Tunnel surrounding rock stability evaluation method and system based on optical fiber monitoring

Abstract

The present invention relates to the technical field of surrounding rock stability evaluation, and specifically to a method and system for evaluating tunnel surrounding rock stability based on optical fiber monitoring. The method comprises the following steps: obtaining time-series monitoring data of multiple excavated sections in deep high-in-situ stress tunnel surrounding rock; obtaining the final deformation of the surrounding rock of the excavated section through a time-series prediction model based on the time-series monitoring data; inverting the mechanical parameters of the excavated section using the final deformation of the surrounding rock, and constructing a finite element model of the deep high-in-situ stress tunnel surrounding rock based on the mechanical parameters; and completing the tunnel surrounding rock stability evaluation based on optical fiber monitoring through the finite element model. The present invention inverts the mechanical parameters of the surrounding rock and then constructs a finite element model to accurately and effectively evaluate the stability of the surrounding rock of deep high-in-situ stress tunnels, providing a basis for the formulation of construction plans, ensuring that the support structure can effectively control the deformation and damage of the surrounding rock, and ensuring construction safety and project quality.

Description

Technical Field

[0001] The present invention relates to the technical field of surrounding rock stability evaluation, and in particular to a tunnel surrounding rock stability evaluation method and system based on optical fiber monitoring. Background Art

[0002] With the increasing depletion of shallow coal resources, major mines have mostly expanded into the kilometer-high mining range. Deep mining creates significant disturbances and high ground stress, making it highly susceptible to disasters such as dynamic impacts. Ensuring coal mine production presupposes the safety of coal mine roadways, specifically the vital passages for construction workers. Roadway safety is closely linked to the strength of the support, making the selection of an appropriate support method a crucial consideration in coal mine production operations.

[0003] In the past, the support methods for surrounding rock in coal mine roadways were primarily determined by technical personnel's observations, often ignoring the influence of potential factors. This led to the use of incorrect support methods, resulting in waste of support materials or threats to the personal safety of construction workers. Therefore, when designing roadway support schemes, modern emerging technologies should be combined to accurately and effectively assess the stability of the surrounding rock in coal mine roadways. This can then determine the construction difficulty and optimize the support structure design, providing a basis for the formulation of construction plans, ensuring that the support structure can effectively control the deformation and damage of the surrounding rock, and guaranteeing construction safety and project quality. Summary of the Invention

[0004] In view of the shortcomings of existing methods and the needs of practical applications, in order to solve the problem of accurately and effectively evaluating the stability of surrounding rocks of deep high-in-situ stress tunnels. On the one hand, the present invention provides a tunnel surrounding rock stability evaluation method based on optical fiber monitoring, comprising the following steps: obtaining time-series monitoring data of multiple excavated sections in the surrounding rocks of deep high-in-situ stress tunnels; based on the time-series monitoring data, obtaining the final deformation of the surrounding rocks of the excavated sections through a time-series prediction model; using the final deformation of the surrounding rocks to invert the mechanical parameters of the excavated sections, and constructing a finite element model of the surrounding rocks of the deep high-in-situ stress tunnels according to the mechanical parameters; completing the tunnel surrounding rock stability evaluation based on optical fiber monitoring through the finite element model. The present invention inverts the mechanical parameters of the surrounding rocks and then constructs a finite element model to accurately and effectively evaluate the stability of the surrounding rocks of deep high-in-situ stress tunnels, providing a basis for the formulation of construction plans, ensuring that the support structure can effectively control the deformation and damage of the surrounding rocks, and ensuring construction safety and project quality.

[0005] Optionally, the method for evaluating tunnel surrounding rock stability based on optical fiber monitoring further includes the following steps:

[0006] The time series monitoring data is subjected to isometric interpolation processing; and the final deformation of the surrounding rock is corrected. The present invention is beneficial to improving the accuracy of the present invention by pre-processing the time series monitoring data and correcting the final deformation of the surrounding rock.

[0007] Optionally, the final deformation of the surrounding rock is corrected to satisfy the following formula:

[0008]

[0009] in, represents the final deformation of the surrounding rock after correction, represents the final deformation of the surrounding rock before correction, represents the displacement release rate, The present invention corrects the final deformation of the surrounding rock based on the displacement release rate and the surrounding rock grade, eliminating the influence of the surrounding rock deformation before monitoring and improving the rationality of the present invention.

