CN117744010B - Small data driven real-time positioning method for pressure abnormality of coal mine support - Google Patents
Small data driven real-time positioning method for pressure abnormality of coal mine support Download PDFInfo
- Publication number
- CN117744010B CN117744010B CN202410173225.0A CN202410173225A CN117744010B CN 117744010 B CN117744010 B CN 117744010B CN 202410173225 A CN202410173225 A CN 202410173225A CN 117744010 B CN117744010 B CN 117744010B
- Authority
- CN
- China
- Prior art keywords
- data
- abnormal
- contribution
- acquiring
- principal component
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000005856 abnormality Effects 0.000 title claims abstract description 47
- 239000003245 coal Substances 0.000 title claims abstract description 41
- 230000002159 abnormal effect Effects 0.000 claims abstract description 98
- 238000012544 monitoring process Methods 0.000 claims abstract description 66
- 238000012546 transfer Methods 0.000 claims abstract description 66
- 239000011435 rock Substances 0.000 claims abstract description 42
- 230000005540 biological transmission Effects 0.000 claims abstract description 29
- 238000005070 sampling Methods 0.000 claims abstract description 25
- 238000012216 screening Methods 0.000 claims abstract description 22
- 230000015572 biosynthetic process Effects 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 19
- 238000000513 principal component analysis Methods 0.000 claims description 13
- 230000001364 causal effect Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 7
- 230000010485 coping Effects 0.000 abstract description 4
- 238000005755 formation reaction Methods 0.000 description 20
- 238000004458 analytical method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 238000005065 mining Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004807 localization Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000739 chaotic effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000012847 principal component analysis method Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000001687 destabilization Effects 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The application provides a small data driven real-time positioning method for pressure abnormality of a coal mine support, which comprises the following steps: acquiring monitoring data of each bracket in the current sampling time; screening abnormal data caused by rock stratum instability according to the monitoring data; acquiring a first transfer coefficient which leads to the abnormal data according to the abnormal data; and acquiring the position of the support with abnormal pressure according to the first transmission coefficient. The method can only rely on monitoring data in a relatively short sampling time, and abnormal data caused by rock stratum instability is screened out from the monitoring data, and the rapid positioning of the pressure abnormality of the coal mine support is realized through the acquisition operation of the first transmission coefficient of the abnormal data, so that the time for positioning the pressure abnormality of the coal mine support is saved to the greatest extent, and the efficiency and accuracy of potential ground pressure disaster coping are improved.
Description
Technical Field
The application relates to the technical field of geological exploration design and application, in particular to a small data-driven real-time positioning method for pressure abnormality of a coal mine support.
Background
Coal can produce rock burst phenomena during the mining process, namely the destruction and movement of rock formations. Rock burst can lead to accidents, and therefore, prediction and prevention of rock burst are one of important tasks of coal mine safety management. Hydraulic support (hereinafter simply referred to as support) pressure analysis is widely used in rock burst control. By monitoring the pressure change of the support, the stress state of the support corresponding to the top plate can be determined, and whether rock strata above stoping (in mining engineering, the mining engineering is generally from front to back for safety, a roadway is firstly opened to enter a distance of a planned mining area, and a working face during formal mining is called a stoping working face) is in a stable state or not is judged, so that an operator is assisted in analyzing the possibility of rock burst disasters. However, the mine environment is complex, various unpredictable events bring a great deal of noise to the stent monitoring data, and the ability of the intelligent system to accurately and rapidly locate the stent pressure abnormality is limited.
It should be noted that the foregoing description of the background art is only for the purpose of providing a clear and complete description of the technical solution of the present application and is presented for the convenience of understanding by those skilled in the art. The above-described solutions are not considered to be known to the person skilled in the art simply because they are set forth in the background of the application section.
Disclosure of Invention
The present application aims to solve at least one of the technical problems in the related art to some extent.
Therefore, the embodiment of the application provides a small data-driven real-time positioning method for the pressure abnormality of the coal mine support, which can only rely on monitoring data in a relatively short sampling time, and screen abnormal data caused by rock stratum instability from the monitoring data, and the rapid positioning of the pressure abnormality of the coal mine support is realized through the acquisition operation of a first transmission coefficient of the abnormal data, so that the time for positioning the pressure abnormality of the coal mine support is saved to the greatest extent, and the efficiency and accuracy of potential ground pressure disaster coping are improved.
The application discloses a small data-driven real-time positioning method for pressure abnormality of a coal mine support, which comprises the following steps:
acquiring monitoring data of each bracket in the current sampling time;
screening abnormal data caused by rock stratum instability according to the monitoring data;
acquiring a first transfer coefficient which leads to the abnormal data according to the abnormal data;
and acquiring the position of the support with abnormal pressure according to the first transmission coefficient.
Optionally, screening abnormal data caused by rock stratum instability according to the monitoring data, including:
acquiring first contribution data of each bracket to overall abnormality according to the monitoring data;
And screening abnormal data caused by rock stratum instability according to the first contribution data.
Optionally, the acquiring, according to the monitoring data, first contribution data of each bracket to the overall abnormality includes:
Processing the monitoring data of each bracket based on principal component analysis PCA, and establishing principal component models of all brackets on a stoping working surface;
According to the principal component model, acquiring contribution parameters of each bracket to the whole abnormality;
Based on the contribution parameters, first contribution data of each stent to the overall anomaly is determined.
