Tunnel surrounding rock loosening zone testing method, device, electronic equipment and storage medium

Abstract

The present invention relates to the technical field of tunnel surrounding rock testing, and is a tunnel surrounding rock loosening zone testing method, device, electronic device and storage medium, including: obtaining basic data of tunnel surrounding rock to be predicted, wherein the basic data includes tunnel section design parameters and surrounding rock geological characteristic parameters, inputting the basic data of tunnel surrounding rock to be predicted into a deep loosening zone thickness prediction model, and obtaining the corresponding tunnel surrounding rock loosening zone thickness. The present invention establishes a deep loosening zone thickness prediction model, and uses the deep loosening zone thickness prediction model to predict the thickness of the tunnel surrounding rock loosening zone of the tunnel surrounding rock to be predicted, which is not affected by the mining depth of the mine and the complexity of the application environment, and can quickly and accurately obtain the thickness of the tunnel surrounding rock loosening zone, and the deep loosening zone thickness prediction model can be updated regularly to ensure the accuracy of the calculation of the tunnel surrounding rock loosening zone thickness, and provide data support for subsequent surrounding rock stability evaluation and support design.

Description

Technical Field

[0001] The invention relates to the technical field of tunnel surrounding rock testing, and specifically relates to a tunnel surrounding rock loosening zone testing method, device, electronic equipment and storage medium. Background Art

[0002] With the large-scale exploitation of shallow resources, high-deep well mining will become an important mode of mining metal mine resources in my country. After the excavation of deep underground tunnels, the surrounding rock stress is redistributed. Under high stress conditions, a certain range of surrounding rock loosening zone is bound to form around the tunnel. The size of the surrounding rock loosening zone is crucial to the support design and stability evaluation of underground engineering.

[0003] At present, the commonly used methods for testing the loosening zone of tunnel surrounding rock are the acoustic wave method, the panoramic image method of borehole television and the multi-point displacement meter method. The acoustic wave method evaluates the mechanical properties and plastic failure of the coal body by measuring the propagation speed and waveform changes of the acoustic waves in the coal body; this method relies on the test of acoustic wave parameters and can judge the changes in the mechanical properties and plastic failure of the coal body. The panoramic image method of borehole television uses a borehole television system for testing. This method installs a camera in the borehole to shoot the internal structure of the surrounding rock to form a panoramic image. This method can intuitively observe the fracture of the surrounding rock and the range of the loosening zone, and is suitable for loosening zone testing under various geological conditions. The multi-point displacement meter method monitors the deformation of the surrounding rock by installing multiple displacement meters in the surrounding rock. This method can monitor the displacement changes of the surrounding rock in real time, thereby judging the range and stability of the loosening zone.

[0004] Although the above methods can intuitively test the size of the loose zone of the tunnel surrounding rock, they require on-site testing, and there are problems such as cumbersome and complicated on-site operations, long time periods, high testing costs, and small test coverage areas.

[0005] At present, with the large-scale exploitation of shallow resources and the continuous increase in mining depth, the geological environment of deep rock mass has become more and more complex. Under the conditions of mechanical fracture development and rock mass fragmentation, the existing tunnel surrounding rock loosening zone test method is difficult to quickly determine the thickness of the tunnel surrounding rock loosening zone under different geological conditions, which will directly affect the safe production of metal mines. In addition, the scope of the surrounding rock loosening zone directly affects the safe construction of underground projects and the life and property safety of underground workers and equipment. The rapid and accurate determination of the size of the tunnel surrounding rock loosening zone has important guiding significance for the stability evaluation of underground projects, the optimization of tunnel support design and the safety of underground personnel. Summary of the invention

[0006] The present invention provides a method that overcomes the deficiencies of the above-mentioned prior art and can effectively solve the problems of the existing commonly used tunnel surrounding rock loosening zone testing method, such as complicated on-site operation, long time period, small test coverage area, and unsuitability for high-deep well mining.

[0007] One of the technical solutions of the present invention is achieved by the following measures: A method for testing the loosening zone of surrounding rock in a tunnel, comprising:

[0008] Obtaining basic data of the surrounding rock of the tunnel to be predicted, wherein the basic data includes tunnel section design parameters and surrounding rock geological characteristic parameters, the tunnel section design parameters include tunnel layout direction and tunnel section size, and the surrounding rock geological characteristic parameters include tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade;

[0009] The basic data of the tunnel surrounding rock to be predicted is input into the deep loose zone thickness prediction model to obtain the corresponding tunnel surrounding rock loose zone thickness, wherein the deep loose zone thickness prediction model is obtained by machine learning of a number of samples, wherein each of the several samples includes the surrounding rock characteristics of the deep mine tunnel and a label identifying the corresponding tunnel surrounding rock loose zone thickness, and the surrounding rock characteristics of the deep mine tunnel include tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade.