[0010] Optionally, the inversion of the mechanical parameters of the excavated section using the final deformation of the surrounding rock comprises the following steps:

[0011] Based on the range of values ​​of the mechanical parameters, multiple mechanical parameter matrices are constructed; a surrounding rock deformation dataset is obtained based on the mechanical parameter matrices; an improved sparrow search algorithm is introduced to optimize the hyperparameters of the learning network model, and the optimized learning network model is trained using the surrounding rock deformation dataset; and the mechanical parameters of the excavated section are obtained using the trained learning network model. The present invention utilizes the improved sparrow search algorithm to optimize the hyperparameters of the learning network model, which facilitates rapid and accurate training of the learning network model, thereby improving the accuracy of the present invention.

[0012] Optionally, the introducing of the improved sparrow search algorithm to optimize the hyperparameters of the learning network model comprises the following steps:

[0013] Through the first mapping model, a sparrow population with the hyperparameters as sparrow individuals is randomly generated; the discoverer position update formula, the follower position update formula and the sentinel position update formula are improved, and the improved sparrow search algorithm is used to iteratively optimize and obtain the optimal hyperparameters of the learning network model.

[0014] Optionally, the first mapping model satisfies the following formula:

[0015]

[0016] in, The first values, The first values, The present invention generates an initial sparrow population through the first mapping model, and the population is highly uniform and reasonable, which is conducive to improving iteration efficiency.

[0017] Optionally, the improved discoverer location update formula satisfies the following formula:

[0018]

[0019] in, Indicates the The sparrow discovered The updated position after iterations, Indicates the The discoverer sparrow The position at the iteration, represents the maximum number of iterations, express A random number, Indicates belonging The warning value of Indicates belonging The warning threshold, represents random numbers that follow a standard normal distribution, Indicates that the element is 1 matrix, Indicates the spatial dimension of the sparrow's position. As a search direction, it is helpful to improve the search ability of the discoverer.

[0020] Optionally, the follower position update formula is improved to satisfy the following formula:

[0021]

[0022] in, Indicates the Follower Sparrow in the The updated position after iterations, represents random numbers that follow a standard normal distribution, Indicates in The global worst position at the iteration, Indicates the Follower Sparrow in the The position at the iteration, Indicates the number of sparrows, Represents the follower learning factor and satisfies , represents the maximum number of iterations, Indicates in The global optimal position at the iteration Represents the follower's adaptive inertia weight factor and satisfies The present invention further improves the search efficiency of the present invention by improving the follower's adaptive learning factor and introducing an adaptive inertia weight factor.

[0023] Optionally, the sentinel position update formula is improved to satisfy the following formula:

[0024]

[0025] in, Indicates the A vigilante sparrow in the The updated position after iterations, represents the maximum number of iterations, Indicates the A vigilante sparrow in the The position at the iteration, Indicates in The global optimal position at the iteration Indicates in The global worst position at the iteration, express The present invention utilizes a spiral jump method to increase the search range of the sentinel, avoids premature convergence, and further improves the accuracy of the present invention.

[0026] In a second aspect, in order to efficiently execute the tunnel surrounding rock stability evaluation method based on optical fiber monitoring provided by the present invention, the present invention also provides a tunnel surrounding rock stability evaluation system based on optical fiber monitoring, comprising a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the tunnel surrounding rock stability evaluation method based on optical fiber monitoring as described in the first aspect of the present invention. The tunnel surrounding rock stability evaluation system based on optical fiber monitoring of the present invention has a compact structure and stable performance, and can stably execute the tunnel surrounding rock stability evaluation method based on optical fiber monitoring provided by the present invention, further enhancing the overall applicability and practical application capabilities of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A flow chart of a method for evaluating tunnel surrounding rock stability based on optical fiber monitoring provided by an embodiment of the present invention;

[0028] Figure 2 A framework diagram of a tunnel surrounding rock stability evaluation system based on optical fiber monitoring provided by an embodiment of the present invention;

[0029] Figure 3 A schematic structural diagram of a tunnel surrounding rock stability evaluation device based on optical fiber monitoring provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] Specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are for illustrative purposes only and are not intended to limit the present invention. In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that these specific details are not necessarily required to practice the present invention. In other instances, well-known circuits, software, or methods are not specifically described to avoid obscuring the present invention.

