A method and system for determining the stability grade of roadway surrounding rock based on laser scanning

Abstract

The application provides a roadway surrounding rock stability grade determination method and system based on laser scanning. The method comprises the following steps: acquiring roadway surface topography point cloud data at a preset time length start moment and roadway surface topography point cloud data at a preset time length end moment; preprocessing the roadway surface topography point cloud data to obtain coordinate information of each scattered point block of each tray of the roadway at the start moment and coordinate information of each scattered point block of each tray of the roadway at the end moment; inputting the coordinate information of each scattered point block of each tray of the roadway at the end moment into a pre-trained machine learning model to obtain force information of each tray anchor rod of the roadway at the end moment; determining the surrounding rock deformation amount of each tray position of the roadway within the preset time length; and determining the surrounding rock stability grade of each tray position of the roadway. The technical scheme provided by the application determines the roadway surrounding rock stability grade based on the surrounding rock deformation information and the support force information, thereby improving the accuracy of the surrounding rock stability grade determination.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of roadway support, in particular to a roadway surrounding rock stability grade determination method and system based on laser scanning. BACKGROUND

[0002] With the continuous deepening of mineral resources exploitation, the problem of roadway surrounding rock stability is increasingly prominent. Roadway surrounding rock stability evaluation is an important part of mine safety production. The traditional roadway support design process is to design a support system based on environmental information and numerical simulation methods. After the support is installed, the evaluation of surrounding rock stability is in the initial stage, and in most cases, it is evaluated by visualizing abnormal events such as surrounding rock deformation, anchor rod falling off, and other phenomena. Some complex surrounding rock stability analysis systems rely on geological exploration data, structure surface data and other environmental information, and evaluate them through numerical simulation, machine learning and other means, which is a customized evaluation, not a normalized stability evaluation method. In addition, the roadway support system, especially the anchor rod and anchor support system, is rarely used in the design of surrounding rock stability evaluation method, which makes the existing method less accurate. Therefore, it is urgent to propose a normalized stability determination scheme with higher accuracy. SUMMARY

[0003] The present application provides a roadway surrounding rock stability grade determination method and system based on laser scanning to at least solve the technical problem of low accuracy of the prior art.

[0004] The first aspect embodiment of the present application provides a roadway surrounding rock stability grade determination method based on laser scanning, which comprises:

[0005] Obtaining roadway surface topography point cloud data at a preset time length start time and roadway surface topography point cloud data at a preset time length end time;

[0006] Preprocessing the roadway surface topography point cloud data to obtain coordinate information of each scattered point block of each tray of the roadway at the start time and coordinate information of each scattered point block of each tray of the roadway at the end time;

[0007] Inputting the coordinate information of each scattered point block of each tray of the roadway at the end time into a pre-trained machine learning model to obtain force information of each anchor rod of each tray of the roadway at the end time;

[0008] Determining the surrounding rock deformation amount of each tray position of the roadway within the preset time length according to the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time;

[0009] The stress information of each tray anchor rod of the roadway and the surrounding rock deformation of each tray position of the roadway are used to determine the surrounding rock stability level of each tray position of the roadway.

[0010] Preferably, the training process of the machine learning model comprises:

[0011] The coordinate information of each scatter point block of each tray of the roadway at each time in a historical period and the stress information of each tray anchor rod corresponding to the coordinate information of each scatter point block of each tray of the roadway are acquired.

[0012] The coordinate information of each scatter point block of each tray of the roadway at each time in the historical period is used as input, and the stress information of each tray anchor rod corresponding to the coordinate information of each scatter point block of each tray of the roadway is used as output, and an initial CNN convolutional neural network is trained to obtain a trained machine learning model.

[0013] Further, the surrounding rock deformation of each tray position of the roadway in a preset time period is determined according to the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time, comprising:

[0014] The roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time are registered by using an ICP method to obtain a transformation matrix of the roadway surface topography point cloud data at the start time and a deviation matrix of the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time.

[0015] The surrounding rock deformation of each tray position of the roadway is determined according to the transformation matrix and the deviation matrix.

[0016] Further, the calculation formula of the surrounding rock deformation of each tray position of the roadway is as follows:

[0017] Dis i =||q i -(Rp i +T)||

[0018] In the formula, Dis i is the surrounding rock deformation of the i-th tray position of the roadway, q i is the point cloud data of the i-th tray position of the roadway at the end time, R is the transformation matrix, T is the deviation matrix, and p i is the point cloud data of the i-th tray position of the roadway at the start time.