[0010] The following are further optimizations and / or improvements to the above technical solutions:

[0011] The above-mentioned deep loose zone thickness prediction model construction process includes:

[0012] A number of samples are obtained and divided into a training set and a test set according to a ratio, wherein each sample includes surrounding rock characteristics of deep mine tunnels and a label indicating the thickness of the corresponding loose zone of the tunnel surrounding rock. The surrounding rock characteristics of deep mine tunnels include tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength, and surrounding rock mass quality grade;

[0013] The particle swarm algorithm is trained using the training set. When the preset number of iterations is reached or a specific stop condition is met, the training is terminated to obtain a deep loose zone thickness prediction model.

[0014] The deep loose zone thickness prediction model is tested using the test set, the model parameters of the deep loose zone thickness prediction model are optimized, and the deep loose zone thickness prediction model that meets the test evaluation requirements is output.

[0015] The above samples are randomly selected from the tunnel surrounding rock loose zone thickness database, and the construction process of the tunnel surrounding rock loose zone thickness database includes:

[0016] Obtain the tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loose zone thickness of several historical deep mine tunnels, among which the tunnel section design parameters include tunnel layout direction and tunnel section size, and the surrounding rock geological characteristic parameters include tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade;

[0017] The tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loose zone thickness of all historical deep mine tunnels are stored in the database to obtain a tunnel surrounding rock loose zone thickness database;

[0018] The database update frequency is set, and the new tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loose zone thickness of historical deep mine tunnels are stored in the tunnel surrounding rock loose zone thickness database according to the database update frequency.

[0019] The calculation process of the above tunnel depth includes:

[0020] The test obtains the vertical ground stress, the maximum horizontal principal stress and the minimum horizontal principal stress of the roadway;

[0021] The tunnel burial depth is calculated using the tunnel vertical ground stress, the tunnel maximum horizontal principal stress, and the tunnel minimum horizontal principal stress. The calculation formula is as follows:

[0022]

[0023] Among them, σ v is the vertical ground stress of the tunnel; hmax is the maximum horizontal principal stress in the tunnel; σ hmin is the minimum horizontal principal stress of the tunnel, and H is the tunnel burial depth;

[0024] or / and,

[0025] The calculation process of surrounding rock strength includes:

[0026] Obtain rock samples of the tunnel surrounding rock;

[0027] The rock specimens were tested using uniaxial compression test and Brazilian splitting test to obtain the surrounding rock strength.

[0028] or / and,

[0029] The surrounding rock mass quality grade is obtained using the Barton rock mass quality Q system classification method, and the corresponding formula is as follows:

[0030]

[0031] Where Q is the quality grade of the surrounding rock mass; RQD is Deere's rock quality index; J n is the number of joint groups; J r is the roughness coefficient of the most fragile joint; J a J is the erosion degree or filling condition of the most vulnerable joint surface; w is the fracture water reduction factor; SRF is the stress reduction factor.

[0032] The second technical solution of the present invention is achieved by the following measures: a tunnel surrounding rock loosening zone testing device, comprising:

[0033] A data acquisition unit obtains basic data of the surrounding rock of the tunnel to be predicted, wherein the basic data includes tunnel section design parameters and surrounding rock geological characteristic parameters, the tunnel section design parameters include tunnel layout direction and tunnel section size, and the surrounding rock geological characteristic parameters include tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade;

[0034] The prediction unit inputs the basic data of the tunnel surrounding rock to be predicted into the deep loose zone thickness prediction model to obtain the corresponding tunnel surrounding rock loose zone thickness, wherein the deep loose zone thickness prediction model is obtained by machine learning of a number of samples, wherein each of the several samples includes the surrounding rock characteristics of the deep mine tunnel and a label identifying the corresponding tunnel surrounding rock loose zone thickness, and the surrounding rock characteristics of the deep mine tunnel include tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade.

[0035] The following are further optimizations and / or improvements to the above technical solutions:

[0036] The above also includes a model building unit, including:

[0037] The sample acquisition module acquires a number of samples and divides them into a training set and a test set according to a ratio, wherein each sample includes the surrounding rock characteristics of deep mine tunnels and a label indicating the thickness of the corresponding loose zone of the tunnel surrounding rock. The surrounding rock characteristics of deep mine tunnels include tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength, and surrounding rock mass quality grade;

[0038] The training module uses the training set to train the particle swarm algorithm. When the preset number of iterations is reached or a specific stop condition is met, the training is terminated to obtain a deep loose zone thickness prediction model.

