Roadway surrounding rock stability grade determination method and system based on laser scanning

Abstract

The invention provides a roadway surrounding rock stability grade determination method and system based on laser scanning. The method comprises the steps that roadway surface topography point cloud data at the starting moment of a preset duration and roadway surface topography point cloud data at the ending moment of the preset duration are acquired; preprocessing the roadway surface topography point cloud data to obtain coordinate information of each scatter block of each pallet of the roadway at a starting moment and coordinate information of each scatter block of each pallet of the roadway at an ending moment; inputting the coordinate information of each scatter block of each tray of the roadway at the end moment into a pre-trained machine learning model to obtain stress information of each tray anchor rod of the roadway at the end moment; determining the surrounding rock deformation of each tray position of the roadway within a preset time length; and determining the surrounding rock stability grade of each pallet position of the roadway. According to the technical scheme, the roadway surrounding rock stability grade is determined based on the surrounding rock deformation information and the support stress information, and the accuracy of determining the surrounding rock stability grade is improved.

Description

Technical Field

[0001] The present application relates to the technical field of tunnel support, and in particular to a method and system for determining the stability grade of tunnel surrounding rock based on laser scanning. Background Art

[0002] With the continuous deepening of mineral resource mining, the stability problem of tunnel surrounding rock has become increasingly prominent. Tunnel surrounding rock stability evaluation is an important part of mine safety production. The traditional tunnel support design process is to design the support system based on environmental information and numerical simulation and other methods. After the support is installed, the evaluation of surrounding rock stability is in the original stage. In most cases, it is evaluated by visual abnormal events, such as increased deformation of surrounding rock and bolt shedding. Some complex surrounding rock stability analysis systems rely on geological exploration data, structural surface data and other environmental information, and evaluate them through numerical simulation, machine learning and other means. It is a customized evaluation rather than a normalized stability evaluation method. In addition, tunnel support systems, especially anchor and cable support systems, as important systems for maintaining surrounding rock stability, are rarely used in the design of surrounding rock stability evaluation methods, making the existing methods less accurate. Therefore, it is urgent to propose a normalized stability determination scheme with higher accuracy. Summary of the invention

[0003] The present application provides a method and system for determining the stability grade of tunnel surrounding rock based on laser scanning, so as to at least solve the technical problem of low accuracy in the prior art.

[0004] The first embodiment of the present application proposes a method for determining the stability grade of surrounding rock of a tunnel based on laser scanning, the method comprising:

[0005] Acquire the tunnel surface morphology point cloud data at the start time of the preset time length and the tunnel surface morphology point cloud data at the end time of the preset time length;

[0006] Preprocessing the lane surface morphology point cloud data to obtain coordinate information of each scattered point block of each pallet in the lane at the start time and coordinate information of each scattered point block of each pallet in the lane at the end time;

[0007] Input the coordinate information of each scattered point block of each pallet in the lane at the end time into a pre-trained machine learning model to obtain the force information of the anchor rods of each pallet in the lane at the end time;

[0008] Determine the surrounding rock deformation at each tray position of the lane within a preset time period according to the lane surface morphology point cloud data at the start time and the lane surface morphology point cloud data at the end time;

[0009] The surrounding rock stability level of each tray position in the tunnel is determined according to the force information of each tray anchor rod in the tunnel and the deformation of the surrounding rock at each tray position in the tunnel.

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

[0011] Obtaining coordinate information of each scattered point block of each pallet in the lane at each moment in the historical period and force information of each pallet anchor rod corresponding to the coordinate information of each scattered point block of each pallet in the lane;

[0012] Taking the coordinate information of each scattered point block of each pallet in the lane at each moment in the historical period as input, and taking the force information of each pallet anchor rod corresponding to the coordinate information of each scattered point block of each pallet in the lane as output, the initial CNN convolutional neural network is trained to obtain a trained machine learning model.