[0019] Further, the surrounding rock stability level of each tray position of the roadway is determined according to the stress information of each tray anchor rod of the roadway and the surrounding rock deformation of each tray position of the roadway, comprising:

[0020] construct a surrounding rock state coordinate of each tray position of the roadway based on force information of each tray anchor rod of the roadway and a surrounding rock deformation amount of each tray position of the roadway;

[0021] classify the surrounding rock state coordinates of each tray position of the roadway unsupervised by a support vector machine method according to a preset number of classification clusters, to obtain each surrounding rock state coordinate after clustering;

[0022] classify each surrounding rock state coordinate after clustering by a two-dimensional quadrant method, to obtain a surrounding rock state coordinate classification result of each tray position of the roadway;

[0023] determine a surrounding rock stability level of each tray position of the roadway based on the surrounding rock state coordinate classification result;

[0024] The force information is a horizontal coordinate of the surrounding rock state coordinate, and the surrounding rock deformation amount is a vertical coordinate of the surrounding rock state coordinate.

[0025] Further, the surrounding rock state coordinate classification result includes: Class I, Class II, Class III, and Class IV.

[0026] Further, the determination of the surrounding rock stability level of each tray position of the roadway based on the surrounding rock state coordinate classification result includes:

[0027] when the classification result of the surrounding rock state coordinate is Class I, the surrounding rock stability level corresponding to the surrounding rock state coordinate is a support failure level;

[0028] when the classification result of the surrounding rock state coordinate is Class II, the surrounding rock stability level corresponding to the surrounding rock state coordinate is a support deficiency level;

[0029] when the classification result of the surrounding rock state coordinate is Class III, the surrounding rock stability level corresponding to the surrounding rock state coordinate is a support excess level;

[0030] when the classification result of the surrounding rock state coordinate is Class IV, the surrounding rock stability level corresponding to the surrounding rock state coordinate is a support reasonable level.

[0031] The second aspect embodiment of the application provides a roadway surrounding rock stability level determination system based on laser scanning, comprising:

[0032] an acquisition module configured to acquire roadway surface topography point cloud data at a preset start time and roadway surface topography point cloud data at a preset end time;

[0033] a preprocessing module configured to preprocess the roadway surface topography point cloud data to obtain coordinate information of each scatter point block of each tray of the roadway at the start time and coordinate information of each scatter point block of each tray of the roadway at the end time.

[0034] a first determining module, configured to input coordinate information of each scattered point block of each tray of the roadway at the end time into a machine learning model trained in advance to obtain force information of each anchor rod of each tray of the roadway at the end time;

[0035] a second determining module, configured to determine a surrounding rock deformation amount of each tray position of the roadway within a preset time period according to the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time;

[0036] a third determining module, configured to determine a surrounding rock stability level of each tray position of the roadway according to the force information of each anchor rod of each tray of the roadway and the surrounding rock deformation amount of each tray position of the roadway.

[0037] The third aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement the method of the first aspect.

[0038] The fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the method of the first aspect.

[0039] The technical scheme provided by the embodiments of the present application at least brings the following beneficial effects:

[0040] The present application provides a roadway surrounding rock stability level determination method and system based on laser scanning, which comprises the following steps: obtaining roadway surface topography point cloud data at a start time of a preset time period and roadway surface topography point cloud data at an end time of the preset time period; preprocessing the roadway surface topography point cloud data to obtain coordinate information of each scattered point block of each tray of the roadway at the start time and coordinate information of each scattered point block of each tray of the roadway at the end time; inputting the coordinate information of each scattered point block of each tray of the roadway at the end time into a machine learning model trained in advance to obtain force information of each anchor rod of each tray of the roadway at the end time; determining a surrounding rock deformation amount of each tray position of the roadway within a preset time period according to the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time; and determining a surrounding rock stability level of each tray position of the roadway according to the force information of each anchor rod of each tray of the roadway and the surrounding rock deformation amount of each tray position of the roadway. The technical scheme provided by the present application determines the roadway surrounding rock stability level based on the surrounding rock deformation information and the support force information, thereby improving the accuracy of the surrounding rock stability level determination.