Optionally, the principal component analysis PCA processes the monitoring data of each stent, and establishes a principal component model of all stents on the stope face, including:
acquiring a first matrix composed of the monitoring data;
Performing dimension reduction operation on the first matrix, and extracting a corresponding first feature vector;
Determining a principal component direction according to the first feature vector;
and establishing a principal component model according to the principal component direction.
Optionally, the screening abnormal data caused by rock stratum instability according to the first contribution data includes:
Determining adjacent brackets of each bracket according to each bracket, and carrying out difference operation on the first contribution data of each bracket and the first contribution data of the adjacent brackets to obtain second contribution data;
and screening abnormal data caused by rock stratum instability according to the second contribution data.
Optionally, according to the abnormal data, acquiring a first transfer coefficient which causes the abnormal data includes:
performing generalization operation on the abnormal data to obtain third contribution data causing abnormal formation stability;
and acquiring a first transfer coefficient which leads to the abnormal data according to the third contribution data.
Optionally, the generalizing the abnormal data to obtain third contribution data that causes abnormal formation stability includes:
Acquiring a label corresponding to the abnormal data, acquiring first contribution data of the last moment corresponding to the label, and comparing the first contribution data of the current moment of the label with the first contribution data of the last moment;
third contribution data that causes formation stability anomalies is determined based on the comparison.
Optionally, the acquiring, according to the third contribution data, a first transfer coefficient that causes the abnormal data includes:
Establishing causal relation connection for the third contribution data based on a transfer entropy method, and acquiring transfer entropy parameters of the third contribution data;
and acquiring a first transfer coefficient which leads to the abnormal data according to the transfer entropy parameter.
Optionally, the obtaining a first transfer coefficient that causes the abnormal data according to the transfer entropy parameter includes:
calculating the mean value and the variance of the transfer entropy parameters in the current sampling time, and summing the mean value and the variance to obtain a first intermediate variable;
When the transfer entropy parameter is greater than or equal to the first intermediate variable, carrying out a '1' giving operation on the first transfer coefficient; and when the transfer entropy parameter is smaller than the first intermediate variable, carrying out a 0-giving operation on the first transfer coefficient.
Optionally, the acquiring the position of the support with abnormal pressure according to the first transmission coefficient includes:
Counting the first transfer coefficient to obtain a second transfer coefficient;
and according to the result of the second transmission coefficient, acquiring the position of the support with abnormal pressure.
Additional aspects and advantages of the application 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 application.
Drawings
The foregoing and/or additional aspects and advantages of the application 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 flow chart of a first method for real-time positioning of pressure anomalies in a small data-driven coal mine support provided by an embodiment of the application;
FIG. 2 is a flow chart of a second method for real-time positioning of pressure anomalies in a small data-driven coal mine support provided by an embodiment of the present application;
FIG. 3 is a flow chart of a third method for real-time positioning of pressure anomalies in a small data-driven coal mine support provided by an embodiment of the present application;
FIG. 4 is a schematic structural diagram of a real-time positioning device for pressure abnormality of a coal mine support driven by small data, which is provided by the embodiment of the application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
Fig. 6 is a schematic structural diagram of another electronic device according to an embodiment of the present application;
Fig. 7 is a schematic structural diagram of a chip according to an embodiment of the present application.
Detailed Description
Embodiments of the present application 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 illustrative and intended to explain the present application and should not be construed as limiting the application.
The existing bracket pressure analysis method obtains periodic pressure (periodic pressure refers to monitoring data with equal length (equal length usually takes a circumference as a measuring unit) when a coal face continues to advance and the suspension span of an old roof reaches a certain length, the old roof breaks and collapses along the coal wall even in the coal wall under the effects of the dead weight and the overlying strata load, and the old roof collapses to appear repeatedly along with the advance of the working face), so that the position information of strata instability cannot be provided timely. In order to solve the technical problems, the application provides a small data-driven real-time positioning method for the pressure abnormality of the coal mine support, and because small data analysis usually adopts a statistical method, the analysis mode is from top to bottom, and the reality and the representativeness of the data are more concerned; meanwhile, the small data is more focused, and strict discrimination is provided for the source of the data; in addition, the small data is guided by the result, and the internal mechanism behind the phenomenon is more focused, so that the real-time positioning of the stent pressure abnormality can be completed through small data analysis, and the method is concretely implemented as follows:
The embodiment of the application relates to a method and a device for real-time positioning of pressure abnormality of a coal mine support driven by small data, and the method and the device are described below with reference to the accompanying drawings.
Fig. 1 is a flow chart of a first method for real-time positioning of pressure anomalies of a coal mine support driven by small data, which is provided by an embodiment of the application. As shown in fig. 1, the method includes, but is not limited to, the steps of:
s101, acquiring monitoring data of each bracket in the current sampling time.
The support is supporting equipment of the stope face, and has the main functions of supporting a stope roof, maintaining a safe working space and pushing the face mining and transporting equipment. The supporting and bearing principle of the bracket refers to the mechanical principle of interaction between the bracket and the top plate, the working resistance is usually represented by working resistance, the working resistance represents the supporting force of the bracket, and is an important parameter of the bracket.