[0039] The test module uses the test set to test the deep loosening zone thickness prediction model, optimizes the model parameters of the deep loosening zone thickness prediction model, and outputs the deep loosening zone thickness prediction model that meets the test evaluation requirements.

[0040] The above also includes a database construction unit, including:

[0041] The first construction module obtains the tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loosening zone thickness of several historical deep mine tunnels, stores the tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loosening zone thickness of all historical deep mine tunnels in the database, and obtains the tunnel surrounding rock loosening zone thickness database, wherein the tunnel section design parameters include the tunnel layout direction and tunnel section size, and the surrounding rock geological characteristic parameters include the tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade;

[0042] The second construction module sets the database update frequency, and stores new historical deep mine tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loose zone thickness in the tunnel surrounding rock loose zone thickness database according to the database update frequency.

[0043] The third technical solution of the present invention is achieved through the following measures: an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to implement the steps in the tunnel surrounding rock loosening zone testing method.

[0044] The fourth technical solution of the present invention is achieved through the following measures: a storage medium, on which is stored a computer program that can be read by a computer, and the computer program is configured to execute the steps in the tunnel surrounding rock loosening zone testing method when running.

[0045] The present invention uses historical deep mine tunnel surrounding rock characteristics and corresponding tunnel surrounding rock loosening zone thickness training based on machine learning to obtain a deep loosening zone thickness prediction model, and then uses the deep loosening zone thickness prediction model to predict the tunnel surrounding rock loosening zone thickness. This method is not affected by the mining depth of the mine and the complexity of the application environment, and can quickly and accurately obtain the tunnel surrounding rock loosening zone thickness. The deep loosening zone thickness prediction model can be updated regularly to ensure the accuracy of the tunnel surrounding rock loosening zone thickness calculation, providing data support for subsequent surrounding rock stability evaluation and support design. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Attached Figure 1 A schematic diagram of an implementation environment provided for an embodiment of the present invention.

[0047] Attached Figure 2 A schematic flow chart of a method for testing the loosening zone of surrounding rock in a tunnel provided in accordance with an embodiment of the present invention.

[0048] Attached Figure 3 A schematic diagram of a model building method flow chart provided for one embodiment of the present invention.

[0049] Attached Figure 4 A schematic diagram of a single-hole sonic loosening ring test provided for an embodiment of the present invention.

[0050] Attached Figure 5 A schematic diagram of a rock specimen and a loading method for a uniaxial compression test and a Brazilian splitting test provided in one embodiment of the present invention.

[0051] Attached Figure 6 A schematic diagram for obtaining the lane layout direction provided by an embodiment of the present invention.

[0052] Attached Figure 7 A schematic diagram of obtaining the cross-sectional dimensions of a tunnel provided in one embodiment of the present invention.

[0053] Attached Figure 8 A schematic structural diagram of a tunnel surrounding rock loosening zone testing device provided in accordance with an embodiment of the present invention.

[0054] Attached Fig. 9 A schematic structural diagram of another tunnel surrounding rock loosening zone testing device provided as an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The present invention is not limited by the following embodiments, and specific implementation methods can be determined based on the technical solution of the present invention and actual conditions.

[0056] Those skilled in the art will understand that, unless otherwise stated, in the embodiments of the present invention, a "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as a processing circuit or memory) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of an overall module or unit that includes the function of the module or unit.

[0057] In addition, the term “plurality” in the embodiments of the present invention refers to two or more than two, and “first” and “second” are used to distinguish descriptions and should not be understood as implying relative importance.

[0058] At present, the commonly used methods for testing the loosening circle of tunnel surrounding rock include the sonic method, the panoramic image method of drilling television and the multi-point displacement meter method, which can intuitively test the size of the loosening circle of tunnel surrounding rock, but require on-site testing, and there are problems such as cumbersome and complicated on-site operation, long time period, high testing cost and small testing coverage area. However, due to the current large-scale exploitation of shallow resources, the mining depth is constantly increasing, and the geological environment of deep rock mass is becoming more and more complex. It is difficult to implement the commonly used loosening circle testing method of tunnel surrounding rock under the conditions of mechanical crack development and rock mass fragmentation. Even if the existing loosening circle testing method of tunnel surrounding rock is used, it is difficult to quickly determine the thickness of the loosening circle of tunnel surrounding rock under different geological conditions, which will directly affect the safe production of metal mines. Therefore, for the tunnel surrounding rock of deep mines, the present invention provides a method, device, electronic equipment and storage medium for testing the loosening circle of tunnel surrounding rock.