[0041] Additional aspects and advantages of the present application will be made apparent by the following description and the appended claims. BRIEF DESCRIPTION OF DRAWINGS

[0042] The above and / or additional aspects and advantages of the present application will become apparent and be more readily understood from the following description, by reference to which:

[0043] Figure 1 A flow chart of a method for determining a stability grade of a surrounding rock of a roadway based on laser scanning according to an embodiment of the present application;

[0044] Figure 2 A point cloud diagram of a tray and a surrounding rock according to an embodiment of the present application;

[0045] Figure 3 A force information diagram of each anchor rod according to an embodiment of the present application;

[0046] Figure 4 A classification result diagram according to an embodiment of the present application;

[0047] Figure 5 A structure diagram of a system for determining a stability grade of a surrounding rock of a roadway based on laser scanning according to an embodiment of the present application. DETAILED DESCRIPTION

[0048] Embodiments of the present application are described in detail below with reference to the attached drawings, which are meant to be exemplary and not limiting.

[0049] This application proposes a method and system for determining the stability level of roadway surrounding rock based on laser scanning. The method includes: acquiring point cloud data of roadway surface topography at the start and end of a preset time period; preprocessing the point cloud data to obtain coordinate information of scattered points of each tray at the start and end of the roadway; inputting the coordinate information of scattered points of each tray at the end of the roadway into a pre-trained machine learning model to obtain the force information of the anchor bolts of each tray at the end of the roadway; determining the surrounding rock deformation at the location of each tray within the preset time period based on the point cloud data of roadway surface topography at the start and end of the roadway; and determining the surrounding rock stability level at the location of each tray based on the force information of the anchor bolts of each tray and the surrounding rock deformation at the location of each tray. The technical solution proposed in this application determines the stability level of the surrounding rock in the roadway based on the deformation information of the surrounding rock itself and the stress information of the support, thereby improving the accuracy of the determination of the stability level of the surrounding rock.

[0050] The following describes a method and system for determining the stability level of roadway surrounding rock based on laser scanning, with reference to the accompanying drawings.

[0051] Example 1

[0052] Figure 1 This is a flowchart illustrating a method for determining the stability level of roadway surrounding rock based on laser scanning, according to an embodiment of this application. Figure 1 As shown, the method includes:

[0053] Step 1: Obtain the point cloud data of the roadway surface topography at the start time of the preset duration and the point cloud data of the roadway surface topography at the end time of the preset duration;

[0054] It should be noted that a three-dimensional laser scanning device was used to scan the surrounding rock of the tunnel multiple times to obtain point cloud data of the tunnel surface morphology at different times.

[0055] Step 2: Preprocess the point cloud data of the roadway surface topography to obtain the coordinate information of each scattered point block of each tray in the roadway at the start time and the coordinate information of each scattered point block of each tray in the roadway at the end time.

[0056] It should be noted that the roadway surface topography point cloud data is processed using a roadway support component identification and segmentation method based on 3D point cloud data, namely target detection and segmentation technology. This process extracts the position and 3D surface topography information of the roadway's full-section anchor bolt and cable group, i.e., the xyz coordinates of each point cloud on the tray. Figure 2 As shown, the light-colored areas correspond to the surrounding rock point cloud, and the dark-colored areas correspond to the tray point cloud.

[0057] Step 3: input the coordinate information of each scattered point block of each tray of the roadway at the end time into the pre-trained machine learning model to obtain the force information of each anchor rod of each tray of the roadway at the end time, as shown in the following table. Figure 3 The force information of each anchor rod is shown in the table.

[0058] It should be noted that the input form is a point cloud matrix, and the form is N*3, N represents the number of tray point clouds, and 3 represents x, y, and z coordinates.

[0059] In the embodiments of the present disclosure, the training process of the machine learning model comprises:

[0060] obtaining the coordinate information of each scattered point block of each tray of the roadway at each time in a historical period and the force information of each anchor rod corresponding to the coordinate information of each scattered point block of each tray of the roadway;

[0061] taking the coordinate information of each scattered point block of each tray of the roadway at each time in the historical period as input and taking the force information of each anchor rod corresponding to the coordinate information of each scattered point block of each tray of the roadway as output, training an initial CNN convolutional neural network to obtain a trained machine learning model.

