CN114519392B - Rock burst danger prediction algorithm based on microseismic time sequence data - Google Patents
Rock burst danger prediction algorithm based on microseismic time sequence data Download PDFInfo
- Publication number
- CN114519392B CN114519392B CN202210151070.1A CN202210151070A CN114519392B CN 114519392 B CN114519392 B CN 114519392B CN 202210151070 A CN202210151070 A CN 202210151070A CN 114519392 B CN114519392 B CN 114519392B
- Authority
- CN
- China
- Prior art keywords
- time sequence
- sequence data
- subsections
- microseismic
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000011435 rock Substances 0.000 title claims abstract description 60
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000002372 labelling Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 14
- 238000010606 normalization Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims 2
- 238000013499 data model Methods 0.000 claims 1
- 238000000034 method Methods 0.000 description 38
- 238000012360 testing method Methods 0.000 description 20
- 239000003245 coal Substances 0.000 description 10
- 238000004590 computer program Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 6
- 238000005070 sampling Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 238000003064 k means clustering Methods 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005489 elastic deformation Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Geophysics And Detection Of Objects (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a rock burst danger prediction algorithm based on microseismic time sequence data, which relates to the technical field of data processing, and is characterized in that microseismic time sequence data to be detected are obtained, the microseismic time sequence data are segmented to obtain microseismic time sequence data subsections, all microseismic time sequence data subsections are sequentially input into a preset early warning model, so that the preset early warning model recognizes characteristic information in all microseismic time sequence data subsections, and corresponding safety attribute information is output according to the characteristic information; and carrying out rock burst early warning according to the safety attribute information. Characteristic information in the micro-seismic time sequence data subsections can be accurately identified based on a preset early warning model, so that different safety attribute information corresponding to each characteristic information is output, and dangerous early warning of rock burst is realized based on the safety attribute information.
Description
Technical Field
The disclosure relates to the technical field of data processing, in particular to a rock burst hazard prediction algorithm based on microseismic time sequence data.
Background
The rock burst of the coal mine is also called coal explosion, which refers to the dynamic phenomenon of sudden and violent damage of coal bodies around a coal mine roadway or a working surface due to the instantaneous release of elastic deformation energy, is often accompanied with the phenomena of instantaneous displacement, throwing, bang, air wave and the like of the coal bodies, has great destructiveness, and is one of the serious disasters of the coal mine. Along with the continuous increase of the mining intensity and mining depth of the mine, the frequency and intensity of coal rock dynamic disasters such as rock burst, coal and gas protrusion, roof caving, roadway deformation and the like are also continuously increased, and the safety production of the mine is seriously threatened. The rock burst brings serious threat to the safety production of mines due to the sudden and abrupt occurrence of rock burst and the rapid damage to surrounding rocks of the roadways, and serious economic loss and serious casualties are caused by serious danger.
At present, aiming at coal mine rock burst danger prediction, two main solutions are provided: firstly, researching rock burst occurrence mechanism through experimental means based on mechanical knowledge, and carrying out danger prediction by combining rock state and mechanical behavior; and secondly, mining the dangerous information of the rock burst from the monitoring data based on the modern advanced computer technology and combining an artificial intelligence algorithm.
The inventor finds that although the rock burst can be pre-warned to a certain extent when implementing the two solutions, the pre-warning accuracy is not high.
Disclosure of Invention
The disclosure provides a rock burst risk prediction algorithm based on microseismic time sequence data.
According to a first aspect of the present disclosure, there is provided a rock burst risk prediction algorithm based on microseismic time series data, including:
acquiring microseismic time sequence data to be detected, and segmenting the microseismic time sequence data to obtain microseismic time sequence data subsections;
sequentially inputting all the micro-seismic time sequence data subsections into a preset early warning model, so that the preset early warning model recognizes characteristic information in all the micro-seismic time sequence data subsections, and obtaining and outputting safety attribute information corresponding to different micro-seismic time sequence data subsections according to the characteristic information;
and carrying out rock burst early warning according to the safety attribute information.
Optionally, the microseismic time sequence data comprises index information of rock burst;
the segmenting the microseismic timing data comprises:
carrying out format normalization processing on the index information in the microseismic time sequence data;
segmenting the normalized microseismic time sequence data according to a preset time interval to obtain the microseismic time sequence data subsections.
