CN117270039A - Multi-channel microseismic signal small sample integrated learning directional vibration pickup algorithm - Google Patents
Multi-channel microseismic signal small sample integrated learning directional vibration pickup algorithm Download PDFInfo
- Publication number
- CN117270039A CN117270039A CN202311568373.4A CN202311568373A CN117270039A CN 117270039 A CN117270039 A CN 117270039A CN 202311568373 A CN202311568373 A CN 202311568373A CN 117270039 A CN117270039 A CN 117270039A
- Authority
- CN
- China
- Prior art keywords
- data
- target
- determining
- vector sequence
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 17
- 239000013598 vector Substances 0.000 claims abstract description 128
- 238000012544 monitoring process Methods 0.000 claims abstract description 116
- 239000011159 matrix material Substances 0.000 claims abstract description 50
- 238000013507 mapping Methods 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 24
- 239000003245 coal Substances 0.000 claims description 33
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000002759 z-score normalization Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/288—Event detection in seismic signals, e.g. microseismics
-
- 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
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Acoustics & Sound (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Geophysics (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The disclosure provides a multichannel microseismic signal small sample integrated learning directional vibration pickup algorithm, comprising: the method comprises the steps of obtaining a plurality of target sample data sets and data sets to be processed, carrying out standardization processing on the target sample data sets, generating a first data vector sequence and a second data vector sequence corresponding to the target sample data sets based on the processed target sample data sets, processing the first data vector sequence and the second data vector sequence corresponding to the target sample data sets to obtain a first mapping matrix corresponding to the first data vector sequence, determining a first monitoring statistic threshold corresponding to the target sample data sets according to the first mapping matrix and the first data vector sequence, determining a second monitoring statistic threshold according to the plurality of first monitoring statistic thresholds, determining a microseismic monitoring result according to the first mapping matrix, the second monitoring statistic threshold and the data sets to be processed, and accurately identifying microseismic events in an environment where a large amount of interference and noise signals exist.
Description
Technical Field
The disclosure relates to the technical field of microseismic monitoring, in particular to a multichannel microseismic signal small sample integrated learning directional vibration picking algorithm.
Background
Various safety risks exist in the coal mining process, and the risks not only threaten the life safety of miners, but also seriously damage the ecological environment. With the increase of underground mining depth, the influence degree of underground rock burst disasters on the safety of underground operation is increased, and the monitoring of microseismic events in an underground operation area means that the internal environment and the running state of a coal mine are monitored and analyzed in real time by using modern technical means, so that the safety risk is found and early warned in time.
At present, coal mines are used as complex dynamic industrial systems, and a large amount of interference and noise signals are contained in microseismic monitoring original data due to a large amount of mechanical and ray interference, so that microseismic event monitoring of an underground operation area has a large limitation.
Disclosure of Invention
The present disclosure aims to solve, at least to some extent, one of the technical problems in the related art.
Therefore, the purpose of the disclosure is to provide a multi-channel micro-seismic signal small sample integrated learning directional vibration picking algorithm, which can accurately identify micro-seismic events in an environment where a large amount of interference and noise signals exist.
To achieve the above objective, a multi-channel microseismic signal small sample integrated learning directional pickup algorithm according to an embodiment of the first aspect of the present disclosure includes: obtaining a plurality of target sample data sets and data sets to be processed, carrying out standardization processing on the target sample data sets, generating a first data vector sequence and a second data vector sequence corresponding to the target sample data sets based on the standardized processed target sample data sets, processing the first data vector sequence and the second data vector sequence corresponding to the target sample data sets based on a standard variable analysis method to obtain a first mapping matrix corresponding to the first data vector sequence, determining a first monitoring statistic threshold corresponding to the target sample data sets according to the first mapping matrix and the first data vector sequence, determining a second monitoring statistic threshold according to the plurality of first monitoring statistic thresholds, and determining a microseismic monitoring result according to the first mapping matrix, the second monitoring statistic threshold and the data sets to be processed.