[0062] Step 4: determining the surrounding rock deformation of each tray position of the roadway within a preset time period according to the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time;

[0063] In the embodiments of the present disclosure, the step 4 specifically comprises:

[0064] 4.1 registering the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time by using an ICP method to obtain a transformation matrix of the roadway surface topography point cloud data at the start time and a deviation matrix of the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time;

[0065] It should be noted that the point cloud data at different times is registered based on the ICP method, as shown in the following formula. The optimal transformation matrix is obtained by continuously iterating R and T.

[0066] wherein k is the total number of point clouds, represents the modulus of a vector;

[0067] 4.2 determining the surrounding rock deformation of each tray position of the roadway according to the transformation matrix and the deviation matrix.

[0068] Further, the calculation formula of the surrounding rock deformation of each tray position of the roadway is as follows:

[0069] Dis i ||q i -(Rp i +T)||

[0070] In the formula, Dis i is the deformation of the surrounding rock of the i-th tray position of the roadway, q i is the point cloud data of the i-th tray position of the roadway at the end time, R is a transformation matrix, T is a deviation matrix, and p i is the point cloud data of the i-th tray position of the roadway at the start time.

[0071] Step 5: determining the surrounding rock stability level of each tray position of the roadway according to the force information of each tray anchor rod of the roadway and the deformation of the surrounding rock of each tray position of the roadway.

[0072] In the embodiment of the present disclosure, the step 5 specifically comprises:

[0073] 5.1 constructing the surrounding rock state coordinates of each tray position of the roadway based on the force information of each tray anchor rod of the roadway and the deformation of the surrounding rock of each tray position of the roadway; wherein the force information is the horizontal coordinate of the surrounding rock state coordinates, and the deformation of the surrounding rock is the vertical coordinate of the surrounding rock state coordinates.

[0074] 5.2 performing unsupervised classification on the surrounding rock state coordinates of each tray position of the roadway according to a preset number of classification clusters and through a support vector machine method to obtain each surrounding rock state coordinate after clustering;

[0075] 5.3 classifying each surrounding rock state coordinate after clustering through a two-dimensional quadrant method to obtain a classification result of the surrounding rock state coordinates of each tray position of the roadway.

[0076] It should be noted that the classification result of the surrounding rock state coordinates comprises: class I, class II, class III, and class IV.

[0077] 5.4 determining the surrounding rock stability level of each tray position of the roadway based on the classification result of the surrounding rock state coordinates.

[0078] Further, the determination of the surrounding rock stability level of each tray position of the roadway based on the classification result of the surrounding rock state coordinates comprises:

[0079] when the classification result of the surrounding rock state coordinates is class I, the surrounding rock stability level corresponding to the surrounding rock state coordinates is a support failure level;

[0080] when the classification result of the surrounding rock state coordinates is class II, the surrounding rock stability level corresponding to the surrounding rock state coordinates is a support deficiency level;

[0081] When the classification result of the surrounding rock state coordinate is type III, the surrounding rock stability level corresponding to the surrounding rock state coordinate is a support excess level.

[0082] When the classification result of the surrounding rock state coordinate is type IV, the surrounding rock stability level corresponding to the surrounding rock state coordinate is a support reasonable level.

[0083] It should be noted that, in combination with the roadway full-face bolt stress state and the surrounding rock deformation at the corresponding position, the surrounding rock stability is classified by using the two-dimensional quadrant method and the support vector machine method. The roadway full-face bolt stress is taken as the horizontal coordinate, and the surrounding rock deformation at the position of the tray is taken as the vertical coordinate. The obtained coordinate is called the surrounding rock state coordinate. Then, the surrounding rock state coordinate can be classified unsupervised by using the support vector machine method. The number of preset classification clusters is 4. The classification result can also be obtained by the experience of roadway support under similar geological conditions. Then, the horizontal and vertical coordinate classification threshold values can be obtained, and the two-dimensional quadrant method segmentation label and the surrounding rock state coordinate classification result can be obtained. The horizontal and vertical coordinate classification threshold values can be obtained by the support vector machine method, the preset classification number is 4, then the point aggregation degree is separated, and then the mean value of the horizontal and vertical coordinates of the center of each class can be used as the threshold value. The threshold value can also be obtained by the experience of engineers.