[0031] Throughout this specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present invention. Therefore, appearances of the phrases "in one embodiment," "in an embodiment," "an example," or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combinations and / or subcombinations in one or more embodiments or examples. Furthermore, those of ordinary skill in the art will appreciate that the figures provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0032] See also Figure 1 In order to solve the problem of accurately and effectively evaluating the stability of surrounding rock of deep high-stress tunnels, the present invention provides a tunnel surrounding rock stability evaluation method based on optical fiber monitoring, such as Figure 1 As shown, in one embodiment, the method includes the following steps:

[0033] S1. Obtain time-series monitoring data of multiple excavated sections in the surrounding rock of deep high-in-situ stress roadways.

[0034] In the field of mine research, deep usually refers to mines with deeper coal seams. Different countries have different definition standards for deep mines. For example, in Japan, a depth of about 700m is considered the limit of deep mines, while in South Africa, Germany, Canada and other countries, 800m~1000m is used as the standard for deep mines; high ground stress refers to the high stress state of the tunnel surrounding rock, which is usually the result of the combined action of multiple factors such as crustal movement and the rock's own gravity; tunnel surrounding rock refers to the surrounding rock or soil used to support the tunnel after the tunnel is excavated; the excavated section refers to the cross-sectional shape and size of the underground space formed after the completion of the engineering excavation activity on a certain horizontal or vertical plane; time series monitoring data refers to data recorded according to timestamps. Each data point contains a timestamp and corresponding data value, which is used to describe and analyze dynamic changes.

[0035] In this embodiment, strain monitoring data for multiple excavated sections of the surrounding rock of a deep, high-in-situ stress tunnel is obtained based on fiber optic sensing technology. Specifically, several rigid anchor rods, a first optical fiber for detecting strain, and a second optical fiber for detecting temperature are evenly anchored into the surrounding rock on both sides and at the top of the tunnel. The rigid anchor rods are provided with an axially extending temperature measurement fiber optic channel. The second optical fiber passes forward from the rear end of the rigid anchor rod into the temperature measurement fiber optic channel and then passes backward from the front end of the rigid anchor rod through the temperature measurement fiber optic channel. Each first optical fiber is connected in series, and each second optical fiber is connected in series. The first optical fiber in the series circuit is then connected to a first light source and a distributed fiber optic temperature measurement system, respectively. The first second optical fiber in the series circuit is then connected to a second light source and a distributed fiber optic temperature measurement system, respectively.

[0036] A first light source emits probe light into a first optical fiber, and the distributed optical fiber strain sensing system processes the optical signal reflected from the first optical fiber to obtain strain data of the monitored object. A second light source emits probe light into a second optical fiber, and the distributed optical fiber temperature measurement system processes the optical signal reflected from the second optical fiber to obtain temperature data of the monitored object. Based on the obtained temperature data, the relationship between temperature and optical fiber strain is used to obtain the first optical fiber strain data caused by temperature. The strain data processed by the distributed optical fiber strain sensing system is then revised based on the first optical fiber strain data caused by temperature to obtain the final surrounding rock strain monitoring data. In other embodiments, data can also be directly retrieved from a relevant database.

[0037] Furthermore, after acquiring time-series monitoring data from multiple excavated sections in the surrounding rock of a deep, high-stress roadway, the data was subjected to equidistant interpolation. It should be understood that the continuity of deformation data is a prerequisite for ensuring the accuracy of time-series prediction. In engineering projects, different monitoring frequencies are often selected based on the deformation rate of the surrounding rock. The measured deformation values ​​are often discontinuous, making it difficult to meet the requirements of time-series prediction.

[0038] Equidistant interpolation involves inserting new data points at equal distances between known data points. These new data points are calculated using an interpolation method to even out the spacing between data points. Interpolation methods can be selected based on specific needs, such as linear interpolation, cubic spline interpolation, piecewise cubic Hermite interpolation, and polynomial interpolation.