Optionally, before all the micro-seismic time sequence data subsections are sequentially input into the preset early warning model, the method further comprises:
performing first labeling on the safety attribute information of the sub-section of the sample microseismic time sequence data based on a preset number of classifiers; the safety attribute information is obtained by labeling the same sample microseismic time sequence data subsections by each classifier, and the safety attribute information comprises: dangerous properties and safety properties;
selecting all the first sample microseismic time sequence data subsections and the preset second sample microseismic time sequence data subsections, wherein the first sample microseismic time sequence data subsections are sample microseismic time sequence data subsections with the safety attribute information being dangerous attributes, and the second sample microseismic time sequence data subsections are sample microseismic time sequence data subsections with the safety attribute information being safety attributes;
training according to the first sample microseismic time sequence data subsection and the second sample microseismic time sequence data subsection to generate the preset early warning model, wherein the preset early warning model comprises characteristic information corresponding to the dangerous attribute and characteristic information corresponding to the safety attribute.
Optionally, the method further comprises:
performing second labeling of safety attribute information on the test microseismic time sequence data subsections based on a preset log file; the test microseism time sequence data subsections are obtained by segmenting test microseism time sequence data according to time intervals;
inputting the test microseismic time sequence data subsection into the preset early warning model so as to test the preset early warning model according to the output result of the preset early warning model and the second label.
Optionally, the training according to the first sample microseismic timing data sub-segment and the second sample microseismic timing data sub-segment includes:
and training the first sample microseismic time sequence data subsection and the second sample microseismic time sequence data subsection based on a K-medoids clustering algorithm.
According to a second aspect of the present disclosure, there is provided a rock burst risk prediction apparatus based on microseismic time series data, comprising:
the acquisition unit is used for acquiring microseismic time sequence data to be detected;
the segmentation unit is used for segmenting the microseismic time sequence data to obtain microseismic time sequence data subsections;
the input unit is used for sequentially inputting all the micro-seismic time sequence data subsections into a preset early warning model so that the preset early warning model can identify characteristic information in all the micro-seismic time sequence data subsections and output corresponding safety attribute information according to the characteristic information;
and the early warning unit is used for carrying out early warning on rock burst according to the safety attribute information.
Optionally, the microseismic time sequence data comprises index information of rock burst;
the segmentation unit includes:
the processing module is used for carrying out format normalization processing on the index information in the microseismic time sequence data;
the segmentation module is used for segmenting the normalized microseismic time sequence data according to a preset time interval to obtain the microseismic time sequence data subsections.
Optionally, the apparatus further includes:
the first labeling unit is used for carrying out first labeling on the safety attribute information of the sample microseismic time sequence data subsections based on a preset number of classifiers before the input unit sequentially inputs all the microseismic time sequence data subsections into a preset early warning model; the safety attribute information is obtained by labeling the same sample microseismic time sequence data subsections by each classifier, and the safety attribute information comprises: dangerous properties and safety properties;
the device comprises a selection unit, a first sampling micro-seismic time sequence data sub-section and a preset number of second sampling micro-seismic time sequence data sub-sections, wherein the first sampling micro-seismic time sequence data sub-section is a sampling micro-seismic time sequence data sub-section with the safety attribute information being a dangerous attribute, and the second sampling micro-seismic time sequence data sub-section is a sampling micro-seismic time sequence data sub-section with the safety attribute information being a safety attribute;
the training unit is used for training according to the first sample microseismic time sequence data subsection and the second sample microseismic time sequence data subsection so as to generate the preset early warning model, wherein the preset early warning model comprises characteristic information corresponding to the dangerous attribute and characteristic information corresponding to the safety attribute.
Optionally, the apparatus further includes:
the second labeling unit is used for carrying out second labeling on the safety attribute information of the test microseism time sequence data subsections based on a preset log file; the test microseism time sequence data subsections are obtained by segmenting test microseism time sequence data according to time intervals;
the test unit is used for inputting the test microseism time sequence data subsections into the preset early warning model so as to test the preset early warning model according to the output result of the preset early warning model and the second label.
Optionally, the training unit is further configured to train the first sample microseismic time-series data sub-segment and the second sample microseismic time-series data sub-segment based on a K-means clustering algorithm.
According to a third aspect of the present disclosure, there is provided an electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of the first aspect.
According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method according to the first aspect.