[0059] An embodiment of the present invention provides a method, device, electronic device and storage medium for testing the loose zone of tunnel surrounding rock. A deep loose zone thickness prediction model is constructed through machine learning. The basic data of the tunnel surrounding rock to be predicted is input into the deep loose zone thickness prediction model to obtain the corresponding tunnel surrounding rock loose zone thickness, wherein the basic data includes tunnel section design parameters and surrounding rock geological characteristic parameters. The tunnel section design parameters include tunnel layout direction and tunnel section size. The surrounding rock geological characteristic parameters include tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade.

[0060] Among them, the method provided by the embodiment of the present invention may involve artificial intelligence (AI) technology, and can be implemented based on artificial intelligence technology, for example, using a deep learning approach and using sample training to obtain a corresponding model.

[0061] Among them, Machine Learning (ML) is a multi-disciplinary interdisciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence.

[0062] Among them, Deep Learning (DL) specifically refers to machine learning based on deep neural network models and methods. It is developed based on statistical machine learning, artificial neural network and other algorithm models, combined with the development of contemporary big data and large computing power. The most important technical feature of deep learning is the ability to automatically extract features.

[0063] The above-mentioned machine learning and deep learning usually include technologies such as neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning.

[0064] As attached Figure 1 As shown, it shows a schematic diagram of an implementation environment provided by an embodiment of the present invention. The implementation environment may include: training equipment and use equipment.

[0065] Both the training device and the use device are computer devices; optionally, the computer device is a terminal device, such as a mobile phone, a tablet computer, a PC (Personal Computer) and other electronic devices; or, the computer device is a server, which can be a single server, a server cluster composed of multiple servers, or a cloud computing service center, which is not limited to the embodiments of the present invention.

[0066] The training device refers to a computer device with machine learning capabilities. Optionally, the training device has the ability to obtain an algorithm model, and train and learn it according to application requirements. For example, the training device obtains an algorithm model for machine learning from other devices through the network, and then trains it through training samples according to application requirements, so that the algorithm model has the ability to obtain the thickness of the loose zone of the tunnel surrounding rock; Optionally, the training device has the ability to build an algorithm model, and it can build an algorithm model by itself according to application requirements, and then train and learn it. For example, in order to obtain the thickness of the loose zone of the tunnel surrounding rock according to the tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade of the tunnel surrounding rock to be predicted, the training device builds an algorithm model by itself, and then trains and learns it through samples according to application requirements.

[0067] The device used refers to a computer device that has the requirements for using the algorithm model. Optionally, the device uses the algorithm model according to the application requirements and obtains the algorithm model from other devices through the network. For example, if the device uses the requirements for predicting the optimal drilling fluid ratio and drilling parameter combination, it can obtain the algorithm model for completing training and learning to predict the thickness of the loose zone of the tunnel surrounding rock from other devices through the network, and use the algorithm model to predict the thickness of the loose zone of the tunnel surrounding rock.

[0068] Based on this, the technical solution of the present invention will be introduced and explained in combination with several examples below.

[0069] Embodiment 1: As attached Figure 2 As shown, the embodiment of the present invention discloses a method for testing a loose zone of surrounding rock in a tunnel, comprising:

[0070] Step S110, obtaining basic data of the surrounding rock of the tunnel to be predicted, wherein the basic data includes tunnel section design parameters and surrounding rock geological characteristic parameters, the tunnel section design parameters include tunnel layout direction and tunnel section size, and the surrounding rock geological characteristic parameters include tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade;

[0071] Step S120, input the basic data of the tunnel surrounding rock to be predicted into the deep loose zone thickness prediction model to obtain the corresponding tunnel surrounding rock loose zone thickness, wherein the deep loose zone thickness prediction model is obtained by machine learning of a number of samples, wherein each of the several samples includes the surrounding rock characteristics of the deep mine tunnel and a label identifying the corresponding tunnel surrounding rock loose zone thickness, and the surrounding rock characteristics of the deep mine tunnel include tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade.

[0072] An embodiment of the present invention discloses a method for testing the loosening zone of tunnel surrounding rock. Based on machine learning, a deep loosening zone thickness prediction model is obtained by training the surrounding rock characteristics of historical deep mine tunnels and the corresponding loosening zone thickness of the tunnel surrounding rock. The deep loosening zone thickness prediction model is then used to predict the thickness of the loosening zone of the tunnel surrounding rock to be predicted. This method is not affected by the mining depth of the mine and the complexity of the application environment. The thickness of the loosening zone of the tunnel surrounding rock can be obtained quickly and accurately. The deep loosening zone thickness prediction model can be updated regularly to ensure the accuracy of the calculation of the loosening zone thickness of the tunnel surrounding rock, thereby providing data support for subsequent surrounding rock stability evaluation and support design.