According to the multi-channel microseismic signal small sample integrated learning directional vibration picking algorithm, a plurality of target sample data sets and data sets to be processed are obtained, the target sample data sets are subjected to standardized processing, a first data vector sequence and a second data vector sequence corresponding to the target sample data sets are generated based on the standardized processed target sample data sets, the first data vector sequence and the second data vector sequence corresponding to the target sample data sets are processed based on a standard variable analysis method, so that a first mapping matrix corresponding to the first data vector sequence is obtained, a first monitoring statistic threshold corresponding to the target sample data sets is determined according to the first mapping matrix and the first data vector sequence, a second monitoring statistic threshold is determined according to the plurality of first monitoring statistic thresholds, and a microseismic monitoring result is determined according to the first mapping matrix, the second monitoring statistic and the data sets to be processed, so that microseismic events can be accurately identified in environments with a large amount of interference and noise signals.
Additional aspects and advantages of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
The foregoing and/or additional aspects and advantages of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a schematic flow chart of a multi-channel microseismic signal small sample ensemble learning directional vibration picking algorithm according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of a multi-channel microseismic signal small sample ensemble learning directional vibration picking algorithm according to another embodiment of the present disclosure.
Detailed Description
Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present disclosure and are not to be construed as limiting the present disclosure. On the contrary, the embodiments of the disclosure include all alternatives, modifications, and equivalents as may be included within the spirit and scope of the appended claims.
Fig. 1 is a schematic flow chart of a multi-channel microseismic signal small sample integrated learning directional vibration picking algorithm according to an embodiment of the present disclosure.
It should be noted that, the execution body of the multi-channel micro-seismic signal small sample integrated learning directional vibration pickup algorithm in this embodiment is a multi-channel micro-seismic signal small sample integrated learning directional vibration pickup algorithm device, and the device may be implemented in a software and/or hardware manner, and the device may be configured in an electronic device, where the electronic device may include, but is not limited to, a terminal, a server, and the like, and the terminal may be, for example, a mobile phone, a palm computer, and the like.
As shown in fig. 1, the multi-channel microseismic signal small sample integrated learning directional vibration pickup algorithm comprises:
s101: a plurality of target sample data sets and data sets to be processed are acquired.
The target sample data set may be a data set formed by historical data acquired by a sensor preset in the underground coal mine when the underground coal mine is determined not to generate a microseismic event in a historical time period, and the data set to be processed may be a data set formed by real-time data acquired by the sensor preset in the underground coal mine in a current time period.
Optionally, in some embodiments, the acquiring the plurality of target sample data sets may be acquiring a plurality of initial sample data based on a sensor preset in the underground coal mine when no microseismic event occurs in the underground coal mine, clustering the plurality of initial sample data based on a preset cluster number to obtain a preset cluster number of sample data clusters, selecting the data selection number of initial sample data from each sample data cluster for a plurality of times based on a data selection number preset for each sample data cluster, and taking the initial sample data selected from the plurality of sample data as one target sample data set each time.
When no microseismic event occurs in the underground coal mine, the initial sample data are acquired by a sensor preset in the underground coal mine.
That is, for example, in the embodiments of the present disclosure, when no microseismic event occurs downhole in a coal mine, a plurality of initial sample data may be acquired based on sensors preset downhole in the coal mineAnd comprising n monitored variables, e.gWherein m is the sampling number, and clustering the plurality of initial sample data based on the preset cluster number (2) to obtain 2 sample data clusters (which can be expressed as +.>And->) Then, the method of put-back extraction may be adopted, the number of initial sample data is selected from each sample data cluster by multiple times (H times), the initial sample data selected from the multiple sample data at a time is taken as a target sample data set, and the target sample data set may be expressed as +.>I is a positive integer, and W is the number of target sample data in the target sample data set.
S102: and carrying out standardization processing on the target sample data set, and generating a first data vector sequence and a second data vector sequence corresponding to the target sample data set based on the target sample data set after the standardization processing.
After acquiring the plurality of target sample data sets and the data set to be processed, the embodiment of the disclosure may perform normalization processing on the target sample data sets, and generate a first data vector sequence and a second data vector sequence corresponding to the target sample data sets based on the normalized target sample data sets.
For example, it may be for a target sample data setThe normalization processing is performed (wherein the normalization processing method may be, for example, mean variance normalization processing, Z-score normalization processing, without limitation), and a first data vector sequence containing past information and a second data vector sequence containing future information corresponding to the target sample data set are generated based on the target sample data set after the normalization processing.
The first data vector sequence comprises target sample data in a preset time interval before a set time in the target sample data set.