According to the rock burst prediction method, the device, the electronic equipment and the storage medium, the microseismic time sequence data to be detected are obtained, the microseismic time sequence data are segmented to obtain microseismic time sequence data subsections, all microseismic time sequence data subsections are sequentially input into a preset early warning model, so that the preset early warning model can recognize characteristic information in all microseismic time sequence data subsections, and corresponding safety attribute information is output according to the characteristic information; and carrying out rock burst early warning according to the safety attribute information. Compared with the related art, the method and the device can accurately identify the characteristic information in the micro-seismic time sequence data subsection based on the preset early warning model so as to output different safety attribute information corresponding to each characteristic information, and realize dangerous early warning of rock burst based on the safety attribute information.
It should be understood that the description of this section is not intended to identify key or critical features of the embodiments of the application or to delineate the scope of the application. Other features of the present application will become apparent from the description that follows.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
fig. 1 is a schematic flow chart of a rock burst risk prediction method based on microseismic time series data according to an embodiment of the present disclosure;
FIG. 2 is a flow chart of a method for segmenting microseismic timing data according to an embodiment of the present application;
fig. 3 is a flowchart of a method for constructing a preset early warning model according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a rock burst risk prediction device based on microseismic time series data according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of another rock burst risk prediction device based on microseismic time series data according to an embodiment of the present disclosure;
fig. 6 is a schematic block diagram of an example electronic device 600 provided by an embodiment of the disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The following describes a method, an apparatus, an electronic device, and a storage medium for predicting rock burst according to an embodiment of the present disclosure with reference to the accompanying drawings.
Fig. 1 is a flow chart of a rock burst risk prediction method based on microseismic time series data according to an embodiment of the present disclosure.
As shown in fig. 1, the method comprises the steps of:
and 101, acquiring microseismic time sequence data to be detected, and segmenting the microseismic time sequence data to obtain microseismic time sequence data subsections.
In the practical application process, the microseism event can be acquired and analyzed through the microseism monitoring equipment, the microseism time sequence data can be finally obtained, the microseism time sequence data comprises 3 indexes of microseism occurrence time, coordinates and energy, the microseism time sequence data in the practical application can also comprise indexes such as coal rock breaking time, space and strength, and the like, however, in the implementation of the embodiment, an analysis mode of the 3 indexes of the microseism occurrence time, coordinates and energy is adopted, and the concrete indexes are not intended to be limited.
Because the time of the microseismic occurrence is uncertain, the time interval of the microseismic time sequence data acquired by the microseismic monitoring device is uneven, and therefore, in order to realize the accuracy of microseismic monitoring, the microseismic time sequence data with different time intervals need to be subjected to segmentation operation. Based on the non-uniform nature of the time interval, the segmentation may be performed in, but is not limited to, the following ways, such as: the microseismic timing data is segmented by a fixed window length, segmented by a fixed interval duration, or any other form of segmentation. In the following embodiments, the embodiments of the present application segment microseismic time series data by using a fixed window length, however, it should be noted that the implementation is not limited to a specific segmentation means.
It should be noted that, although the segmentation time interval is preset, it is not invariable, and it can be flexibly changed according to actual needs, and the microseismic time sequence data is divided into different numbers of subsections, and the number of subsections into which one microseismic time sequence data can be divided is not limited in the embodiment of the present application.
And 102, sequentially inputting all the micro-seismic time sequence data subsections into a preset early warning model so that the preset early warning model can identify the characteristic information in all the micro-seismic time sequence data subsections, and outputting corresponding safety attribute information according to the characteristic information.
Based on the study data, the following two practical results were obtained, the first: the larger the time interval between the current microseismic and the last microseismic is, the larger the sudden property of the microseismic is, and the smaller the influence of the last microseismic is; second kind: each sudden microseismic will drive nearby microseisms, and the closer to the microseismic occurrence point, the larger the influence is. According to the two practical results, the solution for the specificity of the microseismic time sequence data is provided in the embodiment of the application: namely, a preset early warning model is constructed, the preset early warning model can identify characteristic information in all micro-seismic time sequence data subsections, and corresponding safety attribute information is output according to the characteristic information, and the safety attribute information comprises: dangerous properties and safety properties.
In practical application, all the micro-seismic time sequence data subsections are input into a preset early warning model, so that the safety attribute information corresponding to the micro-seismic time sequence data subsections output by the preset early warning model can be obtained.
And 103, carrying out rock burst early warning according to the safety attribute information.