[0013] Further, the method of determining the deformation of the surrounding rock at each tray position of the tunnel within a preset time period according to the tunnel surface morphology point cloud data at the start time and the tunnel surface morphology point cloud data at the end time includes:

[0014] Using the ICP method, the tunnel surface morphology point cloud data at the start time is registered with the tunnel surface morphology point cloud data at the end time, to obtain a transformation matrix of the tunnel surface morphology point cloud data at the start time and a deviation matrix between the tunnel surface morphology point cloud data at the start time and the tunnel surface morphology point cloud data at the end time;

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

[0016] Furthermore, the calculation formula for the surrounding rock deformation at each tray position in the tunnel is as follows:

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

[0018] Where, Dis i is the deformation of the surrounding rock at the i-th tray position in the tunnel, q i is the point cloud data of the i-th pallet position in the lane at the end time, R is the transformation matrix, T is the deviation matrix, and p i It is the point cloud data of the i-th pallet position in the lane at the starting time.

[0019] Further, the determining of the surrounding rock stability level at each position of the tray in the tunnel according to the force information of each tray anchor rod in the tunnel and the deformation of the surrounding rock at each position of the tray in the tunnel includes:

[0020] Constructing the surrounding rock state coordinates of each pallet position in the tunnel based on the force information of each pallet anchor rod in the tunnel and the deformation of the surrounding rock at each pallet position in the tunnel;

[0021] According to the preset number of classification clusters, the surrounding rock state coordinates of each pallet position in the tunnel are unsupervisedly classified by a support vector machine method to obtain clustered surrounding rock state coordinates;

[0022] The clustered surrounding rock state coordinates are classified using a two-dimensional quadrant method to obtain classification results of the surrounding rock state coordinates at each tray position in the tunnel;

[0023] Determine the surrounding rock stability level of each tray position in the tunnel based on the surrounding rock state coordinate classification result;

[0024] The force 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.

[0025] Furthermore, the surrounding rock state coordinate classification results include: Class I, Class II, Class III, and Class IV.

[0026] Further, the determining of the surrounding rock stability level of each pallet position in the tunnel based on the surrounding rock state coordinate classification result includes:

[0027] 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 the support failure level;

[0028] 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 the insufficient support level;

[0029] 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 the support excess level;

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

[0031] The second embodiment of the present application proposes a system for determining the stability grade of surrounding rock in a tunnel based on laser scanning, comprising:

[0032] An acquisition module, used to acquire the tunnel surface morphology point cloud data at the start time of a preset time length and the tunnel surface morphology point cloud data at the end time of the preset time length;

[0033] A preprocessing module, used to preprocess the lane surface morphology point cloud data to obtain the coordinate information of each scattered point block of each pallet in the lane at the start time and the coordinate information of each scattered point block of each pallet in the lane at the end time;

[0034] A first determination module is used to input the coordinate information of each scattered point block of each pallet in the lane at the end time into a pre-trained machine learning model to obtain the force information of the anchor rods of each pallet in the lane at the end time;

[0035] A second determination module is used to determine the surrounding rock deformation at each tray position of the lane within a preset time period according to the lane surface morphology point cloud data at the start time and the lane surface morphology point cloud data at the end time;

[0036] The third determination module is used to determine the surrounding rock stability level of each tray position in the tunnel according to the force information of each tray anchor rod in the tunnel and the surrounding rock deformation at each tray position in the tunnel.

[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, wherein when the processor executes the program, the method described in the first aspect is implemented.

[0038] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect of the present application.

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

[0040] The present application proposes a method and system for determining the stability grade of tunnel surrounding rock based on laser scanning, the method comprising: obtaining tunnel surface morphology point cloud data at the start time of a preset time length and tunnel surface morphology point cloud data at the end time of the preset time length; preprocessing the tunnel surface morphology point cloud data to obtain coordinate information of each scattered point block of each tray in the tunnel at the start time and coordinate information of each scattered point block of each tray in the tunnel at the end time; inputting the coordinate information of each scattered point block of each tray in the tunnel at the end time into a pre-trained machine learning model to obtain force information of anchor rods of each tray in the tunnel at the end time; determining the surrounding rock deformation at each tray position in the tunnel within the preset time length according to the tunnel surface morphology point cloud data at the start time and the tunnel surface morphology point cloud data at the end time; determining the surrounding rock stability grade at each tray position in the tunnel according to the force information of the anchor rods of each tray in the tunnel and the surrounding rock deformation at each tray position in the tunnel. The technical solution proposed in this application determines the stability grade of the tunnel surrounding rock based on the surrounding rock's own deformation information and support force information, thereby improving the accuracy of determining the surrounding rock stability grade.