Wherein the set time may be, for example, t, i.e., the target sample data in the set time interval (k) before the set time t is formed into the first data vector sequence，/>A is an element in the first data vector sequence.
Wherein the second data vector sequence includes target sample data in a plurality of preset time intervals after a set time in the target sample data set, namely, the target sample data in the preset time interval (k) after the set time is formed into the first data vector sequence，/>A is an element in the second sequence of data vectors.
S103: the first data vector sequence and the second data vector sequence corresponding to the target sample data set are processed based on a canonical variate analysis method to obtain a first mapping matrix corresponding to the first data vector sequence.
In the embodiment of the disclosure, after the target sample data set is subjected to standardization processing and the first data vector sequence and the second data vector sequence corresponding to the target sample data set are generated based on the standardized target sample data set, the first data vector sequence and the second data vector sequence corresponding to the target sample data set can be processed based on a canonical variable analysis method so as to obtain a first mapping matrix corresponding to the first data vector sequence.
For example, there may be a plurality of first data vector sequences separated from a target data setForm a matrix P, < > of k columns>A plurality of second data vector sequences to be separated from a target data set +.>Form a matrix F, < > of k columns>Processing a matrix P formed by the first data vector sequence and a matrix F formed by the second data vector sequence based on a canonical variable analysis method, and calculating a first mapping matrix J corresponding to the first data vector sequence by a outlier decomposition method, wherein the calculation mode can be expressed as:
；
wherein,u and D are intermediate parameters, and D is a canonical correlation matrix.
S104: a first monitoring statistic threshold corresponding to the target sample dataset is determined from the first mapping matrix and the first sequence of data vectors.
After processing a first data vector sequence and a second data vector sequence corresponding to a target sample data set based on a canonical variable analysis method to obtain a first mapping matrix corresponding to the first data vector sequence, the embodiments of the disclosure may determine a first monitoring statistic threshold corresponding to the target sample data set according to the first mapping matrix and the first data vector sequence.
Optionally, in some embodiments, the determining the first monitoring statistic threshold corresponding to the target sample data set according to the first mapping matrix and the first data vector sequence may be calculated by using the following formula:
；
wherein,，/>for the first data vector sequence, J is the first mapping matrix, W is the number of first data vector sequences,/I>Representative ofJFront of (2)kColumn (S)/(S)>K is a preset time interval,Tfor transposed symbol +.>And a first monitoring statistic threshold value corresponding to the ith target sample data set.
S105: a second monitoring statistic threshold is determined from the plurality of first monitoring statistic thresholds.
After determining a first monitoring statistic threshold corresponding to the target sample dataset according to the first mapping matrix and the first data vector sequence, the embodiments of the disclosure may determine a second monitoring statistic threshold according to the plurality of first monitoring statistic thresholds.
Alternatively, in some embodiments, the second monitoring statistic threshold is determined according to a plurality of first monitoring statistic thresholds, and the second monitoring statistic threshold may be calculated by adopting the following formula:
；
where H is the number of first monitoring statistic thresholds,for the second monitoring statistic threshold, +.>And a first monitoring statistic threshold value corresponding to the ith target sample data set.
S106: and determining a microseismic monitoring result according to the first mapping matrix, the second monitoring statistic threshold and the data set to be processed.
In the embodiment of the disclosure, after determining the second monitoring statistic threshold according to the plurality of first monitoring statistic thresholds, the microseismic monitoring result may be determined according to the first mapping matrix, the second monitoring statistic threshold and the data set to be processed.
In some embodiments, the microseismic monitoring result is determined according to the first mapping matrix, the second monitoring statistic threshold value and the to-be-processed data set, which may be that the to-be-processed data set is standardized according to the method as in S102, a data vector sequence corresponding to the to-be-processed data set is generated based on the standardized to-be-processed data set, a plurality of monitoring statistic values corresponding to the to-be-processed data set are determined according to the first mapping matrix and the data vector sequence corresponding to the to-be-processed data set, and then the target monitoring statistic value is determined according to the plurality of monitoring statistic values by adopting the method as in S105.