[0039] Linear interpolation calculates the value of the insertion point based on the straight-line relationship between two known data points. The calculation is simple, but it may not accurately reflect the nonlinear changes of the data.

[0040] Cubic spline interpolation is to construct a cubic polynomial between each adjacent known data point, so that these polynomials are continuous and smooth on the data points, which can better reflect the nonlinear changes of the data and the interpolation results are smooth.

[0041] Piecewise cubic Hermite interpolation is similar to cubic spline interpolation, but it focuses more on maintaining local features of the data, such as monotonicity and concavity. It is suitable for scenarios where local features of the data need to be maintained.

[0042] S2. Based on the time series monitoring data, the final deformation of the surrounding rock of the excavated section is obtained through a time series prediction model.

[0043] It is understandable that it is difficult to obtain the final deformation value of the surrounding rock in a short period of time during construction. Therefore, a sufficient amount of measured deformation data in the early stage can be used to better predict the final deformation value of the surrounding rock.

[0044] Time series forecasting refers to making scientific inferences and judgments about the future development trends or states of specific objects based on the development trends and change laws of objective things. The basic principle of the time series forecasting model is based on the continuity of the development of things, using historical time series data for statistics and analysis, mining the change laws of things, and exploring the future existence form of things based on the change laws.

[0045] Time series prediction models include traditional time series prediction models and machine learning time series prediction models.

[0046] Commonly used traditional time series forecasting models include mean regression, autoregressive integrated moving average (ARIMA) model, exponential smoothing forecasting method, etc. These methods are usually low in complexity and fast in calculation speed, and have great advantages in dealing with single-variable forecasting problems. However, if the forecasting problem is more complex or there are too many variables, traditional time series forecasting models may be prone to shortcomings.

[0047] Machine learning time series prediction models include LSTM (long short-term memory network), Transformer, CNN (convolutional neural network), etc. Different deep learning model architectures can also be designed through combination to achieve more complex prediction model design.

[0048] Specifically, the final deformation of the surrounding rock includes the settlement of the arch crown, the horizontal convergence of the upper step, the horizontal convergence of the middle step, and the horizontal convergence of the lower step.

[0049] Furthermore, the quantity and timeliness of monitoring data are the prerequisites for ensuring the accuracy of time series prediction. On the basis of ensuring that the time series prediction model is fully learned, it is also necessary to continuously update the samples through the single-step rolling prediction method.

[0050] Furthermore, tunnel construction will disturb the surrounding rock in front of the tunnel face, causing it to pre-converge before excavation. The displacement obtained through monitoring is only a part of the actual deformation displacement of the surrounding rock. Therefore, after obtaining the final deformation of the surrounding rock of the excavated section through the time series prediction model, the final deformation of the surrounding rock needs to be corrected.

[0051] Specifically, the final deformation of the surrounding rock is corrected to satisfy the following formula:

[0052]

[0053] in, represents the final deformation of the surrounding rock after correction, represents the final deformation of the surrounding rock before correction, represents the displacement release rate, Indicates the grade of surrounding rock.

[0054] The surrounding rock grade is to divide the infinite rock sequence into a finite number of categories with different stability levels based on factors such as rock integrity, rock strength, degree of development of joints and fissures, groundwater conditions and rock stability.

[0055] The surrounding rock grades are generally divided into six levels, namely Ⅰ, Ⅱ, Ⅲ, Ⅳ, Ⅴ, and Ⅵ, corresponding to The scale is 1-6. The smaller the number, the better the surrounding rock properties and the higher the stability. The specific classification standards are as follows:

[0056] Level I (stable): The rock is fresh and intact, slightly affected by geological structures, with little or no joints and fissures, mostly closed and not very long; there are no or only weak structural surfaces with a width generally less than 0.1m; there is little groundwater activity;

[0057] Level II (basically stable): The rock is fresh or slightly weathered, generally affected by geological structures, with slightly developed or developed joints and fissures, and a few weak structural surfaces with a width of no more than 0.5-0.6m; the cave wall is damp with water seepage or dripping;

[0058] Level III (poor stability): The rock is slightly or weakly weathered and severely affected by geological structures. Joints and fissures are well developed, some of which are open and filled with mud. There are many weak structural planes with a width of less than 1.0m. There is significant groundwater activity.

