114154542B (en) | 2024-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lin et al. | Automatic recognition and classification of multi-channel microseismic waveform based on DCNN and SVM | |
| Yin et al. | Real-time prediction of rockburst intensity using an integrated CNN-Adam-BO algorithm based on microseismic data and its engineering application | |
| Peng et al. | Automatic Classification of Microseismic Signals Based on MFCC and GMM‐HMM in Underground Mines | |
| Scarpetta et al. | Automatic classification of seismic signals at Mt. Vesuvius volcano, Italy, using neural networks | |
| CN114037020A (en) | Microseism event identification and classification method, device, equipment and storage medium | |
| Peng et al. | Automatic classification of microseismic records in underground mining: a deep learning approach | |
| Carniel et al. | Machine learning in volcanology: a review | |
| CN106066493A (en) | Bayes's petrofacies method of discrimination and device | |
| US10621506B2 (en) | Apparatus and method for activity detection and classification from sensor data | |
| CN103487832A (en) | Method for classifying supervised waveforms in three-dimensional seismic signal | |
| Kabiesz et al. | Application of rule-based models for seismic hazard prediction in coal mines. | |
| Li et al. | Automatic recognition and classification of microseismic waveforms based on computer vision | |
| He et al. | Injection-induced seismic risk management using machine learning methodology–a perspective study | |
| Zhu et al. | Accurate identification of microseismic P-and S-phase arrivals using the multi-step AIC algorithm | |
| CN115327613A (en) | Mine micro-seismic waveform automatic classification and identification method in multilayer multistage mode | |
| Hossain et al. | Lithology prediction using well logs: A granular computing approach | |
| CN114154542B (en) | Microseism event classification method, device, equipment and readable storage medium | |
| Curilem et al. | Discriminating seismic events of the Llaima volcano (Chile) based on spectrogram cross-correlations | |
| CN114966845A (en) | Unsupervised clustering seismic waveform real-time classification detection method | |
| Brusil et al. | A semi-supervised approach for microseisms classification from Cotopaxi volcano | |
| Wang | PCA-LSTM: An Impulsive Ground-Shaking Identification Method Based on Combined Deep Learning. | |
| Dong et al. | Comparisons of Logistic regression and Fisher discriminant classifier to seismic event identification | |
| Sun et al. | Micro‐seismic Event Detection of Hot Dry Rock based on the Gated Recurrent Unit Model and a Support Vector Machine | |
| Hu et al. | Discriminator of mining blasts and microseismic events based on multi-scale discrete wavelet transform | |
| Xin et al. | Microseismic Signal Classification Based on Artificial Neural Networks |
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 |