[0084] The classification result is as shown in Figure 4 The type I represents a support failure area. At this time, the surrounding rock deformation is large, and the support stress is relatively small. This means that the support system is not up to standard or the installation depth is insufficient, and thus the surrounding rock has the highest risk of roof fall. The type II represents a support insufficient area. At this time, the surrounding rock deformation is large, and the support stress is also large. This means that the support system plays a role, but is easy to be damaged, and thus additional support is needed. At this time, the surrounding rock is in a potential roof fall risk area. The type III represents a support excess area. The surrounding rock deformation is small, and the support stress is also small. At this time, the support system is far from reaching the bearing limit, and thus the surrounding rock has no risk of roof fall. However, the support density can be reduced under similar conditions in the future. The type IV represents a support reasonable area. The surrounding rock deformation is small, and the support stress is in a good state. Thus, the surrounding rock has no risk of roof fall, and the support system is designed reasonably.

[0085] To sum up, the method for determining the surrounding rock stability level of a roadway based on laser scanning provided in the embodiment determines the surrounding rock stability level of a roadway based on the deformation information and support stress information of the surrounding rock, and improves the accuracy of the determination of the surrounding rock stability level.

[0086] Embodiment Two

[0087] Figure 5 The structure diagram of a system for determining the surrounding rock stability level of a roadway based on laser scanning provided according to an embodiment of the present application is as shown in Figure 5 The system comprises:

[0088] The acquisition module 100 is configured to acquire roadway surface topography point cloud data at a preset time length start moment and roadway surface topography point cloud data at a preset time length end moment.

[0089] The preprocessing module 200 is configured to preprocess the roadway surface topography point cloud data to obtain coordinate information of each scattered point block of each tray of the roadway at the start moment and coordinate information of each scattered point block of each tray of the roadway at the end moment.

[0090] The first determination module 300 is configured to input the coordinate information of each scattered point block of each tray of the roadway at the end moment into a pre-trained machine learning model to obtain force information of each anchor rod of each tray of the roadway at the end moment.

[0091] The training process of the machine learning model includes:

[0092] The coordinate information of each scattered point block of each tray of the roadway at each moment in a historical period and force information of each anchor rod corresponding to the coordinate information of each scattered point block of each tray of the roadway are acquired.

[0093] The coordinate information of each scattered point block of each tray of the roadway at each moment in the historical period is taken as input, and the force information of each anchor rod corresponding to the coordinate information of each scattered point block of each tray of the roadway is taken as output, and an initial CNN convolutional neural network is trained to obtain the trained machine learning model.

[0094] The second determination module 400 is configured to determine a surrounding rock deformation amount of each tray position of the roadway in the preset time length according to the roadway surface topography point cloud data at the start moment and the roadway surface topography point cloud data at the end moment.

[0095] The third determination module 500 is configured to determine a surrounding rock stability level of each tray position of the roadway according to the force information of each anchor rod of each tray of the roadway and the surrounding rock deformation amount of each tray position of the roadway.

[0096] In the embodiments of the present disclosure, the second determination module 400 is further configured to:

[0097] The ICP method is used to register the roadway surface topography point cloud data at the start moment and the roadway surface topography point cloud data at the end moment to obtain a transformation matrix of the roadway surface topography point cloud data at the start moment and a deviation matrix of the roadway surface topography point cloud data at the start moment and the roadway surface topography point cloud data at the end moment.

[0098] The surrounding rock deformation amount of each tray position of the roadway is determined according to the transformation matrix and the deviation matrix.

[0099] Wherein, the calculation formula of the surrounding rock deformation of each tray position of the roadway is as follows:

[0100] Dis i = || q i -(Rp i +T)|

[0101] In the formula, Dis i is the surrounding rock deformation of the i-th tray position of the roadway, q i is the point cloud data of the i-th tray position of the roadway at the end time, R is a transformation matrix, T is a bias matrix, and p i is the point cloud data of the i-th tray position of the roadway at the start time.

[0102] In the embodiment of the present disclosure, the third determination module 500 is further configured to:

[0103] construct the surrounding rock state coordinates of each tray position of the roadway based on the stress information of each tray anchor rod of the roadway and the surrounding rock deformation of each tray position of the roadway;

[0104] perform unsupervised classification on the surrounding rock state coordinates of each tray position of the roadway according to a preset number of classification clusters and by using a support vector machine method, to obtain each surrounding rock state coordinate after clustering;

[0105] classify each surrounding rock state coordinate after clustering by using a two-dimensional quadrant method, to obtain a classification result of the surrounding rock state coordinates of each tray position of the roadway;

[0106] determine the surrounding rock stability level of each tray position of the roadway based on the classification result of the surrounding rock state coordinates;

[0107] In the formula, the stress information is the horizontal coordinate of the surrounding rock state coordinates, and the surrounding rock deformation is the vertical coordinate of the surrounding rock state coordinates.

