Tunnel anchor rod or anchor cable support parameter optimization method and system based on laser scanning

Abstract

The invention provides a roadway anchor rod or anchor cable support parameter optimization method and system based on laser scanning, and the method comprises the steps: obtaining roadway surface topography point cloud data of a current roadway, carrying out the preprocessing, and obtaining the coordinate information of each pallet of the roadway at each moment within a preset time; according to the coordinate information of the trays of the roadway at the moments in the preset duration, determining stress information of anchor rods or anchor cables of the trays of the roadway at the moments in the preset duration and historical maximum axial force data borne by the anchor rods or anchor cables in the preset duration; and performing optimization design on the anchor rod or anchor cable support parameters of the to-be-optimized roadway according to the stress information of the anchor rod or anchor cable of each tray of the roadway at each moment within the preset duration and the historical maximum axial force data borne by each anchor rod or anchor cable within the preset duration. According to the technical scheme provided by the invention, supporting reinforcement is carried out on the insufficient supporting area in time, subsequent design and optimization of roadway supporting parameters are guided according to the excessive supporting condition, and the safety and economic benefits of roadway supporting are 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 optimizing tunnel anchor rod or anchor cable support parameters based on laser scanning. Background Art

[0002] Coal mines are mainly mined underground, and tunnel stability is the premise of this development method. In order to maintain the stability of the tunnel, anchor or cable support is currently the most widely used measure. However, the current design of anchor or cable support parameters is still based on manual experience, that is, by comparing the previous geological exploration data, establishing a finite element model, designing anchor or cable support parameters, and then numerical simulation to verify the effectiveness of the support. This method is often too conservative, resulting in an increase in support costs. At the same time, this method does not refer to the response during tunnel operation. Once the support parameters are determined, they can no longer be updated and optimized in real time. At the same time, the design of anchor or cable parameters depends on the existing tunnel, and the rationality of the parameters cannot be evaluated. Therefore, it is urgent to propose a tunnel anchor or cable support parameter optimization scheme that can make full use of the surrounding rock deformation-support force response information during the entire operation cycle of the tunnel. Summary of the invention

[0003] The present application provides a method and system for optimizing tunnel anchor or anchor cable support parameters based on laser scanning, so as to at least solve the technical problem that support parameters are too conservative and cannot be updated and optimized in real time.

[0004] The first embodiment of the present application proposes a tunnel bolt or anchor cable support parameter optimization method based on laser scanning, the method comprising:

[0005] Acquire the lane surface morphology point cloud data of the current lane at each moment within a preset time length, and pre-process the lane surface morphology point cloud data to obtain the coordinate information of each pallet in the lane at each moment within the preset time length;

[0006] Determine the force information of the anchor rods or anchor cables of each pallet in the lane at each moment in the preset time length and the historical maximum axial force data of each anchor rod or anchor cable in the preset time length according to the coordinate information of each pallet in the lane at each moment in the preset time length;

[0007] The anchor rod or anchor cable support parameters of the optimized lane are optimized according to the force information of each pallet anchor rod or anchor cable in the lane at each moment within the preset time and the historical maximum axial force data of each anchor rod or anchor cable within the preset time.

[0008] Preferably, the preprocessing of the tunnel surface topography point cloud data includes:

[0009] Performing registration processing on the tunnel surface topography point cloud data to obtain the tunnel surface topography point cloud data after registration at each moment;

[0010] The registered lane surface morphology point cloud data at each moment is processed using target detection and segmentation technology to obtain coordinate information of each pallet in the lane at each moment.

[0011] Further, the force information of the anchor rods or anchor cables of each pallet in the lane at each moment in the preset time length and the historical maximum axial force data of each anchor rod or anchor cable in the preset time length are determined according to the coordinate information of each pallet in the lane at each moment in the preset time length, including:

[0012] Inputting the coordinate information of each pallet in the lane at each moment within the preset time length into a pre-trained point cloud block extraction model to obtain the point cloud block of each pallet in the lane at each moment within the preset time length;

[0013] Input the point cloud blocks of each pallet in the lane at each moment within the preset time length into a pre-trained anchor rod or anchor cable axial force extraction model to obtain the force information of the anchor rod or anchor cable of each pallet in the lane at each moment within the preset time length;

[0014] Determine the deformation of each pallet in the lane at each moment within the preset time period corresponding to each force information;

[0015] Divide each force information into force levels to obtain the deformation of each pallet in the lane at each moment within the preset time length under each force level;

[0016] Theil-Sen regression is performed based on the deformation of each pallet in the lane at each moment within the preset time under each force level to obtain the historical maximum axial force data of each anchor rod or anchor cable within the preset time.