[0073] Embodiment 2: As attached Figure 3 The embodiment of the present invention shown is a further optimization of the above embodiment, wherein the process of building a deep loose zone thickness prediction model includes:

[0074] Step S210, obtain a number of samples and divide them into a training set and a test set according to the ratio, wherein each sample includes the surrounding rock characteristics of the deep mine tunnel and a label indicating the thickness of the corresponding loose zone of the tunnel surrounding rock. The surrounding rock characteristics of the deep mine tunnel include tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade.

[0075] In this embodiment, the ratio of the training set to the test set may be 8:2, and further, cross-validation may be used for training.

[0076] In this embodiment, the thickness of the loose zone of the tunnel surrounding rock can be obtained by using the single-hole acoustic wave loose zone test method. The corresponding test schematic diagram is shown in the attached figure. Figure 4 As shown in the figure, the single-hole acoustic wave loosening circle test method is that the sounding probe and the receiving probe are placed in the same measuring hole, and the degree of rock damage is judged by measuring the propagation speed of the sound wave from the sounding probe to the receiving probe through the surrounding rock at different depths in the hole.

[0077] Step S220, using the training set to train the particle swarm algorithm, when reaching a preset number of iterations or satisfying a specific stop condition, the training is terminated to obtain a deep loose zone thickness prediction model.

[0078] In this embodiment, the particle swarm algorithm is trained using a training set, including:

[0079] Initialize parameters, including: define the fitness function of the problem; set the population size (number of particles) and number of iterations

[0080] Randomly initialize the position and velocity of each particle; set the individual best position of each particle (pBest) and the global best position of the entire group (gBest).

[0081] The fitness function can be the loss function of the neural network model, or it can be the fitness function as shown below:

[0082]

[0083] Among them, y i and i * They are the actual value of the thickness of the loosened zone of the tunnel surrounding rock and the predicted value of the thickness of the loosened zone of the tunnel surrounding rock, respectively.

[0084] Iterative optimization, as follows:

[0085] If each individual characteristic data of the loose rock zone of the tunnel is regarded as a particle, then the series of characteristic data can be regarded as a dense group of characteristic data particles. Assume that the entire complete database is the search target of F dimension and is a group composed of n particles, where the position of the i particle is represented by X i =(x 1 i ,x 2 i. x 3 i ,……x F i ). The position of each particle is a potential solution, and the best position of a single feature data is IP i =(ip 1 i ,ip 2 i. ip 3 i ,……ip F i ), the best position of the entire feature data particle swarm is IP b =(ip 1 b ,ip 2b. ip 3 b ,……ip F b ), the velocity of the characteristic data particle is recorded as V i =(v 1 i ,v 2 i. v 3 i ,……v F i ). In this process, the position of each characteristic data particle is continuously updated by the following formula:

[0086]

[0087]

[0088] w is the inertia factor; learning factors c1 and c2 are non-negative constants; r1 and r2 are random numbers that change in the range of [0, 1]; α is the constraint factor.

[0089] In addition, the following formula is used to continuously update the movement speed of the characteristic data particles, effectively changing and controlling the movement speed of the particles to achieve an effective balance between the global search and local search of the algorithm.

[0090]

[0091] C=c1+c2

[0092] Among them, β is the compression factor.

[0093] It should also be noted that the specific stopping condition in this embodiment is the maximum fitness.

[0094] Output the results, through continuous iterative calculation and optimization, output the C value and b value corresponding to the best fitness, and obtain the deep loose zone thickness prediction model.

[0095] Step S230, using the test set to test the deep loose zone thickness prediction model, optimize the model parameters of the deep loose zone thickness prediction model, and output the deep loose zone thickness prediction model that meets the test evaluation requirements.

[0096] In this embodiment, the test evaluation can be selected as needed, and the embodiment of the present invention does not limit it. At the same time, by continuously updating the samples, the deep loose zone thickness prediction model can be continuously updated, so that the model maintains calculation accuracy and is applicable to various application environments.

[0097] It should also be noted that several samples are randomly selected from the tunnel surrounding rock loose zone thickness database, and the construction process of the tunnel surrounding rock loose zone thickness database includes:

[0098] (1) Obtaining tunnel section design parameters, surrounding rock geological characteristic parameters, and tunnel surrounding rock loosening zone thickness of several historical deep mine tunnels, where tunnel section design parameters include tunnel layout direction and tunnel section size, and surrounding rock geological characteristic parameters include tunnel burial depth, surrounding rock strength, and surrounding rock mass quality grade;

[0099] (2) storing the tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loose zone thickness of all historical deep mine tunnels in a database to obtain a tunnel surrounding rock loose zone thickness database;

[0100] (3) Setting the database update frequency, and storing the new tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loose zone thickness of historical deep mine tunnels in the tunnel surrounding rock loose zone thickness database according to the database update frequency.