When the stent pressure is acquired, the sampling time may be a set time length, in which the stent may acquire a plurality of monitoring data, alternatively, the sampling time may be set to 1 to 2 minutes, and may be sampled every 10 seconds, and ten or more monitoring data may be acquired. It should be noted that the sampling time includes, but is not limited to, 1 to 2 minutes, and the sampling time should be determined according to the response speed of the actual environment, which is not limited to the present embodiment. In a mining environment, pressure monitoring data of a bracket is often affected by various interference factors, such as geological changes, equipment vibration and the like, and the fluctuation of the monitoring data is increased due to the interference, so how to effectively eliminate the fluctuation factors, improve the accuracy of anomaly detection and quickly locate the abnormal bracket is an important problem to be solved in the following operation.
S102, screening abnormal data caused by rock stratum instability according to the monitoring data.
Formation stabilization refers to the formation not producing destructive shear slip, plastic deformation, or fracture failure over time, under certain natural conditions and artifacts. The stability of the formation, deformation and damage to the formation are primarily dependent on the nature of the various structural planes within the formation and the extent of cutting of the formation. Under the mining environment, the stability of the rock stratum is affected by the gradual exploitation of the coal seam, corresponding acting force is provided for the top plate through the supporting and bearing principle of the support, so that the stability of the rock stratum is maintained in a specific time, once the acting force provided by the support cannot maintain the stability of the rock stratum, the rock stratum is unstable, the pressure of the support is abnormal according to the relation between the acting force and the reaction force, abnormal pressure data, namely abnormal data, are displayed, and if the abnormal pressure is continuously increased, safety accidents such as collapse and the like can be caused. Therefore, in a stable stratum environment, the pressure parameter of the support is in a constant range, the pressure of the support can be suddenly changed under accidental geological change or equipment vibration, and the pressure parameter of the support can be returned to a constant range along with the disappearance of accidental factors. The pressure of the bracket is abnormal, so that the pressure parameter of the bracket is continuously increased, and the coping speed and accuracy of the potential low-pressure disaster can be improved due to the fact that the increase is a continuous process and how to lock the abnormality in advance in a short time.
As a possible implementation manner, the collected monitoring data may be tracked to obtain a pressure variation trend of each support, and determine whether the pressure variation trend accords with a pressure variation trend caused by rock stratum instability. And determining the monitoring data of which the pressure change trend accords with the pressure change trend caused by rock stratum instability as abnormal data.
As another possible implementation manner, principal component analysis PCA (collectively referred to as PRINCIPAL COMPONENT ANALYSIS, i.e., principal component analysis method, which is a data dimension-reduction algorithm) may be used to process the monitoring data of these stents, and a principal component model of the stent may be built, after the principal component model is built, the contribution parameters of each stent to the whole abnormality may be obtained by analyzing the influence of the variable of each dimension on the principal component variable T at each sampling time on the observation space of the principal component model, and based on the contribution parameters, the abnormal data may be determined from the monitoring data.
S103, according to the abnormal data, acquiring a first transfer coefficient which leads to the abnormal data.
Because the monitoring data of the bracket has serious discretization, if the monitoring data is directly analyzed, inaccurate positioning results can be generated. In order to avoid data fluctuation and influence the detection and positioning analysis of stent abnormality, in S101, abnormal data caused by rock stratum instability is screened out, and each stent contributes to the whole abnormality.
Since the formation is integral, the destabilization is caused by anomalies caused by the forces transmitted to the stents by the formation, which can be analyzed by causal relationships between the stents, characterized by a first transmission coefficient.
In thermodynamics, entropy is used to measure the degree of confusion of a system, representing the progress of a substance in an irregular direction, i.e., an increasingly chaotic system. In the embodiment of the application, the causal relationship between the brackets can be analyzed by a transfer entropy method, and the stronger the causal relationship is, the stronger the degree of abnormality caused by the force transferred from the rock stratum to the brackets is, and the analysis of the transfer entropy parameters is continued. Optionally, a transmission entropy method may be used to make contribution data to the stent, and a causal relationship may be established for analysis, to obtain a first transmission coefficient that results in abnormal data.
S104, acquiring the position of the support with abnormal pressure according to the first transmission coefficient.
If the abnormal pressure of the bracket is simply counted, the numerical value of the pressure belongs to a real number, the accumulated pressure in the sampling time can be larger, and the difference between the numerical values of the pressures of the adjacent brackets is not easy to distinguish, so that the bracket with abnormal pressure is positioned by adopting the first transmission coefficient. Can be represented by the following formula.
Wherein,Characterised by a second transfer coefficient,/>The first transmission coefficient is characterized as a first transmission coefficient, when the second transmission coefficient is not 0, the abnormal stent monitoring data is indicated, the first transmission coefficient of the abnormal stent is continuously accumulated, and the first transmission coefficient is either 1 or 0, so that the difference between the abnormal stent and the adjacent stent can be easily characterized. And recording a second transmission coefficient, and acquiring a serial number of the second transmission, so as to obtain the position of the support with abnormal pressure.