[0108] The classification result of the surrounding rock state coordinates includes: Class I, Class II, Class III, and Class IV.

[0109] Further, the third determination module 500 is further configured to:

[0110] when the classification result of the surrounding rock state coordinates is Class I, the surrounding rock stability level corresponding to the surrounding rock state coordinates is a support failure level;

[0111] when the classification result of the surrounding rock state coordinates is Class II, the surrounding rock stability level corresponding to the surrounding rock state coordinates is a support deficiency level;

[0112] when the classification result of the surrounding rock state coordinates is Class III, the surrounding rock stability level corresponding to the surrounding rock state coordinates is a support excess level.

[0113] When the classification result of the surrounding rock state coordinate is class IV, the surrounding rock stability level corresponding to the surrounding rock state coordinate is a support reasonable level.

[0114] To sum up, the roadway surrounding rock stability level determination system based on laser scanning provided in the embodiment determines the roadway surrounding rock stability level based on the surrounding rock deformation information and support stress information, and improves the accuracy of the surrounding rock stability level determination.

[0115] Embodiment three

[0116] In order to realize the above-mentioned embodiment, the present disclosure further provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to realize the method of the embodiment one.

[0117] Embodiment four

[0118] In order to realize the above-mentioned embodiment, the present disclosure further provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the method of the embodiment one.

[0119] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any suitable manner in any one or more embodiments or examples. In addition, the skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0120] Any process or method descriptions in flow charts or described elsewhere herein can be understood as representing code modules, segments, or portions of code which include one or more executable instructions for implementing specific logic functions (or steps) in the process, and the preferred embodiments of the application include additional implementations in which the order of steps can differ from those shown or discussed, including a step can occur at similar times implementing functions in a manner different from that shown or discussed, including according to the function involved, as will be appreciated by those skilled in the art.

[0121] Although the embodiments of the present application have been shown and described above, it is understood that the above-described embodiments are exemplary and are not to be construed as limiting the present application, and that changes, modifications, substitutions and variations can be made by those skilled in the art without departing from the scope of the present application.

Claims

1. A method for determining the stability grade of a roadway surrounding rock based on laser scanning, characterized in that, The method comprises: obtaining roadway surface topography point cloud data at a preset time length start time and roadway surface topography point cloud data at a preset time length end time; preprocessing the roadway surface topography point cloud data to obtain coordinate information of each scattered point block of each tray of the roadway at the start time and coordinate information of each scattered point block of each tray of the roadway at the end time; inputting the coordinate information of each scattered point block of each tray of the roadway at the end time into a pre-trained machine learning model to obtain force information of each anchor rod of each tray of the roadway at the end time; determining a surrounding rock deformation amount of each tray position of the roadway within a preset time length according to the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time; determining a surrounding rock stability level of each tray position of the roadway according to the force information of each anchor rod of each tray of the roadway and the surrounding rock deformation amount of each tray position of the roadway; wherein the determination of the surrounding rock deformation amount of each tray position of the roadway within a preset time length according to the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time comprises: aligning the roadway surface topography point cloud data at the start time with the roadway surface topography point cloud data at the end time by using an ICP method to obtain a transformation matrix of the roadway surface topography point cloud data at the start time and a deviation matrix of the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time; determining the surrounding rock deformation amount of each tray position of the roadway according to the transformation matrix and the deviation matrix; the determination of the surrounding rock stability level of each tray position of the roadway according to the force information of each anchor rod of each tray of the roadway and the surrounding rock deformation amount of each tray position of the roadway comprises: constructing a surrounding rock state coordinate of each tray position of the roadway based on the force information of each anchor rod of each tray of the roadway and the surrounding rock deformation amount of each tray position of the roadway; performing unsupervised classification on the surrounding rock state coordinate of each tray position of the roadway according to a preset number of classification clusters and by using a support vector machine method to obtain each clustered surrounding rock state coordinate; classifying each clustered surrounding rock state coordinate by using a two-dimensional quadrant method to obtain a surrounding rock state coordinate classification result of each tray position of the roadway; determining the surrounding rock stability level of each tray position of the roadway based on the surrounding rock state coordinate classification result; wherein the force information is a horizontal coordinate of a surrounding rock state coordinate, and the surrounding rock deformation amount is a vertical coordinate of a surrounding rock state coordinate.