[0101] Embodiment 3: Embodiment 3 of the present invention is a further optimization of the above embodiment, wherein:

[0102] (1) The calculation process of tunnel depth includes:

[0103] The test obtains the vertical ground stress, the maximum horizontal principal stress and the minimum horizontal principal stress of the roadway;

[0104] The tunnel burial depth is calculated using the tunnel vertical ground stress, the tunnel maximum horizontal principal stress, and the tunnel minimum horizontal principal stress. The calculation formula is as follows:

[0105]

[0106] Among them, σ v is the vertical ground stress of the tunnel; hmax is the maximum horizontal principal stress in the tunnel; σ hmin is the minimum horizontal principal stress of the tunnel, and H is the buried depth of the tunnel.

[0107] Since the magnitude of tunnel geostress is closely related to tunnel depth, and generally the geostress increases linearly with the increase of tunnel depth, this embodiment uses tunnel vertical geostress, tunnel maximum horizontal principal stress and tunnel minimum horizontal principal stress to calculate the tunnel depth.

[0108] (2) The calculation process of surrounding rock strength includes:

[0109] Obtain rock samples of the tunnel surrounding rock;

[0110] The rock specimens were tested using uniaxial compression test and Brazilian splitting test to obtain the surrounding rock strength.

[0111] The rock specimens and loading methods of the above uniaxial compression test and Brazilian splitting test are shown in the attached figure. Figure 5 As shown in the figure, the rock specimen sizes for the uniaxial compression test and the Brazilian splitting test are and Indicates the specimen diameter;

[0112] The calculation methods of uniaxial compression strength (UCS) and Brazilian splitting tensile strength (BTS) of rock are as follows:

[0113]

[0114] s=πr 2

[0115]

[0116] Where F and P are peak loads, S is the cross-sectional area of ​​the specimen, D is the diameter, and T is the thickness of the specimen.

[0117] (3) The surrounding rock mass quality grade is obtained using the Barton rock mass quality Q system classification method, and the corresponding formula is as follows:

[0118]

[0119] Where Q is the quality grade of the surrounding rock mass; RQD is Deere's rock quality index; J n is the number of joint groups; J r is the roughness coefficient of the most fragile joint; J a J is the erosion degree or filling condition of the most vulnerable joint surface; w is the fracture water reduction factor; SRF is the stress reduction factor.

[0120] (4) Lane layout direction, as shown in the attached Figure 6 As shown, the tunnel layout direction is the angle a between the tunnel excavation centerline and the maximum horizontal principal stress.

[0121] (5) Tunnel cross-sectional dimensions. The cross-sectional shape of tunnels in deep mines is mostly a three-center arch shape, in which the cross-sectional dimensions include width, arch height and wall height. The tunnel cross-sectional dimensions are shown in the attached figure. Figure 7 As shown, the actual cross-sectional dimensions of the on-site tunnel are measured using a laser rangefinder or a tape measure.

[0122] Embodiment 4: As attached Figure 8 As shown, an embodiment of the present invention discloses a tunnel surrounding rock loosening zone testing device, comprising:

[0123] A data acquisition unit obtains basic data of the surrounding rock of the tunnel to be predicted, wherein the basic data includes tunnel section design parameters and surrounding rock geological characteristic parameters, the tunnel section design parameters include tunnel layout direction and tunnel section size, and the surrounding rock geological characteristic parameters include tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade;

[0124] The prediction unit inputs the basic data of the tunnel surrounding rock to be predicted into the deep loose zone thickness prediction model to obtain the corresponding tunnel surrounding rock loose zone thickness, wherein the deep loose zone thickness prediction model is obtained by machine learning of a number of samples, wherein each of the several samples includes the surrounding rock characteristics of the deep mine tunnel and a label identifying the corresponding tunnel surrounding rock loose zone thickness, and the surrounding rock characteristics of the deep mine tunnel include tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade.

[0125] Embodiment 5: As attached Fig. 9 As shown, an embodiment of the present invention discloses a tunnel surrounding rock loosening zone testing device, comprising:

[0126] Model building unit, including:

[0127] The sample acquisition module acquires a number of samples and divides them into a training set and a test set according to a ratio, wherein each sample includes the surrounding rock characteristics of deep mine tunnels and a label indicating the thickness of the corresponding loose zone of the tunnel surrounding rock. The surrounding rock characteristics of deep mine tunnels include tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength, and surrounding rock mass quality grade;

[0128] The training module uses the training set to train the particle swarm algorithm. When the preset number of iterations is reached or a specific stop condition is met, the training is terminated to obtain a deep loose zone thickness prediction model.