And carrying out early warning on the microseismic time sequence data subsections with dangerous attributes according to the safety attribute information corresponding to the microseismic time sequence data subsections. In the practical application process, the early warning can be realized by adopting the following modes: triggering an alarm for early warning, flashing a warning lamp for early warning and the like. Specifically, the embodiment of the application does not limit the early warning mode.
According to the rock burst prediction method provided by the embodiment of the disclosure, the microseismic time sequence data to be detected are obtained, the microseismic time sequence data are segmented to obtain microseismic time sequence data subsections, all the microseismic time sequence data subsections are sequentially input into a preset early warning model, so that the preset early warning model can identify characteristic information in all the microseismic time sequence data subsections, and safety attribute information corresponding to different microseismic time sequence data subsections is obtained and output according to the characteristic information; and carrying out rock burst early warning according to the safety attribute information. Compared with the related art, the method and the device can accurately identify the characteristic information in the micro-seismic time sequence data subsection based on the preset early warning model so as to output different safety attribute information corresponding to each characteristic information, and realize dangerous early warning of rock burst based on the safety attribute information.
As a refinement to the foregoing embodiment, when the step 101 is executed to segment the microseismic time-series data, as shown in fig. 2, the following manner may be adopted, and fig. 2 is a flowchart of a method for segmenting the microseismic time-series data according to an embodiment of the present application, as shown in fig. 2, where the method includes:
The format normalization processing is to normalize coordinates and energy in the index information in the microseismic time sequence data to be a numerical value between 0 and 1; the format normalization is performed for the purpose of facilitating subsequent data processing.
For convenience of understanding, the fixed window length is taken as an illustration in a segmentation mode, in specific implementation, the normalization processing of the coordinate index and the energy index is respectively carried out to obtain a numerical value between 0 and 1, and in segmentation, a preset time interval can be set based on actual requirements, wherein the preset time interval is the length of the fixed window, for example, the preset time interval is one hour, half hour, one day or the like, and the setting of the preset time interval is not limited in the embodiment of the present application.
The embodiment of the application also provides a method for constructing a preset early warning model, as shown in fig. 3, the method includes:
It should be noted that, the execution of step 302 may be the same as that of step 202 in the previous embodiment, and the details are not repeated here.
The preset number of classifiers are used for classifying the safety attributes of the sub-segments of the sample microseismic time sequence data, and each classifier classifies the sub-segments of the same sample microseismic time sequence data. In order to facilitate understanding of the description of the following example, it is assumed that the number of preset classifiers is 10, all the classifiers can classify the same sample microseismic time sequence data subsections simultaneously or sequentially, if one classifier marks the dangerous attribute on the sample microseismic time sequence data subsections, the dangerous probability is 0.1, if two classifiers marks the dangerous attribute on the sample microseismic time sequence data subsections, the dangerous probability is 0.1 on the sample microseismic time sequence data subsections, namely, the dangerous probability of the sample microseismic time sequence data subsections is 0.2. And so on.
The aim of selecting the total number of first sample microseismic time sequence data subsections is that: the next training can identify all characteristic information of the dangerous attribute. In practical applications, the number of the first sample microseismic timing data subsections may be far smaller than that of the second sample microseismic timing data subsections, so that a preset number of second sample microseismic timing data subsections need to be randomly selected from the second sample microseismic timing data subsections, and the purpose of the method is to reduce the number of the second sample microseismic timing data subsections so as to better learn and train the first sample microseismic timing data subsections. The preset number is a tested value, but in the setting process, the number of the micro-seismic time sequence data subsections of the first sample is required to be smaller than that of the micro-seismic time sequence data subsections of the first sample, so that the duty ratio of the micro-seismic time sequence data subsections of the first sample in all the selected micro-seismic time sequence data is increased, and the purpose is that the characteristic information corresponding to the dangerous attribute can be accurately identified, and further the prediction accuracy is improved.
Training the first sample microseismic time sequence data subsection and the second sample microseismic time sequence data subsection, identifying feature information corresponding to the dangerous attribute and feature information corresponding to the safety attribute, and generating a preset early warning model based on the feature information and the feature information.
In the implementation process, due to the characteristic of unequal data lengths of the sub-segments of the sample microseismic time sequence data, the first sub-segment of the sample microseismic time sequence data and the second sub-segment of the sample microseismic time sequence data can be trained based on a K-medoids clustering algorithm during training. The above K-means clustering algorithm is merely illustrative, and any implementation manner in the related art may be referred to in the specific implementation process, which is not limited in this embodiment of the present application.