[0017] Furthermore, the calculation formula for the historical maximum axial force data of each anchor rod or anchor cable within the preset time period is as follows:

[0018] F h,m,d =F i k Flat,d -b

[0019] In the formula, F h,m,d is the historical maximum axial force data of the dth anchor rod or anchor cable, F i is the preset pallet deformation threshold, R Flat,d is the regression gradient corresponding to the dth anchor or cable, k is the first empirical regression parameter, and b is the second empirical regression parameter;

[0020] in, In the formula, The force on the tray at the dth anchor rod or anchor cable is F j The deformation matrix of the flat plate area of ​​the pallet is The force on the tray at the dth anchor rod or anchor cable is F i The deformation matrix of the flat plate area of ​​the pallet.

[0021] Furthermore, the optimization design of the anchor rod or anchor cable support parameters of the lane to be optimized according to the force information of each anchor rod or anchor cable of each pallet in the lane at each moment within the preset time and the historical maximum axial force data of each anchor rod or anchor cable within the preset time includes:

[0022] When the lane to be optimized is the current lane:

[0023] Obtain the surrounding rock deformation at each pallet position in the tunnel within a preset time, and determine the ratio of the axial force increase at each pallet position in the tunnel within the preset time to the surrounding rock deformation.

[0024] If the ratio is greater than a preset first ratio threshold, or the force information is greater than a preset first force threshold, the spacing of the pallet anchor rods or anchor cables of the current lane is adjusted according to a preset spacing adjustment amount;

[0025] If the surrounding rock deformation is greater than a preset first deformation threshold, the anchor rod or anchor cable support density and prestress strength of the current tunnel are adjusted according to a preset support adjustment amount and a preset prestress strength adjustment amount;

[0026] When the lane to be optimized and the current lane are different lanes:

[0027] Obtain the breaking load of each anchor rod or anchor cable, and determine the percentage of the difference between the breaking load of each anchor rod or anchor cable and the historical maximum axial force data of each anchor rod or anchor cable;

[0028] If the difference percentage is less than 20%, the anchor rod or anchor cable support parameters of the current tunnel are adjusted according to the preset prestress increase value, the preset spacing reduction value and the preset strength increase value, and the adjusted rod support parameters are used as the anchor rod or anchor cable support parameters of the tunnel to be optimized;

[0029] If the difference percentage is greater than or equal to 20% and less than or equal to 40%, the anchor rod or anchor cable support parameters of the current tunnel are used as the anchor rod or anchor cable support parameters of the tunnel to be optimized;

[0030] If the difference percentage is greater than forty percent, the anchor rod or anchor cable support parameters of the current tunnel are adjusted according to the preset prestress reduction value, the preset spacing increase value and the preset strength reduction value, and the adjusted rod support parameters are used as the anchor rod or anchor cable support parameters of the tunnel to be optimized.

[0031] Furthermore, the training process of the point cloud block extraction model includes:

[0032] Obtaining coordinate information of each pallet in the lane at each moment in the historical period, and label information of each coordinate information, wherein the label information includes: the pallet number described in the coordinate information;

[0033] Taking the coordinate information of each pallet in the lane at each time in the historical period as input and the label information of each coordinate information as output, the initial PointNet++ model is trained to obtain a trained point cloud block extraction model;

[0034] The training process of the anchor rod or anchor cable axial force extraction model includes:

[0035] Obtaining coordinate information of each pallet in the lane at each time in the historical period and force information of anchor rods or anchor cables of each pallet corresponding to the coordinate information of each pallet in the lane;

[0036] Taking the coordinate information of each pallet in the lane at each moment in the historical period as input, and taking the force information of the anchor rods or anchor cables of each pallet corresponding to the coordinate information of each pallet in the lane as output, the initial CNN convolutional neural network is trained to obtain a trained anchor rod or anchor cable axial force extraction model.

[0037] The second embodiment of the present application proposes a tunnel bolt or cable support parameter optimization system based on laser scanning, including:

[0038] An acquisition module is used to acquire the lane surface morphology point cloud data of the current lane at each moment within a preset time length, and pre-process the lane surface morphology point cloud data to obtain the coordinate information of each pallet in the lane at each moment within the preset time length;

[0039] A determination module, used to determine the force information of the anchor rods or anchor cables of each pallet in the lane at each moment in the preset time length and the historical maximum axial force data of each anchor rod or anchor cable in the preset time length according to the coordinate information of each pallet in the lane at each moment in the preset time length;

[0040] The optimization module is used to optimize the anchor or anchor cable support parameters of the optimized lane according to the force information of each pallet anchor or anchor cable in the lane at each moment within the preset time and the historical maximum axial force data of each anchor or anchor cable within the preset time.