After determining the target monitoring statistic value corresponding to the data set to be processed, the embodiment of the disclosure can compare the target monitoring statistic value with the determined second monitoring statistic threshold value, determine that the microseismic monitoring result is a microseismic event in the coal mine well when the target monitoring statistic value is greater than the second monitoring statistic threshold value, and determine that the microseismic monitoring result is not a microseismic event in the coal mine well when the target monitoring statistic value is less than or equal to the second monitoring statistic threshold value.
In the embodiment of the disclosure, a plurality of target sample data sets and a data set to be processed are acquired, then the target sample data sets are subjected to standardization processing, a first data vector sequence and a second data vector sequence corresponding to the target sample data sets are generated based on the standardized processed target sample data sets, then the first data vector sequence and the second data vector sequence corresponding to the target sample data sets are processed based on a standard variable analysis method, so that a first mapping matrix corresponding to the first data vector sequence is obtained, then a first monitoring statistic threshold corresponding to the target sample data sets is determined according to the first mapping matrix and the first data vector sequence, then a second monitoring statistic threshold is determined according to the plurality of first monitoring statistic thresholds, and a microseismic monitoring result is determined according to the first mapping matrix, the second monitoring statistic threshold and the data set to be processed.
Fig. 2 is a schematic flow chart of a multi-channel microseismic signal small sample ensemble learning directional vibration picking algorithm according to another embodiment of the present disclosure.
As shown in fig. 2, the multi-channel microseismic signal small sample integrated learning directional vibration pickup algorithm comprises:
s201: a plurality of target sample data sets and data sets to be processed are acquired.
S202: and carrying out standardization processing on the target sample data set, and generating a first data vector sequence and a second data vector sequence corresponding to the target sample data set based on the target sample data set after the standardization processing.
S203: the first data vector sequence and the second data vector sequence corresponding to the target sample data set are processed based on a canonical variate analysis method to obtain a first mapping matrix corresponding to the first data vector sequence.
S204: a first monitoring statistic threshold corresponding to the target sample dataset is determined from the first mapping matrix and the first sequence of data vectors.
S205: a second monitoring statistic threshold is determined from the plurality of first monitoring statistic thresholds.
The descriptions of S201 to S205 may be specifically referred to the above embodiments, and are not repeated herein.
S206: and carrying out standardization processing on the data set to be processed, and generating a third data vector sequence based on the standardized data set to be processed, wherein the third data vector sequence comprises data to be processed in a preset time interval before the set time of the data set to be processed.
In the embodiment of the disclosure, the normalization processing may be performed on the data set Y to be processed (where the normalization processing method may be, for example, mean variance normalization processing, and Z-score normalization processing, which are not limited thereto), and a third data vector sequence is generated based on the data set to be processed after the normalization processing, where the third data vector sequence includes data to be processed in a preset time interval before a set time in the data set to be processed.
For example, the set time may be, for example, t, i.e., the data Y to be processed in the set time interval (k) before the set time t is formed into the third data vector sequence，/>。
S207: and determining a first monitoring statistical value corresponding to the data set to be processed according to the first mapping matrix and the third data vector sequence.
In the embodiment of the disclosure, after the data set to be processed is subjected to standardization processing and the third data vector sequence is generated based on the standardized data set to be processed, the first monitoring statistical value corresponding to the data set to be processed may be determined according to the first mapping matrix and the third data vector sequence.
In the embodiment of the disclosure, according to the first mapping matrix and the third data vector sequence, the first monitoring statistical value corresponding to the data set to be processed may be determined by calculating the first monitoring statistical value using the following formula:
；
wherein J is a first mapping matrix,representative ofJFront of (2)kColumn (S)/(S)>K is a preset time interval,Tfor transposed symbol +.>For the first monitored statistical quantity.
S208: and determining a second monitoring statistic according to the first monitoring statistic.
In an embodiment of the disclosure, after determining the first monitoring statistic value corresponding to the data set to be processed according to the first mapping matrix and the third data vector sequence, the second monitoring statistic value may be determined according to the plurality of first monitoring statistic values.
In the embodiment of the disclosure, the determining the second monitored statistical value according to the plurality of first monitored statistical values may be calculating the second monitored statistical value by adopting the following formula:
；
wherein,for the first monitored statistical value, J is the first mapping matrix,>representative ofJFront of (2)kThe number of columns in a row,k is a preset time interval,Tfor transposed symbol +.>For the second monitored statistical value, H is the number of the first monitored statistical values.