The small data-driven real-time positioning method for the pressure abnormality of the coal mine support, provided by the embodiment of the application, can only rely on monitoring data in a relatively short sampling time, and screen abnormal data caused by rock stratum instability from the monitoring data, and can realize the rapid positioning of the pressure abnormality of the coal mine support by acquiring the first transmission coefficient of the abnormal data, thereby greatly saving the time for positioning the pressure abnormality of the coal mine support and improving the efficiency and accuracy of coping with potential ground pressure disasters.
Referring to fig. 2, fig. 2 is a flow chart of a second method for real-time positioning of pressure anomalies in a coal mine support driven by small data according to an embodiment of the present application. As shown in fig. 2, the method may include, but is not limited to, the following steps:
S201, acquiring monitoring data of each bracket in the current sampling time.
For a specific description of step S201, reference may be made to the description of the related content in the above embodiment, and the description is omitted here.
S202, acquiring first contribution data of each bracket to overall abnormality according to the monitoring data.
Optionally, processing the monitoring data of each bracket based on principal component analysis PCA, establishing principal component models of all brackets on the stope face, acquiring contribution parameters of each bracket to the whole abnormality according to the principal component models, and determining first contribution data of each bracket to the whole abnormality based on the contribution parameters.
Optionally, a first matrix composed of the monitoring data is obtained, the first matrix is subjected to dimension reduction operation, a corresponding first feature vector is extracted, the principal component direction is determined according to the first feature vector, and a principal component model is established according to the principal component direction.
Let X ε R n×m be the monitored data, where R is the value of the monitored data, typically a constant, m is the number of stents, and n is the number of collected monitored data. The extraction working surface is provided with a plurality of supports, each support has a plurality of monitoring data in sampling time, a matrix formed by the monitoring data of the supports is not a square matrix generally, the matrix can be a sparse matrix with a plurality of 0 s, if the matrix is directly operated, the matrix can cause large storage capacity and waste calculation space, so that the monitoring data of the supports can be operated for extracting main features, and the workload can be reduced by analyzing the main features, thereby improving the efficiency.
Optionally, principal component analysis PCA (generally referred to as PRINCIPAL COMPONENT ANALYSIS, i.e., principal component analysis method, which is a data dimension reduction algorithm) may be used to process the monitoring data of these scaffolds, and a principal component model of the scaffold is built, so that a sparse matrix may be effectively reduced, which is equivalent to only preserving dimension features including most variance, and ignoring feature dimensions including variance being almost 0, to implement dimension reduction processing on the monitoring data, extract corresponding feature vectors, and represent the information content Sig of each feature vector by the value of the principal diagonal of the matrix Ʌ after dimension reduction:
wherein X T is denoted as the transpose of X; v is a singular matrix obtained by singular value conversion of monitoring data X; v T is denoted as the transpose of V.
Then, after the values on the principal diagonal lines in the matrix Ʌ are arranged in descending order, a feature vector whose information amount exceeds 90% of the total information amount is selected as the principal component direction in general, and the monitor data X is mapped into principal component variables constructed from the principal component direction by the following formula.
Wherein,For projection matrix, a is the number of principal component variables reserved, and T is the principal component variable.
And then, on the basis of principal component variables, a principal component model is established, and the contribution parameters of each bracket to the whole abnormality can be obtained by analyzing the influence of the variable of each dimension on the observation space of the principal component model on the principal component variable T at each sampling time, wherein the contribution parameters are represented by the following formula:
Wherein, The principal component variable is the ith dimension of the t moment; /(I)Variance of T i; p j,i is the mapping coefficient of the j observation variable to the i principal element variable; c is expressed as the anomaly probability of each stent due to anomaly of the monitoring data at each sampling time, that is, the first contribution data of each stent to the overall anomaly.
It should be noted that, the manner of processing the monitoring data of the stent includes, but is not limited to, principal component analysis PCA, and may also use multidimensional scaling, equidistant feature mapping, linear discriminant analysis, etc. to process the monitoring data, so long as the first contribution data of each stent to the overall anomaly can be obtained, any manner of processing the monitoring data of the stent is applicable, and the present embodiment is not limited thereto.
Since the strata is integral, the forces applied by the strata to the stents are malleable, and the pressure of each stent, in addition to the forces applied by the strata in its respective location, also has forces transmitted by adjacent stents in response to the strata. Further, it can be distinguished whether the fluctuation of the stent monitoring data is caused by an emergency or caused by a rock stratum instability by the following equation.
Wherein,Characterized as second contribution data, C representing first contribution data for each stent for the overall anomaly; if/>> 0, Then mean that the fluctuation of the j-th stent is caused by an incident; if/>< 0, It indicates that the fluctuation of the j-th scaffold is caused by rock formation instability, on which the following analysis is performed.
It should be noted that, the second contribution data may also be obtained by adopting a breakpoint regression mode, a dual-differential mode, and the like, and the specific operation process is not described herein, so long as it can be distinguished whether the fluctuation of the stent monitoring data is caused by an emergency or caused by the instability of the rock stratum, any second contribution data obtaining mode is applicable, and the embodiment is not limited thereto.
S203, screening abnormal data caused by rock stratum instability according to the first contribution data.
And determining adjacent brackets of each bracket according to each bracket, performing difference operation on the first contribution data of each bracket and the first contribution data of the adjacent brackets to obtain second contribution data, and screening abnormal data caused by rock stratum instability according to the second contribution data.