[0041] Preferably, the acquisition module is also used for:

[0042] Performing registration processing on the tunnel surface topography point cloud data to obtain the tunnel surface topography point cloud data after registration at each moment;

[0043] The registered lane surface morphology point cloud data at each moment is processed using target detection and segmentation technology to obtain coordinate information of each pallet in the lane at each moment.

[0044] 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.

[0045] 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.

[0046] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0047] The present application proposes a method and system for optimizing the parameters of anchor rods or anchor cables in a tunnel based on laser scanning, the method comprising: obtaining the tunnel surface morphology point cloud data of the current tunnel at each moment within a preset time length, and preprocessing the tunnel surface morphology point cloud data to obtain the coordinate information of each tray in the tunnel at each moment within the preset time length; determining the force information of the anchor rods or anchor cables of each tray in the tunnel at each moment within the preset time length and the historical maximum axial force data of each anchor rod or anchor cable within the preset time length according to the coordinate information of each tray in the tunnel at each moment within the preset time length; optimizing the design of the anchor rod or anchor cable support parameters of the tunnel to be optimized according to the force information of the anchor rods or anchor cables of each tray in the tunnel at each moment within the preset time length and the historical maximum axial force data of each anchor rod or anchor cable within the preset time length. The technical solution proposed in the present application can timely strengthen the support of the insufficiently supported area, and guide the design and optimization of the subsequent tunnel support parameters for the excessively supported situation, thereby improving the safety and economic benefits of the tunnel support.

[0048] 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

[0049] 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:

[0050] Figure 1 A flowchart of a method for optimizing tunnel bolt or cable support parameters based on laser scanning according to an embodiment of the present application;

[0051] Figure 2 A detailed flow chart of a method for optimizing tunnel bolt or cable support parameters based on laser scanning according to an embodiment of the present application;

[0052] Figure 3 The present invention is a structural diagram of a tunnel anchor or cable support parameter optimization system based on laser scanning according to one embodiment of the present application. DETAILED DESCRIPTION

[0053] The 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.

[0054] The present application proposes a method and system for optimizing the parameters of anchor rods or anchor cables in a tunnel based on laser scanning, the method comprising: obtaining the tunnel surface morphology point cloud data of the current tunnel at each moment within a preset time length, and preprocessing the tunnel surface morphology point cloud data to obtain the coordinate information of each tray in the tunnel at each moment within the preset time length; determining the force information of the anchor rods or anchor cables of each tray in the tunnel at each moment within the preset time length and the historical maximum axial force data of each anchor rod or anchor cable within the preset time length according to the coordinate information of each tray in the tunnel at each moment within the preset time length; optimizing the design of the anchor rod or anchor cable support parameters of the tunnel to be optimized according to the force information of the anchor rods or anchor cables of each tray in the tunnel at each moment within the preset time length and the historical maximum axial force data of each anchor rod or anchor cable within the preset time length. The technical solution proposed in the present application can timely strengthen the support of the insufficiently supported area, and guide the design and optimization of the subsequent tunnel support parameters for the excessively supported situation, thereby improving the safety and economic benefits of the tunnel support.

[0055] The following describes, with reference to the accompanying drawings, a method and system for optimizing tunnel bolt or cable support parameters based on laser scanning according to an embodiment of the present application.

[0056] Embodiment 1

[0057] Figure 1 A flowchart of a method for optimizing tunnel bolt or cable support parameters based on laser scanning according to an embodiment of the present application is provided. Figure 1 As shown, the method includes:

[0058] Step 1: Obtain the lane surface morphology point cloud data of the current lane at each moment within a preset time length, and pre-process the lane surface morphology point cloud data to obtain the coordinate information of each pallet in the lane at each moment within the preset time length.

[0059] 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 each moment within a preset time.

[0060] In the disclosed embodiment, the preprocessing of the tunnel surface topography point cloud data includes:

[0061] 1. Performing registration processing on the tunnel surface topography point cloud data to obtain the tunnel surface topography point cloud data after registration at each moment;

[0062] It should be noted that the registration process includes:

[0063] Using the target balls pre-placed in the lane, and the formula Calculate the transformation matrix R between point clouds; where R is the transformation matrix, T is the deviation matrix, k is the total number of target balls, usually at least 4, p i is the coordinate of the center of the target sphere in the source point cloud, i.e., the point cloud obtained by the initial scan, q i is the coordinate of the center of the target sphere in the target point cloud, i.e. the deformed point cloud.