S209: if the second monitoring statistic value is larger than the second monitoring statistic threshold value, determining that the microseismic monitoring result is that a microseismic event occurs in the coal mine underground.
According to the embodiment of the disclosure, after the second monitoring statistic value is determined according to the plurality of first monitoring statistic values, the second monitoring statistic value can be compared with the determined second monitoring statistic threshold value, when the second monitoring statistic value is larger than the second monitoring statistic threshold value, the microseism monitoring result is determined to be a microseism event in the coal mine underground, and when the second monitoring statistic value is smaller than or equal to the second monitoring statistic threshold value, the microseism monitoring result is determined to be the microseism event in the coal mine underground.
S210: a target zone in which a microseismic event occurs is determined from a plurality of data acquisition zones downhole in a coal mine.
In the embodiment of the disclosure, the data to be processed in the data set to be processed is acquired by sensors preset in different data acquisition areas under the coal mine.
That is, in the embodiment of the disclosure, corresponding sensors may be preset for different data acquisition areas in the coal mine, for example, corresponding sensors may be respectively set in data acquisition areas such as a roadway bottom area, a roadway top area, a roadway front area, a roadway rear area and the like, so that data to be processed acquired based on the sensors set in the different data acquisition areas can be supported subsequently, and a target area where a microseismic event occurs is determined from a plurality of data acquisition areas in the coal mine.
Optionally, in some embodiments, the determining the target area where the microseismic event occurs from the multiple data acquisition areas under the coal mine may be determining multiple target data vectors obtained by processing to-be-processed data acquired by sensors preset in different initial areas at occurrence time of the microseismic event from a third data vector sequence, determining multiple first weights of each target data vector relative to each first monitored statistical value, where the first weights are used for describing an influence degree of each target data vector on the first monitored statistical value, determining a second weight corresponding to each target data vector according to the multiple first weights of each target data vector relative to each first monitored statistical value, determining a second weight with a maximum value from the multiple second weights, and determining the data acquisition area of to-be-processed data corresponding to the second weight with the maximum value as the target area.
That is, in the embodiment of the present disclosure, a plurality of target data vectors obtained by processing the data to be processed acquired by the sensors preset in different initial areas at the occurrence time of the microseismic event may be determined from the third data vector sequence, and the plurality of target data vectors may be expressed asI is an identification of the data acquisition area.
In embodiments of the present disclosure, a plurality of first weights may be determined for each target data vector relative to each first monitored statistical quantity value, where the first weights are used to describe the extent to which the target data vector affects the first monitored statistical quantity value.
Alternatively, in some embodiments, determining the plurality of first weights for each target data vector relative to each first monitored statistical value may be calculated using the following formula:
；
wherein i is the identification of the data acquisition area, a plurality of target data vectorsJ is a first mapping matrix, +.>For the first weight, T is the transposed symbol.
In the embodiment of the disclosure, the effective duty ratio of the signal channel with higher weight can be effectively improved by using the exponential weight calculation algorithm after improvement, the influence of negative numbers in the calculation process is avoided, and the orientation precision of the microseismic event after weight calculation is improved.
After determining the plurality of first weights for each target data vector relative to each first monitored statistical value, embodiments of the present disclosure may be based on the plurality of first weights for each target data vector relative to each first monitored statistical value.
Optionally, in some embodiments, according to a plurality of first weights of each target data vector relative to each first monitored statistical value, determining a second weight corresponding to each target data vector, and calculating the second weight by using the following formula:
；
wherein,for the second weight, R is the number of the first monitored statistical value,/for>Is a first weight.
In the embodiment of the disclosure, the second weight corresponding to each target data vector is determined, the second weight with the largest value is determined from the plurality of second weights, and the data acquisition area of the data to be processed corresponding to the second weight with the largest value is determined as the target area, so that preliminary orientation of the microseismic event under the coal mine can be realized.
In some embodiments of the present disclosure, if the second monitoring statistics value is less than or equal to the second monitoring statistics threshold value, after determining that the microseismic monitoring result is that no microseismic event occurs in the underground coal mine, a method such as S210 may also be adopted to determine a second weight corresponding to each target data vector, so that a data acquisition area of the data to be processed corresponding to the second weight with the largest value may be determined to have larger signal interference or device signal noise, and thus, the data acquisition area where the signal interference or device signal noise exists may be oriented.