[0129] The test module uses the test set to test the deep loosening zone thickness prediction model, optimizes the model parameters of the deep loosening zone thickness prediction model, and outputs the deep loosening zone thickness prediction model that meets the test evaluation requirements.

[0130] Database building unit, including:

[0131] The first construction module obtains the tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loosening zone thickness of several historical deep mine tunnels, stores the tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loosening zone thickness of all historical deep mine tunnels in the database, and obtains the tunnel surrounding rock loosening zone thickness database, wherein the tunnel section design parameters include the tunnel layout direction and tunnel section size, and the surrounding rock geological characteristic parameters include the tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade;

[0132] The second construction module sets the database update frequency, and stores new historical deep mine tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loose zone thickness in the tunnel surrounding rock loose zone thickness database according to the database update frequency.

[0133] The data acquisition unit obtains the basic data of the surrounding rock of the tunnel to be predicted, wherein the basic data includes the tunnel section design parameters and the surrounding rock geological characteristic parameters. The tunnel section design parameters include the tunnel layout direction and tunnel section size. The surrounding rock geological characteristic parameters include the tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade.

[0134] The prediction unit inputs the basic data of the tunnel surrounding rock to be predicted into the deep loose zone thickness prediction model to obtain the corresponding tunnel surrounding rock loose zone thickness, wherein the deep loose zone thickness prediction model is obtained by machine learning of a number of samples, wherein each of the several samples includes the surrounding rock characteristics of the deep mine tunnel and a label identifying the corresponding tunnel surrounding rock loose zone thickness, and the surrounding rock characteristics of the deep mine tunnel include tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade.

[0135] Embodiment 6: The embodiment of the present invention discloses a storage medium, on which a computer program readable by a computer is stored, and the computer program is configured to execute a method for testing a loosening zone of surrounding rock in a tunnel when the computer program is run.

[0136] The above storage medium may include, but is not limited to: a USB flash drive, a read-only memory, a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0137] Embodiment 7: The embodiment of the present invention discloses an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to implement a method for testing the loosening zone of surrounding rock in a tunnel.

[0138] The processor may be a central processing unit (CPU), a general purpose processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. It may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The memory may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory, a mobile hard disk, a magnetic disk or an optical disk.

[0139] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0140] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0141] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0142] The above technical features constitute the best embodiment of the present invention, which has strong adaptability and best implementation effect. Non-essential technical features can be added or reduced according to actual needs to meet the requirements of different situations.

[0143] The above content is only a specific implementation mode of the present invention, which has strong adaptability and implementation effect, but the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered within the protection scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope covered by the present invention.

Claims

1. A method for testing the loose zone of surrounding rock in a tunnel, characterized in that: include: Obtaining basic data of the surrounding rock of the tunnel to be predicted, wherein the basic data includes tunnel section design parameters and surrounding rock geological characteristic parameters, the tunnel section design parameters include tunnel layout direction and tunnel section size, and the surrounding rock geological characteristic parameters include tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade; The basic data of the tunnel surrounding rock to be predicted is input into the deep loose zone thickness prediction model to obtain the corresponding tunnel surrounding rock loose zone thickness, wherein the deep loose zone thickness prediction model is obtained by machine learning of a number of samples, wherein each of the several samples includes the surrounding rock characteristics of the deep mine tunnel and a label identifying the corresponding tunnel surrounding rock loose zone thickness, and the surrounding rock characteristics of the deep mine tunnel include tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade.

2. The method for testing the loose zone of surrounding rock in a tunnel according to claim 1 is characterized in that: The process of constructing the deep loose zone thickness prediction model includes: A number of samples are obtained and divided into a training set and a test set according to a ratio, wherein each sample includes surrounding rock characteristics of deep mine tunnels and a label indicating the thickness of the corresponding loose zone of the tunnel surrounding rock. The surrounding rock characteristics of deep mine tunnels include tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength, and surrounding rock mass quality grade; The particle swarm algorithm is trained using the training set. When the preset number of iterations is reached or a specific stop condition is met, the training is terminated to obtain a deep loose zone thickness prediction model. The deep loose zone thickness prediction model is tested using the test set, the model parameters of the deep loose zone thickness prediction model are optimized, and the deep loose zone thickness prediction model that meets the test evaluation requirements is output.

3. The method for testing the loose zone of surrounding rock in a tunnel according to claim 1 or 2, characterized in that: The plurality of samples are randomly selected from a database of thickness of loosened zone of surrounding rock of a roadway, wherein the process of constructing the database of thickness of loosened zone of surrounding rock of a roadway includes: Obtain the tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loose zone thickness of several historical deep mine tunnels, among which the tunnel section design parameters include tunnel layout direction and tunnel section size, and the surrounding rock geological characteristic parameters include tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade; The tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loose zone thickness of all historical deep mine tunnels are stored in the database to obtain a tunnel surrounding rock loose zone thickness database; The database update frequency is set, and the new tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loose zone thickness of historical deep mine tunnels are stored in the tunnel surrounding rock loose zone thickness database according to the database update frequency.