S204, according to the abnormal data, acquiring a first transfer coefficient which leads to the abnormal data.
Because of the serious discretization problem of the monitoring data of the bracket, if the monitoring data is directly analyzed, extremely inaccurate results are generated. For avoiding data fluctuation and influencing detection and positioning analysis of stent abnormality, the application firstly uses the first contribution data C to replace original monitoring data so as to characterize contribution parameters of each stent to the whole abnormality, and on the basis of the first contribution data C, generalization operation is carried out on the first contribution data C (the generalization operation on the first contribution data C is the generalization operation on the monitoring data because the first contribution data C replaces the original monitoring data) by the following formula.
Wherein,Characterized as third contribution data,/>Equal to 1, this indicates that the contribution of the ith scaffold to formation stability anomalies is being exacerbated; /(I)Equal to 0, it means that the ith scaffold does not affect the stability of the formation.
It should be noted that, the above formula can reduce the degree of discretization of the monitored data, and retain the key information required for positioning and monitoring, so as to facilitate the next operation step. It should be noted that, the degree of discretization of the monitored data may also be reduced by adopting modes of attribute-oriented induction, data focusing, and the like, and specific processes are not described herein.
Alternatively, the analysis may be performed by establishing a causal relationship for the third contribution data using a transitive entropy method, and establishing a causal relationship connection for the third contribution data using the following equation.
Wherein CT is characterized by a transfer entropy parameter,The probability that the key leading to formation stability anomalies is shifted from scaffold i to ip within the window representing sampling times ts to te.
In thermodynamics, entropy is used to measure the degree of confusion of a system, representing the progress of a substance in an irregular direction, i.e., an increasingly chaotic system. The transmission entropy method analyzes the causal relationship between the brackets, and the stronger the causal relationship is, the stronger the degree of abnormality caused by the force transmitted to the brackets by the rock stratum is, and the analysis of the transmission entropy parameters is continued.
The acquisition of the first transfer coefficient that causes the abnormal data according to the transfer entropy parameter can be expressed as follows.
And setting a threshold value of the transfer entropy parameter by utilizing the transfer entropy parameter, and obtaining the dimension of the degree of abnormality caused by the force transferred to the bracket by the rock stratum by comparing the transfer entropy parameter with the threshold value, so as to obtain a first transfer parameter.
S205, according to the first transmission coefficient, the position of the support with abnormal pressure is obtained.
For a specific description of step S205, reference may be made to the description of the related content in the above embodiment, and the description is omitted here.
Referring to fig. 3, fig. 3 is a flow chart of a third method for real-time positioning of pressure anomalies in a coal mine support driven by small data according to an embodiment of the present application. As shown in fig. 3, the method may include, but is not limited to, the following steps:
s301, acquiring monitoring data of each bracket in the current sampling time.
S302, processing the monitoring data of each bracket based on principal component analysis PCA, and establishing principal component models of all brackets on the stope face.
S303, acquiring contribution parameters of each bracket to the whole abnormality.
S304, determining first contribution data of each bracket to the overall abnormality based on the contribution parameters.
S305, determining adjacent brackets of each bracket according to each bracket, and carrying out difference operation on the first contribution data of each bracket and the first contribution data of the adjacent brackets to obtain second contribution data.
S306, screening out abnormal data caused by rock stratum instability based on the second contribution data.
If the second contribution data >0 is true, indicating that the fluctuation is caused by the emergency, and ending the flow; if the second contribution data < 0 holds, indicating that the anomaly data is caused by formation instability, then subsequent operations continue.
S307, performing generalization operation on the abnormal data.
S308, acquiring the label corresponding to the abnormal data, acquiring the first contribution data of the last moment corresponding to the label, and comparing the first contribution data of the current moment of the label with the first contribution data of the last moment.
S309, determining third contribution data causing formation stability abnormality based on the comparison result.
S310, establishing causal relation connection for the third contribution data based on a transfer entropy method, and acquiring transfer entropy parameters of the third contribution data.
S311, calculating the mean value and the variance of the transfer entropy parameters in the current sampling time, and summing the mean value and the variance to obtain a first intermediate variable.
If the transfer entropy parameter is smaller than the first intermediate variable, the process is ended, and the process is stopped; if the transfer entropy parameter is equal to or greater than the first intermediate variable, continuing the subsequent operation.
S312, according to the first transmission coefficient, the position of the support with abnormal pressure is obtained.
For a specific description of steps S307 to S312, reference may be made to the description of the related content in the above embodiment, and the description is omitted here.
According to the small data-driven real-time positioning method for the pressure abnormality of the coal mine support, provided by the embodiment of the application, the abnormal data caused by rock stratum instability can be screened out from the monitored data only by means of the monitored data in a relatively short sampling time, and the rapid positioning of the pressure abnormality of the coal mine support is realized through the acquisition operation of the first transmission coefficient of the abnormal data.
Fig. 4 is a schematic structural diagram of a small data-driven real-time positioning device for pressure abnormality of a coal mine support according to an embodiment of the application. As shown in fig. 4, the small data-driven real-time positioning device 40 for pressure abnormality of a coal mine support comprises:
a first obtaining module 401, configured to obtain monitoring data of each stent in a current sampling time;
a first screening module 402, configured to screen out abnormal data caused by rock stratum instability according to the monitoring data;
a second obtaining module 403, configured to obtain, according to the abnormal data, a first transfer coefficient that causes the abnormal data;
and a third obtaining module 404, configured to obtain, according to the first transmission coefficient, a position of the support with abnormal pressure.