[0059] Level IV (poor stability): The rock mass condition is the same as that of Level III, but with more weak structural planes, with a width of less than 2.0m; local crushed stone-like structures; and significant groundwater activity.

[0060] Level V (extremely unstable): Strongly weathered or completely weathered rock mass, severely affected by geological structures, with extremely developed joints and fissures; the width of the fault fracture zone is greater than 2m, and the fissures are mostly filled with mud; there is strong groundwater activity, with a large amount of water inflow;

[0061] Level VI (soft soil): mainly soft soil surrounding rock, such as loose soil layer, sand layer, etc.

[0062] S3. Invert the mechanical parameters of the excavated section using the final deformation of the surrounding rock, and construct a finite element model of the surrounding rock of the deep high-in-situ stress tunnel based on the mechanical parameters.

[0063] In an embodiment, the inversion of the mechanical parameters of the excavated section using the final deformation of the surrounding rock comprises the following steps:

[0064] S31. Constructing multiple mechanical parameter matrices based on the value range of the mechanical parameters.

[0065] The mechanical parameters include elastic modulus, Poisson's ratio, internal friction angle, dilatancy angle, cohesion, and plastic strain. It should be understood that in deeply buried tunnels, under high ground stress, the surrounding rock gradually transitions from an elastic state to a plastic state, undergoing a certain range of plastic deformation. During the elastic deformation stage, the surrounding rock conforms to a linear elastic model, and the factors affecting the surrounding rock deformation are mainly elastic modulus and Poisson's ratio. During the plastic deformation stage, the factors affecting the surrounding rock deformation are internal friction angle, dilatancy angle, cohesion, and plastic strain.

[0066] Specifically, the matrix is ​​divided equally according to the corresponding value range of each mechanical parameter, and an orthogonal design is performed based on the results of the equal division to obtain multiple mechanical parameter matrices. It should be noted that the equal division according to the corresponding value range of each mechanical parameter needs to be determined based on the accuracy requirements and computing power. In the embodiment, five equal divisions are sufficient.

[0067] S32. Obtain a surrounding rock deformation data set according to the mechanical parameter matrix.

[0068] Specifically, the mechanical parameters are assigned to the finite element simulation software, and a joint model is established to establish a numerical model of tunnel excavation for calculation to obtain the final deformation of the surrounding rock predicted by the model. Then, based on the mechanical parameters and the corresponding predicted final deformation of the surrounding rock, a surrounding rock deformation data set is constructed and divided into a data training set and a data verification set according to a certain proportion.

[0069] S33. Introduce an improved sparrow search algorithm to optimize the hyperparameters of the learning network model, and use the surrounding rock deformation dataset to train the optimized learning network model.

[0070] In an embodiment, the learning network model is a machine learning model such as an extreme learning machine, a support vector machine, or a neural network. Hyperparameters of a machine learning model are parameters that need to be set before training the model. They are not obtained through training but need to be set manually and have a significant impact on the performance of the model.

[0071] Furthermore, the step S33 of introducing the improved sparrow search algorithm to optimize the hyperparameters of the learning network model includes the following steps:

[0072] S331. Randomly generate a sparrow population using the hyperparameters as individual sparrows through a first mapping model.

[0073] Specifically, one or more chaotic sequences are generated through the first mapping model, and the generated chaotic sequences are mapped to the solution space of the problem, including scaling the values ​​of the chaotic sequences to between the upper and lower limits of the solution space and converting them into corresponding solutions. Finally, the mapped solutions are used as individuals of the initial population.

[0074] Furthermore, the first mapping model satisfies the following formula:

[0075]

[0076] in, The first values, The first values, Represents a random number in [0,1].

[0077] S332. Improve the discoverer position update formula, follower position update formula and sentinel position update formula, and iteratively search for the optimal parameters of the learning network model through the improved sparrow search algorithm.