[0041] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

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

[0044] Figure 2 A point cloud schematic diagram of a pallet and surrounding rocks provided according to an embodiment of the present application;

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

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

[0047] Figure 5 The present invention is a structural diagram of a system for determining the stability grade of surrounding rock in a tunnel 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, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0049] The present application proposes a method and system for determining the stability grade of tunnel surrounding rock based on laser scanning, the method comprising: obtaining tunnel surface morphology point cloud data at the start time of a preset time length and the tunnel surface morphology point cloud data at the end time of the preset time length; preprocessing the tunnel surface morphology point cloud data to obtain the coordinate information of each scattered point block of each tray in the tunnel at the start time and the coordinate information of each scattered point block of each tray in the tunnel at the end time; inputting the coordinate information of each scattered point block of each tray in the tunnel at the end time into a pre-trained machine learning model to obtain the force information of the anchor rod of each tray in the tunnel at the end time; determining the surrounding rock deformation at the position of each tray in the tunnel within the preset time length according to the tunnel surface morphology point cloud data at the start time and the tunnel surface morphology point cloud data at the end time; determining the surrounding rock stability grade of each tray position in the tunnel according to the force information of the anchor rod of each tray in the tunnel and the surrounding rock deformation at the position of each tray in the tunnel. The technical solution proposed in this application determines the stability grade of the tunnel surrounding rock based on the surrounding rock's own deformation information and support force information, thereby improving the accuracy of determining the surrounding rock stability grade.

[0050] A method and system for determining the stability grade of surrounding rock in a tunnel based on laser scanning according to an embodiment of the present application will be described below with reference to the accompanying drawings.

[0051] Embodiment 1

[0052] Figure 1 Flow chart of a method for determining the stability grade of tunnel surrounding rock based on laser scanning according to one embodiment of the present application, as shown in FIG. Figure 1 As shown, the method includes:

[0053] Step 1: Obtaining the tunnel surface morphology point cloud data at the start time of the preset time length and the tunnel surface morphology point cloud data at the end time of the preset time length;

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

[0055] Step 2: pre-processing the lane surface morphology point cloud data to obtain the coordinate information of each scattered point block of each pallet in the lane at the start time and the coordinate information of each scattered point block of each pallet in the lane at the end time;

[0056] It should be noted that the tunnel support component recognition and segmentation method for three-dimensional point cloud data, namely, the target detection and segmentation technology, is used to process the tunnel surface morphology point cloud data to extract the position of the full-section anchor bolt group and the surface three-dimensional morphology information, namely, the xyz coordinates of each point cloud of the tray, such as Figure 2 As shown, the light-colored area corresponds to the surrounding rock point cloud, and the dark-colored area corresponds to the pallet point cloud.

[0057] Step 3: Input the coordinate information of each scattered point block of each pallet in the lane at the end time into the pre-trained machine learning model to obtain the force information of the anchor rods of each pallet in the lane at the end time, such as Figure 3 As shown, the force information of each anchor rod.

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

[0059] In the embodiment of the present disclosure, the training process of the machine learning model includes:

[0060] Obtaining coordinate information of each scattered point block of each pallet in the lane at each moment in the historical period and force information of each pallet anchor rod corresponding to the coordinate information of each scattered point block of each pallet in the lane;

[0061] Taking the coordinate information of each scattered point block of each pallet in the lane at each moment in the historical period as input, and taking the force information of each pallet anchor rod corresponding to the coordinate information of each scattered point block of each pallet in the lane as output, the initial CNN convolutional neural network is trained to obtain a trained machine learning model.

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

[0063] In the embodiment of the present disclosure, step 4 specifically includes:

[0064] 4.1 Using the ICP method, the tunnel surface morphology point cloud data at the start time is registered with the tunnel surface morphology point cloud data at the end time, and a transformation matrix of the tunnel surface morphology point cloud data at the start time and a deviation matrix of the tunnel surface morphology point cloud data at the start time and the tunnel surface morphology point cloud data at the end time are obtained;

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

[0066] Among them, k is the total number of points in the point cloud, It means to find the magnitude of a vector;

[0067] 4.2 Determine the surrounding rock deformation at each tray position in the tunnel based on the transformation matrix and the deviation matrix.