Optionally, the first screening module 402 is further configured to:
acquiring first contribution data of each bracket to overall abnormality according to the monitoring data;
And screening abnormal data caused by rock stratum instability according to the first contribution data.
Optionally, the first screening module 402 is further configured to:
Processing the monitoring data of each bracket based on principal component analysis PCA, and establishing principal component models of all brackets on a stoping working surface;
According to the principal component model, acquiring contribution parameters of each bracket to the whole abnormality;
Based on the contribution parameters, first contribution data of each stent to the overall anomaly is determined.
Optionally, the first screening module 402 is further configured to:
acquiring a first matrix composed of the monitoring data;
Performing dimension reduction operation on the first matrix, and extracting a corresponding first feature vector;
Determining a principal component direction according to the first feature vector;
and establishing a principal component model according to the principal component direction.
Optionally, the first screening module 402 is further configured to:
Determining adjacent brackets of each bracket according to each bracket, and carrying out difference operation on the first contribution data of each bracket and the first contribution data of the adjacent brackets to obtain second contribution data;
and screening abnormal data caused by rock stratum instability according to the second contribution data.
Optionally, the second obtaining module 403 is further configured to:
performing generalization operation on the abnormal data to obtain third contribution data causing abnormal formation stability;
and acquiring a first transfer coefficient which leads to the abnormal data according to the third contribution data.
Optionally, the second obtaining module 403 is further configured to:
Acquiring a label corresponding to the abnormal data, acquiring first contribution data of the last moment corresponding to the label, and comparing the first contribution data of the current moment of the label with the first contribution data of the last moment;
third contribution data that causes formation stability anomalies is determined based on the comparison.
Optionally, the second obtaining module 403 is further configured to:
Establishing causal relation connection for the third contribution data based on a transfer entropy method, and acquiring transfer entropy parameters of the third contribution data;
and acquiring a first transfer coefficient which leads to the abnormal data according to the transfer entropy parameter.
Optionally, the second obtaining module 403 is further configured to:
calculating the mean value and the variance of the transfer entropy parameters in the current sampling time, and summing the mean value and the variance to obtain a first intermediate variable;
When the transfer entropy parameter is greater than or equal to the first intermediate variable, carrying out a '1' giving operation on the first transfer coefficient; and when the transfer entropy parameter is smaller than the first intermediate variable, carrying out a 0-giving operation on the first transfer coefficient.
Optionally, the third obtaining module 404 is further configured to:
Counting the first transfer coefficient to obtain a second transfer coefficient;
and according to the result of the second transmission coefficient, acquiring the position of the support with abnormal pressure.
It should be noted that, for details not disclosed in the small data driven real-time positioning device for abnormal pressure of a coal mine support in the embodiment of the present disclosure, please refer to details disclosed in the small data driven real-time positioning method for abnormal pressure of a coal mine support provided in the foregoing embodiment of the present disclosure, and details are not repeated here.
The embodiment of the application also provides electronic equipment, which comprises: a processor; a memory for storing the processor executable instructions, wherein the processor is configured to execute the instructions to implement the small data driven method of real-time localization of coal mine support pressure anomalies as described above.
To achieve the above embodiments, the present application also proposes a non-transitory computer-readable storage medium.
Wherein the instructions in the storage medium, when executed by the processor of the electronic device, enable the electronic device to perform the small data driven method of real-time localization of coal mine support pressure anomalies as described above.
To achieve the above embodiments, the present application also provides a computer program product.
Wherein the computer program product, when being executed by a processor of an electronic device, enables the electronic device to perform the method as described above
Fig. 5 is a schematic diagram of an electronic device according to an exemplary embodiment. As shown in fig. 5, the electronic device 50 includes a small data-driven real-time localization device 40 of the coal mine support pressure anomaly. The electronic device may be a mobile electronic device or a non-mobile electronic device. The mobile electronic device may be an industrial mobile phone, an industrial tablet computer, an industrial notebook computer, or the like, and the non-mobile electronic device may be a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), or the like, which is not particularly limited in the embodiments of the present application.
Fig. 6 is a schematic diagram of another electronic device shown according to an exemplary embodiment. The electronic device shown in fig. 6 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the application.
As shown in fig. 6, the electronic device 600 includes a processor 601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a Memory 606 into a random access Memory (RAM, random Access Memory) 603. In the RAM 603, various programs and data required for the operation of the electronic apparatus 600 are also stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An Input/Output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: a memory 606 including a hard disk and the like; and a communication section 607 including a network interface card such as a LAN (local area network ) card, a modem, or the like, the communication section 607 performing communication processing via a network such as the internet; the drive 608 is also connected to the I/O interface 605 as needed.
In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program embodied on a computer readable medium, the computer program containing program code for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 607. The above-described functions defined in the method of the application are performed when the computer program is executed by the processor 601.
In an exemplary embodiment, a storage medium is also provided, such as a memory, comprising instructions executable by the processor 601 of the electronic device 600 to perform the above-described method. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.