[0064] Then, the deformed point cloud is transformed using the transformation matrices R and T to obtain the registered deformed point cloud, that is, the registered tunnel surface morphology point cloud data at each moment.

[0065] 2. Use target detection and segmentation technology to process the aligned lane surface morphology point cloud data at each moment to obtain the coordinate information of each pallet in the lane at each moment.

[0066] 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 after registration at each moment to extract the position of the full-section anchor rod or anchor cable group of the tunnel and the three-dimensional surface morphology information, namely the xyz coordinates of the pallet point cloud.

[0067] Step 2: Determine the force information of the anchor rods or anchor cables of each pallet in the lane at each moment in the preset time length and the historical maximum axial force data of each anchor rod or anchor cable in the preset time length according to the coordinate information of each pallet in the lane at each moment in the preset time length.

[0068] In the embodiment of the present disclosure, step 2 specifically includes:

[0069] 2.1 Input the coordinate information of each pallet in the lane at each moment within the preset time length into the pre-trained point cloud block extraction model to obtain the point cloud block of each pallet in the lane at each moment within the preset time length;

[0070] 2.2 Input the point cloud blocks of each pallet in the lane at each moment within the preset time length into the pre-trained anchor rod or anchor cable axial force extraction model to obtain the force information of the anchor rod or anchor cable of each pallet in the lane at each moment within the preset time length;

[0071] 2.3 Determine the deformation of each pallet in the lane at each moment within the preset time period corresponding to each force information;

[0072] It should be noted that the coordinate information of each pallet in the lane and the distance from the standard part are resampled in the horizontal direction within the preset time length, with a resolution of 1mm, to obtain the deformation corresponding to each force information of each pallet in the lane at each moment within each preset time length.

[0073] 2.4 Divide each force information into force levels to obtain the deformation of each pallet in the lane at each moment within the preset time length under each force level;

[0074] 2.5 Based on the deformation of each pallet in the lane at each moment within the preset time length under each force level, Theil-Sen regression is performed to obtain the historical maximum axial force data of each anchor rod or anchor cable within the preset time length.

[0075] It should be noted that the deformation under each force level is expanded into a sequence, and the deformations with the same index under different force levels are used as the horizontal and vertical coordinates for Theil-Sen regression to obtain the regression gradient, and then the historical maximum axial force can be calculated based on the regression gradient.

[0076] It should be noted that the calculation formula for the historical maximum axial force data of each anchor rod or anchor cable within the preset time period is as follows:

[0077] F h,m,d =F i k Flat,d -b

[0078] In the formula, F h,m,d is the historical maximum axial force data of the dth anchor rod or anchor cable, F i is the preset pallet deformation threshold, R Flat,d is the regression gradient corresponding to the dth anchor or cable, k is the first empirical regression parameter, and b is the second empirical regression parameter; wherein, the F i It can be 80kN.

[0079] in, In the formula, The force on the tray at the dth anchor rod or anchor cable is F j The deformation matrix of the flat plate area of ​​the pallet is The force on the tray at the dth anchor rod or anchor cable is F i The deformation matrix of the flat plate area of ​​the pallet.

[0080] It should be noted that the training process of the point cloud block extraction model includes:

[0081] Obtaining coordinate information of each pallet in the lane at each moment in the historical period, and label information of each coordinate information, wherein the label information includes: the pallet number described in the coordinate information;

[0082] Taking the coordinate information of each pallet in the lane at each time in the historical period as input and the label information of each coordinate information as output, the initial PointNet++ model is trained to obtain a trained point cloud block extraction model;

[0083] The training process of the anchor rod or anchor cable axial force extraction model includes:

[0084] Obtaining coordinate information of each pallet in the lane at each time in the historical period and force information of anchor rods or anchor cables of each pallet corresponding to the coordinate information of each pallet in the lane;

[0085] Taking the coordinate information of each pallet in the lane at each moment in the historical period as input, and taking the force information of the anchor rods or anchor cables of each pallet corresponding to the coordinate information of each pallet in the lane as output, the initial CNN convolutional neural network is trained to obtain a trained anchor rod or anchor cable axial force extraction model.

[0086] Step 3: Optimize the anchor or anchor cable support parameters of the optimized lane according to the force information of each anchor or anchor cable of the lane at each moment within the preset time and the historical maximum axial force data of each anchor or anchor cable within the preset time.

[0087] In the embodiment of the present disclosure, step 3 specifically includes:

[0088] 3.1 When the lane to be optimized is the current lane:

[0089] Obtain the surrounding rock deformation at each pallet position in the tunnel within a preset time, and determine the ratio of the axial force increase at each pallet position in the tunnel within the preset time to the surrounding rock deformation.

[0090] If the ratio is greater than a preset first ratio threshold α, or the force information is greater than a preset first force threshold β, the spacing of the pallet anchor rods or anchor cables of the current lane is adjusted according to a preset spacing adjustment amount;

[0091] For example, the spacing adjustment amount can be 0.2m, reducing the spacing between anchor rods or anchor cables from 1m to 0.8m.

[0092] If the surrounding rock deformation is greater than a preset first deformation threshold value γ, adjusting the anchor rod or anchor cable support density and prestress strength of the current tunnel according to a preset support adjustment amount and a preset prestress strength adjustment amount;

[0093] For example, for the optimization of the same tunnel, the axial force increase of the nearest row of anchors or cables is calculated every 1m of tunnel excavation, and then the surrounding rock deformation during this period is calculated, the ratio is calculated, and then the support parameters of the next row of anchors or cables are determined.

[0094] It should be noted that the calculation formula for the surrounding rock deformation at each tray position in the tunnel is as follows:

[0095] Dis i =||q i -(Rp i +T)||

[0096] 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.

[0097] 3.2 When the lane to be optimized and the current lane are different lanes:

[0098] Obtain the breaking load of each anchor rod or anchor cable, and determine the percentage of the difference between the breaking load of each anchor rod or anchor cable and the historical maximum axial force data of each anchor rod or anchor cable;

[0099] If the difference percentage is less than 20%, the anchor rod or anchor cable support parameters of the current tunnel are adjusted according to the preset prestress increase value, the preset spacing reduction value and the preset strength increase value, and the adjusted rod support parameters are used as the anchor rod or anchor cable support parameters of the tunnel to be optimized;

[0100] If the difference percentage is greater than or equal to 20% and less than or equal to 40%, the anchor rod or anchor cable support parameters of the current tunnel are used as the anchor rod or anchor cable support parameters of the tunnel to be optimized;

[0101] If the difference percentage is greater than forty percent, the anchor rod or anchor cable support parameters of the current tunnel are adjusted according to the preset prestress reduction value, the preset spacing increase value and the preset strength reduction value, and the adjusted rod support parameters are used as the anchor rod or anchor cable support parameters of the tunnel to be optimized.

[0102] It should be noted that after the current working face mining is completed, based on the maximum historical axial force data of the entire mining process, the support parameters of the future mining tunnels with similar geological conditions are optimized. If the maximum axial force of the current working face anchor or anchor cable mining history is between 60% and 80% of the anchor or anchor cable breaking load, the same support parameters can be used in the mining tunnels with similar geological conditions, including prestress, spacing, anchor or anchor cable strength, etc. If the maximum axial force of the current working face anchor or anchor cable mining history is greater than 80% of the anchor or anchor cable breaking load, the support level and support parameters for the mining tunnels with similar geological conditions should be improved, including increasing prestress, reducing spacing, and increasing anchor or anchor cable strength. If the maximum axial force of the current working face anchor or anchor cable mining history is less than 60% of the anchor or anchor cable breaking load, the support level and support parameters for the mining tunnels with similar geological conditions should be reduced, including reducing prestress, increasing spacing, and reducing anchor or anchor cable strength.

[0103] like Figure 2 As shown, the detailed flow chart of the tunnel anchor rod or anchor cable support parameter optimization method implemented in this embodiment will not be repeated here.

[0104] It should be noted that the tunnel bolt or cable support parameter optimization method based on laser scanning proposed in this embodiment has the following advantages:

[0105] (1) Through multiple three-dimensional laser scanning, the pre-trained machine learning model and the historical maximum axial force calculation method are used to estimate the stress state of the full-section anchor bolts or anchor cable groups in the tunnel, providing an important basis for optimizing the anchor bolt or anchor cable support parameters under the support state during operation;

[0106] (2) It provides strong technical support for mine safety production and provides an engineering analogy method that combines existing tunnel data to provide a reference for the design of new tunnel support, which helps to reduce the incidence of tunnel surrounding rock accidents and improve the efficiency of mineral resource mining.