In the specific implementation process of generating the preset early warning model in steps 301 to 305, in order to ensure the accuracy of identifying the preset early warning model, the generated preset early warning model is checked in this step.
And 306, carrying out second labeling on the safety attribute information of the test microseismic time sequence data sub-segment based on a preset log file.
The preset log file records a test microseismic time sequence data subsection which is confirmed to be dangerous, and the test microseismic time sequence data subsection is checked after second labeling of safety attribute information (dangerous attribute) is carried out, so that the accuracy of a preset early warning model is further improved.
The number of the test microseismic time sequence data subsections is not limited by the preset log file.
And comparing whether the first label with the safety attribute being the dangerous attribute is consistent with the second label with the safety attribute being the dangerous attribute, and performing accuracy test on the preset early warning model.
In summary, the rock burst risk prediction algorithm based on microseismic time sequence data provided by the embodiment of the application can realize the following effects:
(1) The input data microseismic time sequence data of the pre-warning model is preset, the acquisition is simple and convenient, and the experimental operation cost is low;
(2) The specificity (occurrence time interval is uneven) of the microseismic time sequence data is fully considered, so that the prediction accuracy through a preset early warning model is greatly improved;
(3) The false alarm rate of the algorithm is reduced through the integrated learning of a preset early warning model.
Corresponding to the rock burst risk prediction algorithm based on microseismic time series data provided in fig. 1, the present disclosure also provides a rock burst risk prediction device based on microseismic time series data, and since the rock burst risk prediction device based on microseismic time series data provided in the embodiment of the present disclosure corresponds to the rock burst risk prediction algorithm based on microseismic time series data provided in the embodiment of fig. 1, the implementation of the rock burst risk prediction algorithm based on microseismic time series data is also applicable to the rock burst risk prediction device based on microseismic time series data provided in the embodiment of the present disclosure, which is not described in detail in the embodiment of the present disclosure.
Fig. 4 is a device for controlling early warning of rock burst according to an embodiment of the present application, as shown in fig. 4, where the device includes:
an acquisition unit 41 for acquiring microseismic timing data to be detected.
The segmentation unit 42 is configured to segment the microseismic timing data according to a preset time interval, so as to obtain microseismic timing data subsections.
The input unit 43 is configured to sequentially input all the micro-seismic time sequence data subsections into a preset early warning model, so that the preset early warning model identifies characteristic information in all the micro-seismic time sequence data subsections, and output corresponding safety attribute information according to the characteristic information.
And the early warning unit 44 is used for carrying out early warning on rock burst according to the safety attribute information.
According to the rock burst danger prediction device based on the microseismic time sequence data, after the microseismic time sequence data to be detected is obtained, the microseismic time sequence data subsections are segmented to obtain the microseismic time sequence data subsections, all the microseismic time sequence data subsections are sequentially input into a preset early warning model, so that safety attribute information corresponding to different microseismic time sequence data subsections is obtained, and early warning of rock burst is carried out according to the safety attribute information. Compared with the related art, the method and the device have the advantages that the characteristics of the sample microseismic time sequence data are mined and repeatedly learned, so that the early warning of rock burst can be realized, and the prediction accuracy is remarkably improved.
Further, in another implementation manner of the present application, as shown in fig. 5, the microseismic time sequence data includes index information of rock burst;
the segmentation unit 42 includes:
a processing module 421, configured to perform format normalization processing on the index information in the microseismic time sequence data;
the segmentation module 422 is configured to segment the normalized microseismic time sequence data according to a preset time interval, so as to obtain the microseismic time sequence data subsections.
Further, in another implementation manner of the present application, as shown in fig. 5, the apparatus further includes:
the first labeling unit 45 is configured to perform a first labeling on the security attribute information of the sample microseismic time sequence data subsections based on a preset number of classifiers before the input unit 43 sequentially inputs all the microseismic time sequence data subsections into a preset early warning model; the safety attribute information is obtained by labeling the same sample microseismic time sequence data subsections by each classifier, and the safety attribute information comprises: dangerous properties and safety properties;
a selecting unit 46, configured to select a total number of first sample microseismic time-series data subsections, and a preset number of second sample microseismic time-series data subsections, where the first sample microseismic time-series data subsections are sample microseismic time-series data subsections with the security attribute information being a dangerous attribute, and the second sample microseismic time-series data subsections are sample microseismic time-series data subsections with the security attribute information being a security attribute;
the training unit 47 is configured to perform training according to the first sample microseismic time sequence data subsection and the second sample microseismic time sequence data subsection, so as to generate the preset early-warning model, where the preset early-warning model includes feature information corresponding to the dangerous attribute and feature information corresponding to the safety attribute.