In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Fig. 7 is a block diagram illustrating a chip configuration according to an exemplary embodiment. The chip illustrated in fig. 7 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present application. As shown in fig. 7, the chip 700 includes a processor 701 and a memory 702. The memory 702 is used for storing program codes, and the processor 701 is connected with the memory 702 and is used for reading the program codes from the memory 702 so as to implement the small data driven real-time positioning method for the pressure abnormality of the coal mine support in the embodiment.
Alternatively, the number of processors 701 may be one or more.
Optionally, the chip may further include an interface 703, and the number of the interfaces 703 may be plural. The interface 703 may be connected to an application program and may receive data of an external device such as a sensor, etc.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (3)
1. The method for positioning the pressure abnormality of the coal mine support driven by small data in real time is characterized by comprising the following steps of:
acquiring monitoring data of each bracket in the current sampling time;
screening abnormal data caused by rock stratum instability according to the monitoring data;
acquiring a first transfer coefficient which leads to the abnormal data according to the abnormal data;
acquiring the position of the support with abnormal pressure according to the first transmission coefficient;
Screening abnormal data caused by rock stratum instability according to the monitoring data, wherein the abnormal data comprises the following steps:
Processing the monitoring data of each bracket based on principal component analysis PCA, and establishing principal component models of all brackets on a stoping working surface;
According to the principal component model, acquiring contribution parameters of each bracket to the whole abnormality;
determining first contribution data of each bracket to the overall abnormality based on the contribution parameters;
screening abnormal data caused by rock stratum instability according to the first contribution data;
according to the abnormal data, acquiring a first transfer coefficient which leads to the abnormal data, wherein the first transfer coefficient comprises:
performing generalization operation on the abnormal data to obtain third contribution data causing abnormal formation stability;
acquiring a first transfer coefficient which leads to the abnormal data according to the third contribution data;
the generalizing operation is performed on the abnormal data, and third contribution data causing abnormal formation stability is obtained, including:
Acquiring a label corresponding to the abnormal data, acquiring first contribution data of the last moment corresponding to the label, and comparing the first contribution data of the current moment of the label with the first contribution data of the last moment;
Determining third contribution data resulting in formation stability anomalies based on the comparison;
The step of obtaining a first transfer coefficient which leads to the abnormal data according to the third contribution data comprises the following steps:
Establishing causal relation connection for the third contribution data based on a transfer entropy method, and acquiring transfer entropy parameters of the third contribution data;
acquiring a first transfer coefficient which leads to the abnormal data according to the transfer entropy parameter; the obtaining a first transfer coefficient which leads to the abnormal data according to the transfer entropy parameter comprises the following steps:
calculating the mean value and the variance of the transfer entropy parameters in the current sampling time, and summing the mean value and the variance to obtain a first intermediate variable;
When the transfer entropy parameter is greater than or equal to the first intermediate variable, carrying out a '1' giving operation on the first transfer coefficient; when the transfer entropy parameter is smaller than the first intermediate variable, carrying out a 0-giving operation on the first transfer coefficient;
The step of obtaining the position of the support with abnormal pressure according to the first transmission coefficient comprises the following steps:
Counting the first transfer coefficient to obtain a second transfer coefficient;
and according to the result of the second transmission coefficient, acquiring the position of the support with abnormal pressure.
2. The method for real-time positioning of pressure anomalies of small data-driven coal mine supports according to claim 1, wherein the principal component analysis PCA based on principal component analysis processes the monitored data of each support to establish principal component models of all supports on a stope face, comprising:
acquiring a first matrix composed of the monitoring data;
Performing dimension reduction operation on the first matrix, and extracting a corresponding first feature vector;
Determining a principal component direction according to the first feature vector;
and establishing a principal component model according to the principal component direction.