[0107] To sum up, the laser scanning-based tunnel anchor or cable support parameter optimization method proposed in this embodiment can timely strengthen the support of insufficiently supported areas, and guide the design and optimization of subsequent tunnel support parameters for excessive support situations, thereby improving the safety and economic benefits of tunnel support.

[0108] Embodiment 2

[0109] Figure 3 The structure diagram of a tunnel bolt or anchor cable support parameter optimization system based on laser scanning according to one embodiment of the present application is shown in FIG. Figure 3 As shown, the system comprises:

[0110] The acquisition module 100 is used to acquire the lane surface morphology point cloud data of the current lane at each moment within a preset time length, and pre-process the lane surface morphology point cloud data to obtain the coordinate information of each pallet in the lane at each moment within the preset time length;

[0111] A determination module 200 is used to determine the force information of the anchor rods or anchor cables of each pallet in the lane at each moment in the preset time length and the historical maximum axial force data of each anchor rod or anchor cable in the preset time length according to the coordinate information of each pallet in the lane at each moment in the preset time length;

[0112] The optimization module 300 is used to optimize the anchor or anchor cable support parameters of the optimized lane according to the force information of each pallet anchor or anchor cable in the lane at each moment within the preset time and the historical maximum axial force data of each anchor or anchor cable within the preset time.

[0113] In the embodiment of the present disclosure, the acquisition module 100 is further used for:

[0114] Performing registration processing on the tunnel surface topography point cloud data to obtain the tunnel surface topography point cloud data after registration at each moment;

[0115] The registered lane surface morphology point cloud data at each moment is processed using target detection and segmentation technology to obtain coordinate information of each pallet in the lane at each moment.

[0116] In the embodiment of the present disclosure, the determining module 200 is further used to:

[0117] Inputting the coordinate information of each pallet in the lane at each moment within the preset time length into a pre-trained point cloud block extraction model to obtain the point cloud block of each pallet in the lane at each moment within the preset time length;

[0118] Input the point cloud blocks of each pallet in the lane at each moment within the preset time length into a pre-trained anchor rod or anchor cable axial force extraction model to obtain the force information of the anchor rod or anchor cable of each pallet in the lane at each moment within the preset time length;

[0119] Determine the deformation of each pallet in the lane at each moment within the preset time period corresponding to each force information;

[0120] Divide each force information into force levels to obtain the deformation of each pallet in the lane at each moment within the preset time length under each force level;

[0121] Theil-Sen regression is performed based on the deformation of each pallet in the lane at each moment within the preset time under each force level to obtain the historical maximum axial force data of each anchor rod or anchor cable within the preset time.

[0122] The calculation formula of the historical maximum axial force data of each anchor rod or anchor cable within the preset time period is as follows:

[0123] F h,m,d =F i k Flat,d -b

[0124] In the formula, F h,m,d is the historical maximum axial force data of the dth anchor rod or anchor cable, F i is the preset pallet deformation threshold, R Flat,d is the regression gradient corresponding to the dth anchor or cable, k is the first empirical regression parameter, and b is the second empirical regression parameter;

[0125] in, In the formula, The force on the tray at the dth anchor rod or anchor cable is F j The deformation matrix of the flat plate area of ​​the pallet is The force on the tray at the dth anchor rod or anchor cable is F i The deformation matrix of the flat plate area of ​​the pallet.

[0126] The training process of the point cloud block extraction model includes:

[0127] Obtaining coordinate information of each pallet in the lane at each moment in the historical period, and label information of each coordinate information, wherein the label information includes: the pallet number described in the coordinate information;

[0128] Taking the coordinate information of each pallet in the lane at each time in the historical period as input and the label information of each coordinate information as output, the initial PointNet++ model is trained to obtain a trained point cloud block extraction model;

[0129] The training process of the anchor rod or anchor cable axial force extraction model includes:

[0130] Obtaining coordinate information of each pallet in the lane at each time in the historical period and force information of anchor rods or anchor cables of each pallet corresponding to the coordinate information of each pallet in the lane;

[0131] Taking the coordinate information of each pallet in the lane at each moment in the historical period as input, and taking the force information of the anchor rods or anchor cables of each pallet corresponding to the coordinate information of each pallet in the lane as output, the initial CNN convolutional neural network is trained to obtain a trained anchor rod or anchor cable axial force extraction model.

[0132] In the embodiment of the present disclosure, the optimization module 300 is also used for:

[0133] When the lane to be optimized is the current lane:

[0134] Obtain the surrounding rock deformation at each pallet position in the tunnel within a preset time, and determine the ratio of the axial force increase at each pallet position in the tunnel within the preset time to the surrounding rock deformation.