Further, in another implementation manner of the present application, as shown in fig. 5, the apparatus further includes:
the second labeling unit 48 is configured to perform second labeling of the security attribute information on the sub-section of the sample microseismic time sequence data based on the preset log file; the sub-section of the sample microseismic time sequence data is obtained by segmenting the sample microseismic time sequence data according to a time interval;
and the testing unit 49 is configured to input the sub-segment of the sample microseismic time sequence data into the preset early warning model, so as to test the preset early warning model according to the output result of the preset early warning model and the second label.
Further, in another implementation of the present application, the training unit 47 is further configured to train the first sample microseismic time-series data sub-segment and the second sample microseismic time-series data sub-segment based on a K-means clustering algorithm. The foregoing explanation of the method embodiment is also applicable to the apparatus of this embodiment, and the principle is the same, and this embodiment is not limited thereto.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 6 illustrates a schematic block diagram of an example electronic device 600 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the apparatus 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 602 or a computer program loaded from a storage unit 608 into a RAM (Random Access Memory ) 603. In the RAM603, various programs and data required for the operation of the device 600 may also be stored. The computing unit 601, ROM602, and RAM603 are connected to each other by a bus 604. An I/O (Input/Output) interface 605 is also connected to bus 604.
Various components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, mouse, etc.; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing units 601 include, but are not limited to, a CPU (Central Processing Unit ), a GPU (Graphic Processing Units, graphics processing unit), various dedicated AI (Artificial Intelligence ) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processor, digital signal processors), and any suitable processors, controllers, microcontrollers, and the like. The computing unit 601 performs the various methods and processes described above, such as a rock burst risk prediction algorithm based on microseismic time series data. For example, in some embodiments, a rock burst risk prediction algorithm based on microseismic time series data may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM602 and/or the communication unit 609. When the computer program is loaded into RAM603 and executed by the computing unit 601, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured by any other suitable means (e.g., by means of firmware) to perform a rock burst risk prediction algorithm based on microseismic time series data as described previously.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit System, FPGA (Field Programmable Gate Array ), ASIC (Application-Specific Integrated Circuit, application-specific integrated circuit), ASSP (Application Specific Standard Product, special-purpose standard product), SOC (System On Chip ), CPLD (Complex Programmable Logic Device, complex programmable logic device), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory, erasable programmable read-Only Memory) or flash Memory, an optical fiber, a CD-ROM (Compact Disc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Di splay ) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network ), WAN (Wide Area Network, wide area network), internet and blockchain networks.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service ("Virtual Private Server" or simply "VPS") are overcome. The server may also be a server of a distributed system or a server that incorporates a blockchain.
It should be noted that, artificial intelligence is a subject of studying a certain thought process and intelligent behavior (such as learning, reasoning, thinking, planning, etc.) of a computer to simulate a person, and has a technology at both hardware and software level. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, a machine learning/deep learning technology, a big data processing technology, a knowledge graph technology and the like.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein. The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (5)
1. The rock burst risk prediction algorithm based on microseismic time sequence data is characterized by comprising the following steps of:
acquiring microseism time sequence data to be detected, respectively carrying out format normalization processing on coordinate index information and energy index information included in the microseism time sequence data, and segmenting the normalized microseism time sequence data according to a preset time interval to obtain microseism time sequence data subsections;
sequentially inputting all the micro-seismic time sequence data subsections into a preset early-warning model so that the preset early-warning model recognizes characteristic information in all the micro-seismic time sequence data subsections, and outputting corresponding safety attribute information according to the characteristic information, wherein before sequentially inputting all the micro-seismic time sequence data subsections into the preset early-warning model, sample micro-seismic time sequence data are segmented according to preset time intervals to obtain sample micro-seismic time sequence data subsections, a preset number of classifiers are adopted to carry out first labeling on the safety attribute information of the sample micro-seismic time sequence data subsections, the safety attribute information comprises dangerous attributes and safety attributes, all the sample micro-seismic time sequence data subsections with dangerous attributes are used as first sample micro-seismic time sequence data subsections, a preset number of sample micro-seismic time sequence data subsections with safety attributes are used as second sample micro-seismic time sequence data subsections, the number of the second sample micro-seismic time sequence data subsections is smaller than the number of the first sample micro-seismic time sequence data subsections, the first sample micro-seismic time sequence data subsections are subjected to first labeling according to the preset time sequence data subsections, the preset time sequence data models are used for carrying out first labeling on the safety attribute information of the sample micro-seismic time sequence data, and the early-warning model is used for determining the preset time sequence data, and the sample data is used as a preset time sequence data log, and the early-warning model is used for confirming the preset data, and the sample data is used for carrying out a preset data to be based on the preset data and a preset model, and a corresponding data is used to be sent as a early model;
and carrying out rock burst early warning according to the safety attribute information.