In the embodiment of the disclosure, a plurality of target sample data sets and data sets to be processed are obtained, then the target sample data sets are subjected to standardization processing, and a first data vector sequence and a second data vector sequence corresponding to the target sample data sets are generated based on the standardized processed target sample data sets, and then the first data vector sequence and the second data vector sequence corresponding to the target sample data sets are processed based on a standard variable analysis method, so as to obtain a first mapping matrix corresponding to the first data vector sequence, and according to the first mapping matrix and the first data vector sequence, a first monitoring statistic threshold corresponding to the target sample data sets is determined, and then a second monitoring statistic threshold is determined according to the plurality of first monitoring statistic thresholds, and then the standardized processing is performed on the target sample data sets, and a third data vector sequence is generated based on the standardized processed data sets, wherein the third data vector sequence comprises data to be processed in a preset time interval before the set time of the data sets to be processed, and according to the first mapping matrix and the third data vector sequence, a first statistic value corresponding to the data sets to be processed is determined, and then a coal mine well noise statistic value is determined, and a plurality of the first statistic values are determined, and a plurality of the second statistic values are determined, and a plurality of the first statistic values are accurately monitored in a coal mine well noise region under a micro-vibration region, and a micro-vibration region is accurately monitored, and a micro-noise is determined under a micro-vibration region is in a region, and a large-scale-vibration environment is determined, and a micro-vibration environment is well is accurately is monitored.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
It should be noted that in the description of the present disclosure, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Furthermore, in the description of the present disclosure, unless otherwise indicated, the meaning of "a plurality" is two or more.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present disclosure in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present disclosure.
It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
Furthermore, each functional unit in the embodiments of the present disclosure may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present disclosure have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the present disclosure, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the present disclosure.
Claims (10)
1. The multi-channel microseismic signal small sample integrated learning directional vibration pickup algorithm is characterized by comprising the following steps of:
acquiring a plurality of target sample data sets and a data set to be processed;
performing standardization processing on the target sample data set, and generating a first data vector sequence and a second data vector sequence corresponding to the target sample data set based on the standardized target sample data set;
processing a first data vector sequence and a second data vector sequence corresponding to the target sample data set based on a canonical variate analysis method to obtain a first mapping matrix corresponding to the first data vector sequence;
determining a first monitoring statistic threshold corresponding to the target sample dataset according to the first mapping matrix and the first data vector sequence;
determining a second monitoring statistic threshold according to the plurality of first monitoring statistic thresholds;
and determining a microseismic monitoring result according to the first mapping matrix, the second monitoring statistic threshold value and the data set to be processed.
2. The method of claim 1, wherein the first sequence of data vectors includes target sample data in a preset time interval prior to a set time in the target sample data set;
the second data vector sequence includes target sample data in a plurality of preset time intervals after a set time in the target sample data set.
3. The method of claim 2, wherein the determining a first monitoring statistic threshold corresponding to the target sample dataset from the first mapping matrix and the first sequence of data vectors comprises:
the first monitoring statistic threshold value is calculated by adopting the following formula:
；
wherein,，/>for the first sequence of data vectors,Jfor the first mapping matrix, W is the number of first data vector sequences, +.>Representative ofJFront of (2)kColumn (S)/(S)>K is a preset time interval,Tin order to transpose the symbol,and a first monitoring statistic threshold value corresponding to the ith target sample data set.
4. The method of claim 3, wherein said determining a second monitoring statistic threshold from a plurality of said first monitoring statistic thresholds comprises:
the second monitoring statistic threshold value is calculated by adopting the following formula:
；
where H is the number of first monitoring statistic thresholds,for the second monitoring statistic threshold, +.>And a first monitoring statistic threshold value corresponding to the ith target sample data set.
5. The method of claim 1, wherein the determining the microseismic monitoring result from the first mapping matrix, the second monitoring statistic threshold, and the data set to be processed comprises:
carrying out standardization processing on the data set to be processed, and generating a third data vector sequence based on the standardized data set to be processed, wherein the third data vector sequence comprises data to be processed in a preset time interval before the set time in the data set to be processed;
determining a first monitoring statistical value corresponding to the data set to be processed according to the first mapping matrix and the third data vector sequence;
determining a second monitored statistical magnitude according to the plurality of first monitored statistical magnitudes;
and if the second monitoring statistic value is larger than the second monitoring statistic threshold value, determining that the microseismic monitoring result is that a microseismic event occurs underground the coal mine.
6. The method of claim 5, wherein the data to be processed in the data set to be processed is acquired by sensors preset in different data acquisition areas under the coal mine;
wherein after determining that the microseismic monitoring result is a microseismic event occurring downhole in the coal mine if the second monitoring statistic is greater than the second monitoring statistic threshold, further comprising:
a target region in which the microseismic event occurs is determined from a plurality of the data acquisition regions downhole in the coal mine.
7. The method of claim 6, wherein said determining a target area from a plurality of said data acquisition areas downhole in a coal mine where said microseismic event occurred comprises:
determining a plurality of target data vectors obtained by processing the data to be processed acquired in different data acquisition areas at the occurrence time of a microseismic event from the third data vector sequence;
determining a plurality of first weights of each target data vector relative to each first monitoring statistic, wherein the first weights are used for describing the influence degree of the target data vector on the first monitoring statistic;
determining a second weight corresponding to each target data vector according to the plurality of first weights of each target data vector relative to each first monitoring statistic value;
determining a second weight with the largest value from the second weights;
and determining the data acquisition area of the data to be processed corresponding to the second weight with the maximum value as the target area.
8. The method of claim 7, wherein said determining a plurality of first weights for each of said target data vectors relative to each of said first monitored statistical values comprises:
the first weight is calculated by adopting the following formula:
；
wherein i is the identification of the data acquisition area, a plurality of target data vectorsJ is the first mapping matrix,for the first weight, T is the transposed symbol.
9. The method of claim 8, wherein said determining a second weight corresponding to each of said target data vectors based on said plurality of first weights for each of said target data vectors relative to each of said first monitored statistical values comprises:
the second weight is calculated by adopting the following formula:
；
wherein,for the second weight, R is the number of the first monitored statistical value,/for>Is a first weight.
10. The method of claim 1, wherein the acquiring a plurality of target sample data sets comprises:
acquiring a plurality of initial sample data based on a sensor preset in the underground coal mine when no microseismic event occurs in the underground coal mine;
clustering the initial sample data based on the number of preset clusters to obtain a plurality of sample data clusters of the number of preset clusters;
selecting the data selection number of the initial sample data from each sample data cluster for a plurality of times based on the data selection number preset for each sample data cluster;
the initial sample data respectively selected from a plurality of sample data at a time is taken as one target sample data set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311568373.4A CN117270039B (en) | 2023-11-23 | 2023-11-23 | Multi-channel microseismic signal small sample integrated learning directional vibration pickup method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311568373.4A CN117270039B (en) | 2023-11-23 | 2023-11-23 | Multi-channel microseismic signal small sample integrated learning directional vibration pickup method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117270039A true CN117270039A (en) | 2023-12-22 |
| CN117270039B CN117270039B (en) | 2024-02-20 |
Family
ID=89210965
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311568373.4A Active CN117270039B (en) | 2023-11-23 | 2023-11-23 | Multi-channel microseismic signal small sample integrated learning directional vibration pickup method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117270039B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013116748A2 (en) * | 2012-02-03 | 2013-08-08 | Ion Geophysical Corporation | Method and apparatus for processing seismic data |
| US20130336091A1 (en) * | 2012-06-18 | 2013-12-19 | Halliburton Energy Services, Inc. | Statistics-based seismic event detection |
| WO2017206159A1 (en) * | 2016-06-03 | 2017-12-07 | Schlumberger Technology Corporation | Fracture network extraction by microseismic events clustering analysis |
| CN112529031A (en) * | 2020-07-28 | 2021-03-19 | 新汶矿业集团有限责任公司 | Microseismic signal clustering method and device based on improved K-means |
| CN116520433A (en) * | 2023-06-30 | 2023-08-01 | 煤炭科学研究总院有限公司 | Coal mine working face directional vibration pickup method for multichannel signal fusion analysis |
| CN116736375A (en) * | 2023-07-05 | 2023-09-12 | 煤炭科学研究总院有限公司 | Microseism signal state judging and identifying method based on sparse standard variable analysis |
| US20230296800A1 (en) * | 2022-07-11 | 2023-09-21 | Yikang Zheng | DAS Same-Well Monitoring Real-Time Microseismic Effective Event Identification Method Based on Deep Learning |
-
2023
- 2023-11-23 CN CN202311568373.4A patent/CN117270039B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013116748A2 (en) * | 2012-02-03 | 2013-08-08 | Ion Geophysical Corporation | Method and apparatus for processing seismic data |
| US20130336091A1 (en) * | 2012-06-18 | 2013-12-19 | Halliburton Energy Services, Inc. | Statistics-based seismic event detection |
| WO2017206159A1 (en) * | 2016-06-03 | 2017-12-07 | Schlumberger Technology Corporation | Fracture network extraction by microseismic events clustering analysis |
| CN112529031A (en) * | 2020-07-28 | 2021-03-19 | 新汶矿业集团有限责任公司 | Microseismic signal clustering method and device based on improved K-means |
| US20230296800A1 (en) * | 2022-07-11 | 2023-09-21 | Yikang Zheng | DAS Same-Well Monitoring Real-Time Microseismic Effective Event Identification Method Based on Deep Learning |
| CN116520433A (en) * | 2023-06-30 | 2023-08-01 | 煤炭科学研究总院有限公司 | Coal mine working face directional vibration pickup method for multichannel signal fusion analysis |
| CN116736375A (en) * | 2023-07-05 | 2023-09-12 | 煤炭科学研究总院有限公司 | Microseism signal state judging and identifying method based on sparse standard variable analysis |
Non-Patent Citations (2)
| Title |
|---|
| 丛森 等: "煤矿微震监测技术现状与发展前景", 中国矿业, vol. 25, no. 12, pages 87 - 93 * |
| 曹英莉 等: "矿山微震监测台网多目标优化决策模型研究及应用", 矿业研究与开发, vol. 41, no. 11, 30 November 2021 (2021-11-30), pages 34 - 43 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117270039B (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10496466B2 (en) | Preprocessor of abnormality sign diagnosing device and processing method of the same | |
| CN109471171B (en) | Method, device and system for separating aliasing seismic data | |
| CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
| CN108107086B (en) | Gas detection method based on array gas sensor and gas sensor | |
| CN116736375B (en) | Microseism signal state judging and identifying method based on sparse standard variable analysis | |
| Oliver | Geostatistics, rare disease and the environment | |
| CN111369056B (en) | Geological disaster prediction method and electronic equipment | |
| CN117270039B (en) | Multi-channel microseismic signal small sample integrated learning directional vibration pickup method | |
| CN110969645A (en) | Unsupervised abnormal track detection method and unsupervised abnormal track detection device for crowded scenes | |
| CN116842410B (en) | Intelligent helmet antitheft management method and system based on dynamic perception | |
| Palgunadi et al. | Methodology for full waveform near real-time automatic detection and localization of microseismic events using high (8 kHz) sampling rate records in mines: Application to the garpenberg mine (Sweden) | |
| CN110988856B (en) | Target detection trace agglomeration algorithm based on density clustering | |
| CN115080909B (en) | Analysis method for influencing data of internet of things sensing equipment, electronic equipment and storage medium | |
| CN114019139B (en) | Method for detecting heavy metal abnormal data of agricultural land soil | |
| CN110161560B (en) | Method and device for detecting microseismic event | |
| EP3234632B1 (en) | Detection of acoustic events | |
| AU2019369820B2 (en) | Device, method, program, and system for detecting unidentified water | |
| CN114879033A (en) | Motor fault detection method, system and storage medium | |
| CN109241147B (en) | Method for evaluating variability of statistical value | |
| CN110784887B (en) | Method for detecting number of abnormal signal sources in gridding radio signal monitoring system | |
| CN112071009B (en) | Optical fiber pipeline early warning system and method thereof | |
| CN117073728B (en) | Flexible capacitive touch sensor | |
| CN113609207B (en) | Data preprocessing method for slope deformation monitoring data | |
| CN117494030B (en) | Abnormal event identification method and related device based on distributed optical fiber acoustic wave sensing | |
| US8837566B1 (en) | System and method for detection of noise in sparse data sets with edge-corrected measurements |
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 |