[0068] Furthermore, the calculation formula for the surrounding rock deformation at each tray position in the tunnel is as follows:

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

[0070] Where, Dis i is the deformation of the surrounding rock at the i-th tray position in the tunnel, q i is the point cloud data of the i-th pallet position in the lane at the end time, R is the transformation matrix, T is the deviation matrix, and p i It is the point cloud data of the i-th pallet position in the lane at the starting time.

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

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

[0073] 5.1 Based on the force information of each pallet anchor rod in the tunnel and the surrounding rock deformation at each pallet position in the tunnel, the surrounding rock state coordinates of each pallet position in the tunnel are constructed; wherein the force 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.

[0074] 5.2 According to the preset number of classification clusters, the surrounding rock state coordinates of each pallet position in the tunnel are unsupervisedly classified by the support vector machine method to obtain the clustered surrounding rock state coordinates;

[0075] 5.3 Using the two-dimensional quadrant method to classify the clustered surrounding rock state coordinates, the classification results of the surrounding rock state coordinates of each pallet position in the tunnel are obtained;

[0076] It should be noted that the surrounding rock state coordinate classification results include: Class I, Class II, Class III, and Class IV.

[0077] 5.4 Determine the surrounding rock stability level of each pallet position in the tunnel based on the surrounding rock state coordinate classification results.

[0078] Furthermore, the determining of the surrounding rock stability level of each pallet position in the tunnel based on the surrounding rock state coordinate classification result includes:

[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 the 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 the insufficient support level;

[0081] 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 the support excess level;

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

[0083] It should be noted that, combined with the stress state of the anchor rods in the entire section of the tunnel and the deformation of the surrounding rock at the corresponding position, the two-dimensional quadrant method and the support vector machine method are used to classify the stability of the surrounding rock. The force on the tray, that is, the axial force of the anchor rod, is used as the horizontal coordinate, and the deformation of the surrounding rock at the position of the tray is used as the vertical coordinate. The resulting coordinates are called the surrounding rock state coordinates. Subsequently, the surrounding rock state coordinates can be unsupervisedly classified by the support vector machine method, and the preset number of classification clusters is 4. The classification results can also be obtained through the experience of tunnel support under similar geological conditions. Subsequently, the horizontal and vertical coordinate classification thresholds can be obtained, and then the two-dimensional quadrant method segmentation labels and the surrounding rock state coordinate classification results can be obtained. Among them, the horizontal and vertical coordinate classification thresholds can be obtained through the support vector machine, with the preset number of classifications being 4, and then separated by the degree of clustering of the points, and then the mean of the horizontal and vertical coordinates of each type of center can be used as the threshold, which can also be obtained through the experience of engineers.

[0084] The classification results are as follows Figure 4 As shown, Class I represents the support failure area, where the surrounding rock is greatly deformed and the support force is relatively small, which means that the support system is not installed up to standard or the installation depth is insufficient, so the surrounding rock has the highest risk of roof collapse. Class II represents the insufficient support area, where the surrounding rock is greatly deformed and the support force is also large, which means that the support system works but is easily damaged, so additional support is needed. At this time, the surrounding rock is in a potential roof collapse risk area. Class III represents the excess support area, which is characterized by small deformation of the surrounding rock and small support force. At this time, the support system is far from reaching the bearing limit, so there is no risk of roof collapse in the surrounding rock, but it can be considered to reduce the support density under similar conditions in the future. Class IV represents the reasonable support area, which is characterized by small deformation of the surrounding rock and good support force, so there is no risk of roof collapse in the surrounding rock and the support system is reasonably designed.

[0085] In summary, the present embodiment proposes a method for determining the stability grade of tunnel surrounding rock based on laser scanning, which determines the stability grade of tunnel surrounding rock based on the deformation information of the surrounding rock itself and the support force information, thereby improving the accuracy of determining the stability grade of surrounding rock.

[0086] Embodiment 2

[0087] Figure 5 FIG. 1 is a structural diagram of a system for determining the stability grade of surrounding rock in a tunnel based on laser scanning according to an embodiment of the present application, such as Figure 5 As shown, the system comprises:

[0088] An acquisition module 100 is used to acquire the tunnel surface topography point cloud data at the start time of a preset time length and the tunnel surface topography point cloud data at the end time of the preset time length;

[0089] A preprocessing module 200 is used to preprocess the lane surface morphology point cloud data to obtain the coordinate information of each scattered point block of each pallet in the lane at the start time and the coordinate information of each scattered point block of each pallet in the lane at the end time;

[0090] The first determination module 300 is used to input the coordinate information of each scattered point block of each pallet in the lane at the end time into a pre-trained machine learning model to obtain the force information of the anchor rods of each pallet in the lane at the end time;

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

[0092] Obtaining coordinate information of each scattered point block of each pallet in the lane at each moment in the historical period and force information of each pallet anchor rod corresponding to the coordinate information of each scattered point block of each pallet in the lane;

[0093] Taking the coordinate information of each scattered point block of each pallet in the lane at each moment in the historical period as input, and taking the force information of each pallet anchor rod corresponding to the coordinate information of each scattered point block of each pallet in the lane as output, the initial CNN convolutional neural network is trained to obtain a trained machine learning model.

[0094] The second determination module 400 is used to determine the deformation of the surrounding rock at each tray position of the tunnel within a preset time period according to the tunnel surface morphology point cloud data at the start time and the tunnel surface morphology point cloud data at the end time;

[0095] The third determination module 500 is used to determine the surrounding rock stability level of each tray position in the tunnel according to the force information of each tray anchor rod in the tunnel and the deformation of the surrounding rock at each tray position in the tunnel.

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

[0097] Using the ICP method, the tunnel surface morphology point cloud data at the start time is registered with the tunnel surface morphology point cloud data at the end time, to obtain a transformation matrix of the tunnel surface morphology point cloud data at the start time and a deviation matrix between the tunnel surface morphology point cloud data at the start time and the tunnel surface morphology point cloud data at the end time;

[0098] The surrounding rock deformation at each tray position in the tunnel is determined according to the transformation matrix and the deviation matrix.

[0099] The calculation formula for the surrounding rock deformation at each tray position in the tunnel is as follows:

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

[0101] Where, Dis i is the deformation of the surrounding rock at the i-th tray position in the tunnel, q i is the point cloud data of the i-th pallet position in the lane at the end time, R is the transformation matrix, T is the deviation matrix, and p i It is the point cloud data of the i-th pallet position in the lane at the starting time.

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

[0103] Constructing the surrounding rock state coordinates of each pallet position in the tunnel based on the force information of each pallet anchor rod in the tunnel and the deformation of the surrounding rock at each pallet position in the tunnel;

[0104] According to the preset number of classification clusters, the surrounding rock state coordinates of each pallet position in the tunnel are unsupervisedly classified by a support vector machine method to obtain clustered surrounding rock state coordinates;

[0105] The clustered surrounding rock state coordinates are classified using a two-dimensional quadrant method to obtain classification results of the surrounding rock state coordinates at each tray position in the tunnel;

[0106] Determine the surrounding rock stability level of each tray position in the tunnel based on the surrounding rock state coordinate classification result;

[0107] The force 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.

[0108] The surrounding rock state coordinate classification results include: Class I, Class II, Class III, and Class IV.

[0109] Furthermore, the third determining 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 the 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 the insufficient support 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 the support excess level;

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

[0114] In summary, the laser scanning-based tunnel surrounding rock stability grade determination system proposed in this embodiment determines the tunnel surrounding rock stability grade based on the surrounding rock's own deformation information and support force information, thereby improving the accuracy of surrounding rock stability grade determination.

[0115] Embodiment 3

[0116] In order to implement the above embodiments, the present disclosure further proposes an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in Embodiment 1 is implemented.

[0117] Embodiment 4

[0118] In order to implement the above embodiments, the present disclosure further proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in the first embodiment is implemented.

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

[0120] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0121] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for determining the stability grade of tunnel surrounding rock based on laser scanning, characterized in that: The method comprises: Acquire the tunnel surface morphology point cloud data at the start time of the preset time length and the tunnel surface morphology point cloud data at the end time of the preset time length; Preprocessing the lane surface morphology point cloud data to obtain coordinate information of each scattered point block of each pallet in the lane at the start time and coordinate information of each scattered point block of each pallet in the lane at the end time; Input the coordinate information of each scattered point block of each pallet in the lane at the end time into a pre-trained machine learning model to obtain the force information of the anchor rods of each pallet in the lane at the end time; Determine the surrounding rock deformation at each tray position of the lane within a preset time period according to the lane surface morphology point cloud data at the start time and the lane surface morphology point cloud data at the end time; The surrounding rock stability level of each tray position in the tunnel is determined according to the force information of each tray anchor rod in the tunnel and the deformation of the surrounding rock at each tray position in the tunnel.

2. The method according to claim 1, characterized in that The training process of the machine learning model includes: Obtaining coordinate information of each scattered point block of each pallet in the lane at each moment in the historical period and force information of each pallet anchor rod corresponding to the coordinate information of each scattered point block of each pallet in the lane; Taking the coordinate information of each scattered point block of each pallet in the lane at each moment in the historical period as input, and taking the force information of each pallet anchor rod corresponding to the coordinate information of each scattered point block of each pallet in the lane as output, the initial CNN convolutional neural network is trained to obtain a trained machine learning model.

3. The method according to claim 2, characterized in that The step of determining the deformation of surrounding rock at each tray position of the tunnel within a preset time period according to the tunnel surface morphology point cloud data at the start time and the tunnel surface morphology point cloud data at the end time includes: Using the ICP method, the tunnel surface morphology point cloud data at the start time is registered with the tunnel surface morphology point cloud data at the end time, to obtain a transformation matrix of the tunnel surface morphology point cloud data at the start time and a deviation matrix between the tunnel surface morphology point cloud data at the start time and the tunnel surface morphology point cloud data at the end time; The surrounding rock deformation at each tray position in the tunnel is determined according to the transformation matrix and the deviation matrix.

4. The method according to claim 3, characterized in that The calculation formula for the surrounding rock deformation at each tray position in the tunnel is as follows: Dis i =||q i -(Rp i +T)|| Where, Dis i is the deformation of the surrounding rock at the i-th tray position in the tunnel, q i is the point cloud data of the i-th pallet position in the lane at the end time, R is the transformation matrix, T is the deviation matrix, and p i It is the point cloud data of the i-th pallet position in the lane at the starting time.

5. The method according to claim 4, characterized in that Determining the surrounding rock stability level of each tray position in the tunnel according to the force information of each tray anchor rod in the tunnel and the deformation of the surrounding rock at each tray position in the tunnel includes: Constructing the surrounding rock state coordinates of each pallet position in the tunnel based on the force information of the anchor rods of each pallet in the tunnel and the deformation of the surrounding rock at each pallet position in the tunnel; According to the preset number of classification clusters, the surrounding rock state coordinates of each pallet position in the tunnel are unsupervisedly classified by a support vector machine method to obtain clustered surrounding rock state coordinates; The clustered surrounding rock state coordinates are classified using a two-dimensional quadrant method to obtain classification results of the surrounding rock state coordinates at each tray position in the tunnel; Determine the surrounding rock stability level of each tray position in the tunnel based on the surrounding rock state coordinate classification result; The force 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.

6. The method according to claim 5, characterized in that The surrounding rock state coordinate classification results include: Class I, Class II, Class III, and Class IV.

7. The method according to claim 6, characterized in that The determining of the surrounding rock stability level of each pallet position in the tunnel based on the surrounding rock state coordinate classification result includes: 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 the support failure level; 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 the insufficient support level; 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 the support excess level; When the classification result of the surrounding rock state coordinates is Class IV, the surrounding rock stability level corresponding to the surrounding rock state coordinates is the reasonable support level.

8. A system for determining the stability grade of tunnel surrounding rock based on laser scanning, characterized in that: The system comprises: An acquisition module, used to acquire the tunnel surface morphology point cloud data at the start time of a preset time length and the tunnel surface morphology point cloud data at the end time of the preset time length; A preprocessing module, used to preprocess the lane surface morphology point cloud data to obtain the coordinate information of each scattered point block of each pallet in the lane at the start time and the coordinate information of each scattered point block of each pallet in the lane at the end time; A first determination module is used to input the coordinate information of each scattered point block of each pallet in the lane at the end time into a pre-trained machine learning model to obtain the force information of the anchor rods of each pallet in the lane at the end time; A second determination module is used to determine the surrounding rock deformation at each tray position of the lane within a preset time period according to the lane surface morphology point cloud data at the start time and the lane surface morphology point cloud data at the end time; The third determination module is used to determine the surrounding rock stability level of each tray position in the tunnel according to the force information of each tray anchor rod in the tunnel and the surrounding rock deformation at each tray position in the tunnel.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images