2. The rock burst risk prediction algorithm of claim 1, wherein the training according to the first sample microseismic time series data sub-segment and the second sample microseismic time series data sub-segment comprises:
and training the first sample microseismic time sequence data subsection and the second sample microseismic time sequence data subsection based on a K-medoids clustering algorithm.
3. The utility model provides a rock burst dangerous prediction device based on microseism time sequence data which characterized in that includes:
the acquisition unit is used for acquiring microseismic time sequence data to be detected;
the segmentation unit is used for respectively carrying out format normalization processing on the coordinate index information and the energy index information included in the microseismic time sequence data, and segmenting the normalized microseismic time sequence data according to a preset time interval to obtain microseismic time sequence data subsections;
the system comprises an input unit, a detection unit and a detection unit, wherein the input unit is used for sequentially inputting all micro-seismic time sequence data subsections into a preset early warning model so that the preset early warning model can recognize characteristic information in all micro-seismic time sequence data subsections and output corresponding safety attribute information according to the characteristic information, the sample micro-seismic time sequence data are segmented according to preset time intervals before all micro-seismic time sequence data subsections are sequentially input into the preset early warning model so as to obtain sample micro-seismic time sequence data subsections, a preset number of classifiers are adopted to carry out first annotation on the safety attribute information of the sample micro-seismic time sequence data subsections, the safety attribute information comprises dangerous attributes and safety attributes, all the sample micro-seismic time sequence data subsections with dangerous attributes are used as first sample micro-seismic time sequence data subsections, the preset number of sample micro-seismic time sequence data subsections with safety attributes are used as second sample micro-seismic time sequence data subsections, the number of the second sample micro-seismic time sequence data subsections is smaller than the number of the first sample micro-seismic time sequence data subsections, the number of the sample micro-seismic time sequence data subsections is input into the early warning model according to the preset time sequence data log, and the early warning model is confirmed according to the preset time sequence data of the first sample micro-seismic time sequence data, and the early warning model is confirmed;
and the early warning unit is used for carrying out early warning on rock burst according to the safety attribute information.
4. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the rock burst hazard prediction algorithm of claim 1 or 2.
5. A non-transitory computer readable storage medium storing computer instructions for causing the computer to execute the rock burst risk prediction algorithm according to claim 1 or 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210151070.1A CN114519392B (en) | 2022-02-14 | 2022-02-14 | Rock burst danger prediction algorithm based on microseismic time sequence data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210151070.1A CN114519392B (en) | 2022-02-14 | 2022-02-14 | Rock burst danger prediction algorithm based on microseismic time sequence data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114519392A CN114519392A (en) | 2022-05-20 |
| CN114519392B true CN114519392B (en) | 2023-05-23 |
Family
ID=81599247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210151070.1A Active CN114519392B (en) | 2022-02-14 | 2022-02-14 | Rock burst danger prediction algorithm based on microseismic time sequence data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114519392B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112031872A (en) * | 2020-07-15 | 2020-12-04 | 中煤科工开采研究院有限公司 | Rock burst holographic early warning method and device, storage medium and computing equipment |
| CN113469342A (en) * | 2021-07-08 | 2021-10-01 | 北京科技大学 | Rock burst early warning method based on deep learning microseismic monitoring data |
| CN113947197A (en) * | 2021-12-20 | 2022-01-18 | 煤炭科学研究总院 | Micro-seismic event risk prediction method considering rock burst precursor information based on CNN |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10634803B2 (en) * | 2015-09-16 | 2020-04-28 | Schlumberger Technology Corporation | Bayseian microseismic source inversion |