3. The method for real-time positioning of pressure anomalies of a small data-driven coal mine support according to claim 1, wherein the screening out the anomalies caused by rock stratum instability according to the first contribution data comprises the following steps:
Determining adjacent brackets of each bracket according to each bracket, and carrying out difference operation on the first contribution data of each bracket and the first contribution data of the adjacent brackets to obtain second contribution data;
and screening abnormal data caused by rock stratum instability according to the second contribution data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410173225.0A CN117744010B (en) | 2024-02-07 | 2024-02-07 | Small data driven real-time positioning method for pressure abnormality of coal mine support |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410173225.0A CN117744010B (en) | 2024-02-07 | 2024-02-07 | Small data driven real-time positioning method for pressure abnormality of coal mine support |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117744010A CN117744010A (en) | 2024-03-22 |
| CN117744010B true CN117744010B (en) | 2024-04-30 |
Family
ID=90283492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410173225.0A Active CN117744010B (en) | 2024-02-07 | 2024-02-07 | Small data driven real-time positioning method for pressure abnormality of coal mine support |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117744010B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016088362A1 (en) * | 2014-12-05 | 2016-06-09 | 日本電気株式会社 | System analyzing device, system analyzing method and storage medium |
| CN108868748A (en) * | 2018-04-28 | 2018-11-23 | 中国石油化工股份有限公司江汉油田分公司石油工程技术研究院 | A kind of calculation method of shale gas horizontal well refracturing crack cracking pressure |
| CN112119946A (en) * | 2020-08-31 | 2020-12-25 | 浙江大学 | Beehive remote monitoring system based on classification model and intelligent beehive |
| CN113356910A (en) * | 2021-07-09 | 2021-09-07 | 贵州工程应用技术学院 | Temporary support device with warning function for roadway excavation |
| CN114026467A (en) * | 2019-06-24 | 2022-02-08 | 埃尼股份公司 | Detection system for detecting anomalies in discontinuous interface and/or pore pressure in a geological formation |
| CN115436051A (en) * | 2022-09-07 | 2022-12-06 | 国能榆林能源有限责任公司 | Hydraulic support pressure abnormity identification method |
| WO2023138430A1 (en) * | 2022-01-20 | 2023-07-27 | 山东科技大学 | Method for estimating contribution rate of elastic energy of top plate during instability-incurred catastrophe of deep gas-containing coal body |
| CN117514734A (en) * | 2022-08-05 | 2024-02-06 | 横河电机株式会社 | Detection device, detection method, and detection system |
-
2024
- 2024-02-07 CN CN202410173225.0A patent/CN117744010B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016088362A1 (en) * | 2014-12-05 | 2016-06-09 | 日本電気株式会社 | System analyzing device, system analyzing method and storage medium |
| CN108868748A (en) * | 2018-04-28 | 2018-11-23 | 中国石油化工股份有限公司江汉油田分公司石油工程技术研究院 | A kind of calculation method of shale gas horizontal well refracturing crack cracking pressure |
| CN114026467A (en) * | 2019-06-24 | 2022-02-08 | 埃尼股份公司 | Detection system for detecting anomalies in discontinuous interface and/or pore pressure in a geological formation |
| CN112119946A (en) * | 2020-08-31 | 2020-12-25 | 浙江大学 | Beehive remote monitoring system based on classification model and intelligent beehive |
| CN113356910A (en) * | 2021-07-09 | 2021-09-07 | 贵州工程应用技术学院 | Temporary support device with warning function for roadway excavation |
| WO2023138430A1 (en) * | 2022-01-20 | 2023-07-27 | 山东科技大学 | Method for estimating contribution rate of elastic energy of top plate during instability-incurred catastrophe of deep gas-containing coal body |
| CN117514734A (en) * | 2022-08-05 | 2024-02-06 | 横河电机株式会社 | Detection device, detection method, and detection system |
| CN115436051A (en) * | 2022-09-07 | 2022-12-06 | 国能榆林能源有限责任公司 | Hydraulic support pressure abnormity identification method |
Non-Patent Citations (2)
| Title |
|---|
| Research on a Space–Time Continuous Sensing System for Overburden Deformation and Failure during Coal Mining;Gang Cheng等;《Sensors 2023》;20230627;全文 * |
| 基于主元分析的瓦斯抽放系统故障检测方法;路萍;;煤矿现代化;20130815(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117744010A (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110148285B (en) | Intelligent oil well parameter early warning system based on big data technology and early warning method thereof | |
| US11795814B2 (en) | Early warning and automated detection for lost circulation in wellbore drilling | |
| CN107392786A (en) | Mine fiber grating monitoring system missing data compensation method based on SVMs | |
| Mopuri et al. | Early sign detection for the stuck pipe scenarios using unsupervised deep learning | |
| CN112031839B (en) | Mine pressure space-time bi-periodic prediction method, device and equipment under limited data condition | |
| Wang et al. | BIM-based structural health monitoring and early warning for heritage timber structures | |
| CN116108759B (en) | Landslide hazard evaluation method based on characteristic coupling | |
| WO2010047937A1 (en) | Robust filtering and prediction using switching models for machine condition monitoring | |
| CN115146230A (en) | Ancient building health monitoring system, method and equipment | |
| CN114205216A (en) | Root cause positioning method and device for micro-service fault, electronic equipment and medium | |
| CN117744010B (en) | Small data driven real-time positioning method for pressure abnormality of coal mine support | |
| CN115688251A (en) | Earthquake multi-occurrence-zone tunnel risk decision method and system based on deep learning | |
| Fawzy et al. | Framework for automatic detection of anomalies in DevOps | |
| CN117709715A (en) | Tunnel engineering construction risk assessment method, system, terminal and medium | |
| CN116777085B (en) | Coal mine water damage prediction system based on data analysis and machine learning technology | |
| JP2019067139A (en) | Monitoring device, monitoring method, monitoring program, display device, display method and display program | |
| CN115759351A (en) | Slurry shield tunneling comprehensive early warning method and system and storage medium | |
| CN114897225A (en) | Accident prediction method and device for drilling operation, electronic device and storage medium | |
| WO2023106956A1 (en) | Identifying and predicting unplanned drilling events | |
| CN113466951B (en) | Mine electrical method resistivity abnormal response monitoring rapid identification method | |
| CN115659243B (en) | Infrastructure risk monitoring method and monitoring system based on MEMS | |
| Miao et al. | Risk prediction of coal mine rock burst based on machine learning and feature selection algorithm | |
| Reuland et al. | Damage-sensitive features for rapid damage assessment in a seismic context | |
| CN117172561B (en) | Geological disaster risk hidden danger prediction method and system based on intelligent model algorithm | |
| Ma et al. | Research on prediction of rockburst microseismic parameters based on CNN-LSTM hybrid model |
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 |