[0135] If the ratio is greater than a preset first ratio threshold, or the force information is greater than a preset first force threshold, the spacing of the pallet anchor rods or anchor cables of the current lane is adjusted according to a preset spacing adjustment amount;

[0136] If the surrounding rock deformation is greater than a preset first deformation threshold, the anchor rod or anchor cable support density and prestress strength of the current tunnel are adjusted according to a preset support adjustment amount and a preset prestress strength adjustment amount;

[0137] When the lane to be optimized and the current lane are different lanes:

[0138] Obtain the breaking load of each anchor rod or anchor cable, and determine the percentage of the difference between the breaking load of each anchor rod or anchor cable and the historical maximum axial force data of each anchor rod or anchor cable;

[0139] If the difference percentage is less than 20%, the anchor rod or anchor cable support parameters of the current tunnel are adjusted according to the preset prestress increase value, the preset spacing reduction value and the preset strength increase value, and the adjusted rod support parameters are used as the anchor rod or anchor cable support parameters of the tunnel to be optimized;

[0140] If the difference percentage is greater than or equal to 20% and less than or equal to 40%, the anchor rod or anchor cable support parameters of the current tunnel are used as the anchor rod or anchor cable support parameters of the tunnel to be optimized;

[0141] If the difference percentage is greater than forty percent, the anchor rod or anchor cable support parameters of the current tunnel are adjusted according to the preset prestress reduction value, the preset spacing increase value and the preset strength reduction value, and the adjusted rod support parameters are used as the anchor rod or anchor cable support parameters of the tunnel to be optimized.

[0142] To sum up, the tunnel anchor rod or anchor cable support parameter optimization system based on laser scanning proposed in this embodiment can timely strengthen the support of insufficient support areas, and guide the design and optimization of subsequent tunnel support parameters for excessive support conditions, thereby improving the safety and economic benefits of tunnel support.

[0143] Embodiment 3

[0144] 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.

[0145] Embodiment 4

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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 optimizing tunnel bolt or cable support parameters based on laser scanning, characterized in that: The method comprises: Acquire the lane surface morphology point cloud data of the current lane at each moment within a preset time length, and pre-process the lane surface morphology point cloud data to obtain the coordinate information of each pallet in the lane at each moment within the preset time length; Determine the force information of the anchor rods or anchor cables of each pallet in the lane at each moment in the preset time length and the historical maximum axial force data of each anchor rod or anchor cable in the preset time length according to the coordinate information of each pallet in the lane at each moment in the preset time length; The anchor rod or anchor cable support parameters of the optimized lane are optimized according to the force information of each pallet anchor rod or anchor cable in the lane at each moment within the preset time and the historical maximum axial force data of each anchor rod or anchor cable within the preset time.

2. The method according to claim 1, characterized in that The preprocessing of the tunnel surface topography point cloud data includes: Performing registration processing on the tunnel surface topography point cloud data to obtain the tunnel surface topography point cloud data after registration at each moment; The registered lane surface morphology point cloud data at each moment is processed using target detection and segmentation technology to obtain coordinate information of each pallet in the lane at each moment.

3. The method according to claim 2, characterized in that The method of determining the force information of the anchor rods or anchor cables of each pallet in the lane at each moment in the preset time length and the historical maximum axial force data of each anchor rod or anchor cable in the preset time length according to the coordinate information of each pallet in the lane at each moment in the preset time length includes: Inputting the coordinate information of each pallet in the lane at each moment within the preset time length into a pre-trained point cloud block extraction model to obtain the point cloud block of each pallet in the lane at each moment within the preset time length; Input the point cloud blocks of each pallet in the lane at each moment within the preset time length into a pre-trained anchor rod or anchor cable axial force extraction model to obtain the force information of the anchor rod or anchor cable of each pallet in the lane at each moment within the preset time length; Determine the deformation of each pallet in the lane at each moment within the preset time period corresponding to each force information; Divide each force information into force levels to obtain the deformation of each pallet in the lane at each moment within the preset time length under each force level; Theil-Sen regression is performed based on the deformation of each pallet in the lane at each moment within the preset time under each force level to obtain the historical maximum axial force data of each anchor rod or anchor cable within the preset time.