[0078] Specifically, an improved sparrow search algorithm is used to iteratively search for the optimal hyperparameters of the learning network model. This requires defining an objective function, namely a fitness function. In this embodiment, the objective function is the performance indicator of the model, namely the accuracy rate. Secondly, the number of sparrows needs to be determined and a reasonable search range needs to be set for each hyperparameter. Then, the fitness is calculated based on the initialized population, including training the learning network model using the current hyperparameter values, evaluating the performance of the model on the validation set, and calculating the fitness value. The sparrow positions are iteratively updated, and in each iteration, the current optimal individual, namely the optimal hyperparameter combination, is recorded until a predetermined number of iterations is reached or a certain stopping condition is met, such as the fitness no longer improving.

[0079] Furthermore, the improved discoverer location update formula satisfies the following formula:

[0080]

[0081] in, Indicates the The sparrow discovered The updated position after iterations, Indicates the The sparrow discovered The position at the iteration, represents the maximum number of iterations, express A random number, Indicates belonging The warning value of Indicates belonging The warning threshold, represents random numbers that follow a standard normal distribution, Indicates that the element is 1 matrix, Represents the spatial dimension of the sparrow's position.

[0082] In yet another embodiment, the follower position update formula is improved to satisfy the following formula:

[0083]

[0084] in, Indicates the Follower Sparrow in the The updated position after iterations, represents random numbers that follow a standard normal distribution, Indicates in The global worst position at the iteration, Indicates the Follower Sparrow in the The position at the iteration, Indicates the number of sparrows, Represents the follower learning factor and satisfies , represents the maximum number of iterations, Indicates in The global optimal position at the iteration Represents the follower's adaptive inertia weight factor and satisfies .

[0085] In an embodiment, the sentinel position update formula is improved to satisfy the following formula:

[0086]

[0087] in, Indicates the A vigilante sparrow in the The updated position after iterations, represents the maximum number of iterations, Indicates the A vigilante sparrow in the The position at the iteration, Indicates in The global optimal position at the iteration Indicates in The global worst position at the iteration, express A random number.

[0088] In some other embodiments, during each iteration, the ratio of discoverers, followers, and sentinels is dynamically adjusted to balance the search focus in the early and late stages of the iteration.

[0089] Furthermore, the optimized learning network model trained using the surrounding rock deformation dataset needs to be objectively evaluated for its computational accuracy through root mean square error, mean relative error, and symmetric mean absolute percentage error.

[0090] S34. Obtain the mechanical parameters of the excavated section through the trained learning network model.

[0091] Specifically, by learning from a large number of representative samples, a nonlinear mapping relationship between surrounding rock deformation and mechanical parameters is finally established. Then, the measured deformation values ​​of the monitoring points near the surrounding rock section whose mechanical parameters are to be inverted are used as the input values ​​of the learning network model, and the mean of the output values ​​is the mechanical parameters of the surrounding rock section whose mechanical parameters are to be inverted.

[0092] S35. Construct a finite element model of the surrounding rock of the deep high-in-situ stress tunnel according to the mechanical parameters.

[0093] Specifically, the geological parameters of the tunnel surrounding rock are collected, including the compressive strength, tensile strength, weight of the surrounding rock, and the magnitude and direction of the ground stress at the depth of the tunnel, especially the magnitude and ratio of vertical stress to horizontal stress. The parameters also include the shape, size, direction of the tunnel and the rock constraints around the tunnel, such as fixed boundaries, free boundaries, or boundaries with specific stresses, as well as other factors such as groundwater, temperature, rock joints and faults. The finite element model is established by combining the mechanical parameters obtained through the above steps.

[0094] S4. Complete the tunnel surrounding rock stability evaluation based on optical fiber monitoring through the finite element model.

[0095] Specifically, the finite element model is configured with analysis types such as static analysis, dynamic analysis, and solver parameters, and then the finite element analysis is run. During the analysis, the finite element model solves a discretized set of mathematical equations to determine the displacement and stress distribution of the roadway's surrounding rock. By analyzing the displacement distribution of the roadway's surrounding rock, the convergence and deformation of the roadway are assessed. By analyzing the stress distribution of the roadway's surrounding rock, particularly areas of principal and shear stress concentration, it is assessed whether stress concentration is occurring in the surrounding rock and whether the degree of stress concentration exceeds the rock's bearing capacity.