| CN110779574B (en) * | 2019-10-30 | 2020-11-13 | 北京科技大学 | Coal rock dynamic disaster multi-system multi-parameter integrated comprehensive early warning method and system |
| CN112594008B (en) * | 2020-12-17 | 2022-03-01 | 中国矿业大学 | Rock burst early warning method based on dynamic and static load disturbance superposition |
| CN113298299A (en) * | 2021-05-13 | 2021-08-24 | 华北科技学院(中国煤矿安全技术培训中心) | BP neural network-based coal bed impact risk intelligent evaluation method |
| CN113642487A (en) * | 2021-08-18 | 2021-11-12 | 山东红舟信创人工智能有限公司 | Artificial intelligence-based method and system applied to safety production |
| CN114037022A (en) * | 2021-12-14 | 2022-02-11 | 煤炭科学研究总院 | Microseism event risk classification method considering temporal and spatial characteristics of monitoring data |
-
2022
- 2022-02-14 CN CN202210151070.1A patent/CN114519392B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112031872A (en) * | 2020-07-15 | 2020-12-04 | 中煤科工开采研究院有限公司 | Rock burst holographic early warning method and device, storage medium and computing equipment |
| CN113469342A (en) * | 2021-07-08 | 2021-10-01 | 北京科技大学 | Rock burst early warning method based on deep learning microseismic monitoring data |
| CN113947197A (en) * | 2021-12-20 | 2022-01-18 | 煤炭科学研究总院 | Micro-seismic event risk prediction method considering rock burst precursor information based on CNN |
Non-Patent Citations (2)
| Title |
|---|
| Xin Yin等.A novle tree-based algorithm for real-time prediction of rock burst risk using field microseismic monitoring.《Environmental Earth Sciences》.2021,1-53. * |
| 闫宪磊等.综放工作面冲击地压的监测预报技术研究.《第十一届全国煤炭工业生产一线青年技术创新文集》.2018,323-329. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114519392A (en) | 2022-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11043101B2 (en) | Multi-system, multi-parameter, integrated, comprehensive early warning method and system for coal and rock dynamic disaster | |
| e Sousa et al. | The use of data mining techniques in rockburst risk assessment | |
| US20220035733A1 (en) | Method and apparatus for checking automatic driving algorithm, related device and storage medium | |
| CN107642347A (en) | Accident forecast method for early warning and device under shale gas fractured well | |
| CN106792883A (en) | Sensor network abnormal deviation data examination method and system | |
| Li et al. | Automatic recognition and classification of microseismic waveforms based on computer vision | |
| US20220301547A1 (en) | Method for processing audio signal, method for training model, device and medium | |
| NO20220089A1 (en) | Probability Distribution Assessment for Classifying Subterranean Formations Using Machine Learning | |
| CN112031839B (en) | Mine pressure space-time bi-periodic prediction method, device and equipment under limited data condition | |
| CN115640707A (en) | Tunneling monitoring system and method, electronic equipment and storage medium | |
| CA3109021A1 (en) | Facilitating hydrocarbon exploration by applying a machine-learning model to basin data | |
| US9613271B2 (en) | Determining severity of a geomagnetic disturbance on a power grid using similarity measures | |
| CN114553591A (en) | Training method of random forest model, abnormal flow detection method and device | |
| US20220237529A1 (en) | Method, electronic device and storage medium for determining status of trajectory point | |
| CN115359471A (en) | Image processing and joint detection model training method, device, equipment and storage medium | |
| CN110378421B (en) | Coal mine fire identification method based on convolutional neural network | |
| Zhao et al. | A hybrid recognition model of microseismic signals for underground mining based on CNN and LSTM networks | |
| CN114519392B (en) | Rock burst danger prediction algorithm based on microseismic time sequence data | |
| Wang et al. | AdaBoost-driven multi-parameter real-time warning of rock burst risk in coal mines | |
| Di et al. | Method for EMR and AE interference signal identification in coal rock mining based on recurrent neural networks | |
| CN113344882A (en) | Method for counting drill rods of underground drilling machine based on computer vision | |
| US20220227374A1 (en) | Data processing | |
| CN116484186A (en) | Multi-field coupling-based rock burst intelligent early warning method and device | |
| CN115965625A (en) | Instrument detection device based on visual identification and detection method thereof | |
| CN115641360A (en) | Battery detection method and device based on artificial intelligence and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |