CN116975668A

CN116975668A - Method, device and system for determining stress state of roadway surrounding rock

Info

Publication number: CN116975668A
Application number: CN202310893518.1A
Authority: CN
Inventors: 王巍; 贾士耀; 陈苏社; 范东林; 王庆雄; 卢国志; 颜阳; 李鑫; 王涛
Original assignee: Shendong Coal Branch of China Shenhua Energy Co Ltd; Guoneng Shendong Coal Group Co Ltd
Current assignee: Shendong Coal Branch of China Shenhua Energy Co Ltd; Guoneng Shendong Coal Group Co Ltd
Priority date: 2023-07-19
Filing date: 2023-07-19
Publication date: 2023-10-31

Abstract

The application provides a method, a device and a system for determining the stress state of roadway surrounding rock. According to the scheme, two stress data are collected, one is the data of a plurality of detection points at the same moment, one is the time sequence data of a single detection point at different moments, the PCA algorithm is adopted to reduce the dimension of the obtained stress data, unimportant data are removed, important data are obtained, then cluster analysis is carried out according to the important data, clusters of a plurality of clusters are obtained, sample points in each cluster are similar, the risk degree of each cluster is calculated, and the state of stress can be accurately determined according to the calculated result due to the fact that the scale (the number of samples) of the clusters and the sample density of the clusters are considered, namely the risk degree of the stress is determined.

Description

Method, device and system for determining stress state of roadway surrounding rock

Technical Field

The application relates to the technical field of surrounding rock stress detection, in particular to a method and a device for determining the stress state of roadway surrounding rock, a computer-readable storage medium and a stress state determining system.

Background

The current roadway surrounding rock stress transfer rule mainly comprises a research method for stress numerical analysis and observation during ore compaction. The surrounding rock of the coal mine tunnel often causes dynamic pressure phenomena such as loose breaking, severe deformation and the like of the surrounding rock under the influence of original ground stress, dynamic pressure environment, complex geological structure, rock mass components and the like, and the control of the surrounding rock of the tunnel is an important factor for restricting the safe exploitation of the coal mine. At present, the stress monitoring data analysis of the surrounding rock of the roadway lacks a standard system, so that the real stress state of the surrounding rock of the roadway cannot be accurately obtained, and advanced prediction is also prevented, the deformation of the roadway is maintained, and the coal mine is safely mined.

Disclosure of Invention

The application mainly aims to provide a method and a device for determining the stress state of roadway surrounding rock, a computer-readable storage medium and a stress state determining system, so as to at least solve the problem that the actual stress state of the roadway surrounding rock cannot be accurately obtained in the prior art.

In order to achieve the above object, according to one aspect of the present application, there is provided a method for determining a stress state of a roadway surrounding rock, including: acquiring a plurality of initial stress data, wherein the initial stress data comprises first stress data and second stress data, the first stress data is stress data of a plurality of detection points at the same moment, and the second stress data is stress data of the same detection point at different moments; performing feature extraction on the initial stress data by adopting a PCA algorithm to obtain target stress data, wherein the number of the target stress data is smaller than that of the initial stress data; clustering a plurality of target stress data by adopting a DBSCAN algorithm to obtain a clustering result, wherein the clustering result comprises the number of samples and the sample density in clustered clusters, and the clustering result corresponds to the clusters one by one; and calculating the risk of each cluster according to the clustering result, wherein the risk is the product of the number of samples and the sample density, and determining the stress state of the surrounding rock of the roadway according to the magnitude relation between the risk and a preset threshold value, wherein the stress state comprises a safe stress state or a dangerous stress state.

Optionally, acquiring the first stress data includes: acquiring a stress area, wherein the stress area is an area surrounded by a plurality of measuring lines which are sequentially connected in a roadway, one measuring line at least comprises one detecting point, and the lengths of all the measuring lines are preset lengths; acquiring a sequence consisting of the stress data of all the measuring points in the stress area, and performing standardized transformation by adopting a first formula to obtain an updating sequence, wherein the updating sequence comprises a plurality of first stress data, and the first formula is as follows:

wherein y is _i Representing the update sequence, SL _i Representing t ₀ And the first stress data of the ith detection point at the moment.

Optionally, acquiring the second stress data includes: acquisition of the t _i The detection of the momentThe method comprises the steps of measuring first initial sub-stress data of a point, and carrying out dimensionless treatment on the first initial sub-stress data through a second formula to obtain first sub-stress data, wherein the second formula is as follows:

S ₂ ＝(A _i t _i -A _imin )/(A _imax -A _imin )，

wherein A is _i t _i Represents the t _i The first initial sub-stress data of time, A _imin Representing the minimum value of a plurality of the first initial sub-stress data, A _imax Represents the maximum value in a plurality of the first initial sub-stress data, S ₂ Representing the first sub-stress data; acquisition of the t _i The second initial sub-stress data of the detection point at the moment is dimensionless, and is obtained through a third formula, wherein the second initial sub-stress data is the t th sub-stress data _i The difference between the stress data of the detection point at the moment and the stress data of the detection point at the initial moment is as follows:

S ₃ ＝(A _i t _i -0)/(A _imax -0)，

wherein the S is ₃ Representing the second sub-stress data; acquiring third initial sub-stress data, and carrying out dimensionless treatment on the third initial sub-stress data through a fourth formula to obtain third sub-stress data, wherein the third initial sub-stress data is A-th _i Time of day and A _i-1 The time difference of the moments, the fourth formula is:

S ₄ ＝(A _i t _i -A _imin )/(A _imax -A _imin )，

S ₄ representing the third sub-stress data; acquiring fourth initial sub-stress data, and carrying out dimensionless treatment on the fourth initial sub-stress data through a fifth formula to obtain fourth sub-stress data, wherein the fourth initial sub-stress data is the L < th > _i The distance between the detection point and the coal face at the moment and the L-th distance _i+1 The detection point and the sampling point are at the momentThe difference of the distances of the coal working surfaces is expressed as the fifth formula:

S ₅ ＝(L _i t _i -L _imin )/(L _imax -L _imin )，

S ₅ Representing the fourth sub-stress data.

Optionally, feature extraction is performed on the plurality of initial stress data by using a PCA algorithm to obtain a plurality of target stress data, including: forming a first matrix from the initial stress data according to columns, wherein the dimension of the first matrix is N rows and N columns; zero-equalizing each row of the first matrix, and calculating a covariance matrix of the first matrix after zero-equalizing; extracting eigenvalues and eigenvectors of the covariance matrix, wherein the eigenvalues are used for representing the importance degree of the eigenvectors, and the eigenvectors are used for representing the change modes of the initial stress data in different directions; sorting the feature vectors according to a preset sequence according to the magnitude of the feature values, and extracting the first M feature vectors to obtain a feature vector matrix, wherein the number of lines of the feature vector matrix is M; and calculating the product of the first matrix and the eigenvector matrix to obtain a second matrix, wherein the dimension of the second matrix is N rows and M columns, N is greater than M, and the second matrix comprises a plurality of target stress data.

Optionally, clustering the plurality of target stress data by using a DBSCAN algorithm to obtain a clustering result, including: obtaining core points, wherein the number of sample points in the radius of the field of the core points is greater than or equal to the minimum sample number; classifying the sample points with the distance from the core point being smaller than a preset distance by taking the core point as a center to obtain a plurality of temporary clustering clusters; any two temporary cluster clusters are extracted to obtain a first temporary cluster and a second temporary cluster; and extracting any one of the sample points in the first temporary cluster, and merging the first temporary cluster and the second temporary cluster when the extracted sample point is the core point in the first temporary cluster to obtain a cluster until the temporary cluster does not exist.

Optionally, after acquiring the plurality of initial stress data, the method further comprises: determining whether a missing detection point exists in a plurality of detection points, wherein the missing detection point is the detection point with the stress data being empty; and when the missing detection point exists, supplementing the stress data missing from the missing detection point by adopting an interpolation method according to a plurality of stress data corresponding to a plurality of detection points except the missing detection point.

Optionally, determining the stress state of the surrounding rock of the roadway according to the magnitude relation between the risk degree and the preset threshold value includes: determining the stress state of the surrounding rock of the roadway as a first stress state under the condition that the risk is smaller than or equal to a first preset threshold value; determining the stress state of the surrounding rock of the roadway as a second stress state under the condition that the risk is larger than the first preset threshold and smaller than or equal to a second preset threshold, wherein the first preset threshold is smaller than the second preset threshold, and the stress risk degree of the first stress state is smaller than the risk degree of the second stress state; determining the stress state of the surrounding rock of the roadway as a third stress state under the condition that the risk is larger than the second preset threshold and smaller than or equal to a third preset threshold, wherein the second preset threshold is smaller than the third preset threshold, and the stress risk degree of the second stress state is smaller than the risk degree of the third stress state; and determining the stress state of the surrounding rock of the roadway as a fourth stress state under the condition that the risk is larger than the third preset threshold and smaller than or equal to the fourth preset threshold, wherein the third preset threshold is smaller than the fourth preset threshold, and the stress risk degree of the third stress state is smaller than the risk degree of the fourth stress state.

According to another aspect of the present application, there is provided a device for determining a stress state of a roadway surrounding rock, including: the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a plurality of initial stress data, the initial stress data comprise first stress data and second stress data, the first stress data are stress data of a plurality of detection points at the same moment, and the second stress data are stress data of the same detection point at different moments; the first processing unit is used for carrying out feature extraction on the initial stress data by adopting a PCA algorithm to obtain target stress data, wherein the number of the target stress data is smaller than that of the initial stress data; the clustering unit is used for clustering the target stress data by adopting a DBSCAN algorithm to obtain a clustering result, wherein the clustering result comprises the number of samples in a clustered cluster and the sample density, and the clustering result corresponds to the clustered cluster one by one; the second processing unit is used for calculating the risk of each cluster according to the clustering result, wherein the risk is the product of the number of samples and the sample density, and determining the stress state of the surrounding rock of the roadway according to the magnitude relation between the risk and a preset threshold value, and the stress state comprises a safe stress state or a dangerous stress state.

According to still another aspect of the present application, there is provided a computer readable storage medium, where the computer readable storage medium includes a stored program, and when the program runs, the device where the computer readable storage medium is controlled to execute any one of the methods for determining a stress state of surrounding rock of a roadway.

According to yet another aspect of the present application, there is provided a stress state determination system comprising: the system comprises one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising a method for performing the determination of the stress state of any one of the roadway surrounding rocks.

By applying the technical scheme of the application, two stress data are acquired, one is the data of a plurality of detection points at the same moment, one is the time sequence data of a single detection point at different moments, the PCA algorithm is adopted to reduce the dimension of the obtained stress data, the unimportant data is removed, the important data is obtained, then the clustering analysis is carried out according to the important data, a plurality of clustered clusters are obtained, the sample points in each cluster have similarity, the risk of each cluster is calculated, and the stress state, namely the risk degree of the stress, can be accurately determined according to the calculated result by considering the scale (the number of samples) of the clusters and the sample density of the clusters.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

fig. 1 is a block diagram of a hardware structure of a mobile terminal for performing a method for determining a stress state of a roadway surrounding rock according to an embodiment of the present application;

fig. 2 is a flow chart of a method for determining a stress state of a roadway surrounding rock according to an embodiment of the present application;

FIG. 3 shows a schematic diagram of a survey line distribution in roadway surrounding rock;

FIG. 4 is a schematic diagram showing the effect of displaying the second stress data;

FIG. 5 shows a schematic diagram of a dimension reduction process using the PCA algorithm;

FIG. 6 shows a schematic diagram of dimension reduction dynamics using the PCA algorithm;

FIG. 7 shows a schematic diagram of the process of the DBSCAN algorithm;

FIG. 8 shows a schematic diagram of two algorithm parameters in the DBSCAN algorithm;

FIG. 9 shows a schematic diagram of the categories of three points in the DBSCAN algorithm;

FIG. 10 shows a schematic diagram of the relationship of four points in the DBSCAN algorithm;

FIG. 11 shows a schematic diagram of data loss;

FIG. 12 shows a schematic diagram of importance and probability classification of clusters;

FIG. 13 shows a schematic diagram of cluster classification;

FIG. 14 shows a schematic flow chart for ranking risk levels;

FIG. 15 shows a schematic diagram of a data distribution curve;

FIG. 16 is a flow chart illustrating another method of determining a stress state of a roadway surrounding rock;

fig. 17 shows a block diagram of a device for determining a stress state of a roadway surrounding rock according to an embodiment of the present application.

Wherein the above figures include the following reference numerals:

102. a processor; 104. a memory; 106. a transmission device; 108. and an input/output device.

Detailed Description

It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.

In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For convenience of description, the following will describe some terms or terminology involved in the embodiments of the present application:

detecting point: the point positions of the instrument, such as the detection equipment, are arranged according to a certain scale for observation, and the point positions can also be simply called as measurement points in the scheme;

and (5) measuring: an observation line composed of observation points arranged along a straight line according to a certain scale;

minimum roadway unit: an on-line minimum data analysis unit (default 10 m) of surrounding rock stress;

Minimum time analysis unit: time minimum data analysis unit (default 10 min).

For the roadway surrounding rock stress, the overall arrangement, the optimal section shape and the section size of the roadway can be reasonably determined only by mastering the ground stress condition of a specific engineering area. Can make economic, safe and practical design. Current measurement methods fall into five main categories: a construction method, a deformation method, an electromagnetic method, an earthquake method and a radioactivity method. The measurement basic principle is divided into two main categories: direct measurement and indirect measurement. The direct measurement method is to measure the fracture of the rock to determine the rock mass stress, and the rock mass stress is not required to be calculated by using lithology parameters and constitutive relations, such as a hydraulic fracturing method, a sleeve fracturing method and the like. The indirect measurement method is to estimate stress by measuring deformation or physical property change of rock, for example, a core method, an acoustic method, or the like. Due to the extraordinary complexity of rock properties, the rock mass has structural features. The complex environment of the rock mass, such as humidity, water burst, ground humidity, geomagnetic field and the like, can cause a certain test method to fail, any one of the current measurement methods is in development, has defects, and the detected stress state is not very accurate.

As described in the background art, in order to solve the above problems, the embodiments of the present application provide a method, an apparatus, a computer readable storage medium, and a system for determining the stress state of a roadway surrounding rock.

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.

The method embodiments provided in the embodiments of the present application may be performed in a mobile terminal, a computer terminal or similar computing device. Taking the operation on the mobile terminal as an example, fig. 1 is a hardware structure block diagram of the mobile terminal of a method for determining the stress state of the surrounding rock of the roadway in an embodiment of the present application. As shown in fig. 1, a mobile terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting of the structure of the mobile terminal described above. For example, the mobile terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.

The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a display method of device information in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, to implement the above-described method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.

In this embodiment, a method for determining the stress state of a roadway surrounding rock operating in a mobile terminal, a computer terminal or a similar computing device is provided, and it should be noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that although a logical sequence is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in a different order than that illustrated herein.

Fig. 2 is a flow chart of a method for determining a stress state of a roadway surrounding rock according to an embodiment of the application. As shown in fig. 2, the method comprises the steps of:

step S201, obtaining a plurality of initial stress data, wherein the initial stress data comprises first stress data and second stress data, the first stress data is stress data of a plurality of detection points at the same moment, and the second stress data is stress data of the same detection point at different moments;

specifically, in the scheme, the combined analysis method of the plurality of measuring point data at the same time and the online time sequence data analysis method of the stress of a certain measuring point can be combined, and compared with the traditional data analysis method, the combined analysis method of the plurality of measuring point data at the same time and the online time sequence data analysis method of the stress of a certain measuring point are combined, so that the roadway surrounding rock of the coal face can update the stress change in time, and the stress change curve of the roadway surrounding rock of the current coal face is reflected more truly. The stress data may be acquired by a stress sensor.

Step S202, performing feature extraction on a plurality of initial stress data by adopting a PCA algorithm to obtain a plurality of target stress data, wherein the number of the target stress data is smaller than that of the initial stress data;

specifically, principal Component Analysis (PCA) is a commonly used linear dimension reduction technique for converting high-dimensional data into a set of representations with linear independence to extract the principal feature components of the data. By PCA dimension reduction, the dimension of data can be reduced and main information can be reserved, so that the calculated amount is reduced.

Step S203, clustering a plurality of target stress data by adopting a DBSCAN algorithm to obtain a clustering result, wherein the clustering result comprises the number of samples and the sample density in clustered clusters, and the clustering result corresponds to the clusters one by one;

specifically, the DBSCAN algorithm can automatically discover clusters with different densities by finding core points and density-based connectivity.

Step S204, calculating the risk of each cluster according to the clustering result, wherein the risk is the product of the number of samples and the sample density, and determining the stress state of the surrounding rock of the roadway according to the magnitude relation between the risk and a preset threshold value, wherein the stress state comprises a safe stress state or a dangerous stress state.

Specifically, the method and the device can more comprehensively reflect the stress and actual conditions of each point of the rock stratum where the surrounding rock of the roadway of the coal face is located, so that a worker can just master the early warning range of the stress of each point and accurately perform danger early warning.

Specifically, in the scheme, the risk of the clustered clusters is calculated, the risk corresponds to the risk of the detection points, the number of the clusters is multiple, the risk corresponds to the number of the clusters, and further the risk can be sequenced to determine the change condition of the risk of different detection points.

According to the embodiment, two stress data are collected, one is the data of a plurality of detection points at the same moment, one is the time sequence data of a single detection point at different moments, a PCA algorithm is adopted to reduce the dimension of the obtained stress data, unimportant data are removed, important data are obtained, then clustering analysis is carried out according to the important data, a plurality of clustered clusters are obtained, sample points in each cluster are similar, the risk of each cluster is calculated, and the state of stress can be accurately determined according to the calculated result, namely the risk of stress is determined due to the fact that the scale (the number of samples) of the clusters and the sample density of the clusters are considered.

In order to ensure the accuracy of the first stress data and further ensure that the stress state is accurately determined by adopting the first stress data in the follow-up process, the first stress data is acquired in the specific implementation process, and the method can be realized by the following steps: acquiring a stress area, wherein the stress area is an area surrounded by a plurality of measuring lines which are sequentially connected in a roadway, one measuring line at least comprises one detecting point, and the lengths of all the measuring lines are preset lengths; acquiring a sequence composed of the stress data of all the measuring points in the stress area, and performing standardized transformation by adopting a first formula to obtain an updating sequence, wherein the updating sequence comprises a plurality of first stress data, and the first formula is as follows:

In the scheme, the stress data in the area of the measuring line wall can be obtained and sequenced, the sequencing can be from big to small or from small to big, and the stress data in the sequence is converted into a unified format through standardized change, so that the accuracy of the first stress data is ensured, and the follow-up adoption of the first stress data is further ensured to accurately determine the stress state.

Specifically, as shown in fig. 3, there are two lanes, i.e., two lines a and B, and for simple analysis, only one of the lines needs to be selected for analysis. Each line is an analysis entity, one line is generally located in each lane, for any one A _i The measuring points are all provided with A _it Corresponding to the stress value of each measuring point at different momentsAnd (5) melting. ) At this time also corresponds to the distance L of the measuring point from the coal face _it . The minimum roadway unit of the data analysis of the drilling stress meter is D ₀ Default 10m, minimum time unit for analysis of borehole stress meter data is T ₀ Default 10min. The application calculates the area, uses the minimum roadway unit, and the roadway unit distance is fixed and is more scientific. Interpolation can also be performed if missing data exists.

Specifically, for joint analysis of multiple measurement point data at the same time, as shown in fig. 4, let t be ₀ At the moment, the value A corresponding to the A line ₁ t ₀ ，A ₂ t ₀ ，...，A _n t ₀ Each numerical value corresponds to L ₁ t ₀ ，L ₂ t ₀ ，...L _n t ₀ . On-line minimum data analysis unit (a section of roadway, which is 10m and is denoted as D) ₀ )，D ₀ Calculating the area of the enclosed area, wherein the calculated area result is SL ₀ ，SL ₁ ，SL _i ，...，SL _m SL is converted by a first formula _m Unitizing, and forming a new sequence y after standardized transformation ₁ ，y ₂ ，y ₃ ，…，y _m ∈[0,1]And is dimensionless; for at a certain time t _i The stress state S of surrounding rock reacted by one measuring point _f Is expressed by the following formula: s is S ₁ ＝y _i 。

In order to ensure the accuracy of the second stress data and further ensure that the stress state is accurately determined by adopting the second stress data in the following steps, the second stress data is acquired in the specific implementation process, and the method can be realized by the following steps: acquisition of the t _i The first initial sub-stress data of the detection point at the moment is dimensionless, and the first initial sub-stress data is obtained through a second formula, wherein the second formula is as follows:

S ₂ ＝(A _i t _i -A _imin )/(A _imax -A _imin )，

wherein A is _i t _i Represents the t _i Time of dayThe first initial sub-stress data, A _imin Representing the minimum value, A, of a plurality of the first initial sub-stress data _imax Represents the maximum value of a plurality of the first initial sub-stress data, S ₂ Representing the first sub-stress data; acquisition of the t _i The second initial sub-stress data of the detection point at the moment is dimensionless, and is obtained through a third formula, wherein the second initial sub-stress data is the t th sub-stress data _i The third formula is as follows:

S ₃ ＝(A _i t _i -0)/(A _imax -0)，

wherein S is as described above ₃ Representing the second sub-stress data; acquiring third initial sub-stress data, and carrying out dimensionless treatment on the third initial sub-stress data through a fourth formula to obtain third sub-stress data, wherein the third initial sub-stress data is A-th _i Time of day and A _i-1 The time difference of the moments is as follows:

S ₄ ＝(A _i t _i -A _imin )/(A _imax -A _imin )，

S ₄ representing the third sub-stress data; acquiring fourth initial sub-stress data, and carrying out dimensionless treatment on the fourth initial sub-stress data through a fifth formula to obtain fourth sub-stress data, wherein the fourth initial sub-stress data is L < th > _i The distance between the detection point and the coal face and the L-th time _i+1 The difference between the distance between the detection point and the coal face at the moment is as follows:

S ₅ ＝(L _i t _i -L _imin )/(L _imax -L _imin )，

S ₅ represents the fourth sub-stress data (L _i t _i Represents the t _i Time fourth initial sub-stress data, L _imin Representing a plurality of fourth initial sub-stress dataMinimum value of L _imax Representing the maximum of the fourth plurality of initial sub-stress data).

In the scheme, for the stress on-line time sequence data analysis of a single measuring point, one measuring point A can be selected _i Obtaining S ₂ Then, S is mapped by a second formula ₂ Dimensionless, S ₂ Converting into a value within a range of (0, 1) to obtain S ₃ Then, S is paired by a third formula ₃ Dimensionless, S ₃ Converting into a value within a range of (0, 1) to obtain S ₄ Then, S is paired by a fourth formula ₄ Dimensionless, S ₄ Converted into a value in the range of (0, 1), A _i Each time corresponds to one L _i I.e. at L _i The corresponding footage of moment, the distance from the coal face and the moment L at the point are searched _i+1 Is a numerical value of (2). If L _i And L is equal to _i+1 When a plurality of values exist, the maximum value of all the values is needed to be taken, and S is obtained ₅ S is paired by a fifth formula ₅ Dimensionless, S ₅ The method is converted into a numerical value within a range (0, 1), so that a plurality of second stress data can be converted into data in a unified format, further, the subsequent dimension reduction processing is facilitated, the subsequent density analysis processing is facilitated, dimensionless numerical calculation is more objective, and further, the calculation efficiency of the scheme is further improved.

Assuming that S is present in each minimum analysis unit ₁ 、S ₂ 、S ₃ 、S ₄ 、S ₅ In order to solve the problem of high-dimensional data, reduce the computational complexity and visualize, and need to perform dimension reduction processing on the multi-dimensional data, the application adopts PCA algorithm to perform feature extraction on a plurality of initial stress data to obtain a plurality of target stress data, and the method can be realized by the following steps: forming a first matrix from the initial stress data according to columns, wherein the dimension of the first matrix is N rows and N columns; zero-equalizing each row of the first matrix, and calculating a covariance matrix of the first matrix after zero-equalizing; extracting the covariance matrix Wherein the feature value is used for representing the importance degree of the feature vector, and the feature vector is used for representing the change modes of the initial stress data in different directions; according to the magnitude of the characteristic values, sequencing the characteristic vectors according to a preset sequence, and extracting the first M characteristic vectors to obtain a characteristic vector matrix, wherein the number of lines of the characteristic vector matrix is M; and calculating the product of the first matrix and the eigenvector matrix to obtain a second matrix, wherein the dimension of the second matrix is N rows and M columns, N is greater than M, and the second matrix comprises a plurality of target stress data.

In this scheme, principal Component Analysis (PCA) is a commonly used linear dimension reduction technique for converting high-dimensional data into a set of representations with linear independence to extract the principal feature components of the data. Through PCA dimension reduction, the dimension of data can be reduced, main information is reserved, so that the calculated amount is reduced, visualization is performed, and the high accuracy of stress identification in the scheme is further ensured.

In particular, in this scheme, five-dimensional data can be reduced to three dimensions for better understanding and analysis of the data. PCA is a linear dimension reduction technology, and is suitable for data with linear relation, wherein the specific process of dimension reduction data is shown in fig. 5 and 6, and the specific steps are as follows:

1) Data matrixing: forming the original data into a matrix X according to columns, wherein the dimension of the matrix X is 5 rows and 5 columns;

2) Zero-mean: zero-equalizing each row of matrix X, i.e., subtracting the average value of the row from each element, to eliminate the average value difference between rows;

3) Covariance matrix: calculating covariance matrix of zero-averaged data matrix XIt describes statistical correlation between data;

4) Eigenvalue and eigenvector: solving eigenvalues and corresponding eigenvectors of the covariance matrix, wherein the eigenvectors represent the change modes of the data in different directions, and the eigenvalues represent the importance degrees of the eigenvectors;

5) Feature vector ordering: sorting the feature vectors according to the magnitude of the feature values, arranging from large to small, and selecting the first 3 feature vectors to form a feature vector matrix P of 3 rows;

6) Dimension reduction transformation: and multiplying the original data matrix X with the eigenvector matrix P by matrix multiplication operation to obtain a dimensionality-reduced data matrix Y, wherein Y=PX. The dimension of the matrix Y is 5 rows and 3 columns, and the result after the dimension of the data is reduced to 3 dimensions is shown;

through the steps, the PCA can be used for reducing the original data from 5 dimensions to 3 dimensions, so that the dimension reduction processing of the data is realized.

In order to further ensure that the clustering effect of the scheme is better, and then the stress state can be accurately determined according to the better clustering effect, the method adopts the DBSCAN algorithm to cluster a plurality of target stress data to obtain a clustering result, and the method can be realized by the following steps: obtaining core points, wherein the number of sample points in the radius of the field of the core points is larger than or equal to the minimum sample number; classifying the sample points with the distance from the core point being smaller than a preset distance by taking the core point as the center to obtain a plurality of temporary clustering clusters; any two temporary cluster clusters are extracted to obtain a first temporary cluster and a second temporary cluster; and extracting any one of the sample points in the first temporary cluster, and merging the first temporary cluster and the second temporary cluster until the temporary cluster does not exist when the extracted sample point is the core point in the first temporary cluster.

In the scheme, the DBSCAN algorithm can automatically find clusters with different densities by searching core points and density-based connectivity, and identify noise points as isolated points. The clustering mode based on the density is sensitive to parameters, and can effectively process non-convex clustering clusters, so that the accuracy of the clustering effect of the scheme is guaranteed to be good.

Specifically, the dangerous area classification is carried out by the dimension reduction and density clustering big data analysis of the principal component analysis method, so that the big data analysis result has objectivity.

Specifically, the basic concept of DBSCAN is as follows:

1) The core idea is as follows: as shown in fig. 7, DBSCAN clusters based on the density of sample points, which divides data into different clusters by finding dense areas of sample points;

2) Algorithm parameters: as shown in FIG. 8, DBSCAN has two important parameters, namely a neighborhood radius R for determining a distance threshold between sample points and a minimum number of minPoints, which is the minimum number of sample points required in one neighborhood radius R for determining a core point, if the distance between two sample points is equal to or less than R, they are considered as a neighbor relation;

3) Three categories of points: as shown in fig. 9, the core points, boundary points, and noise points are specifically classified as follows:

A. core point: the number of sample points in a neighborhood radius R of one sample point is more than or equal to the minimum number of points minPoints, and the core points are the basis of clustering, have higher density and can be connected into the core of a clustering cluster;

B. boundary points: the condition of core points is not satisfied, namely the number of sample points in the neighborhood radius R is less than the minimum number of points minPoints, but the sample points are positioned in the neighborhood of a certain core point, and boundary points are connected with the core points to form a cluster;

C. Noise point: neither core nor boundary points, which do not satisfy the condition that the number of sample points in the neighborhood radius R > the minimum number of points minPoints, noise points are considered as isolated outliers, and do not belong to any cluster;

4) The relationship of the four points, as shown in FIG. 10, includes density direct, density reachable, density connected and non-density connected, and is specifically classified as follows:

a. density through (Density Directly Reachable): if one sample point A is located in the neighborhood of another sample point B (i.e., A is within the neighborhood radius R of B) and B is a core point, then A is considered to be connected directly to B by density, that is, A can reach B directly through a series of neighborhood points;

b. the density can reach (Density Reachable): for sample points A and B, if there is a sample point sequence P ₁ ,P ₂ ,...,P _n Wherein P is ₁ ＝A，P _n =b, and for arbitrary P _i (1<i<n)，P _i+1 Is directly connected with P through density _i Connected, then A is considered to be connected to B by density reachability, that is, A may reach B through a series of neighborhood points connected by density direct relationships;

c. density-connected (Density Connected): for sample points A and B, if there is a core point C, both A and B are connected to C by density reachable, then A and B are considered to be connected by density, that is, A and B can reach the same core point C by a series of neighborhood points connected by density direct relationship;

d. Non-density phase (Non-Density Connected): two sample points a and B are considered non-density connected if they cannot be connected by a density reachable or density connected manner.

The connectivity of the sample points in the DBSCAN algorithm is defined through the relation among the points, so that the formation of the cluster is determined. Through these relationships, the DBSCAN can find clusters with different densities and can handle the case of noise points and isolated points.