[0096] Furthermore, based on the displacement and stress analysis results, a comprehensive evaluation of the roadway surrounding rock stability is conducted. If the displacement and stress distribution of the roadway surrounding rock are within a reasonable range and no significant stress concentration is observed, the roadway surrounding rock stability is considered good. Conversely, if the displacement and stress distribution of the roadway surrounding rock are abnormal or significant stress concentration is observed, the roadway surrounding rock stability is considered poor and appropriate reinforcement measures are required. Furthermore, based on the results of the finite element model analysis, the roadway design and support scheme are optimized and improved. For example, adjustments to the roadway's geometric dimensions and shape, increased strength and rigidity of the support structure, and optimized support schemes are used to improve the stability of the roadway surrounding rock.

[0097] See also Figure 2 In an embodiment, to efficiently implement the tunnel surrounding rock stability evaluation method based on optical fiber monitoring provided by the present invention, the present invention also provides a tunnel surrounding rock stability evaluation system based on optical fiber monitoring, comprising: an input device, an output device, a processor, and a memory, wherein the input device, output device, processor, and memory are interconnected, and the memory contains program instructions for executing the steps of the tunnel surrounding rock stability evaluation method based on optical fiber monitoring. The tunnel surrounding rock stability evaluation system based on optical fiber monitoring provided by the present invention has a compact structure and stable performance, and is capable of stably implementing the tunnel surrounding rock stability evaluation method based on optical fiber monitoring provided by the present invention, further enhancing the overall applicability and practical application capabilities of the present invention.

[0098] In an embodiment, the processor may be a central processing unit (CPU), which may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The input device may be used to obtain data information. The output device may be used to output the results obtained by storing the program instructions contained in the computer program in the memory provided by the present invention. The memory may include a read-only memory and a random access memory, and provides instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory.

[0099] In yet another alternative embodiment, see Figure 3 In order to efficiently implement the tunnel surrounding rock stability evaluation method based on optical fiber monitoring provided by the present invention, this embodiment also provides a tunnel surrounding rock stability evaluation device based on optical fiber monitoring, such as Figure 3 Shown, including:

[0100] The memory 10 is used to store computer programs; the processor 20 is used to execute the computer programs to implement the above-mentioned method for evaluating tunnel surrounding rock stability based on optical fiber monitoring. The memory 10, processor 20, communication interface 31, and communication bus 32 all communicate with each other via the communication bus 32.

[0101] In an embodiment, the memory 10 is used to store one or more program instructions. The memory 10 may store program instructions for implementing the following functions:

[0102] Acquire time-series monitoring data of multiple excavated sections in the surrounding rock of a deep high-in-situ stress tunnel; obtain the final deformation of the surrounding rock of the excavated section through a time-series prediction model based on the time-series monitoring data; use the final deformation of the surrounding rock to invert the mechanical parameters of the excavated section, and construct a finite element model of the surrounding rock of the deep high-in-situ stress tunnel based on the mechanical parameters; and complete the tunnel surrounding rock stability evaluation based on fiber optic monitoring through the finite element model.

[0103] In one possible implementation, the memory 10 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function, etc.; the data storage area may store data created during use. In addition, the memory 10 may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include NVRAM. The memory stores an operating system and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and processing hardware-based tasks.

[0104] The processor 20 may be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field programmable gate array, or other programmable logic device. The processor 20 may be a microprocessor or any conventional processor. The processor 20 may call programs stored in the memory 10. The communication interface 31 may be an interface of a communication module for connecting to other devices or systems.

[0105] Of course, it needs to be explained that Figure 3 The structure shown does not constitute a limitation on the tunnel surrounding rock stability evaluation device based on optical fiber monitoring in this embodiment. In actual applications, the tunnel surrounding rock stability evaluation device based on optical fiber monitoring may include Figure 3 More or fewer components than shown, or combinations of certain components.

[0106] An embodiment further provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned method for evaluating the stability of surrounding rock of a roadway based on optical fiber monitoring are implemented.

[0107] The storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc., which can store program codes.

[0108] In summary, the present invention inverts the mechanical parameters of the surrounding rock and then constructs a finite element model to accurately and effectively evaluate the stability of the surrounding rock of deep high-stress tunnels, providing a basis for the formulation of construction plans, ensuring that the support structure can effectively control the deformation and damage of the surrounding rock, and ensuring construction safety and project quality.