4. The method according to claim 3, characterized in that The calculation formula for the historical maximum axial force data of each anchor rod or anchor cable within the preset time period is as follows: F h,m,d =F i kR Flat,d -b In the formula, F h,m,d is the historical maximum axial force data of the dth anchor rod or anchor cable, F i is the preset pallet deformation threshold, R Flat,d is the regression gradient corresponding to the dth anchor or cable, k is the first empirical regression parameter, and b is the second empirical regression parameter; in, In the formula, The force on the tray at the dth anchor rod or anchor cable is F j The deformation matrix of the flat plate area of ​​the pallet is The force on the tray at the dth anchor rod or anchor cable is F i The deformation matrix of the flat plate area of ​​the pallet.

5. The method according to claim 4, characterized in that The optimizing design of anchor rod or anchor cable support parameters of the lane to be optimized according to the force information of each anchor rod or anchor cable of each pallet in the lane at each moment within the preset time and the historical maximum axial force data of each anchor rod or anchor cable within the preset time includes: When the lane to be optimized is the current lane: Obtain the surrounding rock deformation at each pallet position in the tunnel within a preset time, and determine the ratio of the axial force increase at each pallet position in the tunnel within the preset time to the surrounding rock deformation. If the ratio is greater than a preset first ratio threshold, or the force information is greater than a preset first force threshold, the spacing of the pallet anchor rods or anchor cables of the current lane is adjusted according to a preset spacing adjustment amount; If the surrounding rock deformation is greater than a preset first deformation threshold, the anchor rod or anchor cable support density and prestress strength of the current tunnel are adjusted according to a preset support adjustment amount and a preset prestress strength adjustment amount; When the lane to be optimized and the current lane are different lanes: Obtain the breaking load of each anchor rod or anchor cable, and determine the percentage of the difference between the breaking load of each anchor rod or anchor cable and the historical maximum axial force data of each anchor rod or anchor cable; If the difference percentage is less than 20%, the anchor rod or anchor cable support parameters of the current tunnel are adjusted according to the preset prestress increase value, the preset spacing reduction value and the preset strength increase value, and the adjusted rod support parameters are used as the anchor rod or anchor cable support parameters of the tunnel to be optimized; If the difference percentage is greater than or equal to 20% and less than or equal to 40%, the anchor rod or anchor cable support parameters of the current tunnel are used as the anchor rod or anchor cable support parameters of the tunnel to be optimized; If the difference percentage is greater than forty percent, the anchor rod or anchor cable support parameters of the current tunnel are adjusted according to the preset prestress reduction value, the preset spacing increase value and the preset strength reduction value, and the adjusted rod support parameters are used as the anchor rod or anchor cable support parameters of the tunnel to be optimized.

6. The method according to claim 3, characterized in that The training process of the point cloud block extraction model includes: Obtaining coordinate information of each pallet in the lane at each time in the historical period, and label information of each coordinate information, wherein the label information includes: the pallet number described in the coordinate information; Taking the coordinate information of each pallet in the lane at each time in the historical period as input and the label information of each coordinate information as output, the initial PointNet++ model is trained to obtain a trained point cloud block extraction model; The training process of the anchor rod or anchor cable axial force extraction model includes: Obtaining coordinate information of each pallet in the lane at each moment in the historical period and force information of anchor rods or anchor cables of each pallet corresponding to the coordinate information of each pallet in the lane; Taking the coordinate information of each pallet in the lane at each moment in the historical period as input, and taking the force information of the anchor rods or anchor cables of each pallet corresponding to the coordinate information of each pallet in the lane as output, the initial CNN convolutional neural network is trained to obtain a trained anchor rod or anchor cable axial force extraction model.

7. A tunnel bolt or cable support parameter optimization system based on laser scanning, characterized in that: The system comprises: An acquisition module is used to acquire the lane surface morphology point cloud data of the current lane at each moment within a preset time length, and pre-process the lane surface morphology point cloud data to obtain the coordinate information of each pallet in the lane at each moment within the preset time length; A determination module, used to determine the force information of the anchor rods or anchor cables of each pallet in the lane at each moment in the preset time length and the historical maximum axial force data of each anchor rod or anchor cable in the preset time length according to the coordinate information of each pallet in the lane at each moment in the preset time length; The optimization module is used to optimize the anchor or anchor cable support parameters of the optimized lane according to the force information of each pallet anchor or anchor cable in the lane at each moment within the preset time and the historical maximum axial force data of each anchor or anchor cable within the preset time.

8. The system according to claim 7, characterized in that The acquisition module is also used for: Performing registration processing on the tunnel surface topography point cloud data to obtain the tunnel surface topography point cloud data after registration at each moment; The registered lane surface morphology point cloud data at each moment is processed using target detection and segmentation technology to obtain coordinate information of each pallet in the lane at each moment.

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 6 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 6 is implemented.

Images