Specifically, the specific steps of clustering by using the DBSCAN algorithm in the scheme are as follows:

1) Finding core points to form temporary clustering clusters:

a. all sample points are scanned and for each sample point the number of points in its neighborhood is calculated.

b. If the number of points in the neighborhood is greater than or equal to the minimum number of points minPoints, marking the sample points as core points, and adding surrounding points into the temporary cluster.

2) Merging the temporary cluster clusters to obtain a cluster:

a. for each temporary cluster, it is checked whether the point therein is a core point.

b. If the point is a core point, combining the temporary cluster corresponding to the point and the current temporary cluster into a new temporary cluster.

c. The merging operation is repeated until each point in the current temporary cluster is either not in the core point list or the point with direct density is already in the temporary cluster.

d. When one temporary cluster cannot be merged any more, it is upgraded to the final cluster.

3) Step 2 (merging temporary clusters to obtain clusters) is repeated until all temporary clusters are processed. This results in a final cluster result, each cluster containing a set of related sample points.

In practical application, the scheme uses a PCA algorithm and a DBSCAN algorithm to combine, uses Principal Component Analysis (PCA) to reduce the five-dimensional data into three dimensions, and applies a DBSCAN density clustering algorithm in a three-dimensional space. The data classification was found and each cluster contained at least 5 points. The final result is obtained by continuously adjusting the scan radius. The specific steps are as follows:

(1) the five-dimensional data is reduced to three dimensions by PCA, which comprises zero-equalizing the data, calculating covariance matrix, calculating eigenvalues and eigenvectors, and selecting the first three eigenvectors to form a dimension reduction matrix.

(2) And in the three-dimensional space after dimension reduction, adopting a DBSCAN density clustering algorithm to perform clustering analysis. An appropriate scan radius epsilon is selected and the minimum inclusion count is set to 5. And then scanning the neighborhood of each data point, and dividing the points in the neighborhood into core points, boundary points or noise points to form a temporary cluster.

(3) And constructing a final clustering result by combining the temporary clustering clusters. By examining the points that satisfy the density reachable relationship, they are combined into one cluster. In this process, the scan radius ε is continuously adjusted until each cluster contains at least 5 points.

(4) A final cluster result is obtained, wherein each cluster will contain a set of related data points. And reducing the five-dimensional data to three dimensions through principal component analysis and a DBSCAN density clustering algorithm, and finding a clustering result meeting the minimum point inclusion requirement.

In a specific application scene, the roadway length is 1000m, and the minimum data analysis unit D ₀ =10m, 100 data obtained over distance, time from 7 am to 7 pm, minimum time analysis unit T ₀ 72 data were obtained over time, eventually 7200 data =10 min. The final data is divided into 53 classes through density clustering, the classes are classified, the quantity contained in each class is observed, and the sorting is carried out according to the quantity in each class from more to less. Since the data near 0 is too scattered and does not belong to the core point, it can be dropped.

Because the number of the detection points arranged in the coal mine roadway is large in the scheme, a certain detection point is likely to be missed, for example, the detection point is trampled by mistake or is hit by dropped coal rocks, so that the detection point is missed, the data of the missing detection point cannot be obtained, and in some embodiments, after a plurality of initial stress data are obtained, the method further comprises the following steps: determining whether a missing detection point exists in the detection points, wherein the missing detection point is the detection point with the empty stress data; when the missing detection point exists, the stress data missing from the missing detection point is supplemented by interpolation based on the stress data corresponding to the detection points other than the missing detection point.

In the scheme, if a missing detection point exists during data acquisition, namely, the situation of data missing, the interpolation method is adopted to supplement data, so that the integrity of the data can be ensured.

Specifically, the minimum time analysis unit T in the present application ₀ (default 10 min). If the minimum data analysis unit has data missing, the interpolation method is adopted to supplement data.

Wherein i is more than or equal to 3, if i is more than or equal to 0 and less than 3, missing data is obtainedInterpolation is performed for two or one of the front and rear regions of (a). As shown in FIG. 11, S of the lower region ₃₀ Lack of data, S ₃₀ ＝α ₁ [S ₂₀ +S ₄₀ ]+α ₂ [S ₁₀ +S ₅₀ ]+α ₃ [S ₀ +S ₆₀ ]Wherein alpha is obtainable from field experience ₁ ＝0.3，α ₂ ＝0.15，α ₃ ＝0.05。

Minimum data analysis unit D in the present application ₀ The range (default 10 m) is not constant. If there is data missing in the minimum data analysis unit, combining the unit of missing data with the unit adjacent to it in front to form a minimum analysis unit (combining YII into one unit), and if there is multiple measuring point data in the minimum analysis unit, defining to take multiple measuring points T _t Mean value of (2) shows S _t ，

The scheme also comprises the steps of dividing and correcting the dangerous base of the measuring point data, and clustering all the state points in the sample library by using density cluster analysis in a state coordinate system. The purpose of clustering is to classify similar state points into a class for prediction and analysis of state values. For status warning of real-time data, a degradation status rate of 10% is used as a threshold. When the state value of the real-time data reaches or exceeds the threshold value, the data early warning is triggered.

In performing density cluster analysis, the state points in the sample library are divided into different clusters. The number and size of clusters will vary depending on the density and similarity of the data points. The clusters are ordered according to the amount of data of each type of cluster. Clusters with a larger amount of data will be ranked in front and clusters with a smaller amount of data will be ranked in back. This ordering may be demonstrated by drawing a pareto chart.

Pareto chart is a common ranking tool used to show the importance and extent of contribution of different factors. Pareto graphs may show the amount of data for each cluster and its proportion in the population. By looking at the pareto chart, it is intuitively known which clusters occupy a larger proportion and which clusters have a smaller data size. This facilitates the determination of important status points and further data analysis.

And clustering all state points in the sample library by using density cluster analysis in a state coordinate system, and carrying out state early warning on real-time data by using a 10% degradation state rate. As shown in fig. 12, the importance and contribution degree of each cluster are intuitively known by sorting the data amounts of the various clusters and drawing a pareto chart.

Fig. 12 shows that the data amount of the first 7 kinds of data has accumulated to 90% or more, i.e., the previous large-scale data is divided into normal sections, the remaining minor groups are divided into degradation groups, and the data in the sections show abnormality.

Therefore, the specific steps of calculating the risk of each cluster according to the clustering result and sorting the risk levels are shown in fig. 13 and 14, including the following;

the core sample is determined by: in each cluster, core samples, i.e. samples with a sufficient number of neighbor points, are found. The core sample is the center point of the cluster and can be used to determine the risk level of the cluster.

Calculating the risk Z: to calculate the risk, two factors are considered: the size S of the class (the number of core samples) and the compactness D of the class (the average distance between samples). The following formula is used: z=s×d calculates the risk of each cluster.

⒊ order classes: and sorting the classes according to the calculated risk, and arranging the classes from low to high.

⒋ hazard classification: the ordered classes are classified into different hazard classes a, B, C, D as required.

And drawing a data distribution curve (shown in fig. 15), and continuously correcting sigma according to the existing accident data in the field, so that the accident data finally fall into the area D as far as possible. If new data is entered at this time, the probability of accident can be judged according to the fact that the new data falls into a certain area. Where M represents the mean of the data. A is on the left side of M, the region of 50% theoretical probability. B is on the right of M, the region of M+ - σ theoretical probability 68.26%. C is on the right of M, the region of M+ -2σ theoretical probability 95.45%. B is on the right of M, the region of 99.73% of the theoretical probability of M+ -3 sigma.

In some embodiments, according to the relationship between the risk and the preset threshold, the stress state of the surrounding rock of the roadway is determined, which can be realized by the following steps: determining the stress state of the surrounding rock of the roadway as a first stress state under the condition that the risk is smaller than or equal to a first preset threshold value; determining the stress state of the surrounding rock of the roadway as a second stress state under the condition that the risk is larger than the first preset threshold and smaller than or equal to a second preset threshold, wherein the first preset threshold is smaller than the second preset threshold, and the stress risk degree of the first stress state is smaller than the risk degree of the second stress state; determining the stress state of the surrounding rock of the roadway as a third stress state under the condition that the risk is larger than the second preset threshold and smaller than or equal to a third preset threshold, wherein the second preset threshold is smaller than the third preset threshold, and the stress risk degree of the second stress state is smaller than the risk degree of the third stress state; and determining the stress state of the surrounding rock of the roadway as a fourth stress state under the condition that the risk is larger than the third preset threshold and the risk is smaller than or equal to a fourth preset threshold, wherein the third preset threshold is smaller than the fourth preset threshold, and the stress risk of the third stress state is smaller than the risk of the fourth stress state.

According to the scheme, the stress state of the surrounding rock of the roadway can be determined directly according to the magnitude relation between the risk and the preset threshold value, a complex determination process is not needed, the mode of determining the stress state of the scheme is simpler and more direct, the basic division of the risk of the measured point data is defined, the difficulty in collecting and analyzing the stress data in the risk level division is greatly reduced, the risk level of the working face can be rapidly and timely analyzed, and the risk early warning can be accurately and reasonably carried out.

Specifically, the risk level determination for the stress state can be determined according to table 1.

TABLE 1

Risk level	No danger/micro-danger	Weak danger	Medium risk	Intense danger
					Actual measurement data hazard level	A	B	C	D
Amplitude value	1	2	3	4

The application can correct the dangerous area according to the field data, and the accident to be happened falls into the area D as much as possible, so that the result has higher accuracy and reliability, thereby accurately analyzing the new data and carrying out early warning.

The above-mentioned application is not limited thereto, and any changes that can be made by those skilled in the art should fall within the scope of the application.

According to the scheme, according to the real-time numerical value of roadway surrounding rock stress and strain monitoring, multiple measuring point data joint analysis at the same moment is adopted, single-point online time sequence data analysis and density clustering big data analysis are adopted, and the number of the data contained in the class is sequenced, so that dangerous index areas are divided, roadway surrounding rock stress is analyzed, and roadway surrounding rock data change of different time points and different test points is revealed; on the basis, the roadway risk level is judged by establishing a data distribution curve and combining a measuring point data risk judging method. The application provides an analysis and judgment scheme for the real-time monitoring data of the stress of the surrounding rock of the roadway, which has important practical significance for the maintenance and the safe exploitation of the roadway of the coal mine

The application discloses a multi-factor multi-index roadway surrounding rock stress on-line data analysis method based on density clustering. According to the method, a joint analysis method of a plurality of measuring point data at the same moment is combined with an online time sequence data analysis method of stress at a certain measuring point, and finally, the corresponding dangerous indexes are divided by using big data analysis of density clustering, so that surrounding rock stress data and stress change curves at each moment can be updated in time for a coal mine, the real production conditions of surrounding rock underground of a coal face roadway can be truly reflected, the problems that traditional stress data analysis is single, fixed threshold hard analysis is set, and the plurality of measuring points cannot be analyzed simultaneously can be solved, workers can more intuitively know whether the change condition of surrounding rock stress of the coal face roadway exceeds a stress early warning range or not, the emergency is met, and the safe production of the coal mine is ensured.

In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the method for determining the stress state of the roadway surrounding rock of the present application will be described in detail below with reference to specific embodiments.

The embodiment relates to a specific method for determining the stress state of roadway surrounding rock, as shown in fig. 16, comprising the following steps:

Acquiring stress data of a plurality of detection points at the same moment to obtain first stress data, performing joint analysis on the data of the plurality of detection points at the same moment, determining an on-line minimum data analysis unit of surrounding rock stress, calculating the stress state of the surrounding rock reflected by a certain detection point at a certain moment, determining whether a data missing condition exists in a minimum time unit, and if the data missing condition exists, performing supplemental data by adopting an interpolation method;

obtaining stress data of the same detection point at different moments to obtain second stress data, designating a detection point, calculating first initial sub-stress data, second initial sub-stress data, third initial sub-stress data and fourth initial sub-stress data, determining whether a data missing condition exists in a minimum data analysis unit, and if the data missing condition exists, carrying out supplemental data by adopting an interpolation method;

performing dimension reduction processing on the acquired stress data, performing density clustering classification, sorting according to the quantity contained in the classes, drawing a data distribution curve, dividing the risk level, debugging according to the occurrence of an accident of an on-site event, finally enabling the occurrence of the accident to fall into a D area, judging the occurrence probability of the data falling into a certain area according to the drawn graph, and giving the risk level.

The embodiment of the application also provides a device for determining the stress state of the surrounding rock of the roadway, and the device for determining the stress state of the surrounding rock of the roadway can be used for executing the method for determining the stress state of the surrounding rock of the roadway. The device is used for realizing the above embodiments and preferred embodiments, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

The device for determining the stress state of the roadway surrounding rock provided by the embodiment of the application is described below.

Fig. 17 is a block diagram of a device for determining a stress state of a roadway surrounding rock according to an embodiment of the present application. As shown in fig. 17, the apparatus includes:

an obtaining unit 10, configured to obtain a plurality of initial stress data, where the initial stress data includes first stress data and second stress data, the first stress data is stress data of a plurality of detection points at the same time, and the second stress data is stress data of the same detection point at different times;

A first processing unit 20, configured to perform feature extraction on a plurality of the initial stress data by using a PCA algorithm to obtain a plurality of target stress data, where the number of the target stress data is less than the number of the initial stress data;

a clustering unit 30, configured to cluster the plurality of target stress data by using a DBSCAN algorithm, so as to obtain a clustering result, where the clustering result includes the number of samples and the sample density in a clustered cluster, and the clustering result corresponds to the clustered cluster one by one;

and a second processing unit 40, configured to calculate a risk of each cluster according to the clustering result, where the risk is a product of the number of samples and the sample density, and determine a stress state of surrounding rock of the roadway according to a magnitude relation between the risk and a preset threshold, where the stress state includes a safe stress state or a dangerous stress state.

In order to ensure the accuracy of the first stress data and further ensure that the stress state is accurately determined by adopting the first stress data in the following process, in a specific implementation process, the acquisition unit comprises a first acquisition module and a first processing module, wherein the first acquisition module is used for acquiring a stress area, the stress area is an area surrounded by a plurality of test lines which are sequentially connected in a roadway, one test line at least comprises one detection point, and the lengths of all the test lines are preset lengths; the first processing module is configured to obtain a sequence composed of the stress data of all the measurement points in the stress area, and perform standardized transformation by using a first formula to obtain an update sequence, where the update sequence includes a plurality of first stress data, and the first formula is:

In order to ensure the accuracy of the second stress data and further ensure that the stress state is accurately determined by adopting the second stress data, in a specific implementation process, the acquisition module comprises a second acquisition module, a third acquisition module, a fourth acquisition module and a fifth acquisition module, wherein the second acquisition module is used for acquiring the t < th > _i The first initial sub-stress data of the detection point at the moment is dimensionless, and the first initial sub-stress data is obtained through a second formula, wherein the second formula is as follows:

S ₂ ＝(A _i t _i -A _imin )/(A _imax -A _imin )，

wherein the method comprises the steps of，A _i t _i Represents the t _i The first initial sub-stress data of time, A _imin Representing the minimum value, A, of a plurality of the first initial sub-stress data _imax Represents the maximum value of a plurality of the first initial sub-stress data, S ₂ Representing the first sub-stress data; the third acquisition module is used for acquiring the t _i The second initial sub-stress data of the detection point at the moment is dimensionless, and is obtained through a third formula, wherein the second initial sub-stress data is the t th sub-stress data _i The third formula is as follows:

S ₃ ＝(A _i t _i -0)/(A _imax -0)，

Wherein S is as described above ₃ Representing the second sub-stress data; the fourth obtaining module is configured to obtain third initial sub-stress data, and dimensionless the third initial sub-stress data according to a fourth formula to obtain third sub-stress data, where the third initial sub-stress data is the A-th sub-stress data _i Time of day and A _i-1 The time difference of the moments is as follows:

S ₄ ＝(A _i t _i -A _imin )/(A _imax -A _imin )，

S ₄ representing the third sub-stress data; the fifth obtaining module is configured to obtain fourth initial sub-stress data, and dimensionless the fourth initial sub-stress data according to a fifth formula to obtain fourth sub-stress data, where the fourth initial sub-stress data is the L-th sub-stress data _i The distance between the detection point and the coal face and the L-th time _i+1 The difference between the distance between the detection point and the coal face at the moment is as follows:

S ₅ ＝(L _i t _i -L _imin )/(L _imax -L _imin )，

S ₅ represents the fourth sub-stress data (L _i t _i Represents the t _i Time fourth initial sub-stress data, L _imin Representing the minimum value, L, in the fourth plurality of initial sub-stress data _imax Representing the maximum of the fourth plurality of initial sub-stress data).

Assuming that S is present in each minimum analysis unit ₁ 、S ₂ 、S ₃ 、S ₄ 、S ₅ In order to solve the problem of high-dimensional data, reduce the computational complexity and visualize, and need to carry out the dimension reduction processing on the multi-dimensional data, a first processing unit of the application comprises a second processing module, a third processing module, a first extraction module, a fourth processing module and a computing module, wherein the second processing module is used for forming a first matrix by a plurality of initial stress data according to columns, and the dimension of the first matrix is N rows and N columns; first, the The third processing module is used for carrying out zero-mean on each row of the first matrix and calculating a covariance matrix of the first matrix after zero-mean; the first extraction module is used for extracting eigenvalues and eigenvectors of the covariance matrix, wherein the eigenvalues are used for representing the importance degree of the eigenvectors, and the eigenvectors are used for representing the change modes of the initial stress data in different directions; the fourth processing module is used for sequencing the feature vectors according to a preset sequence according to the magnitude of the feature values, extracting the first M feature vectors to obtain a feature vector matrix, wherein the number of lines of the feature vector matrix is M; the calculation module is used for calculating the product of the first matrix and the eigenvector matrix to obtain a second matrix, wherein the dimension of the second matrix is N rows and M columns, N is greater than M, and the second matrix comprises a plurality of target stress data.

In order to further ensure that the clustering effect of the scheme is better, and then the stress state can be accurately determined according to the better clustering effect, the clustering unit comprises a sixth acquisition module, a fifth processing module, a second extraction module and a sixth processing module, wherein the sixth acquisition module is used for acquiring core points, and the number of sample points in the radius of the field of the core points is larger than or equal to the minimum sample number; the fifth processing module is used for classifying the sample points with the distances from the core points being smaller than a preset distance by taking the core points as the centers to obtain a plurality of temporary clustering clusters; the second extraction module is used for extracting any two temporary cluster clusters to obtain a first temporary cluster and a second temporary cluster; and a sixth processing module is configured to extract any one of the sample points in the first temporary cluster, and if the extracted sample point is the core point in the first temporary cluster, combine the first temporary cluster and the second temporary cluster to obtain a cluster until the temporary cluster does not exist.

Because the number of the detection points arranged in the coal mine roadway is large, a certain detection point is likely to be missed, for example, the detection point is missed by trampling by mistake or is hit by falling coal rocks, so that the data of the missed detection point cannot be acquired; and a third processing unit configured to, when the missing detection point exists, supplement the missing stress data of the missing detection point by interpolation based on the stress data corresponding to the detection points other than the missing detection point.

In some embodiments, the second processing unit includes a first determining module, a second determining module, a third determining module, and a fourth determining module, where the first determining module is configured to determine that the stress state of the roadway surrounding rock is a first stress state if the risk is less than or equal to a first preset threshold; the second determining module is configured to determine the stress state of the surrounding rock of the roadway to be a second stress state when the risk is greater than the first preset threshold and the risk is less than or equal to a second preset threshold, where the first preset threshold is less than the second preset threshold and the risk of the first stress state is less than the risk of the second stress state; the third determining module is configured to determine the stress state of the surrounding rock of the roadway to be a third stress state when the risk is greater than the second preset threshold and the risk is less than or equal to a third preset threshold, where the second preset threshold is less than the third preset threshold and the risk of the second stress state is less than the risk of the third stress state; the fourth determining module is configured to determine that the stress state of the surrounding rock of the roadway is a fourth stress state when the risk is greater than the third preset threshold and the risk is less than or equal to a fourth preset threshold, where the third preset threshold is less than the fourth preset threshold and the risk of the third stress state is less than the risk of the fourth stress state.

The device for determining the stress state of the roadway surrounding rock comprises a processor and a memory, wherein the acquisition unit, the first processing unit, the clustering unit, the second processing unit and the like are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions. The modules are all located in the same processor; alternatively, the above modules may be located in different processors in any combination.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The inner core can be provided with one or more than one, and the problem that the real stress state of the roadway surrounding rock cannot be accurately obtained in the prior art is solved by adjusting the parameters of the inner core.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

The embodiment of the application provides a computer readable storage medium, which comprises a stored program, wherein the program is controlled to run so as to control equipment where the computer readable storage medium is positioned to execute the method for determining the stress state of the surrounding rock of the roadway.

The embodiment of the application provides a processor which is used for running a program, wherein the method for determining the stress state of the surrounding rock of the roadway is executed when the program runs.

The application also provides a stress state determining system, which comprises one or more processors, a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs comprise a determining method for executing the stress state of any one of the roadway surrounding rocks.

The embodiment of the application provides equipment, which comprises a processor, a memory and a program stored on the memory and capable of running on the processor, wherein the processor realizes the method steps of determining the stress state of at least the following roadway surrounding rock when executing the program. The device herein may be a server, PC, PAD, cell phone, etc.

The application also provides a computer program product adapted to perform a program of method steps initialized with at least the following determination of the stress state of roadway surrounding rock when executed on a data processing device.

It will be appreciated by those skilled in the art that the modules or steps of the application described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, the present application is not limited to any specific combination of hardware and software.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

1) According to the method for determining the stress state of the roadway surrounding rock, two stress data are collected, one is the data of a plurality of detection points at the same moment, the other is the time sequence data of a single detection point at different moments, the PCA algorithm is adopted to reduce the dimension of the obtained stress data, unimportant data are removed, important data are obtained, then cluster analysis is carried out according to the important data, clusters of a plurality of clusters are obtained, sample points in each cluster are similar, the risk of each cluster is calculated, and the stress state, namely the risk of the stress, can be determined accurately according to the calculated result by considering the scale (the number of samples) of the clusters and the sample density of the clusters.

2) The device for determining the stress state of the roadway surrounding rock acquires two stress data, one is the data of a plurality of detection points at the same moment, the other is the time sequence data of a single detection point at different moments, the PCA algorithm is adopted to reduce the dimension of the obtained stress data, unimportant data are removed, important data are obtained, then cluster analysis is carried out according to the important data, clusters of a plurality of clusters are obtained, sample points in each cluster have similarity, the risk of each cluster is calculated, and the stress state, namely the risk of the stress, can be determined accurately according to the calculated result by considering the scale (the number of samples) of the clusters and the sample density of the clusters.