4. The method for testing the loose zone of surrounding rock in a tunnel according to any one of claims 1 to 3, characterized in that: The thickness of the loosened zone of the tunnel surrounding rock in each of the samples is obtained by a single-hole acoustic wave testing method.

5. The method for testing the loose zone of surrounding rock in a tunnel according to any one of claims 1 to 3, characterized in that: The calculation process of the tunnel burial depth includes: The test obtains the vertical ground stress, the maximum horizontal principal stress and the minimum horizontal principal stress of the roadway; The tunnel burial depth is calculated using the tunnel vertical ground stress, the tunnel maximum horizontal principal stress, and the tunnel minimum horizontal principal stress. The calculation formula is as follows: Among them, σ v is the vertical ground stress of the tunnel; hmax is the maximum horizontal principal stress in the tunnel; σ hmin is the minimum horizontal principal stress of the tunnel, and H is the tunnel burial depth; or / and, The calculation process of surrounding rock strength includes: Obtain rock samples of the tunnel surrounding rock; The rock specimens were tested using uniaxial compression test and Brazilian splitting test to obtain the surrounding rock strength. or / and, The surrounding rock mass quality grade is obtained using the Barton rock mass quality Q system classification method, and the corresponding formula is as follows: Where Q is the quality grade of the surrounding rock mass; RQD is Deere's rock quality index; J n is the number of joint groups; J r is the roughness coefficient of the most fragile joint; J a J is the erosion degree or filling condition of the most vulnerable joint surface; w is the fracture water reduction factor; SRF is the stress reduction factor.

6. A tunnel surrounding rock loosening zone testing device using the method as described in any one of claims 1 to 5, characterized in that: include: A data acquisition unit obtains basic data of the surrounding rock of the tunnel to be predicted, wherein the basic data includes tunnel section design parameters and surrounding rock geological characteristic parameters, the tunnel section design parameters include tunnel layout direction and tunnel section size, and the surrounding rock geological characteristic parameters include tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade; The prediction unit inputs the basic data of the tunnel surrounding rock to be predicted into the deep loose zone thickness prediction model to obtain the corresponding tunnel surrounding rock loose zone thickness, wherein the deep loose zone thickness prediction model is obtained by machine learning of a number of samples, wherein each of the several samples includes the surrounding rock characteristics of the deep mine tunnel and a label identifying the corresponding tunnel surrounding rock loose zone thickness, and the surrounding rock characteristics of the deep mine tunnel include tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade.

7. The tunnel surrounding rock loosening zone testing device according to claim 6 is characterized in that: Also included are model building units, including: The sample acquisition module acquires a number of samples and divides them into a training set and a test set according to a ratio, wherein each sample includes the surrounding rock characteristics of deep mine tunnels and a label indicating the thickness of the corresponding loose zone of the tunnel surrounding rock. The surrounding rock characteristics of deep mine tunnels include tunnel layout direction, tunnel cross-sectional dimensions, tunnel burial depth, surrounding rock strength, and surrounding rock mass quality grade; The training module uses the training set to train the particle swarm algorithm. When the preset number of iterations is reached or a specific stop condition is met, the training is terminated to obtain a deep loose zone thickness prediction model. The test module uses the test set to test the deep loosening zone thickness prediction model, optimizes the model parameters of the deep loosening zone thickness prediction model, and outputs the deep loosening zone thickness prediction model that meets the test evaluation requirements.

8. The tunnel surrounding rock loosening zone testing device according to claim 6 or 7, characterized in that: Also included are database building units, including: The first construction module obtains the tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loosening zone thickness of several historical deep mine tunnels, stores the tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loosening zone thickness of all historical deep mine tunnels in the database, and obtains the tunnel surrounding rock loosening zone thickness database, wherein the tunnel section design parameters include the tunnel layout direction and tunnel section size, and the surrounding rock geological characteristic parameters include the tunnel burial depth, surrounding rock strength and surrounding rock mass quality grade; The second construction module sets the database update frequency, and stores new historical deep mine tunnel section design parameters, surrounding rock geological characteristic parameters and tunnel surrounding rock loose zone thickness in the tunnel surrounding rock loose zone thickness database according to the database update frequency.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement the steps in the method according to any one of claims 1 to 5.

10. A storage medium, characterized in that: The storage medium stores a computer program that can be read by a computer, and the computer program is configured to execute the steps of the method according to any one of claims 1 to 5 when running.

Images