2. The method of claim 1, wherein, The training process of the machine learning model comprises: obtaining coordinate information of each scattered point block of each tray of the roadway at each time within a historical period and force information of each tray anchor corresponding to the coordinate information of each scattered point block of each tray of the roadway; training an initial CNN convolutional neural network by taking the coordinate information of each scattered point block of each tray of the roadway at each time within the historical period as input and taking the force information of each tray anchor corresponding to the coordinate information of each scattered point block of each tray of the roadway as output to obtain a trained machine learning model.

3. The method of claim 2, wherein, The calculation formula of the surrounding rock deformation amount of each tray position of the roadway is as follows: In the formula, is the surrounding rock deformation of the i-th tray position of the roadway, is the point cloud data of the i-th tray position of the roadway at the end time, is the transformation matrix, is the deviation matrix, is the point cloud data of the i-th tray position of the roadway at the start time.

4. The method of claim 3, wherein, The surrounding rock state coordinate classification result comprises: Class I, Class II, Class III, and Class IV.

5. The method of claim 4, wherein, The surrounding rock stability level of each tray position of the roadway is determined based on the surrounding rock state coordinate classification result, comprising: when the classification result of the surrounding rock state coordinate is Class I, the surrounding rock stability level corresponding to the surrounding rock state coordinate is a support failure level; when the classification result of the surrounding rock state coordinate is Class II, the surrounding rock stability level corresponding to the surrounding rock state coordinate is a support deficiency level; when the classification result of the surrounding rock state coordinate is Class III, the surrounding rock stability level corresponding to the surrounding rock state coordinate is a support excess level; when the classification result of the surrounding rock state coordinate is Class IV, the surrounding rock stability level corresponding to the surrounding rock state coordinate is a support reasonable level.

6. A laser scanning-based system for determining the stability grade of a surrounding rock of a roadway, characterized by, The system comprises: an acquisition module configured to acquire roadway surface topography point cloud data at a preset time length start time and roadway surface topography point cloud data at a preset time length end time; a preprocessing module configured to preprocess the roadway surface topography point cloud data to obtain coordinate information of each scatter point block of each tray of the roadway at the start time and coordinate information of each scatter point block of each tray of the roadway at the end time; a first determination module configured to input the coordinate information of each scatter point block of each tray of the roadway at the end time into a pre-trained machine learning model to obtain force information of an anchor rod of each tray of the roadway at the end time; a second determination module configured to determine a surrounding rock deformation amount of each tray position of the roadway within a preset time length based on the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time; a third determination module configured to determine a surrounding rock stability level of each tray position of the roadway based on the force information of the anchor rod of each tray of the roadway and the surrounding rock deformation amount of each tray position of the roadway; wherein the determination of the surrounding rock deformation amount of each tray position of the roadway within a preset time length based on the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time comprises: aligning the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time by using an ICP method to obtain a transformation matrix of the roadway surface topography point cloud data at the start time and a deviation matrix of the roadway surface topography point cloud data at the start time and the roadway surface topography point cloud data at the end time; determining the surrounding rock deformation amount of each tray position of the roadway based on the transformation matrix and the deviation matrix; the determination of the surrounding rock stability level of each tray position of the roadway based on the force information of the anchor rod of each tray of the roadway and the surrounding rock deformation amount of each tray position of the roadway comprises: constructing a surrounding rock state coordinate of each tray position of the roadway based on the force information of the anchor rod of each tray of the roadway and the surrounding rock deformation amount of each tray position of the roadway; performing unsupervised classification on the surrounding rock state coordinate of each tray position of the roadway by a support vector machine method according to a preset number of classification clusters to obtain each surrounding rock state coordinate after clustering. The two-dimensional quadrant method is used to classify the surrounding rock state coordinates of each cluster, to obtain the surrounding rock state coordinate classification results of each tray position of the roadway; The surrounding rock stability grade of each tray position of the roadway is determined based on the surrounding rock state coordinate classification results. The stress information is the horizontal coordinate of the surrounding rock state coordinate, and the surrounding rock deformation is the vertical coordinate of the surrounding rock state coordinate.

7. An electronic device, comprising: The method comprises: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein when the processor executes the program, the method according to any one of claims 1-5 is implemented.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method according to any one of claims 1-5.

Images