The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. The method for determining the stress state of the roadway surrounding rock is characterized by comprising the following steps of:

acquiring a plurality of initial stress data, wherein the initial stress data comprises first stress data and second stress data, the first stress data is stress data of a plurality of detection points at the same moment, and the second stress data is stress data of the same detection point at different moments;

performing feature extraction on the initial stress data by adopting a PCA algorithm to obtain target stress data, wherein the number of the target stress data is smaller than that of the initial stress data;

clustering a plurality of target stress data by adopting a DBSCAN algorithm to obtain a clustering result, wherein the clustering result comprises the number of samples and the sample density in clustered clusters, and the clustering result corresponds to the clusters one by one;

And calculating the risk of each cluster according to the clustering result, wherein the risk is the product of the number of samples and the sample density, and determining the stress state of the surrounding rock of the roadway according to the magnitude relation between the risk and a preset threshold value, wherein the stress state comprises a safe stress state or a dangerous stress state.

2. The method of claim 1, wherein acquiring first stress data comprises:

acquiring a stress area, wherein the stress area is an area surrounded by a plurality of measuring lines which are sequentially connected in a roadway, one measuring line at least comprises one detecting point, and the lengths of all the measuring lines are preset lengths;

acquiring a sequence consisting of the stress data of all the measuring points in the stress area, and performing standardized transformation by adopting a first formula to obtain an updating sequence, wherein the updating sequence comprises a plurality of first stress data, and the first formula is as follows:

3. The method of claim 1, wherein obtaining second stress data comprises:

Acquisition of the t _i The method comprises the steps of obtaining first initial sub-stress data of a detection point at moment, and carrying out dimensionless treatment on the first initial sub-stress data through a second formula to obtain first sub-stress data, wherein the second formula is as follows:

S ₂ ＝(A _i t _i -A _imin )/(A _imax -A _imin )，

wherein A is _i t _i Represents the t _i The first initial sub-stress data of time, A _imin Representing the minimum value of a plurality of the first initial sub-stress data, A _imax Represents the maximum value in a plurality of the first initial sub-stress data, S ₂ Representing the first sub-stress data;

acquisition of the t _i The second initial sub-stress data of the detection point at the moment is dimensionless, and is obtained through a third formula, wherein the second initial sub-stress data is the t th sub-stress data _i The difference between the stress data of the detection point at the moment and the stress data of the detection point at the initial moment is as follows:

S ₃ ＝(A _i t _i -0)/(A _imax -0)，

wherein the saidS ₃ Representing the second sub-stress data;

acquiring third initial sub-stress data, and carrying out dimensionless treatment on the third initial sub-stress data through a fourth formula to obtain third sub-stress data, wherein the third initial sub-stress data is A-th _i Time of day and A _i-1 The time difference of the moments, the fourth formula is:

S ₄ ＝(A _i t _i -A _imin )/(A _imax -A _imin )，

S ₄ representing the third sub-stress data;

acquiring fourth initial sub-stress data, and carrying out dimensionless treatment on the fourth initial sub-stress data through a fifth formula to obtain fourth sub-stress data, wherein the fourth initial sub-stress data is the L < th > _i The distance between the detection point and the coal face at the moment and the L-th distance _i+1 The difference value of the distance between the detection point and the coal face at the moment is as follows:

S ₅ ＝(L _i t _i -L _imin )/(L _imax -L _imin )，

S ₅ representing the fourth sub-stress data.

4. The method of claim 1, wherein performing feature extraction on the plurality of initial stress data using a PCA algorithm to obtain a plurality of target stress data comprises:

forming a first matrix from the initial stress data according to columns, wherein the dimension of the first matrix is N rows and N columns;

zero-equalizing each row of the first matrix, and calculating a covariance matrix of the first matrix after zero-equalizing;

extracting eigenvalues and eigenvectors of the covariance matrix, wherein the eigenvalues are used for representing the importance degree of the eigenvectors, and the eigenvectors are used for representing the change modes of the initial stress data in different directions;

Sorting the feature vectors according to a preset sequence according to the magnitude of the feature values, and extracting the first M feature vectors to obtain a feature vector matrix, wherein the number of lines of the feature vector matrix is M;

and calculating the product of the first matrix and the eigenvector matrix to obtain a second matrix, wherein the dimension of the second matrix is N rows and M columns, N is greater than M, and the second matrix comprises a plurality of target stress data.

5. The method of claim 1, wherein clustering the plurality of target stress data using a DBSCAN algorithm to obtain a clustered result comprises:

obtaining core points, wherein the number of sample points in the radius of the field of the core points is greater than or equal to the minimum sample number;

classifying the sample points with the distance from the core point being smaller than a preset distance by taking the core point as a center to obtain a plurality of temporary clustering clusters;

any two temporary cluster clusters are extracted to obtain a first temporary cluster and a second temporary cluster;

and extracting any one of the sample points in the first temporary cluster, and merging the first temporary cluster and the second temporary cluster when the extracted sample point is the core point in the first temporary cluster to obtain a cluster until the temporary cluster does not exist.

6. The method of claim 1, wherein after acquiring the plurality of initial stress data, the method further comprises:

determining whether a missing detection point exists in a plurality of detection points, wherein the missing detection point is the detection point with the stress data being empty;

and when the missing detection point exists, supplementing the stress data missing from the missing detection point by adopting an interpolation method according to a plurality of stress data corresponding to a plurality of detection points except the missing detection point.

7. The method of claim 1, wherein determining the stress state of the roadway surrounding rock according to the magnitude relation between the risk and the preset threshold comprises:

determining the stress state of the surrounding rock of the roadway as a first stress state under the condition that the risk is smaller than or equal to a first preset threshold value;

determining the stress state of the surrounding rock of the roadway as a second stress state under the condition that the risk is larger than the first preset threshold and smaller than or equal to a second preset threshold, wherein the first preset threshold is smaller than the second preset threshold, and the stress risk degree of the first stress state is smaller than the risk degree of the second stress state;

Determining the stress state of the surrounding rock of the roadway as a third stress state under the condition that the risk is larger than the second preset threshold and smaller than or equal to a third preset threshold, wherein the second preset threshold is smaller than the third preset threshold, and the stress risk degree of the second stress state is smaller than the risk degree of the third stress state;

and determining the stress state of the surrounding rock of the roadway as a fourth stress state under the condition that the risk is larger than the third preset threshold and smaller than or equal to the fourth preset threshold, wherein the third preset threshold is smaller than the fourth preset threshold, and the stress risk degree of the third stress state is smaller than the risk degree of the fourth stress state.

8. A device for determining the stress state of a roadway surrounding rock, comprising:

the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a plurality of initial stress data, the initial stress data comprise first stress data and second stress data, the first stress data are stress data of a plurality of detection points at the same moment, and the second stress data are stress data of the same detection point at different moments;

The first processing unit is used for carrying out feature extraction on the initial stress data by adopting a PCA algorithm to obtain target stress data, wherein the number of the target stress data is smaller than that of the initial stress data;

the clustering unit is used for clustering the target stress data by adopting a DBSCAN algorithm to obtain a clustering result, wherein the clustering result comprises the number of samples in a clustered cluster and the sample density, and the clustering result corresponds to the clustered cluster one by one;

the second processing unit is used for calculating the risk of each cluster according to the clustering result, wherein the risk is the product of the number of samples and the sample density, and determining the stress state of the surrounding rock of the roadway according to the magnitude relation between the risk and a preset threshold value, and the stress state comprises a safe stress state or a dangerous stress state.

9. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored program, wherein the program when run controls a device in which the computer readable storage medium is located to perform the method of determining the stress state of a roadway surrounding rock according to any one of claims 1 to 7.

10. A system for determining a stress state, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising a method for performing the determination of the stress state of the roadway surrounding rock of any one of claims 1-7.