[0109] Therefore, the present invention effectively overcomes various shortcomings of the prior art and has high industrial utilization value.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope described in the present invention.

Claims

1. A tunnel surrounding rock stability evaluation method based on optical fiber monitoring is characterized by: The method for evaluating tunnel surrounding rock stability based on optical fiber monitoring comprises the following steps: Obtain time-series monitoring data of multiple excavated sections in the surrounding rock of deep high-in-situ stress roadways; Based on the time series monitoring data, obtaining the final deformation of the surrounding rock of the excavated section through a time series prediction model; Inverting the mechanical parameters of the excavated section using the final deformation of the surrounding rock, and constructing a finite element model of the surrounding rock of the deep high-in-situ stress tunnel based on the mechanical parameters; The finite element model is used to complete the evaluation of the surrounding rock stability of the tunnel based on optical fiber monitoring; The method of inverting the mechanical parameters of the excavated section using the final deformation of the surrounding rock comprises the following steps: Constructing multiple mechanical parameter matrices based on the value range of the mechanical parameters; Obtaining a surrounding rock deformation data set according to the mechanical parameter matrix; An improved sparrow search algorithm is introduced to optimize the hyperparameters of the learning network model, and the optimized learning network model is trained using the surrounding rock deformation dataset; The mechanical parameters of the excavated section are obtained through the trained learning network model; The method of introducing the improved sparrow search algorithm to optimize the hyperparameters of the learning network model includes the following steps: Randomly generating a sparrow population with the hyperparameters as sparrow individuals through the first mapping model; Improve the discoverer position update formula, follower position update formula and sentinel position update formula, and iteratively search for the optimal hyperparameters of the learning network model through the improved sparrow search algorithm; The improved discoverer location update formula satisfies the following formula: in, Indicates the The discoverer sparrow The updated position after iterations, Indicates the The sparrow discovered The position at the iteration, represents the maximum number of iterations, express A random number, Indicates belonging The warning value of Indicates belonging The warning threshold, represents random numbers that follow a standard normal distribution, Indicates that the element is 1 matrix, Indicates the spatial dimension of the sparrow's position; Improve the follower position update formula to meet the following formula: in, Indicates the Follower Sparrow in the The updated position after iterations, represents random numbers that follow a standard normal distribution, Indicates in The global worst position at the iteration, Indicates the Follower Sparrow in the The position at the iteration, Indicates the number of sparrows, Represents the follower learning factor and satisfies , represents the maximum number of iterations, Indicates in The global optimal position at the iteration Represents the follower's adaptive inertia weight factor and satisfies ; Improve the sentinel position update formula to meet the following formula: in, Indicates the A vigilante sparrow in the The updated position after iterations, represents the maximum number of iterations, Indicates the A vigilante sparrow in the The position at the iteration, Indicates in The global optimal position at the iteration Indicates in The global worst position at the iteration, express A random number.

2. The method for evaluating tunnel surrounding rock stability based on optical fiber monitoring according to claim 1, characterized in that: The following steps are also included: Performing equidistant interpolation processing on the time series monitoring data; The final deformation of the surrounding rock is corrected.

3. The method for evaluating tunnel surrounding rock stability based on optical fiber monitoring according to claim 2, characterized in that: The final deformation of the surrounding rock is corrected to satisfy the following formula: in, represents the final deformation of the surrounding rock after correction, represents the final deformation of the surrounding rock before correction, represents the displacement release rate, Indicates the grade of surrounding rock.

4. The method for evaluating tunnel surrounding rock stability based on optical fiber monitoring according to claim 1, characterized in that: The first mapping model satisfies the following formula: in, The first values, The first values, Represents a random number in [0,1].

5. The tunnel surrounding rock stability evaluation system based on optical fiber monitoring is characterized by: The tunnel surrounding rock stability evaluation system based on optical fiber monitoring includes: an input device, an output device, a processor, and a memory. The input device, output device, processor, and memory are interconnected. The memory includes program instructions, and the program instructions are used to execute the tunnel surrounding rock stability evaluation method based on optical fiber monitoring according to any one of claims 1 to 4.

Images